Fix requirements for enzyme 0.3

Add the .ass subtitle extension

.gitignore

@@ -1,4 +1,43 @@
-build
+*.py[co]
+
+# Packages
+*.egg
+*.egg-info
 dist
-subliminal.egg-info
-*.pyc
+build
+eggs
+parts
+bin
+var
+sdist
+develop-eggs
+.installed.cfg
+
+# Installer logs
+pip-log.txt
+
+# Unit test / coverage reports
+.coverage
+.tox
+
+# Translations
+*.mo
+
+# Mr Developer
+.mr.developer.cfg
+
+# Pydev
+.project
+.pydevproject
+.settings
+
+# Rope
+.ropeproject
+
+# Sphinx
+docs/_build
+
+# Subliminal unittests
+tests/*.srt
+tests/*_files
+tests/*_cache

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "docs/_themes"]
+	path = docs/_themes
+	url = git://github.com/Diaoul/diaoul-sphinx-themes.git

.travis.yml

@@ -0,0 +1,9 @@
+language: python
+python:
+  - "2.7"
+install:
+  - pip install -r requirements.txt --use-mirrors
+  - pip install -r optional-requirements.txt --use-mirrors
+script: python setup.py test
+notifications:
+  irc: "irc.freenode.org#subliminal"

COPYING

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<http://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<http://www.gnu.org/philosophy/why-not-lgpl.html>.

COPYING.LESSER

@@ -0,0 +1,165 @@
+                   GNU LESSER GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+
+  This version of the GNU Lesser General Public License incorporates
+the terms and conditions of version 3 of the GNU General Public
+License, supplemented by the additional permissions listed below.
+
+  0. Additional Definitions.
+
+  As used herein, "this License" refers to version 3 of the GNU Lesser
+General Public License, and the "GNU GPL" refers to version 3 of the GNU
+General Public License.
+
+  "The Library" refers to a covered work governed by this License,
+other than an Application or a Combined Work as defined below.
+
+  An "Application" is any work that makes use of an interface provided
+by the Library, but which is not otherwise based on the Library.
+Defining a subclass of a class defined by the Library is deemed a mode
+of using an interface provided by the Library.
+
+  A "Combined Work" is a work produced by combining or linking an
+Application with the Library.  The particular version of the Library
+with which the Combined Work was made is also called the "Linked
+Version".
+
+  The "Minimal Corresponding Source" for a Combined Work means the
+Corresponding Source for the Combined Work, excluding any source code
+for portions of the Combined Work that, considered in isolation, are
+based on the Application, and not on the Linked Version.
+
+  The "Corresponding Application Code" for a Combined Work means the
+object code and/or source code for the Application, including any data
+and utility programs needed for reproducing the Combined Work from the
+Application, but excluding the System Libraries of the Combined Work.
+
+  1. Exception to Section 3 of the GNU GPL.
+
+  You may convey a covered work under sections 3 and 4 of this License
+without being bound by section 3 of the GNU GPL.
+
+  2. Conveying Modified Versions.
+
+  If you modify a copy of the Library, and, in your modifications, a
+facility refers to a function or data to be supplied by an Application
+that uses the facility (other than as an argument passed when the
+facility is invoked), then you may convey a copy of the modified
+version:
+
+   a) under this License, provided that you make a good faith effort to
+   ensure that, in the event an Application does not supply the
+   function or data, the facility still operates, and performs
+   whatever part of its purpose remains meaningful, or
+
+   b) under the GNU GPL, with none of the additional permissions of
+   this License applicable to that copy.
+
+  3. Object Code Incorporating Material from Library Header Files.
+
+  The object code form of an Application may incorporate material from
+a header file that is part of the Library.  You may convey such object
+code under terms of your choice, provided that, if the incorporated
+material is not limited to numerical parameters, data structure
+layouts and accessors, or small macros, inline functions and templates
+(ten or fewer lines in length), you do both of the following:
+
+   a) Give prominent notice with each copy of the object code that the
+   Library is used in it and that the Library and its use are
+   covered by this License.
+
+   b) Accompany the object code with a copy of the GNU GPL and this license
+   document.
+
+  4. Combined Works.
+
+  You may convey a Combined Work under terms of your choice that,
+taken together, effectively do not restrict modification of the
+portions of the Library contained in the Combined Work and reverse
+engineering for debugging such modifications, if you also do each of
+the following:
+
+   a) Give prominent notice with each copy of the Combined Work that
+   the Library is used in it and that the Library and its use are
+   covered by this License.
+
+   b) Accompany the Combined Work with a copy of the GNU GPL and this license
+   document.
+
+   c) For a Combined Work that displays copyright notices during
+   execution, include the copyright notice for the Library among
+   these notices, as well as a reference directing the user to the
+   copies of the GNU GPL and this license document.
+
+   d) Do one of the following:
+
+       0) Convey the Minimal Corresponding Source under the terms of this
+       License, and the Corresponding Application Code in a form
+       suitable for, and under terms that permit, the user to
+       recombine or relink the Application with a modified version of
+       the Linked Version to produce a modified Combined Work, in the
+       manner specified by section 6 of the GNU GPL for conveying
+       Corresponding Source.
+
+       1) Use a suitable shared library mechanism for linking with the
+       Library.  A suitable mechanism is one that (a) uses at run time
+       a copy of the Library already present on the user's computer
+       system, and (b) will operate properly with a modified version
+       of the Library that is interface-compatible with the Linked
+       Version.
+
+   e) Provide Installation Information, but only if you would otherwise
+   be required to provide such information under section 6 of the
+   GNU GPL, and only to the extent that such information is
+   necessary to install and execute a modified version of the
+   Combined Work produced by recombining or relinking the
+   Application with a modified version of the Linked Version. (If
+   you use option 4d0, the Installation Information must accompany
+   the Minimal Corresponding Source and Corresponding Application
+   Code. If you use option 4d1, you must provide the Installation
+   Information in the manner specified by section 6 of the GNU GPL
+   for conveying Corresponding Source.)
+
+  5. Combined Libraries.
+
+  You may place library facilities that are a work based on the
+Library side by side in a single library together with other library
+facilities that are not Applications and are not covered by this
+License, and convey such a combined library under terms of your
+choice, if you do both of the following:
+
+   a) Accompany the combined library with a copy of the same work based
+   on the Library, uncombined with any other library facilities,
+   conveyed under the terms of this License.
+
+   b) Give prominent notice with the combined library that part of it
+   is a work based on the Library, and explaining where to find the
+   accompanying uncombined form of the same work.
+
+  6. Revised Versions of the GNU Lesser General Public License.
+
+  The Free Software Foundation may publish revised and/or new versions
+of the GNU Lesser General Public License from time to time. Such new
+versions will be similar in spirit to the present version, but may
+differ in detail to address new problems or concerns.
+
+  Each version is given a distinguishing version number. If the
+Library as you received it specifies that a certain numbered version
+of the GNU Lesser General Public License "or any later version"
+applies to it, you have the option of following the terms and
+conditions either of that published version or of any later version
+published by the Free Software Foundation. If the Library as you
+received it does not specify a version number of the GNU Lesser
+General Public License, you may choose any version of the GNU Lesser
+General Public License ever published by the Free Software Foundation.
+
+  If the Library as you received it specifies that a proxy can decide
+whether future versions of the GNU Lesser General Public License shall
+apply, that proxy's public statement of acceptance of any version is
+permanent authorization for you to choose that version for the
+Library.

MANIFEST.in

@@ -0,0 +1 @@
+include COPYING COPYING.LESSER NEWS.rst README.rst

NEWS.rst

@@ -0,0 +1,111 @@
+News
+====
+
+0.6.4
+-----
+**release date:** 2013-05-19
+
+* Fix requirements due to enzyme 0.3
+
+0.6.3
+-----
+**release date:** 2013-01-17
+
+* Fix requirements due to requests 1.0
+
+0.6.2
+-----
+**release date:** 2012-09-15
+
+* Fix BierDopje
+* Fix Addic7ed
+* Fix SubsWiki
+* Fix missing enzyme import
+* Add Catalan and Galician languages to Addic7ed
+* Add possible services in help message of the CLI
+* Allow existing filenames to be passed without the ./ prefix
+
+0.6.1
+-----
+**release date:** 2012-06-24
+
+* Fix subtitle release name in BierDopje
+* Fix subtitles being downloaded multiple times
+* Add Chinese support to TvSubtitles
+* Fix encoding issues
+* Fix single download subtitles without the force option
+* Add Spanish (Latin America) exception to Addic7ed
+* Fix group_by_video when a list entry has None as subtitles
+* Add support for Galician language in Subtitulos
+* Add an integrity check after subtitles download for Addic7ed
+* Add error handling for if not strict in Language
+* Fix TheSubDB hash method to return None if the file is too small
+* Fix guessit.Language in Video.scan
+* Fix language detection of subtitles
+
+0.6.0
+-----
+**release date:** 2012-06-16
+**WARNING:** Backward incompatible changes
+
+* Fix --workers option in CLI
+* Use a dedicated module for languages
+* Use beautifulsoup4
+* Improve return types
+* Add scan_filter option
+* Add --age option in CLI
+* Add TvSubtitles service
+* Add Addic7ed service
+
+
+0.5.1
+-----
+**release date:** 2012-03-25
+
+* Improve error handling of enzyme parsing
+
+0.5
+---
+**release date:** 2012-03-25
+**WARNING:** Backward incompatible changes
+
+* Use more unicode
+* New list_subtitles and download_subtitles methods
+* New Pool object for asynchronous work
+* Improve sort algorithm
+* Better error handling
+* Make sorting customizable
+* Remove class Subliminal
+* Remove permissions handling
+
+0.4
+---
+**release date:** 2011-11-11
+
+* Many fixes
+* Better error handling
+
+0.3
+---
+**release date:** 2011-08-18
+
+* Fix a bug when series is not guessed by guessit
+* Fix dependencies failure when installing package
+* Fix encoding issues with logging
+* Add a script to ease subtitles download
+* Add possibility to choose mode of created files
+* Add more checks before adjusting permissions
+
+0.2
+---
+**release date:** 2011-07-11
+
+* Fix plugin configuration
+* Fix some encoding issues
+* Remove extra logging
+
+0.1
+---
+**release date:** not released yet
+
+* Initial release

README.md

@@ -1,6 +0,0 @@
-subliminal
-==========
-Python module to search and download subtitles
-
-* [Project page](https://github.com/Diaoul/subliminal)
-* [Initial project by Patrick Dessalle](http://code.google.com/p/periscope/)

README.rst

@@ -0,0 +1,48 @@
+Subliminal
+==========
+
+.. image:: https://secure.travis-ci.org/Diaoul/subliminal.png?branch=develop
+
+Subliminal is a python library to search and download subtitles.
+
+It uses video hashes and the powerful `guessit <http://guessit.readthedocs.org/>`_ library
+that extracts informations from filenames or filepaths to ensure you have the best subtitles.
+It also relies on `enzyme <https://github.com/Diaoul/enzyme>`_ to detect embedded subtitles
+and avoid duplicates.
+
+Features
+--------
+Multiple subtitles services are available:
+
+* Addic7ed
+* BierDopje
+* OpenSubtitles
+* SubsWiki
+* Subtitulos
+* TheSubDB
+* TvSubtitles
+
+You can use main subliminal's functions with a **file path**, a **file name** or a **folder path**.
+
+CLI
+^^^
+Download english subtitles::
+
+    $ subliminal -l en The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4
+    **************************************************
+    Downloaded 1 subtitle(s) for 1 video(s)
+    The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.srt from opensubtitles
+    **************************************************
+
+Module
+^^^^^^
+List english subtitles::
+
+    >>> subliminal.list_subtitles('The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4', ['en'])
+
+Multi-threaded use
+^^^^^^^^^^^^^^^^^^
+Use 4 workers to achieve the same result::
+
+    >>> with subliminal.Pool(4) as p:
+    ...     p.list_subtitles('The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4', ['en'])

docs/Makefile

@@ -0,0 +1,153 @@
+# Makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+PAPER         =
+BUILDDIR      = _build
+
+# Internal variables.
+PAPEROPT_a4     = -D latex_paper_size=a4
+PAPEROPT_letter = -D latex_paper_size=letter
+ALLSPHINXOPTS   = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+# the i18n builder cannot share the environment and doctrees with the others
+I18NSPHINXOPTS  = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+
+.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext
+
+help:
+	@echo "Please use \`make <target>' where <target> is one of"
+	@echo "  html       to make standalone HTML files"
+	@echo "  dirhtml    to make HTML files named index.html in directories"
+	@echo "  singlehtml to make a single large HTML file"
+	@echo "  pickle     to make pickle files"
+	@echo "  json       to make JSON files"
+	@echo "  htmlhelp   to make HTML files and a HTML help project"
+	@echo "  qthelp     to make HTML files and a qthelp project"
+	@echo "  devhelp    to make HTML files and a Devhelp project"
+	@echo "  epub       to make an epub"
+	@echo "  latex      to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
+	@echo "  latexpdf   to make LaTeX files and run them through pdflatex"
+	@echo "  text       to make text files"
+	@echo "  man        to make manual pages"
+	@echo "  texinfo    to make Texinfo files"
+	@echo "  info       to make Texinfo files and run them through makeinfo"
+	@echo "  gettext    to make PO message catalogs"
+	@echo "  changes    to make an overview of all changed/added/deprecated items"
+	@echo "  linkcheck  to check all external links for integrity"
+	@echo "  doctest    to run all doctests embedded in the documentation (if enabled)"
+
+clean:
+	-rm -rf $(BUILDDIR)/*
+
+html:
+	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
+
+dirhtml:
+	$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
+
+singlehtml:
+	$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
+	@echo
+	@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
+
+pickle:
+	$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
+	@echo
+	@echo "Build finished; now you can process the pickle files."
+
+json:
+	$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
+	@echo
+	@echo "Build finished; now you can process the JSON files."
+
+htmlhelp:
+	$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
+	@echo
+	@echo "Build finished; now you can run HTML Help Workshop with the" \
+	      ".hhp project file in $(BUILDDIR)/htmlhelp."
+
+qthelp:
+	$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
+	@echo
+	@echo "Build finished; now you can run "qcollectiongenerator" with the" \
+	      ".qhcp project file in $(BUILDDIR)/qthelp, like this:"
+	@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/subliminal.qhcp"
+	@echo "To view the help file:"
+	@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/subliminal.qhc"
+
+devhelp:
+	$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
+	@echo
+	@echo "Build finished."
+	@echo "To view the help file:"
+	@echo "# mkdir -p $$HOME/.local/share/devhelp/subliminal"
+	@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/subliminal"
+	@echo "# devhelp"
+
+epub:
+	$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
+	@echo
+	@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
+
+latex:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo
+	@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
+	@echo "Run \`make' in that directory to run these through (pdf)latex" \
+	      "(use \`make latexpdf' here to do that automatically)."
+
+latexpdf:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through pdflatex..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+text:
+	$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
+	@echo
+	@echo "Build finished. The text files are in $(BUILDDIR)/text."
+
+man:
+	$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
+	@echo
+	@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
+
+texinfo:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo
+	@echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
+	@echo "Run \`make' in that directory to run these through makeinfo" \
+	      "(use \`make info' here to do that automatically)."
+
+info:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo "Running Texinfo files through makeinfo..."
+	make -C $(BUILDDIR)/texinfo info
+	@echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
+
+gettext:
+	$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
+	@echo
+	@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
+
+changes:
+	$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
+	@echo
+	@echo "The overview file is in $(BUILDDIR)/changes."
+
+linkcheck:
+	$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
+	@echo
+	@echo "Link check complete; look for any errors in the above output " \
+	      "or in $(BUILDDIR)/linkcheck/output.txt."
+
+doctest:
+	$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
+	@echo "Testing of doctests in the sources finished, look at the " \
+	      "results in $(BUILDDIR)/doctest/output.txt."

docs/_templates/sidebar-intro.html

@@ -0,0 +1,4 @@
+<h3>About</h3>
+<p>
+  Subliminal is a python library to search and download subtitles.
+</p>

docs/_templates/sidebar-links.html

@@ -0,0 +1,6 @@
+<h3>Useful Links</h3>
+<ul>
+  <li><a href="http://pypi.python.org/pypi/subliminal">subliminal @ PyPI</a></li>
+  <li><a href="http://github.com/Diaoul/subliminal">subliminal @ GitHub</a></li>
+  <li><a href="http://github.com/Diaoul/subliminal/issues">Issue Tracker</a></li>
+</ul>

docs/conf.py

@@ -0,0 +1,255 @@
+# -*- coding: utf-8 -*-
+#
+# subliminal documentation build configuration file, created by
+# sphinx-quickstart on Tue Feb 28 16:33:06 2012.
+#
+# This file is execfile()d with the current directory set to its containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+import sys, os
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+sys.path.insert(0, os.path.abspath('..'))
+sys.path.append(os.path.abspath('_themes'))
+import subliminal.infos
+
+# -- General configuration -----------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be extensions
+# coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
+extensions = ['sphinx.ext.autodoc']
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix of source filenames.
+source_suffix = '.rst'
+
+# The encoding of source files.
+#source_encoding = 'utf-8-sig'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = u'subliminal'
+copyright = u'2012, Antoine Bertin'
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+version = subliminal.infos.__version__
+# The full version, including alpha/beta/rc tags.
+release = version
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#language = None
+
+# There are two options for replacing |today|: either, you set today to some
+# non-false value, then it is used:
+#today = ''
+# Else, today_fmt is used as the format for a strftime call.
+#today_fmt = '%B %d, %Y'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+exclude_patterns = ['_build']
+
+# The reST default role (used for this markup: `text`) to use for all documents.
+#default_role = None
+
+# If true, '()' will be appended to :func: etc. cross-reference text.
+#add_function_parentheses = True
+
+# If true, the current module name will be prepended to all description
+# unit titles (such as .. function::).
+#add_module_names = True
+
+# If true, sectionauthor and moduleauthor directives will be shown in the
+# output. They are ignored by default.
+#show_authors = False
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# A list of ignored prefixes for module index sorting.
+#modindex_common_prefix = []
+
+
+# -- Options for HTML output ---------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+html_theme = 'diaoul'
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+html_theme_options = {'github_user': 'Diaoul',
+                      'github_repo': 'subliminal',
+                      'github_branch': 'develop',
+                      'fork_me': 1,
+                      'flattr_href': 'http://subliminal.readthedocs.org/',
+                      'flattr_thing_url': 'http://flattr.com/thing/629842/Subliminal'}
+
+# Add any paths that contain custom themes here, relative to this directory.
+html_theme_path = ['_themes']
+
+# The name for this set of Sphinx documents.  If None, it defaults to
+# "<project> v<release> documentation".
+#html_title = None
+
+# A shorter title for the navigation bar.  Default is the same as html_title.
+#html_short_title = None
+
+# The name of an image file (relative to this directory) to place at the top
+# of the sidebar.
+html_logo = '_static/subliminal-logo.png'
+
+# The name of an image file (within the static path) to use as favicon of the
+# docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
+# pixels large.
+#html_favicon = None
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
+# using the given strftime format.
+#html_last_updated_fmt = '%b %d, %Y'
+
+# If true, SmartyPants will be used to convert quotes and dashes to
+# typographically correct entities.
+#html_use_smartypants = True
+
+# Custom sidebar templates, maps document names to template names.
+html_sidebars = {
+    'index':    ['sidebar-intro.html', 'sidebar-watch.html', 'sidebar-travis-ci.html', 'sidebar-donate.html', 'localtoc.html', 'sidebar-links.html', 'searchbox.html'],
+    '**':       ['localtoc.html', 'relations.html', 'sourcelink.html']
+    }
+
+# Additional templates that should be rendered to pages, maps page names to
+# template names.
+#html_additional_pages = {}
+
+# If false, no module index is generated.
+#html_domain_indices = True
+
+# If false, no index is generated.
+#html_use_index = True
+
+# If true, the index is split into individual pages for each letter.
+#html_split_index = False
+
+# If true, links to the reST sources are added to the pages.
+#html_show_sourcelink = True
+
+# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
+#html_show_sphinx = True
+
+# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
+#html_show_copyright = True
+
+# If true, an OpenSearch description file will be output, and all pages will
+# contain a <link> tag referring to it.  The value of this option must be the
+# base URL from which the finished HTML is served.
+#html_use_opensearch = ''
+
+# This is the file name suffix for HTML files (e.g. ".xhtml").
+#html_file_suffix = None
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'subliminaldoc'
+
+
+# -- Options for LaTeX output --------------------------------------------------
+
+latex_elements = {
+# The paper size ('letterpaper' or 'a4paper').
+#'papersize': 'letterpaper',
+
+# The font size ('10pt', '11pt' or '12pt').
+#'pointsize': '10pt',
+
+# Additional stuff for the LaTeX preamble.
+#'preamble': '',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title, author, documentclass [howto/manual]).
+latex_documents = [
+  ('index', 'subliminal.tex', u'subliminal Documentation',
+   u'Antoine Bertin', 'manual'),
+]
+
+# The name of an image file (relative to this directory) to place at the top of
+# the title page.
+#latex_logo = None
+
+# For "manual" documents, if this is true, then toplevel headings are parts,
+# not chapters.
+#latex_use_parts = False
+
+# If true, show page references after internal links.
+#latex_show_pagerefs = False
+
+# If true, show URL addresses after external links.
+#latex_show_urls = False
+
+# Documents to append as an appendix to all manuals.
+#latex_appendices = []
+
+# If false, no module index is generated.
+#latex_domain_indices = True
+
+
+# -- Options for manual page output --------------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    ('index', 'subliminal', u'subliminal Documentation',
+     [u'Antoine Bertin'], 1)
+]
+
+# If true, show URL addresses after external links.
+#man_show_urls = False
+
+
+# -- Options for Texinfo output ------------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+  ('index', 'subliminal', u'subliminal Documentation',
+   u'Antoine Bertin', 'subliminal', 'One line description of project.',
+   'Miscellaneous'),
+]
+
+# Documents to append as an appendix to all manuals.
+#texinfo_appendices = []
+
+# If false, no module index is generated.
+#texinfo_domain_indices = True
+
+# How to display URL addresses: 'footnote', 'no', or 'inline'.
+#texinfo_show_urls = 'footnote'
+
+# -- Options for autodoc -------------------------------------------------------
+autodoc_member_order = 'bysource'

docs/dev.rst

@@ -0,0 +1,98 @@
+This guide is going to explain the main logic of subliminal and detail
+every class or function.
+
+Services
+--------
+Subliminal aims at downloading subtitles. Over the web, one can find subtitles
+combining different websites but there is no guarantee of a perfect match.
+Even if OpenSubtitles has a gigantic subtitles database, you may not be able to
+find a subtitle on it but you will find it elsewhere, say BierDopje. Sometimes,
+it just takes some time before it shows up on a website even if already available
+on another, but you do not want to wait to watch the latest Big Bang Theory, right?
+
+Given this, to be reliable, subliminal has to use different :mod:`~subliminal.services`
+and use a unified method to gather them all. The :class:`~subliminal.services.ServiceBase`
+class will achieve this.
+
+.. automodule:: subliminal.services
+    :members:
+
+Languages
+---------
+To be able to support many languages, subliminal makes heavy use of ISO-3166 and ISO-639
+in a dedicated module.
+
+.. automodule:: subliminal.language
+    :members:
+    
+    .. data:: subliminal.language.COUNTRIES
+
+        ISO-3166-1 countries list from `Debian package iso-codes 3.36-1 <http://packages.debian.org/fr/sid/iso-codes>`_.
+        Each item of this list is a tuple like ``(‘alpha2’, ‘alpha3’, ‘numeric’, ‘name’)``
+    
+    .. data:: subliminal.language.LANGUAGES
+
+        ISO-639-2 languages list from `the official source <http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt>`_.
+        Each item of this list is a tuple like ``(‘alpha3’, ‘terminologic’, ‘alpha2’, ‘name’, ‘french_name’)``
+    
+
+Tasks
+-----
+Subliminal is IO bound: it mostly waits for IO operations (web requests) to complete.
+Thus, subliminal is a good place for multi-threading. It works with atomic operations
+represented by a :class:`~subliminal.tasks.Task` class which can be consumed with
+:func:`~subliminal.core.consume_task` but we'll see that later.
+
+.. automodule:: subliminal.tasks
+    :members:
+
+Asynchronous
+------------
+To consume those tasks in an asynchronous way without flooding services with requests,
+subliminal uses multiple instances of the :class:`~subliminal.async.Worker` class that
+will consume the same task queue. Each worker will only create a single instance of each
+:mod:`service <subliminal.services>` and this save some initialization time.
+The :class:`~subliminal.async.Pool` is here to instantiate and manage multiple workers
+at a time.
+
+.. automodule:: subliminal.async
+    :members:
+
+Core
+----
+The goal of subliminal's :mod:`~subliminal.core` module is to merge results from
+consumed tasks. Merging has to be intelligent and take user preferences into account.
+Core module is thus responsible for the computation of a :func:`matching confidence
+<subliminal.core.matching_confidence>` so the user knows the chances that the
+:class:`~subliminal.subtitles.ResultSubtitle` matches the :class:`~subliminal.videos.Video`
+
+.. automodule:: subliminal.core
+    :members:
+
+Other objects
+-------------
+Subliminal uses some other self-explanatory functions and classes listed below.
+
+Video
+^^^^^
+
+.. automodule:: subliminal.videos
+    :members:
+
+Subtitle
+^^^^^^^^
+
+.. automodule:: subliminal.subtitles
+    :members:
+
+Utilities
+^^^^^^^^^
+
+.. automodule:: subliminal.utils
+    :members:
+
+Exceptions
+^^^^^^^^^^
+
+.. automodule:: subliminal.exceptions
+    :members:

docs/index.rst

@@ -0,0 +1,79 @@
+.. subliminal documentation master file, created by
+   sphinx-quickstart on Tue Feb 28 16:33:06 2012.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Subliminal
+==========
+Release v\ |version|
+
+Subliminal is a python library to search and download subtitles.
+
+It uses video hashes and the powerful `guessit <http://guessit.readthedocs.org/>`_ library
+that extracts informations from filenames or filepaths to ensure you have the best subtitles.
+It also relies on `enzyme <https://github.com/Diaoul/enzyme>`_ to detect embedded subtitles
+and avoid duplicates.
+
+Features
+--------
+Multiple subtitles services are available:
+
+* Addic7ed
+* BierDopje
+* OpenSubtitles
+* SubsWiki
+* Subtitulos
+* TheSubDB
+* TvSubtitles
+
+You can use main subliminal's functions with a **file path**, a **file name** or a **folder path**.
+
+CLI
+^^^
+Download english subtitles::
+
+    $ subliminal -l en The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4
+    **************************************************
+    Downloaded 1 subtitle(s) for 1 video(s)
+    The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.srt from opensubtitles
+    **************************************************
+
+Module
+^^^^^^
+List english subtitles::
+
+	>>> subliminal.list_subtitles('The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4', ['en'])
+
+Multi-threaded use
+^^^^^^^^^^^^^^^^^^
+Use 4 workers to achieve the same result::
+
+	>>> with subliminal.Pool(4) as p:
+	... 	p.list_subtitles('The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4', ['en'])
+
+User Guide
+----------
+This part of the documentation details how to use subliminal for most common tasks
+
+.. toctree::
+   :maxdepth: 2
+   
+   user
+
+Developer Guide
+---------------
+This part of the documentation explains internal behavior of subliminal and its algorithms
+
+.. toctree::
+   :maxdepth: 2
+   
+   dev
+
+
+API Documentation
+-----------------
+Most common subliminal features are listed here
+
+.. automodule:: subliminal
+    :members:
+    :noindex:

docs/user.rst

@@ -0,0 +1,118 @@
+There are 4 different ways of using subliminal and each one is described in a dedicated section below.
+
+First, here are some basics
+
+Basics
+------
+Services
+^^^^^^^^
+You can use subliminal with multiple services to get the best result.
+Current available services are available in the :data:`subliminal.SERVICES` variable.
+
+.. autodata:: subliminal.SERVICES
+
+Languages
+^^^^^^^^^
+Subliminal supports multiple languages representations based on `ISO-639 <http://en.wikipedia.org/wiki/ISO_639>`_
+and `ISO-3166 <http://en.wikipedia.org/wiki/ISO_3166>`_. Any single ISO-639 string or combination of ISO-639 and
+ISO-3166 is acceptable. For example, you can use ``pt-br`` for Portuguese (Brazil) or ``en`` for English.
+
+Paths
+^^^^^
+All paths parameters in subliminal most commont functions can be either *a file path*,
+*a file name* or a *folder path*
+
+* File path (existing): hashes of the file will be computed and used during the search for services that
+  supports this functionnality.
+* File name (or non-existing file path): the guessit python library will be used to guess informations
+  and a text-based search will be done with services.
+* Folder path (containing video files): the given folder will be searched for video files using their
+  :data:`~subliminal.videos.MIMETYPES` and/or :data:`~subliminal.videos.EXTENSIONS`.
+  The default maximum depth to scan is 3
+
+CLI
+---
+Subliminal is shipped with a Command Line Interface that allows you to
+download subtitles for one or more videos in a multithreaded way.
+
+.. note::
+
+    The cache directory defaults to *~/.config/subliminal*. Even on Windows
+
+Usage
+^^^^^
+You can have the documentation of the CLI using ``subliminal --help``::
+
+    usage: subliminal [-h] [-l LG] [-s NAME] [-m] [-f] [-w N] [-a AGE] [-c]
+                      [-q | -v] [--cache-dir DIR | --no-cache-dir] [--version]
+                      PATH [PATH ...]
+
+    Subtitles, faster than your thoughts
+
+    positional arguments:
+      PATH                  path to video file or folder
+
+    optional arguments:
+      -h, --help            show this help message and exit
+      -l LG, --language LG  wanted language (ISO 639-1)
+      -s NAME, --service NAME
+                            service to use
+      -m, --multi           download multiple subtitle languages
+      -f, --force           replace existing subtitle file
+      -w N, --workers N     use N threads (default: 4)
+      -a AGE, --age AGE     scan only for files newer or older (prefix with +)
+                            than AGE (e.g. 12h, 1w2d, +3d6h)
+      -c, --compatibility   try not to use unicode (use this if you have encoding
+                            errors)
+      -q, --quiet           disable output
+      -v, --verbose         verbose output
+      --cache-dir DIR       cache directory to use
+      --no-cache-dir        do not use cache directory (some services may not
+                            work)
+      --version             show program's version number and exit
+
+Cron job
+^^^^^^^^
+This CLI is well suited for automatic subtitles downloads. For example, to download english and french
+subtitles for videos newer than one week under /path/to/videos/ each day at 1:00AM with a single worker,
+you can use the following crontab line::
+
+    0 1 * * * user /path/to/subliminal -m -l en -l fr -w 1 -a 1w -q /path/to/videos/
+
+Simple module use
+-----------------
+Subliminal comes with two basic functions to search and download subtitles. For example, you
+can do::
+
+    >>> subliminal.list_subtitles('The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4', ['en'])
+
+.. autofunction:: subliminal.list_subtitles
+
+Or even download missing subtitles for each episodes under the given folders in two different languages::
+
+    >>> subliminal.download_subtitles(['/mnt/videos/BBT/Season 05', '/mnt/videos/HIMYM/Season 07'],
+    ...                               ['en', 'fr'], force=False, multi=True)
+
+.. autofunction:: subliminal.download_subtitles
+
+Multi-threaded module use
+-------------------------
+You can call the same functions on a :class:`subliminal.Pool` object previously
+created with the appropriate number of workers.
+
+.. autoclass:: subliminal.Pool
+    :members:
+
+You have to call the :meth:`~subliminal.Pool.start` method before any actions and
+:meth:`~subliminal.Pool.stop` before exiting your program::
+
+    >>> p = subliminal.Pool(4)
+    ... p.start()
+    ... p.list_subtitles('The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4', ['en'])
+    ... p.stop()
+
+To make the use of :class:`~subliminal.Pool` easier, you can use the ``with`` statement
+that takes care of that for you::
+
+    >>> with subliminal.Pool(4) as p:
+    ...     p.list_subtitles('The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4', ['en'])

optional-requirements.txt

@@ -0,0 +1 @@
+lxml

requirements.txt

@@ -0,0 +1,5 @@
+beautifulsoup4>=4.0
+guessit>=0.4.1
+requests<1.0
+enzyme<0.3
+html5lib

scripts/subliminal

@@ -1,100 +1,99 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
 #
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
+# This file is part of subliminal.
 #
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
 # the Free Software Foundation; either version 3 of the License, or
 # (at your option) any later version.
 #
-# Subliminal is distributed in the hope that it will be useful,
+# subliminal is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
+# GNU Lesser General Public License for more details.
 #
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from optparse import OptionParser
-import subliminal
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+import argparse
+import datetime
 import logging
-import mimetypes
 import os
+import re
+import subliminal
 import sys
 
 
 def main():
-    '''Download subtitles'''
-    # parse command line options
-    parser = OptionParser("usage: %prog [options] file1 file2", version=subliminal.__version__)
-    parser.add_option("-l", "--language", action="append", dest="languages", help="wanted language (ISO 639-1 two chars) for the subtitles (e.g. fr, en). Multiple uses allowed such that `%prog -l fr -l en file1`")
-    parser.add_option("-m", "--multi", action="store_true", dest="multi", help="download one subtitle per specified language (instead of one of them) and name them accordingly (e.g. .fr.srt, .en.srt)")
-    parser.add_option("-p", "--plugin", action="append", dest="plugins", help="plugins to activate")
-    parser.add_option("-f", "--force", action="store_true", dest="force", help="force download of a subtitle even there is already one present")
-    parser.add_option("-C", "--no-config-file", action="store_false", dest="config", help="do not use configuration file (requires -l to be specified)")
-    parser.add_option("-c", "--config-file", action="store", dest="config", help="configuration file to use")
-    parser.add_option("-w", "--workers", action="store", dest="workers", help="specify the number of threads to use")
-    parser.add_option("--cache-dir", action="store", dest="cache_dir", help="cache directory to use")
-    parser.add_option("--no-cache-dir", action="store_false", dest="cache_dir", help="do not use cache directory (some plugins may not work)")
-    parser.add_option("--list-all-plugins", action="store_true", dest="list_all_plugins", help="list all plugins available")
-    parser.add_option("--list-api-plugins", action="store_true", dest="list_api_plugins", help="list api-based plugins")
-    parser.add_option("--list-active-plugins", action="store_true", dest="list_active_plugins", help="list currently active plugins")
-    parser.add_option("-v", "--verbose", action="count", dest="verbose", help="increase verbosity (maximum 2 times)")
-    parser.set_defaults(verbose=0, cache_dir=True, config=True, workers=4)
-    (options, args) = parser.parse_args()
-    if not args:
-        print parser.print_help()
-        exit(1)
-    if options.verbose == 2:
-        logging.basicConfig(level=logging.DEBUG, format='%(asctime)s %(name)-24s %(levelname)-8s %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
-    elif options.verbose == 1:
-        logging.basicConfig(level=logging.WARN, format='%(levelname)s: %(name)s %(message)s')
-    else:
-        logging.basicConfig(level=logging.ERROR)
-    if not options.config and not options.languages:
-        parser.error("Option -C (--no-config-file) is used without -l (--language)")
-    subliminal_client = subliminal.Subliminal(config=options.config, cache_dir=options.cache_dir, workers=options.workers, multi=options.multi, force=options.force, max_depth=3, autostart=False)
-    if options.plugins:
-        subliminal_client.plugins = options.plugins
-    if options.list_all_plugins:
-        plugins = subliminal_client.listExistingPlugins()
-        print ', '.join(subliminal_client.listExistingPlugins())
-        exit(0)
-    if options.list_api_plugins:
-        plugins = subliminal_client.list_api_plugins()
-        print ', '.join(subliminal_client.listExistingPlugins())
-        exit(0)
-    if options.list_active_plugins:
-        plugins = subliminal_client.plugins
-        print ', '.join(subliminal_client.listExistingPlugins())
-        exit(0)
-    if options.languages:
-        subliminal_client.languages = options.languages
-    else:
-        logging.info(u"No language given, looking into configuration file")
-        languages = subliminal_client.languages
-        if not languages:
-            logging.error(u"No language found in configuration file")
-            sys.stderr.write("No language found in configuration file")
-            exit(1)
-            parser.exit
-    subliminal_client.startWorkers()
-    subtitles = subliminal_client.downloadSubtitles(args)
-    subliminal_client.stopWorkers()
-    if len(subtitles) == 0:
-        sys.stderr.write("No subtitles found")
-        exit(1)
-    print "*" * 50
-    print "Downloaded %s subtitles" % len(subtitles)
-    for s in subtitles:
-        print s['lang'] + " - " + s['subtitlepath']
-    print "*" * 50
+    parser = argparse.ArgumentParser(description='Subtitles, faster than your thoughts')
+    parser.add_argument('-l', '--language', action='append', dest='languages', help='wanted language (ISO 639-1)', metavar='LG')
+    parser.add_argument('-s', '--service', action='append', dest='services', help='service to use (%s)' % ', '.join(subliminal.core.filter_services(subliminal.SERVICES)), metavar='NAME')
+    parser.add_argument('-m', '--multi', action='store_true', help='download multiple subtitle languages')
+    parser.add_argument('-f', '--force', action='store_true', help='replace existing subtitle file')
+    parser.add_argument('-w', '--workers', action='store', help='use N threads (default: %(default)s)', metavar='N', type=int, default=4)
+    parser.add_argument('-a', '--age', action='store', help='scan only for files newer or older (prefix with +) than AGE (e.g. 12h, 1w2d, +3d6h)', metavar='AGE', default=None)
+    parser.add_argument('-c', '--compatibility', action='store_true', help='try not to use unicode (use this if you have encoding errors)')
+    group_verbosity = parser.add_mutually_exclusive_group()
+    group_verbosity.add_argument('-q', '--quiet', action='store_true', help='disable output')
+    group_verbosity.add_argument('-v', '--verbose', action='store_true', help='verbose output')
+    group_cache = parser.add_mutually_exclusive_group()
+    group_cache.add_argument('--cache-dir', action='store', dest='cache_dir', help='cache directory to use', metavar='DIR', default=os.path.expanduser('~/.config/subliminal'))
+    group_cache.add_argument('--no-cache-dir', action='store_false', dest='cache_dir', help='do not use cache directory (some services may not work)')
+    parser.add_argument('--version', action='version', version=subliminal.__version__)
+    parser.add_argument('paths', nargs='+', help='path to video file or folder', metavar='PATH')
+    args = parser.parse_args()
 
-if __name__ == "__main__":
+    # Set log verbosity
+    if args.verbose:
+        logging.basicConfig(level=logging.DEBUG, format='%(levelname)-8s %(asctime)s %(name)-24s %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
+    elif not args.quiet:
+        logging.basicConfig(level=logging.WARN, format='%(levelname)s: %(name)s %(message)s')
+
+    # Create cache directory
+    if not os.path.exists(args.cache_dir):
+        os.mkdir(args.cache_dir)
+
+    # Create filter function
+    scan_filter = None
+    if args.age:
+        regex = re.compile(r'^(?P<sign>\+?)((?P<weeks>\d+?)w)?((?P<days>\d+?)d)?((?P<hours>\d+?)h)?')
+        parts = regex.match(args.age)
+        if not parts:
+            raise ValueError('Incorrect age format')
+        time_params = {}
+        parts = parts.groupdict()
+        for name, param in parts.iteritems():
+            if param and name != 'sign':
+                time_params[name] = int(param)
+        if parts['sign'] == '+':
+            scan_filter = lambda x: datetime.datetime.now() - datetime.datetime.fromtimestamp(os.path.getmtime(x)) < datetime.timedelta(**time_params)
+        else:
+            scan_filter = lambda x: datetime.datetime.now() - datetime.datetime.fromtimestamp(os.path.getmtime(x)) > datetime.timedelta(**time_params)
+
+    # Compatibility mode
+    if args.compatibility:
+        paths = args.paths
+    else:
+        paths = [unicode(x) for x in args.paths]
+
+    # Download subtitles
+    with subliminal.Pool(args.workers) as p:
+        results = p.download_subtitles(paths, languages=args.languages, services=args.services, cache_dir=args.cache_dir,
+                                       force=args.force, multi=args.multi, scan_filter=scan_filter)
+
+    if not results:
+        if not args.quiet:
+            sys.stderr.write('No subtitles downloaded\n')
+        exit(1)
+    if not args.quiet:
+        print '*' * 50
+        print 'Downloaded %d subtitle(s) for %d video(s)' % (sum([len(s) for s in results.itervalues()]), len(results))
+        for _, subtitles in results.iteritems():
+            for subtitle in subtitles:
+                print '%s from %s' % (subtitle.path, subtitle.service)
+        print '*' * 50
+
+
+if __name__ == '__main__':
     main()

setup.cfg

@@ -0,0 +1,7 @@
+[build_sphinx]
+source-dir = docs/
+build-dir  = docs/_build
+all_files  = 1
+
+[upload_sphinx]
+upload-dir = docs/_build/html

setup.py

@@ -1,45 +1,53 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
 #
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
+# This file is part of subliminal.
 #
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
 # the Free Software Foundation; either version 3 of the License, or
 # (at your option) any later version.
 #
-# Subliminal is distributed in the hope that it will be useful,
+# subliminal is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
+# GNU Lesser General Public License for more details.
 #
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from setuptools import setup
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+import os.path
+import sys
+from setuptools import setup, find_packages
 
 
-execfile('subliminal/version.py')
+def read(fname):
+    return open(os.path.join(os.path.dirname(__file__), fname)).read()
+
+required = ['beautifulsoup4 >= 4.0', 'guessit >= 0.4.1', 'requests < 1.0', 'enzyme < 0.3', 'html5lib']
+if sys.hexversion < 0x20700f0:
+    required.append('argparse >= 1.1')
+
+execfile(os.path.join(os.path.dirname(__file__), 'subliminal', 'infos.py'))
 setup(name='subliminal',
     version=__version__,
     license='LGPLv3',
-    description='Subliminal - Subtitles, faster than your thoughts',
+    description='Subtitles, faster than your thoughts',
+    long_description=read('README.rst') + '\n\n' + read('NEWS.rst'),
     classifiers=['Development Status :: 4 - Beta',
         'License :: OSI Approved :: GNU Library or Lesser General Public License (LGPL)',
         'Intended Audience :: Developers',
         'Operating System :: OS Independent',
         'Programming Language :: Python :: 2.6',
+        'Programming Language :: Python :: 2.7',
         'Topic :: Software Development :: Libraries :: Python Modules',
         'Topic :: Multimedia :: Video'],
-    keywords='subliminal video movie subtitle python library',
+    keywords='subtitle subtitles video movie episode tv show',
     author='Antoine Bertin',
     author_email='diaoulael@gmail.com',
     url='https://github.com/Diaoul/subliminal',
-    packages=['subliminal', 'subliminal/plugins'],
+    packages=find_packages(),
     scripts=['scripts/subliminal'],
-    py_modules=['subliminal'],
-    install_requires=['BeautifulSoup>=3.2.0', 'guessit>=0.2'])
+    test_suite='tests.suite',
+    install_requires=required,
+    extras_require={'full': ['lxml']})

subliminal/PluginWorker.py

@@ -1,71 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import threading
-import plugins
-import logging
-import traceback
-
-
-class PluginWorker(threading.Thread):
-    """Threaded plugin worker"""
-    def __init__(self, taskQueue, resultQueue):
-        threading.Thread.__init__(self)
-        self.taskQueue = taskQueue
-        self.resultQueue = resultQueue
-        self.logger = logging.getLogger('subliminal.worker')
-
-    def run(self):
-        while True:
-            task = self.taskQueue.get()
-            result = None
-            try:
-                if not task:  # this is a poison pill
-                    break
-                elif task['task'] == 'list':  # the task is a listing
-                    # get the corresponding plugin
-                    plugin = getattr(plugins, task['plugin'])(task['config'])
-                    # split tasks if the plugin can't handle multi queries
-                    splitedTasks = plugin.splitTask(task)
-                    myTask = splitedTasks.pop()
-                    for st in splitedTasks:
-                        self.taskQueue.put(st)
-                    result = plugin.list(myTask['filenames'], myTask['languages'])
-                elif task['task'] == 'download':  # the task is to download
-                    result = None
-                    while task['subtitle']:
-                        subtitle = task['subtitle'].pop(0)
-                        # get the corresponding plugin
-                        plugin = getattr(plugins, subtitle['plugin'])(task['config'])
-                        path = plugin.download(subtitle)
-                        if path:
-                            subtitle['subtitlepath'] = path
-                            result = subtitle
-                            break
-                else:
-                    self.logger.error(u'Unknown task %s submited to worker %s' % (task['task'], self.name))
-            except:
-                self.logger.debug(traceback.print_exc())
-                self.logger.error(u"Worker couldn't do the job %s, continue anyway" % task['task'])
-            finally:
-                self.resultQueue.put(result)
-                self.taskQueue.task_done()
-        self.logger.debug(u'Thread %s terminated' % self.name)

subliminal/__init__.py

@@ -1,23 +1,34 @@
 # -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
 #
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
+# This file is part of subliminal.
 #
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
 # the Free Software Foundation; either version 3 of the License, or
 # (at your option) any later version.
 #
-# Subliminal is distributed in the hope that it will be useful,
+# subliminal is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+# GNU Lesser General Public License for more details.
 #
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from .api import list_subtitles, download_subtitles
+from .async import Pool
+from .core import (SERVICES, LANGUAGE_INDEX, SERVICE_INDEX, SERVICE_CONFIDENCE,
+    MATCHING_CONFIDENCE)
+from .infos import __version__
+import logging
+try:
+    from logging import NullHandler
+except ImportError:
+    class NullHandler(logging.Handler):
+        def emit(self, record):
+            pass
 
-from subliminal import Subliminal
-from version import __version__
+
+__all__ = ['SERVICES', 'LANGUAGE_INDEX', 'SERVICE_INDEX', 'SERVICE_CONFIDENCE',
+           'MATCHING_CONFIDENCE', 'list_subtitles', 'download_subtitles', 'Pool']
+logging.getLogger(__name__).addHandler(NullHandler())

subliminal/api.py

@@ -0,0 +1,109 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from .core import (SERVICES, LANGUAGE_INDEX, SERVICE_INDEX, SERVICE_CONFIDENCE,
+    MATCHING_CONFIDENCE, create_list_tasks, consume_task, create_download_tasks,
+    group_by_video, key_subtitles)
+from .language import language_set, language_list, LANGUAGES
+import logging
+
+
+__all__ = ['list_subtitles', 'download_subtitles']
+logger = logging.getLogger(__name__)
+
+
+def list_subtitles(paths, languages=None, services=None, force=True, multi=False, cache_dir=None, max_depth=3, scan_filter=None):
+    """List subtitles in given paths according to the criteria
+
+    :param paths: path(s) to video file or folder
+    :type paths: string or list
+    :param languages: languages to search for, in preferred order
+    :type languages: list of :class:`~subliminal.language.Language` or string
+    :param list services: services to use for the search, in preferred order
+    :param bool force: force searching for subtitles even if some are detected
+    :param bool multi: search multiple languages for the same video
+    :param string cache_dir: path to the cache directory to use
+    :param int max_depth: maximum depth for scanning entries
+    :param function scan_filter: filter function that takes a path as argument and returns a boolean indicating whether it has to be filtered out (``True``) or not (``False``)
+    :return: found subtitles
+    :rtype: dict of :class:`~subliminal.videos.Video` => [:class:`~subliminal.subtitles.ResultSubtitle`]
+
+    """
+    services = services or SERVICES
+    languages = language_set(languages) if languages is not None else language_set(LANGUAGES)
+    if isinstance(paths, basestring):
+        paths = [paths]
+    if any([not isinstance(p, unicode) for p in paths]):
+        logger.warning(u'Not all entries are unicode')
+    results = []
+    service_instances = {}
+    tasks = create_list_tasks(paths, languages, services, force, multi, cache_dir, max_depth, scan_filter)
+    for task in tasks:
+        try:
+            result = consume_task(task, service_instances)
+            results.append((task.video, result))
+        except:
+            logger.error(u'Error consuming task %r' % task, exc_info=True)
+    for service_instance in service_instances.itervalues():
+        service_instance.terminate()
+    return group_by_video(results)
+
+
+def download_subtitles(paths, languages=None, services=None, force=True, multi=False, cache_dir=None, max_depth=3, scan_filter=None, order=None):
+    """Download subtitles in given paths according to the criteria
+
+    :param paths: path(s) to video file or folder
+    :type paths: string or list
+    :param languages: languages to search for, in preferred order
+    :type languages: list of :class:`~subliminal.language.Language` or string
+    :param list services: services to use for the search, in preferred order
+    :param bool force: force searching for subtitles even if some are detected
+    :param bool multi: search multiple languages for the same video
+    :param string cache_dir: path to the cache directory to use
+    :param int max_depth: maximum depth for scanning entries
+    :param function scan_filter: filter function that takes a path as argument and returns a boolean indicating whether it has to be filtered out (``True``) or not (``False``)
+    :param order: preferred order for subtitles sorting
+    :type list: list of :data:`~subliminal.core.LANGUAGE_INDEX`, :data:`~subliminal.core.SERVICE_INDEX`, :data:`~subliminal.core.SERVICE_CONFIDENCE`, :data:`~subliminal.core.MATCHING_CONFIDENCE`
+    :return: downloaded subtitles
+    :rtype: dict of :class:`~subliminal.videos.Video` => [:class:`~subliminal.subtitles.ResultSubtitle`]
+
+    .. note::
+
+        If you use ``multi=True``, :data:`~subliminal.core.LANGUAGE_INDEX` has to be the first item of the ``order`` list
+        or you might get unexpected results.
+
+    """
+    services = services or SERVICES
+    languages = language_list(languages) if languages is not None else language_list(LANGUAGES)
+    if isinstance(paths, basestring):
+        paths = [paths]
+    order = order or [LANGUAGE_INDEX, SERVICE_INDEX, SERVICE_CONFIDENCE, MATCHING_CONFIDENCE]
+    subtitles_by_video = list_subtitles(paths, languages, services, force, multi, cache_dir, max_depth, scan_filter)
+    for video, subtitles in subtitles_by_video.iteritems():
+        subtitles.sort(key=lambda s: key_subtitles(s, video, languages, services, order), reverse=True)
+    results = []
+    service_instances = {}
+    tasks = create_download_tasks(subtitles_by_video, languages, multi)
+    for task in tasks:
+        try:
+            result = consume_task(task, service_instances)
+            results.append((task.video, result))
+        except:
+            logger.error(u'Error consuming task %r' % task, exc_info=True)
+    for service_instance in service_instances.itervalues():
+        service_instance.terminate()
+    return group_by_video(results)

subliminal/async.py

@@ -0,0 +1,142 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from .core import (consume_task, LANGUAGE_INDEX, SERVICE_INDEX,
+    SERVICE_CONFIDENCE, MATCHING_CONFIDENCE, SERVICES, create_list_tasks,
+    create_download_tasks, group_by_video, key_subtitles)
+from .language import language_list, language_set, LANGUAGES
+from .tasks import StopTask
+import Queue
+import logging
+import threading
+
+
+__all__ = ['Worker', 'Pool']
+logger = logging.getLogger(__name__)
+
+
+class Worker(threading.Thread):
+    """Consume tasks and put the result in the queue"""
+    def __init__(self, tasks, results):
+        super(Worker, self).__init__()
+        self.tasks = tasks
+        self.results = results
+        self.services = {}
+
+    def run(self):
+        while 1:
+            result = []
+            try:
+                task = self.tasks.get(block=True)
+                if isinstance(task, StopTask):
+                    break
+                result = consume_task(task, self.services)
+                self.results.put((task.video, result))
+            except:
+                logger.error(u'Exception raised in worker %s' % self.name, exc_info=True)
+            finally:
+                self.tasks.task_done()
+        self.terminate()
+        logger.debug(u'Thread %s terminated' % self.name)
+
+    def terminate(self):
+        """Terminate instantiated services"""
+        for service_name, service in self.services.iteritems():
+            try:
+                service.terminate()
+            except:
+                logger.error(u'Exception raised when terminating service %s' % service_name, exc_info=True)
+
+
+class Pool(object):
+    """Pool of workers"""
+    def __init__(self, size):
+        self.tasks = Queue.Queue()
+        self.results = Queue.Queue()
+        self.workers = []
+        for _ in range(size):
+            self.workers.append(Worker(self.tasks, self.results))
+
+    def __enter__(self):
+        self.start()
+        return self
+
+    def __exit__(self, *args):
+        self.stop()
+        self.join()
+
+    def start(self):
+        """Start workers"""
+        for worker in self.workers:
+            worker.start()
+
+    def stop(self):
+        """Stop workers"""
+        for _ in self.workers:
+            self.tasks.put(StopTask())
+
+    def join(self):
+        """Join the task queue"""
+        self.tasks.join()
+
+    def collect(self):
+        """Collect available results
+
+        :return: results of tasks
+        :rtype: list of :class:`~subliminal.tasks.Task`
+
+        """
+        results = []
+        while 1:
+            try:
+                result = self.results.get(block=False)
+                results.append(result)
+            except Queue.Empty:
+                break
+        return results
+
+    def list_subtitles(self, paths, languages=None, services=None, force=True, multi=False, cache_dir=None, max_depth=3, scan_filter=None):
+        """See :meth:`subliminal.list_subtitles`"""
+        services = services or SERVICES
+        languages = language_set(languages) if languages is not None else language_set(LANGUAGES)
+        if isinstance(paths, basestring):
+            paths = [paths]
+        if any([not isinstance(p, unicode) for p in paths]):
+            logger.warning(u'Not all entries are unicode')
+        tasks = create_list_tasks(paths, languages, services, force, multi, cache_dir, max_depth, scan_filter)
+        for task in tasks:
+            self.tasks.put(task)
+        self.join()
+        results = self.collect()
+        return group_by_video(results)
+
+    def download_subtitles(self, paths, languages=None, services=None, force=True, multi=False, cache_dir=None, max_depth=3, scan_filter=None, order=None):
+        """See :meth:`subliminal.download_subtitles`"""
+        services = services or SERVICES
+        languages = language_list(languages) if languages is not None else language_list(LANGUAGES)
+        if isinstance(paths, basestring):
+            paths = [paths]
+        order = order or [LANGUAGE_INDEX, SERVICE_INDEX, SERVICE_CONFIDENCE, MATCHING_CONFIDENCE]
+        subtitles_by_video = self.list_subtitles(paths, languages, services, force, multi, cache_dir, max_depth, scan_filter)
+        for video, subtitles in subtitles_by_video.iteritems():
+            subtitles.sort(key=lambda s: key_subtitles(s, video, languages, services, order), reverse=True)
+        tasks = create_download_tasks(subtitles_by_video, languages, multi)
+        for task in tasks:
+            self.tasks.put(task)
+        self.join()
+        results = self.collect()
+        return group_by_video(results)

subliminal/cache.py

@@ -0,0 +1,134 @@
+# -*- coding: utf-8 -*-
+# Copyright 2012 Nicolas Wack <wackou@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from collections import defaultdict
+from functools import wraps
+import logging
+import os.path
+import threading
+try:
+    import cPickle as pickle
+except ImportError:
+    import pickle
+
+
+__all__ = ['Cache', 'cachedmethod']
+logger = logging.getLogger(__name__)
+
+
+class Cache(object):
+    """A Cache object contains cached values for methods. It can have
+    separate internal caches, one for each service
+
+    """
+    def __init__(self, cache_dir):
+        self.cache_dir = cache_dir
+        self.cache = defaultdict(dict)
+        self.lock = threading.RLock()
+
+    def __del__(self):
+        for service_name in self.cache:
+            self.save(service_name)
+
+    def cache_location(self, service_name):
+        return os.path.join(self.cache_dir, 'subliminal_%s.cache' % service_name)
+
+    def load(self, service_name):
+        with self.lock:
+            if service_name in self.cache:
+                # already loaded
+                return
+
+            self.cache[service_name] = defaultdict(dict)
+            filename = self.cache_location(service_name)
+            logger.debug(u'Cache: loading cache from %s' % filename)
+            try:
+                self.cache[service_name] = pickle.load(open(filename, 'rb'))
+            except IOError:
+                logger.info('Cache: Cache file "%s" doesn\'t exist, creating it' % filename)
+            except EOFError:
+                logger.error('Cache: cache file "%s" is corrupted... Removing it.' % filename)
+                os.remove(filename)
+
+    def save(self, service_name):
+        filename = self.cache_location(service_name)
+        logger.debug(u'Cache: saving cache to %s' % filename)
+        with self.lock:
+            pickle.dump(self.cache[service_name], open(filename, 'wb'))
+
+    def clear(self, service_name):
+        try:
+            os.remove(self.cache_location(service_name))
+        except OSError:
+            pass
+        self.cache[service_name] = defaultdict(dict)
+
+    def cached_func_key(self, func, cls=None):
+        try:
+            cls = func.im_class
+        except:
+            pass
+        return ('%s.%s' % (cls.__module__, cls.__name__), func.__name__)
+
+    def function_cache(self, service_name, func):
+        func_key = self.cached_func_key(func)
+        return self.cache[service_name][func_key]
+
+    def cache_for(self, service_name, func, args, result):
+        # no need to lock here, dict ops are atomic
+        self.function_cache(service_name, func)[args] = result
+
+    def cached_value(self, service_name, func, args):
+        """Raises KeyError if not found"""
+        # no need to lock here, dict ops are atomic
+        return self.function_cache(service_name, func)[args]
+
+
+def cachedmethod(function):
+    """Decorator to make a method use the cache.
+
+    .. note::
+
+        This can NOT be used with static functions, it has to be used on
+        methods of some class
+
+    """
+    @wraps(function)
+    def cached(*args):
+        c = args[0].config.cache
+        service_name = args[0].__class__.__name__
+        func_key = c.cached_func_key(function, cls=args[0].__class__)
+        func_cache = c.cache[service_name][func_key]
+
+        # we need to remove the first element of args for the key, as it is the
+        # instance pointer and we don't want the cache to know which instance
+        # called it, it is shared among all instances of the same class
+        key = args[1:]
+
+        if key in func_cache:
+            result = func_cache[key]
+            logger.debug(u'Using cached value for %s(%s), returns: %s' % (func_key, key, result))
+            return result
+
+        result = function(*args)
+
+        # note: another thread could have already cached a value in the
+        # meantime, but that's ok as we prefer to keep the latest value in
+        # the cache
+        func_cache[key] = result
+        return result
+    return cached

subliminal/core.py

@@ -0,0 +1,275 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from .exceptions import DownloadFailedError
+from .services import ServiceConfig
+from .tasks import DownloadTask, ListTask
+from .utils import get_keywords
+from .videos import Episode, Movie, scan
+from .language import Language
+from collections import defaultdict
+from itertools import groupby
+import bs4
+import guessit
+import logging
+
+
+__all__ = ['SERVICES', 'LANGUAGE_INDEX', 'SERVICE_INDEX', 'SERVICE_CONFIDENCE', 'MATCHING_CONFIDENCE',
+           'create_list_tasks', 'create_download_tasks', 'consume_task', 'matching_confidence',
+           'key_subtitles', 'group_by_video']
+logger = logging.getLogger(__name__)
+SERVICES = ['opensubtitles', 'bierdopje', 'subswiki', 'subtitulos', 'thesubdb', 'addic7ed', 'tvsubtitles']
+LANGUAGE_INDEX, SERVICE_INDEX, SERVICE_CONFIDENCE, MATCHING_CONFIDENCE = range(4)
+
+
+def create_list_tasks(paths, languages, services, force, multi, cache_dir, max_depth, scan_filter):
+    """Create a list of :class:`~subliminal.tasks.ListTask` from one or more paths using the given criteria
+
+    :param paths: path(s) to video file or folder
+    :type paths: string or list
+    :param set languages: languages to search for
+    :param list services: services to use for the search
+    :param bool force: force searching for subtitles even if some are detected
+    :param bool multi: search multiple languages for the same video
+    :param string cache_dir: path to the cache directory to use
+    :param int max_depth: maximum depth for scanning entries
+    :param function scan_filter: filter function that takes a path as argument and returns a boolean indicating whether it has to be filtered out (``True``) or not (``False``)
+    :return: the created tasks
+    :rtype: list of :class:`~subliminal.tasks.ListTask`
+
+    """
+    scan_result = []
+    for p in paths:
+        scan_result.extend(scan(p, max_depth, scan_filter))
+    logger.debug(u'Found %d videos in %r with maximum depth %d' % (len(scan_result), paths, max_depth))
+    tasks = []
+    config = ServiceConfig(multi, cache_dir)
+    services = filter_services(services)
+    for video, detected_subtitles in scan_result:
+        detected_languages = set(s.language for s in detected_subtitles)
+        wanted_languages = languages.copy()
+        if not force and multi:
+            wanted_languages -= detected_languages
+            if not wanted_languages:
+                logger.debug(u'No need to list multi subtitles %r for %r because %r detected' % (languages, video, detected_languages))
+                continue
+        if not force and not multi and Language('Undetermined') in detected_languages:
+            logger.debug(u'No need to list single subtitles %r for %r because one detected' % (languages, video))
+            continue
+        logger.debug(u'Listing subtitles %r for %r with services %r' % (wanted_languages, video, services))
+        for service_name in services:
+            mod = __import__('services.' + service_name, globals=globals(), locals=locals(), fromlist=['Service'], level=-1)
+            service = mod.Service
+            if not service.check_validity(video, wanted_languages):
+                continue
+            task = ListTask(video, wanted_languages & service.languages, service_name, config)
+            logger.debug(u'Created task %r' % task)
+            tasks.append(task)
+    return tasks
+
+
+def create_download_tasks(subtitles_by_video, languages, multi):
+    """Create a list of :class:`~subliminal.tasks.DownloadTask` from a list results grouped by video
+
+    :param subtitles_by_video: :class:`~subliminal.tasks.ListTask` results with ordered subtitles
+    :type subtitles_by_video: dict of :class:`~subliminal.videos.Video` => [:class:`~subliminal.subtitles.Subtitle`]
+    :param languages: languages in preferred order
+    :type languages: :class:`~subliminal.language.language_list`
+    :param bool multi: download multiple languages for the same video
+    :return: the created tasks
+    :rtype: list of :class:`~subliminal.tasks.DownloadTask`
+
+    """
+    tasks = []
+    for video, subtitles in subtitles_by_video.iteritems():
+        if not subtitles:
+            continue
+        if not multi:
+            task = DownloadTask(video, list(subtitles))
+            logger.debug(u'Created task %r' % task)
+            tasks.append(task)
+            continue
+        for _, by_language in groupby(subtitles, lambda s: languages.index(s.language)):
+            task = DownloadTask(video, list(by_language))
+            logger.debug(u'Created task %r' % task)
+            tasks.append(task)
+    return tasks
+
+
+def consume_task(task, services=None):
+    """Consume a task. If the ``services`` parameter is given, the function will attempt
+    to get the service from it. In case the service is not in ``services``, it will be initialized
+    and put in ``services``
+
+    :param task: task to consume
+    :type task: :class:`~subliminal.tasks.ListTask` or :class:`~subliminal.tasks.DownloadTask`
+    :param dict services: mapping between the service name and an instance of this service
+    :return: the result of the task
+    :rtype: list of :class:`~subliminal.subtitles.ResultSubtitle`
+
+    """
+    if services is None:
+        services = {}
+    logger.info(u'Consuming %r' % task)
+    result = None
+    if isinstance(task, ListTask):
+        service = get_service(services, task.service, config=task.config)
+        result = service.list(task.video, task.languages)
+    elif isinstance(task, DownloadTask):
+        for subtitle in task.subtitles:
+            service = get_service(services, subtitle.service)
+            try:
+                service.download(subtitle)
+                result = [subtitle]
+                break
+            except DownloadFailedError:
+                logger.warning(u'Could not download subtitle %r, trying next' % subtitle)
+                continue
+        if result is None:
+            logger.error(u'No subtitles could be downloaded for video %r' % task.video)
+    return result
+
+
+def matching_confidence(video, subtitle):
+    """Compute the probability (confidence) that the subtitle matches the video
+
+    :param video: video to match
+    :type video: :class:`~subliminal.videos.Video`
+    :param subtitle: subtitle to match
+    :type subtitle: :class:`~subliminal.subtitles.Subtitle`
+    :return: the matching probability
+    :rtype: float
+
+    """
+    guess = guessit.guess_file_info(subtitle.release, 'autodetect')
+    video_keywords = get_keywords(video.guess)
+    subtitle_keywords = get_keywords(guess) | subtitle.keywords
+    logger.debug(u'Video keywords %r - Subtitle keywords %r' % (video_keywords, subtitle_keywords))
+    replacement = {'keywords': len(video_keywords & subtitle_keywords)}
+    if isinstance(video, Episode):
+        replacement.update({'series': 0, 'season': 0, 'episode': 0})
+        matching_format = '{series:b}{season:b}{episode:b}{keywords:03b}'
+        best = matching_format.format(series=1, season=1, episode=1, keywords=len(video_keywords))
+        if guess['type'] in ['episode', 'episodesubtitle']:
+            if 'series' in guess and guess['series'].lower() == video.series.lower():
+                replacement['series'] = 1
+            if 'season' in guess and guess['season'] == video.season:
+                replacement['season'] = 1
+            if 'episodeNumber' in guess and guess['episodeNumber'] == video.episode:
+                replacement['episode'] = 1
+    elif isinstance(video, Movie):
+        replacement.update({'title': 0, 'year': 0})
+        matching_format = '{title:b}{year:b}{keywords:03b}'
+        best = matching_format.format(title=1, year=1, keywords=len(video_keywords))
+        if guess['type'] in ['movie', 'moviesubtitle']:
+            if 'title' in guess and guess['title'].lower() == video.title.lower():
+                replacement['title'] = 1
+            if 'year' in guess and guess['year'] == video.year:
+                replacement['year'] = 1
+    else:
+        logger.debug(u'Not able to compute confidence for %r' % video)
+        return 0.0
+    logger.debug(u'Found %r' % replacement)
+    confidence = float(int(matching_format.format(**replacement), 2)) / float(int(best, 2))
+    logger.info(u'Computed confidence %.4f for %r and %r' % (confidence, video, subtitle))
+    return confidence
+
+
+def get_service(services, service_name, config=None):
+    """Get a service from its name in the service dict with the specified config.
+    If the service does not exist in the service dict, it is created and added to the dict.
+
+    :param dict services: dict where to get existing services or put created ones
+    :param string service_name: name of the service to get
+    :param config: config to use for the service
+    :type config: :class:`~subliminal.services.ServiceConfig` or None
+    :return: the corresponding service
+    :rtype: :class:`~subliminal.services.ServiceBase`
+
+    """
+    if service_name not in services:
+        mod = __import__('services.' + service_name, globals=globals(), locals=locals(), fromlist=['Service'], level=-1)
+        services[service_name] = mod.Service()
+        services[service_name].init()
+    services[service_name].config = config
+    return services[service_name]
+
+
+def key_subtitles(subtitle, video, languages, services, order):
+    """Create a key to sort subtitle using the given order
+
+    :param subtitle: subtitle to sort
+    :type subtitle: :class:`~subliminal.subtitles.ResultSubtitle`
+    :param video: video to match
+    :type video: :class:`~subliminal.videos.Video`
+    :param list languages: languages in preferred order
+    :param list services: services in preferred order
+    :param order: preferred order for subtitles sorting
+    :type list: list of :data:`LANGUAGE_INDEX`, :data:`SERVICE_INDEX`, :data:`SERVICE_CONFIDENCE`, :data:`MATCHING_CONFIDENCE`
+    :return: a key ready to use for subtitles sorting
+    :rtype: int
+
+    """
+    key = ''
+    for sort_item in order:
+        if sort_item == LANGUAGE_INDEX:
+            key += '{0:03d}'.format(len(languages) - languages.index(subtitle.language) - 1)
+            key += '{0:01d}'.format(subtitle.language == languages[languages.index(subtitle.language)])
+        elif sort_item == SERVICE_INDEX:
+            key += '{0:02d}'.format(len(services) - services.index(subtitle.service) - 1)
+        elif sort_item == SERVICE_CONFIDENCE:
+            key += '{0:04d}'.format(int(subtitle.confidence * 1000))
+        elif sort_item == MATCHING_CONFIDENCE:
+            confidence = 0
+            if subtitle.release:
+                confidence = matching_confidence(video, subtitle)
+            key += '{0:04d}'.format(int(confidence * 1000))
+    return int(key)
+
+
+def group_by_video(list_results):
+    """Group the results of :class:`ListTasks <subliminal.tasks.ListTask>` into a
+    dictionary of :class:`~subliminal.videos.Video` => :class:`~subliminal.subtitles.Subtitle`
+
+    :param list_results:
+    :type list_results: list of result of :class:`~subliminal.tasks.ListTask`
+    :return: subtitles grouped by videos
+    :rtype: dict of :class:`~subliminal.videos.Video` => [:class:`~subliminal.subtitles.Subtitle`]
+
+    """
+    result = defaultdict(list)
+    for video, subtitles in list_results:
+        result[video] += subtitles or []
+    return result
+
+
+def filter_services(services):
+    """Filter out services that are not available because of a missing feature
+
+    :param list services: service names to filter
+    :return: a copy of the initial list of service names without unavailable ones
+    :rtype: list
+
+    """
+    filtered_services = services[:]
+    for service_name in services:
+        mod = __import__('services.' + service_name, globals=globals(), locals=locals(), fromlist=['Service'], level=-1)
+        service = mod.Service
+        if service.required_features is not None and bs4.builder_registry.lookup(*service.required_features) is None:
+            logger.warning(u'Service %s not available: none of available features could be used. One of %r required' % (service_name, service.required_features))
+            filtered_services.remove(service_name)
+    return filtered_services

subliminal/encodingKludge.py

@@ -1,66 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Nic Wolfe <nic@wolfeden.ca>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import os
-import subliminal
-
-
-# This module tries to deal with the apparently random behavior of python when dealing with unicode <-> utf-8
-# encodings. It tries to just use unicode, but if that fails then it tries forcing it to utf-8. Any functions
-# which return something should always return unicode.
-
-def fixStupidEncodings(x, silent=False):
-    if type(x) == str:
-        try:
-            return x.decode(subliminal.SYS_ENCODING)
-        except UnicodeDecodeError:
-            subliminal.logger.error(u"Unable to decode value: " + repr(x))
-            return None
-    elif type(x) == unicode:
-        return x
-    else:
-        subliminal.logger.log(u"Unknown value passed in, ignoring it: " + str(type(x)) + " (" + repr(x) + ":" + repr(type(x)) + ")", logging.DEBUG if silent else logging.ERROR)
-        return None
-
-    return None
-
-
-def fixListEncodings(x):
-    if type(x) != list:
-        return x
-    else:
-        return filter(lambda x: x != None, map(fixStupidEncodings, x))
-
-
-def ek(func, *args):
-    result = None
-    if os.name == 'nt':
-        result = func(*args)
-    else:
-        result = func(*[x.encode(subliminal.SYS_ENCODING) if type(x) in (str, unicode) else x for x in args])
-
-    if type(result) == list:
-        return fixListEncodings(result)
-    elif type(result) == str:
-        return fixStupidEncodings(result)
-    else:
-        return result

subliminal/exceptions.py

@@ -0,0 +1,32 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+
+
+class Error(Exception):
+    """Base class for exceptions in subliminal"""
+    pass
+
+
+class ServiceError(Error):
+    """"Exception raised by services"""
+    pass
+
+
+class DownloadFailedError(Error):
+    """"Exception raised when a download task has failed in service"""
+    pass

subliminal/infos.py

@@ -0,0 +1,18 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+__version__ = '0.6.4'

subliminal/plugins/Addic7ed.py

@@ -1,158 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from BeautifulSoup import BeautifulSoup
-import guessit
-import PluginBase
-import zipfile
-import os
-import urllib2
-import urllib
-import traceback
-import httplib
-import re
-import socket
-
-
-class Addic7ed(PluginBase.PluginBase):
-    site_url = 'http://www.addic7ed.com'
-    site_name = 'Addic7ed'
-    server_url = 'http://www.addic7ed.com'
-    multi_languages_queries = True
-    multi_filename_queries = False
-    api_based = False
-    _plugin_languages = {u"English": "en",
-            u"English (US)": "en",
-            u"English (UK)": "en",
-            u"Italian": "it",
-            u"Portuguese": "pt",
-            u"Portuguese (Brazilian)": "pt-br",
-            u"Romanian": "ro",
-            u"Español (Latinoamérica)": "es",
-            u"Español (España)": "es",
-            u"Spanish (Latin America)": "es",
-            u"Español": "es",
-            u"Spanish": "es",
-            u"Spanish (Spain)": "es",
-            u"French": "fr",
-            u"Greek": "el",
-            u"Arabic": "ar",
-            u"German": "de",
-            u"Croatian": "hr",
-            u"Indonesian": "id",
-            u"Hebrew": "he",
-            u"Russian": "ru",
-            u"Turkish": "tr",
-            u"Swedish": "se",
-            u"Czech": "cs",
-            u"Dutch": "nl",
-            u"Hungarian": "hu",
-            u"Norwegian": "no",
-            u"Polish": "pl",
-            u"Persian": "fa"}
-
-    def __init__(self, config_dict=None):
-        super(Addic7ed, self).__init__(self._plugin_languages, config_dict, isRevert=True)
-        #http://www.addic7ed.com/serie/Smallville/9/11/Absolute_Justice
-        self.release_pattern = re.compile(" \nVersion (.+), ([0-9]+).([0-9])+ MBs")
-
-    def list(self, filenames, languages):
-        ''' Main method to call when you want to list subtitles '''
-        # as self.multi_filename_queries is false, we won't have multiple filenames in the list so pick the only one
-        # once multi-filename queries are implemented, set multi_filename_queries to true and manage a list of multiple filenames here
-        if not self.checkLanguages(languages):
-            return []
-        filepath = filenames[0]
-        guess = guessit.guess_file_info(filepath, 'autodetect')
-        if guess['type'] != 'episode':
-            return []
-        # add multiple things to the release group set
-        release_group = set()
-        if 'releaseGroup' in guess:
-            release_group.add(guess['releaseGroup'])
-        else:
-            if 'title' in guess:
-                release_group.add(guess['title'])
-            if 'screenSize' in guess:
-                release_group.add(guess['screenSize'])
-        if 'series' not in guess or len(release_group) == 0:
-            return []
-        self.release_group = release_group  # used to sort results
-        return self.query(guess['series'], guess['season'], guess['episodeNumber'], release_group, filepath, languages)
-
-    def query(self, name, season, episode, release_group, filepath, languages=None):
-        ''' Make a query and returns info about found subtitles '''
-        searchname = name.lower().replace(" ", "_")
-        searchurl = "%s/serie/%s/%s/%s/%s" % (self.server_url, searchname, season, episode, searchname)
-        self.logger.debug(u"Searching in %s" % searchurl)
-        try:
-            req = urllib2.Request(searchurl, headers={'User-Agent': self.user_agent})
-            page = urllib2.urlopen(req, timeout=self.timeout)
-        except urllib2.HTTPError as inst:
-            self.logger.info(u"Error: %s - %s" % (searchurl, inst))
-            return []
-        except urllib2.URLError as inst:
-            self.logger.info(u"TimeOut: %s" % inst)
-            return []
-        soup = BeautifulSoup(page.read())
-        sublinks = []
-        for html_sub in soup("td", {"class": "NewsTitle", "colspan": "3"}):
-            if not self.release_pattern.match(str(html_sub.contents[1])):  # On not needed soup td result
-                continue
-            sub_teams = self.listTeams([self.release_pattern.match(str(html_sub.contents[1])).groups()[0]], [".", "_", " "])
-            if not release_group.intersection(sub_teams):  # On wrong team
-                continue
-            html_language = html_sub.findNext("td", {"class": "language"})
-            sub_language = self.getRevertLanguage(html_language.contents[0].strip().replace('&nbsp;', ''))
-            if languages and not sub_language in languages:  # On wrong language
-                continue
-            html_status = html_language.findNextSibling('td')
-            sub_status = html_status.find('b').string.strip()
-            if not sub_status == 'Completed':  # On not completed subtitles
-                continue
-            sub_link = self.server_url + html_status.findNextSibling('td', {'colspan': '3'}).find('a')['href']
-            self.logger.debug(u'Found a match with teams: %s' % sub_teams)
-            result = {}
-            result["release"] = "%s.S%.2dE%.2d.%s" % (name.replace(" ", "."), int(season), int(episode), '.'.join(sub_teams))
-            result["lang"] = sub_language
-            result["link"] = sub_link
-            result["page"] = searchurl
-            result["filename"] = filepath
-            result["plugin"] = self.getClassName()
-            result["teams"] = sub_teams  # used to sort
-            sublinks.append(result)
-        sublinks.sort(self._cmpTeams)
-        return sublinks
-
-    def download(self, subtitle):
-        '''pass the URL of the sub and the file it matches, will unzip it
-        and return the path to the created file'''
-        suburl = subtitle["link"]
-        videofilename = subtitle["filename"]
-        srtbasefilename = videofilename.rsplit(".", 1)[0]
-        srtfilename = srtbasefilename + self.getExtension(subtitle)
-        self.downloadFile(suburl, srtfilename)
-        return srtfilename
-
-    def _cmpTeams(self, x, y):
-        ''' Sort based on teams matching '''
-        return -cmp(len(x['teams'].intersection(self.release_group)), len(y['teams'].intersection(self.release_group)))

subliminal/plugins/BierDopje.py

@@ -1,170 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from xml.dom import minidom
-import guessit
-import PluginBase
-import os
-import pickle
-import traceback
-import urllib
-import urllib2
-from subliminal import encodingKludge as ek
-
-
-class BierDopje(PluginBase.PluginBase):
-    site_url = 'http://bierdopje.com'
-    site_name = 'BierDopje'
-    server_url = 'http://api.bierdopje.com/A2B638AC5D804C2E/'
-    multi_languages_queries = True
-    multi_filename_queries = False
-    api_based = True
-    exceptions = {'the office': 10358,
-        'the office us': 10358,
-        'greys anatomy': 3733,
-        'sanctuary us': 7904,
-        'human target 2010': 12986,
-        'csi miami': 2187,
-        'castle 2009': 12708,
-        'chase 2010': 14228,
-        'the defenders 2010': 14225,
-        'hawaii five-0 2010': 14211}
-    _plugin_languages = {'en': 'en', 'nl': 'nl'}
-
-    def __init__(self, config_dict):
-        super(BierDopje, self).__init__(self._plugin_languages, config_dict)
-        #http://api.bierdopje.com/23459DC262C0A742/GetShowByName/30+Rock
-        #http://api.bierdopje.com/23459DC262C0A742/GetAllSubsFor/94/5/1/en (30 rock, season 5, episode 1)
-        if not config_dict or not config_dict['cache_dir']:
-            raise Exception('Cache directory is mandatory for this plugin')
-        self.showid_cache = ek.ek(os.path.join, config_dict['cache_dir'], "bierdopje_showid.cache")
-        with self.lock:
-            if not ek.ek(os.path.exists, self.showid_cache):
-                if not ek.ek(os.path.exists, ek.ek(os.path.dirname, self.showid_cache)):
-                    raise Exception("Cache directory doesn't exists")
-                f = open(self.showid_cache, 'w')
-                pickle.dump({}, f)
-                f.close()
-            f = open(self.showid_cache, 'r')
-            self.showids = pickle.load(f)
-            self.logger.debug(u"Reading showids from cache: %s" % self.showids)
-            f.close()
-
-    def list(self, filenames, languages):
-        """Main method to call when you want to list subtitles"""
-        # as self.multi_filename_queries is false, we won't have multiple filenames in the list so pick the only one
-        # once multi-filename queries are implemented, set multi_filename_queries to true and manage a list of multiple filenames here
-        if not self.checkLanguages(languages):
-            return []
-        filepath = filenames[0]
-        guess = guessit.guess_file_info(filepath, 'autodetect')
-        if guess['type'] != 'episode':
-            return []
-        # add multiple things to the release group set
-        release_group = set()
-        if 'releaseGroup' in guess:
-            release_group.add(guess['releaseGroup'].lower())
-        else:
-            if 'title' in guess:
-                release_group.add(guess['title'].lower())
-            if 'screenSize' in guess:
-                release_group.add(guess['screenSize'].lower())
-        if 'series' not in guess or len(release_group) == 0:
-            return []
-        self.release_group = release_group  # used to sort results
-        return self.query(guess['series'], guess['season'], guess['episodeNumber'], release_group, filepath, languages)
-
-    def download(self, subtitle):
-        """Main method to call when you want to download a subtitle"""
-        subpath = subtitle["filename"].rsplit(".", 1)[0] + self.getExtension(subtitle)
-        self.downloadFile(subtitle["link"], subpath)
-        return subpath
-
-    def query(self, name, season, episode, release_group, filepath, languages=None):
-        """Makes a query and returns info (link, lang) about found subtitles"""
-        if languages:
-            available_languages = list(set(languages).intersection((self._plugin_languages.values())))
-        else:
-            available_languages = self._plugin_languages.values()
-        sublinks = []
-
-        # get the show id
-        show_name = name.lower()
-        if show_name in self.exceptions:  # get it from exceptions
-            show_id = self.exceptions[show_name]
-        elif show_name in self.showids:  # get it from cache
-            show_id = self.showids[show_name]
-        else:  # retrieve it
-            show_id_url = "%sGetShowByName/%s" % (self.server_url, urllib.quote(show_name))
-            self.logger.debug(u"Retrieving show id from web at %s" % show_id_url)
-            page = urllib2.urlopen(show_id_url)
-            dom = minidom.parse(page)
-            if not dom or len(dom.getElementsByTagName('showid')) == 0:  # no proper result
-                page.close()
-                return []
-            show_id = dom.getElementsByTagName('showid')[0].firstChild.data
-            self.showids[show_name] = show_id
-            with self.lock:
-                f = open(self.showid_cache, 'w')
-                self.logger.debug(u"Writing showid %s to cache file" % show_id)
-                pickle.dump(self.showids, f)
-                f.close()
-            page.close()
-
-        # get the subs for the show id we have
-        for language in available_languages:
-            subs_url = "%sGetAllSubsFor/%s/%s/%s/%s" % (self.server_url, show_id, season, episode, language)
-            self.logger.debug(u"Getting subtitles at %s" % subs_url)
-            page = urllib2.urlopen(subs_url)
-            dom = minidom.parse(page)
-            page.close()
-            for sub in dom.getElementsByTagName('result'):
-                sub_release = sub.getElementsByTagName('filename')[0].firstChild.data
-                if sub_release.endswith(".srt"):
-                    sub_release = sub_release[:-4]
-                sub_release = sub_release + '.avi'  # put a random extension for guessit not to fail guessing that file
-                # guess information from subtitle
-                sub_guess = guessit.guess_file_info(sub_release, 'episode')
-                sub_release_group = set()
-                if 'releaseGroup' in sub_guess:
-                    sub_release_group.add(sub_guess['releaseGroup'].lower())
-                else:
-                    if 'title' in sub_guess:
-                        sub_release_group.add(sub_guess['title'].lower())
-                    if 'screenSize' in sub_guess:
-                        sub_release_group.add(sub_guess['screenSize'].lower())
-                sub_link = sub.getElementsByTagName('downloadlink')[0].firstChild.data
-                result = {}
-                result["release"] = sub_release
-                result["link"] = sub_link
-                result["page"] = sub_link
-                result["lang"] = language
-                result["filename"] = filepath
-                result["plugin"] = self.getClassName()
-                result["releaseGroup"] = sub_release_group
-                sublinks.append(result)
-        sublinks.sort(self._cmpReleaseGroup)
-        return sublinks
-
-    def _cmpReleaseGroup(self, x, y):
-        """Sort based on teams matching"""
-        return -cmp(len(x['releaseGroup'].intersection(self.release_group)), len(y['releaseGroup'].intersection(self.release_group)))

subliminal/plugins/OpenSubtitles.py

@@ -1,206 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import PluginBase
-import gzip
-import os
-import socket
-import xmlrpclib
-import guessit
-from subliminal import encodingKludge as ek
-
-
-class OpenSubtitles(PluginBase.PluginBase):
-    site_url = 'http://www.opensubtitles.org'
-    site_name = 'OpenSubtitles'
-    server_url = 'http://api.opensubtitles.org/xml-rpc'
-    user_agent = 'Subliminal v0.3'
-    multi_languages_queries = True
-    multi_filename_queries = False
-    api_based = True
-    _plugin_languages = {"en": "eng",
-            "fr": "fre",
-            "hu": "hun",
-            "cs": "cze",
-            "pl": "pol",
-            "sk": "slo",
-            "pt": "por",
-            "pt-br": "pob",
-            "es": "spa",
-            "el": "ell",
-            "ar": "ara",
-            "sq": "alb",
-            "hy": "arm",
-            "ay": "ass",
-            "bs": "bos",
-            "bg": "bul",
-            "ca": "cat",
-            "zh": "chi",
-            "hr": "hrv",
-            "da": "dan",
-            "nl": "dut",
-            "eo": "epo",
-            "et": "est",
-            "fi": "fin",
-            "gl": "glg",
-            "ka": "geo",
-            "de": "ger",
-            "he": "heb",
-            "hi": "hin",
-            "is": "ice",
-            "id": "ind",
-            "it": "ita",
-            "ja": "jpn",
-            "kk": "kaz",
-            "ko": "kor",
-            "lv": "lav",
-            "lt": "lit",
-            "lb": "ltz",
-            "mk": "mac",
-            "ms": "may",
-            "no": "nor",
-            "oc": "oci",
-            "fa": "per",
-            "ro": "rum",
-            "ru": "rus",
-            "sr": "scc",
-            "sl": "slv",
-            "sv": "swe",
-            "th": "tha",
-            "tr": "tur",
-            "uk": "ukr",
-            "vi": "vie"}
-
-    def __init__(self, config_dict=None):
-        super(OpenSubtitles, self).__init__(self._plugin_languages, config_dict)
-
-    def list(self, filenames, languages):
-        """Main method to call when you want to list subtitles """
-        # as self.multi_filename_queries is false, we won't have multiple filenames in the list so pick the only one
-        # once multi-filename queries are implemented, set multi_filename_queries to true and manage a list of multiple filenames here
-        filepath = filenames[0]
-        if ek.ek(os.path.isfile, filepath):
-            filehash = self.hashFile(filepath)
-            size = ek.ek(os.path.getsize, filepath)
-            return self.query(moviehash=filehash, languages=languages, bytesize=size, filepath=filepath)
-        else:
-            return self.query(languages=languages, filepath=filepath)
-
-    def download(self, subtitle):
-        """Main method to call when you want to download a subtitle """
-        subtitleFilename = subtitle["filename"].rsplit(".", 1)[0] + self.getExtension(subtitle)
-        self.downloadFile(subtitle["link"], subtitleFilename + ".gz")
-        f = ek.ek(gzip.open, subtitleFilename + ".gz")
-        dump = ek.ek(open, subtitleFilename, "wb")
-        dump.write(f.read())
-        self.adjustPermissions(subtitleFilename)
-        dump.close()
-        f.close()
-        ek.ek(os.remove, subtitleFilename + ".gz")
-        return subtitleFilename
-
-    def query(self, filepath, imdbID=None, moviehash=None, bytesize=None, languages=None):
-        """Makes a query on OpenSubtitles and returns info about found subtitles.
-            Note: if using moviehash, bytesize is required. """
-        # prepare the search
-        search = {}
-        if moviehash:
-            search['moviehash'] = moviehash
-        if imdbID:
-            search['imdbid'] = imdbID
-        if bytesize:
-            search['moviebytesize'] = str(bytesize)
-        if languages:
-            search['sublanguageid'] = ",".join([self.getLanguage(l) for l in languages])
-        if not imdbID and not moviehash and not bytesize:
-            self.logger.debug(u"No search term, we'll use the filename")
-            guess = guessit.guess_file_info(filepath, 'autodetect')
-            if guess['type'] == 'episode' and 'series' in guess:
-                search['query'] = guess['series']
-            elif guess['type'] == 'movie':
-                search['query'] = guess['title']
-            else:  # we don't know what we have
-                return[]
-        # login
-        self.server = xmlrpclib.Server(self.server_url)
-        socket.setdefaulttimeout(self.timeout)
-        try:
-            log_result = self.server.LogIn("", "", "eng", self.user_agent)
-            if not log_result["status"] or log_result["status"] != '200 OK' or not log_result["token"]:
-                raise Exception('OpenSubtitles login failed')
-            token = log_result["token"]
-        except Exception:
-            self.logger.error(u"Cannot login")
-            token = None
-            socket.setdefaulttimeout(None)
-            return []
-        # search
-        sublinks = self.get_results(token, search, filepath)
-        # logout
-        try:
-            self.server.LogOut(token)
-        except:
-            self.logger.error(u"Cannot logout")
-        socket.setdefaulttimeout(None)
-        return sublinks
-
-    def get_results(self, token, search, filepath):
-        self.logger.debug(u"Query uses token %s and search parameters %s" % (token, search))
-        try:
-            results = self.server.SearchSubtitles(token, [search])
-        except Exception, e:
-            self.logger.debug(u"Cannot query the server")
-            return []
-        if not results['data']:  # no subtitle found
-            return []
-        sublinks = []
-        self.filename = self.getFileName(filepath)
-        for r in sorted(results['data'], self._cmpSubFileName):
-            result = {}
-            result["release"] = r['SubFileName']
-            result["link"] = r['SubDownloadLink']
-            result["page"] = r['SubDownloadLink']
-            result["lang"] = self.getRevertLanguage(r['SubLanguageID'])
-            result["filename"] = filepath
-            result["plugin"] = self.getClassName()
-            if 'query' in search and not r["MovieReleaseName"].replace('.', ' ').startswith(search['query']):  # query mode search, filter results
-                self.logger.debug(u"Skipping %s it does not start with %s" % (r["MovieReleaseName"].replace('.', ' '), search['query']))
-                continue
-            sublinks.append(result)
-        return sublinks
-
-    def _cmpSubFileName(self, x, y):
-        """Sort based on the SubFileName name tag """
-        #TODO add also support for subtitles release
-        xmatch = x['SubFileName'] and (x['SubFileName'].find(self.filename) > -1 or self.filename.find(x['SubFileName']) > -1)
-        ymatch = y['SubFileName'] and (y['SubFileName'].find(self.filename) > -1 or self.filename.find(y['SubFileName']) > -1)
-        if xmatch and ymatch:
-            if x['SubFileName'] == self.filename or x['SubFileName'].startswith(self.filename):
-                return - 1
-            return 0
-        if not xmatch and not ymatch:
-            return 0
-        if xmatch and not ymatch:
-            return - 1
-        if not xmatch and ymatch:
-            return 1
-        return 0

subliminal/plugins/PluginBase.py

@@ -1,188 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import abc
-import logging
-import os
-import re
-import sys
-import urllib2
-import struct
-import threading
-from subliminal import encodingKludge as ek
-
-
-class PluginBase(object):
-    __metaclass__ = abc.ABCMeta
-    multi_languages_queries = False
-    multi_filename_queries = False
-    api_based = True
-    timeout = 3
-    user_agent = 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.3)'
-    lock = threading.Lock()
-
-    @abc.abstractmethod
-    def __init__(self, pluginLanguages, config_dict=None, isRevert=False):
-        self.config_dict = config_dict
-        if not pluginLanguages:
-            self.pluginLanguages = None
-            self.revertPluginLanguages = None
-        elif not isRevert:
-            self.pluginLanguages = pluginLanguages
-            self.revertPluginLanguages = dict((v, k) for k, v in self.pluginLanguages.iteritems())
-        else:
-            self.revertPluginLanguages = pluginLanguages
-            self.pluginLanguages = dict((v, k) for k, v in self.revertPluginLanguages.iteritems())
-        self.logger = logging.getLogger('subliminal.%s' % self.getClassName())
-
-    @staticmethod
-    def getFileName(filepath):
-        filename = filepath
-        if ek.ek(os.path.isfile, filename):
-            filename = ek.ek(os.path.basename, filename)
-        if filename.endswith(('.avi', '.wmv', '.mov', '.mp4', '.mpeg', '.mpg', '.mkv')):
-            filename = filename.rsplit('.', 1)[0]
-        return filename
-
-    def hashFile(self, filename):
-        """Hash a file like OpenSubtitles"""
-        longlongformat = 'q'  # long long
-        bytesize = struct.calcsize(longlongformat)
-        f = ek.ek(open, filename, "rb")
-        filesize = ek.ek(os.path.getsize, filename)
-        hash = filesize
-        if filesize < 65536 * 2:
-            self.logger.error(u"File %s is too small (SizeError < 2**16)" % filename)
-            return []
-        for x in range(65536 / bytesize):
-            buffer = f.read(bytesize)
-            (l_value,) = struct.unpack(longlongformat, buffer)
-            hash += l_value
-            hash = hash & 0xFFFFFFFFFFFFFFFF  # to remain as 64bit number
-        f.seek(max(0, filesize - 65536), 0)
-        for x in range(65536 / bytesize):
-            buffer = f.read(bytesize)
-            (l_value,) = struct.unpack(longlongformat, buffer)
-            hash += l_value
-            hash = hash & 0xFFFFFFFFFFFFFFFF
-        f.close()
-        returnedhash = "%016x" % hash
-        return returnedhash
-
-    def downloadFile(self, url, filename, data=None):
-        """Downloads the given url to the given filename"""
-        try:
-            self.logger.info(u"Downloading %s" % url)
-            req = urllib2.Request(url, headers={'Referer': url, 'User-Agent': self.user_agent})
-            f = urllib2.urlopen(req, data=data)
-            dump = ek.ek(open, filename, "wb")
-            dump.write(f.read())
-            self.adjustPermissions(filename)
-            dump.close()
-            f.close()
-            self.logger.debug(u"Download finished for file %s. Size: %s" % (filename, ek.ek(os.path.getsize, filename)))
-        except urllib2.HTTPError, e:
-            self.logger.error(u"HTTP Error:", e.code, url)
-        except urllib2.URLError, e:
-            self.logger.error(u"URL Error:", e.reason, url)
-
-    def adjustPermissions(self, filepath):
-        if self.config_dict and 'files_mode' in self.config_dict and self.config_dict['files_mode'] != -1:
-            ek.ek(os.chmod, filepath, self.config_dict['files_mode'])
-
-    @abc.abstractmethod
-    def list(self, filenames, languages):
-        """Main method to call when you want to list subtitles"""
-
-    @abc.abstractmethod
-    def download(self, subtitle):
-        """Main method to call when you want to download a subtitle"""
-
-    def getRevertLanguage(self, language):
-        """Returns the short (two-character) representation from the long language name"""
-        try:
-            return self.revertPluginLanguages[language]
-        except KeyError, e:
-            self.logger.warn(u"Ooops, you found a missing language in the configuration file of %s: %s. Send a bug report to have it added." % (self.getClassName(), language))
-
-    def checkLanguages(self, languages):
-        if languages and not set(languages).intersection((self._plugin_languages.values())):
-            self.logger.debug(u'None of requested languages %s are available' % languages)
-            return False
-        return True
-
-    def getLanguage(self, language):
-        """Returns the long naming of the language from a two character code"""
-        try:
-            return self.pluginLanguages[language]
-        except KeyError, e:
-            self.logger.warn(u"Ooops, you found a missing language in the configuration file of %s: %s. Send a bug report to have it added." % (self.getClassName(), language))
-
-    def getExtension(self, subtitle):
-        if self.config_dict and self.config_dict['multi']:
-            return ".%s.srt" % subtitle['lang']
-        return ".srt"
-
-    def getClassName(self):
-        return self.__class__.__name__
-
-    def splitTask(self, task):
-        """Determines if the plugin can handle multi-thing queries and output splited tasks for list task only"""
-        if task['task'] != 'list':
-            return [task]
-        tasks = [task]
-        if not self.multi_filename_queries:
-            tasks = self._splitOnField(tasks, 'filenames')
-        if not self.multi_languages_queries:
-            tasks = self._splitOnField(tasks, 'languages')
-        return tasks
-
-    @staticmethod
-    def _splitOnField(elements, field):
-        """
-        Split a list of dict in a bigger one if the element field in the dict has multiple elements too
-        i.e. [{'a': 1, 'b': [2,3]}, {'a': 7, 'b': [4]}] => [{'a': 1, 'b': [2]}, {'a': 1, 'b': [3]}, {'a': 7, 'b': [4]}]
-        with field = 'b'
-        """
-        results = []
-        for e in elements:
-            for v in e[field]:
-                newElement = {}
-                for (key, value) in e.items():
-                    if key != field:
-                        newElement[key] = value
-                    else:
-                        newElement[key] = [v]
-                results.append(newElement)
-        return results
-
-    def listTeams(self, sub_teams, separators):
-        """List teams of a given string using separators"""
-        for sep in separators:
-            sub_teams = self.splitTeam(sub_teams, sep)
-        return set(sub_teams)
-
-    def splitTeam(self, sub_teams, sep):
-        """Split teams of a given string using separators"""
-        teams = []
-        for t in sub_teams:
-            teams += t.split(sep)
-        return teams

subliminal/plugins/Podnapisi.py

@@ -1,146 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from hashlib import md5, sha256
-import PluginBase
-import xmlrpclib
-import struct
-import socket
-import zipfile
-import os
-import urllib2
-import urllib
-import traceback
-from subliminal import encodingKludge as ek
-
-
-class Podnapisi(PluginBase.PluginBase):
-    site_url = "http://www.podnapisi.net"
-    site_name = "Podnapisi"
-    server_url = 'http://ssp.podnapisi.net:8000'
-    multi_languages_queries = True
-    multi_filename_queries = False
-    api_based = True
-    _plugin_languages = {"sl": "1",
-            "en": "2",
-            "no": "3",
-            "ko": "4",
-            "de": "5",
-            "is": "6",
-            "cs": "7",
-            "fr": "8",
-            "it": "9",
-            "bs": "10",
-            "ja": "11",
-            "ar": "12",
-            "ro": "13",
-            "es-ar": "14",
-            "hu": "15",
-            "el": "16",
-            "zh": "17",
-            "lt": "19",
-            "et": "20",
-            "lv": "21",
-            "he": "22",
-            "nl": "23",
-            "da": "24",
-            "se": "25",
-            "pl": "26",
-            "ru": "27",
-            "es": "28",
-            "sq": "29",
-            "tr": "30",
-            "fi": "31",
-            "pt": "32",
-            "bg": "33",
-            "mk": "35",
-            "sk": "37",
-            "hr": "38",
-            "zh": "40",
-            "hi": "42",
-            "th": "44",
-            "uk": "46",
-            "sr": "47",
-            "pt-br": "48",
-            "ga": "49",
-            "be": "50",
-            "vi": "51",
-            "fa": "52",
-            "ca": "53",
-            "id": "54"}
-
-    def __init__(self, config_dict=None):
-        super(Podnapisi, self).__init__(self._plugin_languages, config_dict)
-        # Podnapisi uses two reference for latin serbian and cyrillic serbian (36 and 47)
-        # add the 36 manually as cyrillic seems to be more used
-        self.revertPluginLanguages["36"] = "sr"
-
-    def list(self, filenames, languages):
-        """Main method to call when you want to list subtitles"""
-        # as self.multi_filename_queries is false, we won't have multiple filenames in the list so pick the only one
-        # once multi-filename queries are implemented, set multi_filename_queries to true and manage a list of multiple filenames here
-        filepath = filenames[0]
-        if not ek.ek(os.path.isfile, filepath):
-            return []
-        return self.query(self.hashFile(filepath), languages)
-
-    def download(self, subtitle):
-        return []
-
-    def query(self, moviehash, languages=None):
-        """Makes a query on podnapisi and returns info (link, lang) about found subtitles"""
-        # login
-        self.server = xmlrpclib.Server(self.server_url)
-        socket.setdefaulttimeout(self.timeout)
-        try:
-            log_result = self.server.initiate(self.user_agent)
-            self.logger.debug(u"Result: %s" % log_result)
-            token = log_result["session"]
-            nonce = log_result["nonce"]
-        except Exception, e:
-            self.logger.error(u"Cannot login" % log_result)
-            socket.setdefaulttimeout(None)
-            return []
-        username = 'getmesubs'
-        password = '99D31$$'
-        hash = md5()
-        hash.update(password)
-        password = hash.hexdigest()
-        hash = sha256()
-        hash.update(password)
-        hash.update(nonce)
-        password = hash.hexdigest()
-        self.server.authenticate(token, username, password)
-        self.logger.debug(u'Authenticated')
-        #if languages:
-        #    self.logger.debug([self.getLanguage(l) for l in languages])
-        #    self.server.setFilters(token, [self.getLanguage(l) for l in languages])
-        #    self.logger.debug('Filers set for languages %s' % languages)
-        self.logger.debug(u"Starting search with token %s and hashs %s" % (token, [moviehash]))
-        results = self.server.search(token, [moviehash])
-        return results
-        subs = []
-        for sub in results['results']:
-            subs.append(sub)
-        d = self.server.download(token, [173793])
-        self.server.terminate(token)
-        return subs

subliminal/plugins/SubScene.py

@@ -1,177 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from BeautifulSoup import BeautifulSoup
-import PluginBase
-import zipfile
-import os
-import urllib2
-import urllib
-import traceback
-import httplib
-from subliminal import encodingKludge as ek
-
-
-class SubScene(PluginBase.PluginBase):
-    site_url = 'http://subscene.com'
-    site_name = 'SubScene'
-    server_url = 'http://subscene.com/s.aspx?subtitle='
-    multi_languages_queries = True
-    multi_filename_queries = False
-    api_based = False
-    _plugin_languages = {"en": "English",
-            "se": "Swedish",
-            "da": "Danish",
-            "fi": "Finnish",
-            "no": "Norwegian",
-            "fr": "French",
-            "es": "Spanish",
-            "is": "Icelandic",
-            "cs": "Czech",
-            "bg": "Bulgarian",
-            "de": "German",
-            "ar": "Arabic",
-            "el": "Greek",
-            "fa": "Farsi/Persian",
-            "nl": "Dutch",
-            "he": "Hebrew",
-            "id": "Indonesian",
-            "ja": "Japanese",
-            "vi": "Vietnamese",
-            "pt": "Portuguese",
-            "ro": "Romanian",
-            "tr": "Turkish",
-            "sr": "Serbian",
-            "pt-br": "Brazillian Portuguese",
-            "ru": "Russian",
-            "hr": "Croatian",
-            "sl": "Slovenian",
-            "zh": "Chinese BG code",
-            "it": "Italian",
-            "pl": "Polish",
-            "ko": "Korean",
-            "hu": "Hungarian",
-            "ku": "Kurdish",
-            "et": "Estonian"}
-
-    def __init__(self, config_dict=None):
-        super(SubScene, self).__init__(self._plugin_languages, config_dict)
-        #http://subscene.com/s.aspx?subtitle=Dexter.S04E01.HDTV.XviD-NoTV
-
-    def list(self, filenames, languages):
-        """Main method to call when you want to list subtitles"""
-        # as self.multi_filename_queries is false, we won't have multiple filenames in the list so pick the only one
-        # once multi-filename queries are implemented, set multi_filename_queries to true and manage a list of multiple filenames here
-        filepath = filenames[0]
-        fname = self.getFileName(filepath)
-        subs = self.query(fname, filepath, languages)
-        if not subs and fname.rfind(".[") > 0:
-            # Try to remove the [VTV] or [EZTV] at the end of the file
-            teamless_filename = fname[0:fname.rfind(".[")]
-            subs = self.query(teamless_filename, filepath, languages)
-            return subs
-        else:
-            return subs
-
-    def download(self, subtitle):
-        """Main method to call when you want to download a subtitle"""
-        subpage = subtitle["page"]
-        page = urllib2.urlopen(subpage)
-        soup = BeautifulSoup(page)
-        dlhref = soup.find("div", {"class": "download"}).find("a")["href"]
-        subtitle["link"] = self.site_url + dlhref.split('"')[7]
-        format = "zip"
-        archivefilename = subtitle["filename"].rsplit(".", 1)[0] + '.' + format
-        self.downloadFile(subtitle["link"], archivefilename)
-        subtitlefilename = None
-        if zipfile.is_zipfile(archivefilename):
-            self.logger.debug(u"Unzipping file " + archivefilename)
-            zf = zipfile.ZipFile(archivefilename, "r")
-            for el in zf.infolist():
-                extension = el.orig_filename.rsplit(".", 1)[1]
-                if extension in ("srt", "sub", "txt"):
-                    subtitlefilename = srtbasefilename + "." + extension
-                    outfile = ek.ek(open, subtitlefilename, "wb")
-                    outfile.write(zf.read(el.orig_filename))
-                    outfile.flush()
-                    self.adjustPermissions(subtitlefilename)
-                    outfile.close()
-                else:
-                    self.logger.info(u"File %s does not seem to be valid " % el.orig_filename)
-            # Deleting the zip file
-            zf.close()
-            ek.ek(os.remove, archivefilename)
-            return subtitlefilename
-        elif archivefilename.endswith('.rar'):
-            self.logger.warn(u'Rar is not really supported yet. Trying to call unrar')
-            import subprocess
-            try:
-                args = ['unrar', 'lb', archivefilename]
-                output = subprocess.Popen(args, stdout=subprocess.PIPE).communicate()[0]
-                for el in output.splitlines():
-                    extension = el.rsplit(".", 1)[1]
-                    if extension in ("srt", "sub"):
-                        args = ['unrar', 'e', archivefilename, el, ek.ek(os.path.dirname, archivefilename)]
-                        subprocess.Popen(args)
-                        tmpsubtitlefilename = ek.ek(os.path.join, ek.ek(os.path.dirname, archivefilename), el)
-                        subtitlefilename = ek.ek(os.path.join, ek.ek(os.path.dirname, archivefilename), srtbasefilename + "." + extension)
-                        if ek.ek(os.path.exists, tmpsubtitlefilename):
-                            # rename it to match the file
-                            ek.ek(os.rename, tmpsubtitlefilename, subtitlefilename)
-                            # exit
-                        return subtitlefilename
-            except OSError, e:
-                self.logger.error(u"Execution failed: %s" % e)
-                return None
-        else:
-            self.logger.info(u"Unexpected file type (not zip) for %s" % archivefilename)
-            return None
-
-    def downloadFile(self, url, filename):
-        """Downloads the given url to the given filename"""
-        #FIXME: Not working
-        super(SubScene, self).downloadFile(url, filename, urllib.urlencode({'__EVENTTARGET': 's$lc$bcr$downloadLink', '__EVENTARGUMENT': '', '__VIEWSTATE': '/wEPDwUHNzUxOTkwNWRk4wau5efPqhlBJJlOkKKHN8FIS04='}))
-
-    def query(self, token, filepath, langs=None):
-        """Make a query on SubScene and returns info about found subtitles"""
-        sublinks = []
-        searchurl = "%s%s" % (self.server_url, urllib.quote(token))
-        self.logger.debug(u"Query: %s" % searchurl)
-        page = urllib2.urlopen(searchurl)
-        soup = BeautifulSoup(page.read())
-        for subs in soup("a", {"class": "a1"}):
-            lang_span = subs.find("span")
-            lang = self.getRevertLanguage(lang_span.contents[0].strip())
-            release_span = lang_span.findNext("span")
-            release = release_span.contents[0].strip().split(" (")[0]
-            sub_page = subs["href"]
-            #http://subscene.com//s-dlpath-260016/78348/rar.zipx
-            if release.lower().startswith(token.lower()) and (not langs or lang in langs):
-                result = {}
-                result["release"] = release
-                result["lang"] = lang
-                result["link"] = None
-                result["page"] = self.site_url + sub_page
-                result["filename"] = filepath
-                result["plugin"] = self.getClassName()
-                sublinks.append(result)
-        return sublinks

subliminal/plugins/SubsWiki.py

@@ -1,156 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from BeautifulSoup import BeautifulSoup
-import PluginBase
-import zipfile
-import urllib2
-import urllib
-import logging
-import traceback
-import httplib
-import re
-import guessit
-from subliminal import encodingKludge as ek
-
-
-class SubsWiki(PluginBase.PluginBase):
-    site_url = 'http://www.subswiki.com'
-    site_name = 'SubsWiki'
-    server_url = 'http://www.subswiki.com'
-    multi_languages_queries = True
-    multi_filename_queries = False
-    api_based = False
-    _plugin_languages = {u"English (US)": "en",
-            u"English (UK)": "en",
-            u"English": "en",
-            u"French": "fr",
-            u"Brazilian": "pt-br",
-            u"Portuguese": "pt",
-            u"Español (Latinoamérica)": "es",
-            u"Español (España)": "es",
-            u"Español": "es",
-            u"Italian": "it",
-            u"Català": "ca"}
-
-    def __init__(self, config_dict=None):
-        super(SubsWiki, self).__init__(self._plugin_languages, config_dict, True)
-        self.release_pattern = re.compile("\nVersion (.+), ([0-9]+).([0-9])+ MBs")
-
-    def list(self, filenames, languages):
-        """Main method to call when you want to list subtitles"""
-        # as self.multi_filename_queries is false, we won't have multiple filenames in the list so pick the only one
-        # once multi-filename queries are implemented, set multi_filename_queries to true and manage a list of multiple filenames here
-        filepath = filenames[0]
-        if not self.checkLanguages(languages):
-            return []
-        guess = guessit.guess_file_info(filepath, 'autodetect')
-        if guess['type'] != 'episode':
-            return []
-        # add multiple things to the release group set
-        release_group = set()
-        if 'releaseGroup' in guess:
-            release_group.add(guess['releaseGroup'])
-        else:
-            if 'title' in guess:
-                release_group.add(guess['title'])
-            if 'screenSize' in guess:
-                release_group.add(guess['screenSize'])
-        if 'series' not in guess or len(release_group) == 0:
-            return []
-        self.release_group = release_group  # used to sort results
-        return self.query(guess['series'], guess['season'], guess['episodeNumber'], release_group, filepath, languages)
-
-    def query(self, name, season, episode, release_group, filepath, languages=None):
-        """Make a query and returns info about found subtitles"""
-        sublinks = []
-        searchname = name.lower().replace(" ", "_")
-        searchurl = "%s/serie/%s/%s/%s/" % (self.server_url, searchname, season, episode)
-        self.logger.debug(u"Searching in %s" % searchurl)
-        try:
-            req = urllib2.Request(searchurl, headers={'User-Agent': self.user_agent})
-            page = urllib2.urlopen(req, timeout=self.timeout)
-        except urllib2.HTTPError as inst:
-            self.logger.info(u"Error: %s - %s" % (searchurl, inst))
-            return []
-        except urllib2.URLError as inst:
-            self.logger.info(u"TimeOut: %s" % inst)
-            return []
-        soup = BeautifulSoup(page.read())
-        for subs in soup("td", {"class": "NewsTitle"}):
-            sub_teams = self.listTeams([self.release_pattern.search("%s" % subs.contents[1]).group(1)], [".", "_", " ", "/", "-"])
-            if not release_group.intersection(sub_teams):  # On wrong team
-                continue
-            self.logger.debug(u"Team from website: %s" % sub_teams)
-            self.logger.debug(u"Team from file: %s" % release_group)
-            for html_language in subs.parent.parent.findAll("td", {"class": "language"}):
-                sub_language = self.getRevertLanguage(html_language.string.strip())
-                self.logger.debug(u"Subtitle reverted language: %s" % sub_language)
-                if languages and not sub_language in languages:  # On wrong language
-                    continue
-                html_status = html_language.findNextSibling('td')
-                sub_status = html_status.find('strong').string.strip()
-                if not sub_status == 'Completed':  # On not completed subtitles
-                    continue
-                sub_link = html_status.findNext("td").find("a")["href"]
-                result = {}
-                result["release"] = "%s.S%.2dE%.2d.%s" % (name.replace(" ", "."), int(season), int(episode), '.'.join(sub_teams))
-                result["lang"] = sub_language
-                result["link"] = self.server_url + sub_link
-                result["page"] = searchurl
-                result["filename"] = filepath
-                result["plugin"] = self.getClassName()
-                result["teams"] = sub_teams  # used to sort
-                sublinks.append(result)
-        sublinks.sort(self._cmpTeams)
-        return sublinks
-
-    def download(self, subtitle):
-        """Main method to call when you want to download a subtitle"""
-        subtitleFilename = subtitle["filename"].rsplit(".", 1)[0] + self.getExtension(subtitle)
-        self.downloadFile(subtitle["link"], subtitleFilename)
-        return subtitleFilename
-
-    def listTeams(self, subteams, separators):
-        teams = []
-        for sep in separators:
-            subteams = self.splitTeam(subteams, sep)
-        return set(subteams)
-
-    def splitTeam(self, subteams, sep):
-        teams = []
-        for t in subteams:
-            teams += t.split(sep)
-        return teams
-
-    def downloadFile(self, url, filename):
-        """Downloads the given url to the given filename"""
-        req = urllib2.Request(url, headers={'Referer': url, 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.3)'})
-        f = urllib2.urlopen(req)
-        dump = ek.ek(open, filename, "wb")
-        dump.write(f.read())
-        dump.close()
-        f.close()
-
-    def _cmpTeams(self, x, y):
-        """Sort based on teams matching"""
-        return -cmp(len(x['teams'].intersection(self.release_group)), len(y['teams'].intersection(self.release_group)))

subliminal/plugins/SubtitleSource.py

@@ -1,122 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import ConfigParser
-import PluginBase
-import traceback
-import urllib
-import urllib2
-import xml.dom.minidom
-
-
-class SubtitleSource(PluginBase.PluginBase):
-    site_url = 'http://www.subtitlesource.org'
-    site_name = 'SubtitleSource'
-    server_url = 'http://www.subtitlesource.org/api/%s/3.0/xmlsearch'
-    multi_languages_queries = True
-    multi_filename_queries = False
-    api_based = True
-    _plugin_languages = {"en": "English",
-            "sv": "Swedish",
-            "da": "Danish",
-            "fi": "Finnish",
-            "no": "Norwegian",
-            "fr": "French",
-            "es": "Spanish",
-            "is": "Icelandic"}
-
-    def __init__(self, config_dict=None):
-        super(SubtitleSource, self).__init__(self._plugin_languages, config_dict)
-        if config_dict and "subtitlesource_key" in config_dict:
-            self.server_url = self.server_url % config_dict["subtitlesource_key"]
-        else:
-            self.logger.error(u'SubtitleSource API Key is mandatory for this plugin')
-            raise Exception('SubtitleSource API Key is mandatory for this plugin')
-
-    def list(self, filenames, languages):
-        """Main method to call when you want to list subtitles"""
-        filepath = filenames[0]
-        fname = self.getFileName(filepath)
-        subs = self.query(fname, languages)
-        if not subs and fname.rfind(".[") > 0:
-            # Try to remove the [VTV] or [EZTV] at the end of the file
-            teamless_filename = fname[0:fname.rfind(".[")]
-            subs = self.query(teamless_filename, languages)
-            return subs
-        else:
-            return subs
-
-    def query(self, token, languages=None):
-        """Makes a query on SubtitlesSource and returns info (link, lang) about found subtitles"""
-        self.logger.debug(u"Local file is: %s " % token)
-        sublinks = []
-        if not languages:  # langs is empty of None
-            languages = ["all"]
-        else:  # parse each lang to generate the equivalent lang
-            languages = [self._plugin_languages[l] for l in languages if l in self._plugin_languages.keys()]
-        # Get the CD part of this
-        metaData = self.guessFileData(token)
-        multipart = metaData.get('part', None)
-        part = metaData.get('part')
-        if not part:  # part will return None if not found using the regex
-            part = 1
-        for lang in languages:
-            searchurl = "%s/%s/%s/0" % (self.server_url, urllib.quote(token), lang)
-            self.logger.debug(u"dl'ing %s" % searchurl)
-            page = urllib2.urlopen(searchurl, timeout=self.timeout)
-            xmltree = xml.dom.minidom.parse(page)
-            subs = xmltree.getElementsByTagName("sub")
-            for sub in subs:
-                sublang = self.getRevertLanguage(self.getValue(sub, "language"))
-                if languages and not sublang in languages:
-                    continue  # The language of this sub is not wanted => Skip
-                if multipart and not int(self.getValue(sub, 'cd')) > 1:
-                    continue  # The subtitle is not a multipart
-                dllink = "http://www.subtitlesource.org/download/text/%s/%s" % (self.getValue(sub, "id"), part)
-                self.logger.debug(u"Link added: %s (%s)" % (dllink, sublang))
-                result = {}
-                result["release"] = self.getValue(sub, "releasename")
-                result["link"] = dllink
-                result["page"] = dllink
-                result["lang"] = sublang
-                releaseMetaData = self.guessFileData(result['release'])
-                teams = set(metaData['teams'])
-                srtTeams = set(releaseMetaData['teams'])
-                self.logger.debug(u"Analyzing: %s " % result['release'])
-                self.logger.debug(u"Local file has: %s " % metaData['teams'])
-                self.logger.debug(u"Remote sub has: %s " % releaseMetaData['teams'])
-                if result['release'].startswith(token) or (releaseMetaData['name'] == metaData['name'] and releaseMetaData['type'] == metaData['type'] and (teams.issubset(srtTeams) or srtTeams.issubset(teams))):
-                    sublinks.append(result)
-        return sublinks
-
-    def download(self, subtitle):
-        """Main method to call when you want to download a subtitle"""
-        suburl = subtitle["link"]
-        videofilename = subtitle["filename"]
-        srtfilename = videofilename.rsplit(".", 1)[0] + self.getExtension(subtitle)
-        self.downloadFile(suburl, srtfilename)
-        return srtfilename
-
-    def getValue(self, sub, tagName):
-        for node in sub.childNodes:
-            if node.nodeType == node.ELEMENT_NODE and node.tagName == tagName:
-                return node.childNodes[0].nodeValue

subliminal/plugins/Subtitulos.py

@@ -1,150 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from BeautifulSoup import BeautifulSoup
-import guessit
-import zipfile
-import urllib2
-import urllib
-import logging
-import traceback
-import httplib
-import re
-import PluginBase
-from subliminal import encodingKludge as ek
-
-
-class Subtitulos(PluginBase.PluginBase):
-    site_url = 'http://www.subtitulos.es'
-    site_name = 'Subtitulos'
-    server_url = 'http://www.subtitulos.es'
-    multi_languages_queries = True
-    multi_filename_queries = False
-    api_based = False
-    _plugin_languages = {u"English (US)": "en",
-            u"English (UK)": "en",
-            u"English": "en",
-            u"French": "fr",
-            u"Brazilian": "pt-br",
-            u"Portuguese": "pt",
-            u"Español (Latinoamérica)": "es",
-            u"Español (España)": "es",
-            u"Español": "es",
-            u"Italian": "it",
-            u"Català": "ca"}
-
-    def __init__(self, config_dict=None):
-        super(Subtitulos, self).__init__(self._plugin_languages, config_dict, True)
-        self.release_pattern = re.compile("Versi&oacute;n (.+) ([0-9]+).([0-9])+ megabytes")
-
-    def list(self, filenames, languages):
-        """Main method to call when you want to list subtitles"""
-        # as self.multi_filename_queries is false, we won't have multiple filenames in the list so pick the only one
-        # once multi-filename queries are implemented, set multi_filename_queries to true and manage a list of multiple filenames here
-        if not self.checkLanguages(languages):
-            return []
-        filepath = filenames[0]
-        guess = guessit.guess_file_info(filepath, 'autodetect')
-        if guess['type'] != 'episode':
-            return []
-        # add multiple things to the release group set
-        release_group = set()
-        if 'releaseGroup' in guess:
-            release_group.add(guess['releaseGroup'].lower())
-        else:
-            if 'title' in guess:
-                release_group.add(guess['title'].lower())
-            if 'screenSize' in guess:
-                release_group.add(guess['screenSize'].lower())
-        if 'series' not in guess or len(release_group) == 0:
-            return []
-        self.release_group = release_group  # used to sort results
-        return self.query(guess['series'], guess['season'], guess['episodeNumber'], release_group, filepath, languages)
-
-    def query(self, name, season, episode, release_group, filepath, languages=None):
-        """Make a query and returns info about found subtitles"""
-        sublinks = []
-        searchname = name.lower().replace(" ", "-")
-        searchurl = "%s/%s/%sx%.2d" % (self.server_url, searchname, season, episode)
-        self.logger.debug(u"Searching in %s" % searchurl)
-        try:
-            req = urllib2.Request(searchurl, headers={'User-Agent': self.user_agent})
-            page = urllib2.urlopen(req, timeout=self.timeout)
-        except urllib2.HTTPError as inst:
-            self.logger.info(u"Error: %s - %s" % (searchurl, inst))
-            return []
-        except urllib2.URLError as inst:
-            self.logger.info(u"TimeOut: %s" % inst)
-            return []
-        soup = BeautifulSoup(page.read())
-        for subs in soup("div", {"id": "version"}):
-            version = subs.find("p", {"class": "title-sub"})
-            sub_teams = self.listTeams([self.release_pattern.search("%s" % version.contents[1]).group(1).lower()], [".", "_", " ", "/"])
-            if not release_group.intersection(sub_teams):  # On wrong team
-                continue
-            self.logger.debug(u"Team from website: %s" % sub_teams)
-            self.logger.debug(u"Team from file: %s" % release_group)
-            for html_language in subs.findAllNext("ul", {"class": "sslist"}):
-                sub_language = self.getRevertLanguage(html_language.findNext("li", {"class": "li-idioma"}).find("strong").contents[0].string.strip())
-                if languages and not sub_language in languages:  # On wrong language
-                    continue
-                html_status = html_language.findNext("li", {"class": "li-estado green"})
-                sub_status = html_status.contents[0].string.strip()
-                if not sub_status == 'Completado':  # On not completed subtitles
-                    continue
-                sub_link = html_status.findNext("span", {"class": "descargar green"}).find("a")["href"]
-                result = {}
-                result["release"] = "%s.S%.2dE%.2d.%s" % (name.replace(" ", "."), int(season), int(episode), '.'.join(sub_teams))
-                result["lang"] = sub_language
-                result["link"] = sub_link
-                result["page"] = searchurl
-                result["filename"] = filepath
-                result["plugin"] = self.getClassName()
-                result["teams"] = sub_teams  # used to sort
-                sublinks.append(result)
-        sublinks.sort(self._cmpTeams)
-        return sublinks
-
-    def download(self, subtitle):
-        """
-        Pass the URL of the sub and the file it matches, will unzip it
-        and return the path to the created file
-        """
-        suburl = subtitle["link"]
-        videofilename = subtitle["filename"]
-        srtbasefilename = videofilename.rsplit(".", 1)[0]
-        srtfilename = srtbasefilename + ".srt"
-        self.downloadFile(suburl, srtfilename)
-        return srtfilename
-
-    def downloadFile(self, url, filename):
-        """Downloads the given url to the given filename"""
-        req = urllib2.Request(url, headers={'Referer': url, 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.3)'})
-        f = urllib2.urlopen(req)
-        dump = ek.ek(open, filename, "wb")
-        dump.write(f.read())
-        dump.close()
-        f.close()
-
-    def _cmpTeams(self, x, y):
-        """Sort based on teams matching"""
-        return -cmp(len(x['teams'].intersection(self.release_group)), len(y['teams'].intersection(self.release_group)))

subliminal/plugins/TheSubDB.py

@@ -1,125 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import PluginBase
-import hashlib
-import os
-import urllib2
-from subliminal import encodingKludge as ek
-
-
-class TheSubDB(PluginBase.PluginBase):
-    site_url = 'http://thesubdb.com'
-    site_name = 'SubDB'
-    server_url = 'http://api.thesubdb.com'  # for testing purpose, use http://sandbox.thesubdb.com instead
-    multi_languages_queries = True
-    multi_filename_queries = False
-    api_based = True
-    user_agent = 'SubDB/1.0 (Subliminal/0.1; https://github.com/Diaoul/subliminal)'  # defined by the API
-    _plugin_languages = {'cs': 'cs',  # the whole list is available with the API: http://sandbox.thesubdb.com/?action=languages
-            'da': 'da',
-            'de': 'de',
-            'en': 'en',
-            'fi': 'fi',
-            'fr': 'fr',
-            'hu': 'hu',
-            'id': 'id',
-            'it': 'it',
-            'nl': 'nl',
-            'no': 'no',
-            'pl': 'pl',
-            'pt': 'pt',
-            'ro': 'ro',
-            'ru': 'ru',
-            'sl': 'sl',
-            'sr': 'sr',
-            'sv': 'sv',
-            'tr': 'tr'}
-
-    def __init__(self, config_dict=None):
-        super(TheSubDB, self).__init__(self._plugin_languages, config_dict)
-
-    def list(self, filenames, languages):
-        """Main method to call when you want to list subtitles"""
-        # as self.multi_filename_queries is false, we won't have multiple filenames in the list so pick the only one
-        # once multi-filename queries are implemented, set multi_filename_queries to true and manage a list of multiple filenames here
-        filepath = filenames[0]
-        if not ek.ek(os.path.isfile, filepath):
-            return []
-        return self.query(filepath, self.hashFile(filepath), languages)
-
-    def query(self, filepath, moviehash, languages=None):
-        searchurl = "%s/?action=%s&hash=%s" % (self.server_url, "search", moviehash)
-        self.logger.debug(u'Query URL: %s' % searchurl)
-        try:
-            req = urllib2.Request(searchurl, headers={'User-Agent': self.user_agent})
-            page = urllib2.urlopen(req, timeout=self.timeout)
-        except urllib2.HTTPError as inst:
-            if inst.code == 404:  # no result found
-                return []
-            self.logger.error(u"Error: %s - %s" % (searchurl, inst))
-            return []
-        except urllib2.URLError as inst:
-            self.logger.error(u"TimeOut: %s" % inst)
-            return []
-        available_languages = page.readlines()[0].split(',')
-        self.logger.debug(u'Available languages: %s' % available_languages)
-        subs = []
-        for l in available_languages:
-            if not languages or l in languages:
-                result = {}
-                result['release'] = filepath
-                result['lang'] = l
-                result['link'] = "%s/?action=download&hash=%s&language=%s" % (self.server_url, moviehash, l)
-                result['page'] = result['link']
-                result['filename'] = filepath
-                result['plugin'] = self.getClassName()
-                subs.append(result)
-        return subs
-
-    def hashFile(self, name):
-        """This hash function receives the filename and returns the hash code"""
-        readsize = 64 * 1024
-        with ek.ek(open, name, 'rb') as f:
-            size = ek.ek(os.path.getsize, name)
-            data = f.read(readsize)
-            f.seek(-readsize, os.SEEK_END)
-            data += f.read(readsize)
-        return hashlib.md5(data).hexdigest()
-
-    def download(self, subtitle):
-        """Main method to call when you want to download a subtitle"""
-        suburl = subtitle["link"]
-        videofilename = subtitle["filename"]
-        srtfilename = videofilename.rsplit(".", 1)[0] + self.getExtension(subtitle)
-        self.downloadFile(suburl, srtfilename)
-        return srtfilename
-
-    def downloadFile(self, url, srtfilename):
-        """Downloads the given url to the given filename"""
-        req = urllib2.Request(url)
-        req.add_header('User-Agent', self.user_agent)
-        f = urllib2.urlopen(req)
-        dump = open(srtfilename, "wb")
-        dump.write(f.read())
-        dump.close()
-        f.close()

subliminal/plugins/__init__.py

@@ -1,31 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from Addic7ed import Addic7ed
-from BierDopje import BierDopje
-from OpenSubtitles import OpenSubtitles
-#from Podnapisi import Podnapisi
-#from SubScene import SubScene
-from SubsWiki import SubsWiki
-#from SubtitleSource import SubtitleSource
-from Subtitulos import Subtitulos
-from TheSubDB import TheSubDB

subliminal/services/__init__.py

@@ -0,0 +1,256 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from ..cache import Cache
+from ..exceptions import DownloadFailedError, ServiceError
+from ..language import language_set, Language
+from ..subtitles import EXTENSIONS
+import logging
+import os
+import requests
+import threading
+import zipfile
+
+
+__all__ = ['ServiceBase', 'ServiceConfig']
+logger = logging.getLogger(__name__)
+
+
+class ServiceBase(object):
+    """Service base class
+
+    :param config: service configuration
+    :type config: :class:`ServiceConfig`
+
+    """
+    #: URL to the service server
+    server_url = ''
+
+    #: User Agent for any HTTP-based requests
+    user_agent = 'subliminal v0.6'
+
+    #: Whether based on an API or not
+    api_based = False
+
+    #: Timeout for web requests
+    timeout = 5
+
+    #: :class:`~subliminal.language.language_set` of available languages
+    languages = language_set()
+
+    #: Map between language objects and language codes used in the service
+    language_map = {}
+
+    #: Default attribute of a :class:`~subliminal.language.Language` to get with :meth:`get_code`
+    language_code = 'alpha2'
+
+    #: Accepted video classes (:class:`~subliminal.videos.Episode`, :class:`~subliminal.videos.Movie`, :class:`~subliminal.videos.UnknownVideo`)
+    videos = []
+
+    #: Whether the video has to exist or not
+    require_video = False
+
+    #: List of required features for BeautifulSoup
+    required_features = None
+
+    def __init__(self, config=None):
+        self.config = config or ServiceConfig()
+        self.session = None
+
+    def __enter__(self):
+        self.init()
+        return self
+
+    def __exit__(self, *args):
+        self.terminate()
+
+    def init(self):
+        """Initialize connection"""
+        logger.debug(u'Initializing %s' % self.__class__.__name__)
+        self.session = requests.session(timeout=10, headers={'User-Agent': self.user_agent})
+
+    def init_cache(self):
+        """Initialize cache, make sure it is loaded from disk"""
+        if not self.config or not self.config.cache:
+            raise ServiceError('Cache directory is required')
+        self.config.cache.load(self.__class__.__name__)
+
+    def save_cache(self):
+        self.config.cache.save(self.__class__.__name__)
+
+    def clear_cache(self):
+        self.config.cache.clear(self.__class__.__name__)
+
+    def cache_for(self, func, args, result):
+        return self.config.cache.cache_for(self.__class__.__name__, func, args, result)
+
+    def cached_value(self, func, args):
+        return self.config.cache.cached_value(self.__class__.__name__, func, args)
+
+    def terminate(self):
+        """Terminate connection"""
+        logger.debug(u'Terminating %s' % self.__class__.__name__)
+
+    def get_code(self, language):
+        """Get the service code for a :class:`~subliminal.language.Language`
+
+        It uses the :data:`language_map` and if there's no match, falls back
+        on the :data:`language_code` attribute of the given :class:`~subliminal.language.Language`
+
+        """
+        if language in self.language_map:
+            return self.language_map[language]
+        if self.language_code is None:
+            raise ValueError('%r has no matching code' % language)
+        return getattr(language, self.language_code)
+
+    def get_language(self, code):
+        """Get a :class:`~subliminal.language.Language` from a service code
+
+        It uses the :data:`language_map` and if there's no match, uses the
+        given code as ``language`` parameter for the :class:`~subliminal.language.Language`
+        constructor
+
+        .. note::
+
+            A warning is emitted if the generated :class:`~subliminal.language.Language`
+            is "Undetermined"
+
+        """
+        if code in self.language_map:
+            return self.language_map[code]
+        language = Language(code, strict=False)
+        if language == Language('Undetermined'):
+            logger.warning(u'Code %s could not be identified as a language for %s' % (code, self.__class__.__name__))
+        return language
+
+    def query(self, *args):
+        """Make the actual query"""
+        raise NotImplementedError()
+
+    def list(self, video, languages):
+        """List subtitles
+
+        As a service writer, you can either override this method or implement
+        :meth:`list_checked` instead to have the languages pre-filtered for you
+
+        """
+        if not self.check_validity(video, languages):
+            return []
+        return self.list_checked(video, languages)
+
+    def list_checked(self, video, languages):
+        """List subtitles without having to check parameters for validity"""
+        raise NotImplementedError()
+
+    def download(self, subtitle):
+        """Download a subtitle"""
+        self.download_file(subtitle.link, subtitle.path)
+        return subtitle
+
+    @classmethod
+    def check_validity(cls, video, languages):
+        """Check for video and languages validity in the Service
+
+        :param video: the video to check
+        :type video: :class:`~subliminal.videos.video`
+        :param languages: languages to check
+        :type languages: :class:`~subliminal.language.Language`
+        :rtype: bool
+
+        """
+        languages = (languages & cls.languages) - language_set(['Undetermined'])
+        if not languages:
+            logger.debug(u'No language available for service %s' % cls.__name__.lower())
+            return False
+        if cls.require_video and not video.exists or not isinstance(video, tuple(cls.videos)):
+            logger.debug(u'%r is not valid for service %s' % (video, cls.__name__.lower()))
+            return False
+        return True
+
+    def download_file(self, url, filepath):
+        """Attempt to download a file and remove it in case of failure
+
+        :param string url: URL to download
+        :param string filepath: destination path
+
+        """
+        logger.info(u'Downloading %s in %s' % (url, filepath))
+        try:
+            r = self.session.get(url, headers={'Referer': url, 'User-Agent': self.user_agent})
+            with open(filepath, 'wb') as f:
+                f.write(r.content)
+        except Exception as e:
+            logger.error(u'Download failed: %s' % e)
+            if os.path.exists(filepath):
+                os.remove(filepath)
+            raise DownloadFailedError(str(e))
+        logger.debug(u'Download finished')
+
+    def download_zip_file(self, url, filepath):
+        """Attempt to download a zip file and extract any subtitle file from it, if any.
+        This cleans up after itself if anything fails.
+
+        :param string url: URL of the zip file to download
+        :param string filepath: destination path for the subtitle
+
+        """
+        logger.info(u'Downloading %s in %s' % (url, filepath))
+        try:
+            zippath = filepath + '.zip'
+            r = self.session.get(url, headers={'Referer': url, 'User-Agent': self.user_agent})
+            with open(zippath, 'wb') as f:
+                f.write(r.content)
+            if not zipfile.is_zipfile(zippath):
+                # TODO: could check if maybe we already have a text file and
+                # download it directly
+                raise DownloadFailedError('Downloaded file is not a zip file')
+            with zipfile.ZipFile(zippath) as zipsub:
+                for subfile in zipsub.namelist():
+                    if os.path.splitext(subfile)[1] in EXTENSIONS:
+                        with open(filepath, 'w') as f:
+                            f.write(zipsub.open(subfile).read())
+                        break
+                else:
+                    raise DownloadFailedError('No subtitles found in zip file')
+            os.remove(zippath)
+        except Exception as e:
+            logger.error(u'Download %s failed: %s' % (url, e))
+            if os.path.exists(zippath):
+                os.remove(zippath)
+            if os.path.exists(filepath):
+                os.remove(filepath)
+            raise DownloadFailedError(str(e))
+        logger.debug(u'Download finished')
+
+
+class ServiceConfig(object):
+    """Configuration for any :class:`Service`
+
+    :param bool multi: whether to download one subtitle per language or not
+    :param string cache_dir: cache directory
+
+    """
+    def __init__(self, multi=False, cache_dir=None):
+        self.multi = multi
+        self.cache_dir = cache_dir
+        self.cache = None
+        if cache_dir is not None:
+            self.cache = Cache(cache_dir)
+
+    def __repr__(self):
+        return 'ServiceConfig(%r, %s)' % (self.multi, self.cache.cache_dir)

subliminal/services/addic7ed.py

@@ -0,0 +1,120 @@
+# -*- coding: utf-8 -*-
+# Copyright 2012 Olivier Leveau <olifozzy@gmail.com>
+# Copyright 2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from . import ServiceBase
+from ..cache import cachedmethod
+from ..exceptions import DownloadFailedError
+from ..language import Language, language_set
+from ..subtitles import get_subtitle_path, ResultSubtitle
+from ..utils import get_keywords, split_keyword
+from ..videos import Episode
+from bs4 import BeautifulSoup
+import logging
+import os
+import re
+
+
+logger = logging.getLogger(__name__)
+
+
+class Addic7ed(ServiceBase):
+    server_url = 'http://www.addic7ed.com'
+    api_based = False
+    #TODO: Complete this
+    languages = language_set(['ar', 'ca', 'de', 'el', 'en', 'es', 'eu', 'fr', 'ga', 'gl', 'he', 'hr', 'hu',
+                              'it', 'pl', 'pt', 'ro', 'ru', 'se', 'pt-br'])
+    language_map = {'Portuguese (Brazilian)': Language('por-BR'), 'Greek': Language('gre'),
+                    'Spanish (Latin America)': Language('spa'), 'Galego': Language('glg'),
+                    u'Català': Language('cat')}
+    videos = [Episode]
+    require_video = False
+    required_features = ['permissive']
+
+    @cachedmethod
+    def get_series_id(self, name):
+        """Get the show page and cache every show found in it"""
+        r = self.session.get('%s/shows.php' % self.server_url)
+        soup = BeautifulSoup(r.content, self.required_features)
+        for html_series in soup.select('h3 > a'):
+            series_name = html_series.text.lower()
+            match = re.search('show/([0-9]+)', html_series['href'])
+            if match is None:
+                continue
+            series_id = int(match.group(1))
+            self.cache_for(self.get_series_id, args=(series_name,), result=series_id)
+        return self.cached_value(self.get_series_id, args=(name,))
+
+    def list_checked(self, video, languages):
+        return self.query(video.path or video.release, languages, get_keywords(video.guess), video.series, video.season, video.episode)
+
+    def query(self, filepath, languages, keywords, series, season, episode):
+        logger.debug(u'Getting subtitles for %s season %d episode %d with languages %r' % (series, season, episode, languages))
+        self.init_cache()
+        try:
+            series_id = self.get_series_id(series.lower())
+        except KeyError:
+            logger.debug(u'Could not find series id for %s' % series)
+            return []
+        r = self.session.get('%s/show/%d&season=%d' % (self.server_url, series_id, season))
+        soup = BeautifulSoup(r.content, self.required_features)
+        subtitles = []
+        for row in soup('tr', {'class': 'epeven completed'}):
+            cells = row('td')
+            if int(cells[0].text.strip()) != season or int(cells[1].text.strip()) != episode:
+                continue
+            if cells[6].text.strip():
+                logger.debug(u'Skipping hearing impaired')
+                continue
+            sub_status = cells[5].text.strip()
+            if sub_status != 'Completed':
+                logger.debug(u'Wrong subtitle status %s' % sub_status)
+                continue
+            sub_language = self.get_language(cells[3].text.strip())
+            if sub_language not in languages:
+                logger.debug(u'Language %r not in wanted languages %r' % (sub_language, languages))
+                continue
+            sub_keywords = split_keyword(cells[4].text.strip().lower())
+            #TODO: Maybe allow empty keywords here? (same in Subtitulos)
+            if not keywords & sub_keywords:
+                logger.debug(u'None of subtitle keywords %r in %r' % (sub_keywords, keywords))
+                continue
+            sub_link = '%s/%s' % (self.server_url, cells[9].a['href'])
+            sub_path = get_subtitle_path(filepath, sub_language, self.config.multi)
+            subtitle = ResultSubtitle(sub_path, sub_language, self.__class__.__name__.lower(), sub_link, keywords=sub_keywords)
+            subtitles.append(subtitle)
+        return subtitles
+
+    def download(self, subtitle):
+        logger.info(u'Downloading %s in %s' % (subtitle.link, subtitle.path))
+        try:
+            r = self.session.get(subtitle.link, headers={'Referer': subtitle.link, 'User-Agent': self.user_agent})
+            soup = BeautifulSoup(r.content, self.required_features)
+            if soup.title is not None and u'Addic7ed.com' in soup.title.text.strip():
+                raise DownloadFailedError('Download limit exceeded')
+            with open(subtitle.path, 'wb') as f:
+                f.write(r.content)
+        except Exception as e:
+            logger.error(u'Download failed: %s' % e)
+            if os.path.exists(subtitle.path):
+                os.remove(subtitle.path)
+            raise DownloadFailedError(str(e))
+        logger.debug(u'Download finished')
+        return subtitle
+
+
+Service = Addic7ed

subliminal/services/bierdopje.py

@@ -0,0 +1,103 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from . import ServiceBase
+from ..cache import cachedmethod
+from ..exceptions import ServiceError
+from ..language import language_set
+from ..subtitles import get_subtitle_path, ResultSubtitle, EXTENSIONS
+from ..utils import to_unicode
+from ..videos import Episode
+from bs4 import BeautifulSoup
+import logging
+import urllib
+try:
+    import cPickle as pickle
+except ImportError:
+    import pickle
+
+
+logger = logging.getLogger(__name__)
+
+
+class BierDopje(ServiceBase):
+    server_url = 'http://api.bierdopje.com/A2B638AC5D804C2E/'
+    user_agent = 'Subliminal/0.6'
+    api_based = True
+    languages = language_set(['eng', 'dut'])
+    videos = [Episode]
+    require_video = False
+    required_features = ['xml']
+
+    @cachedmethod
+    def get_show_id(self, series):
+        r = self.session.get('%sGetShowByName/%s' % (self.server_url, urllib.quote(series.lower())))
+        if r.status_code != 200:
+            logger.error(u'Request %s returned status code %d' % (r.url, r.status_code))
+            return None
+        soup = BeautifulSoup(r.content, self.required_features)
+        if soup.status.contents[0] == 'false':
+            logger.debug(u'Could not find show %s' % series)
+            return None
+        return int(soup.showid.contents[0])
+
+    def load_cache(self):
+        logger.debug(u'Loading showids from cache...')
+        with self.lock:
+            with open(self.showids_cache, 'r') as f:
+                self.showids = pickle.load(f)
+
+    def query(self, filepath, season, episode, languages, tvdbid=None, series=None):
+        self.init_cache()
+        if series:
+            request_id = self.get_show_id(series.lower())
+            if request_id is None:
+                return []
+            request_source = 'showid'
+            request_is_tvdbid = 'false'
+        elif tvdbid:
+            request_id = tvdbid
+            request_source = 'tvdbid'
+            request_is_tvdbid = 'true'
+        else:
+            raise ServiceError('One or more parameter missing')
+        subtitles = []
+        for language in languages:
+            logger.debug(u'Getting subtitles for %s %d season %d episode %d with language %s' % (request_source, request_id, season, episode, language.alpha2))
+            r = self.session.get('%sGetAllSubsFor/%s/%s/%s/%s/%s' % (self.server_url, request_id, season, episode, language.alpha2, request_is_tvdbid))
+            if r.status_code != 200:
+                logger.error(u'Request %s returned status code %d' % (r.url, r.status_code))
+                return []
+            soup = BeautifulSoup(r.content, self.required_features)
+            if soup.status.contents[0] == 'false':
+                logger.debug(u'Could not find subtitles for %s %d season %d episode %d with language %s' % (request_source, request_id, season, episode, language.alpha2))
+                continue
+            path = get_subtitle_path(filepath, language, self.config.multi)
+            for result in soup.results('result'):
+                release = to_unicode(result.filename.contents[0])
+                if not release.endswith(tuple(EXTENSIONS)):
+                    release += '.srt'
+                subtitle = ResultSubtitle(path, language, self.__class__.__name__.lower(), result.downloadlink.contents[0],
+                                          release=release)
+                subtitles.append(subtitle)
+        return subtitles
+
+    def list_checked(self, video, languages):
+        return self.query(video.path or video.release, video.season, video.episode, languages, video.tvdbid, video.series)
+
+
+Service = BierDopje

subliminal/services/opensubtitles.py

@@ -0,0 +1,158 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from . import ServiceBase
+from ..exceptions import ServiceError, DownloadFailedError
+from ..language import Language, language_set
+from ..subtitles import get_subtitle_path, ResultSubtitle
+from ..utils import to_unicode
+from ..videos import Episode, Movie
+import gzip
+import logging
+import os.path
+import xmlrpclib
+
+
+logger = logging.getLogger(__name__)
+
+
+class OpenSubtitles(ServiceBase):
+    server_url = 'http://api.opensubtitles.org/xml-rpc'
+    api_based = True
+    # Source: http://www.opensubtitles.org/addons/export_languages.php
+    languages = language_set(['aar', 'abk', 'ace', 'ach', 'ada', 'ady', 'afa', 'afh', 'afr', 'ain', 'aka', 'akk',
+                              'alb', 'ale', 'alg', 'alt', 'amh', 'ang', 'apa', 'ara', 'arc', 'arg', 'arm', 'arn',
+                              'arp', 'art', 'arw', 'asm', 'ast', 'ath', 'aus', 'ava', 'ave', 'awa', 'aym', 'aze',
+                              'bad', 'bai', 'bak', 'bal', 'bam', 'ban', 'baq', 'bas', 'bat', 'bej', 'bel', 'bem',
+                              'ben', 'ber', 'bho', 'bih', 'bik', 'bin', 'bis', 'bla', 'bnt', 'bos', 'bra', 'bre',
+                              'btk', 'bua', 'bug', 'bul', 'bur', 'byn', 'cad', 'cai', 'car', 'cat', 'cau', 'ceb',
+                              'cel', 'cha', 'chb', 'che', 'chg', 'chi', 'chk', 'chm', 'chn', 'cho', 'chp', 'chr',
+                              'chu', 'chv', 'chy', 'cmc', 'cop', 'cor', 'cos', 'cpe', 'cpf', 'cpp', 'cre', 'crh',
+                              'crp', 'csb', 'cus', 'cze', 'dak', 'dan', 'dar', 'day', 'del', 'den', 'dgr', 'din',
+                              'div', 'doi', 'dra', 'dua', 'dum', 'dut', 'dyu', 'dzo', 'efi', 'egy', 'eka', 'ell',
+                              'elx', 'eng', 'enm', 'epo', 'est', 'ewe', 'ewo', 'fan', 'fao', 'fat', 'fij', 'fil',
+                              'fin', 'fiu', 'fon', 'fre', 'frm', 'fro', 'fry', 'ful', 'fur', 'gaa', 'gay', 'gba',
+                              'gem', 'geo', 'ger', 'gez', 'gil', 'gla', 'gle', 'glg', 'glv', 'gmh', 'goh', 'gon',
+                              'gor', 'got', 'grb', 'grc', 'grn', 'guj', 'gwi', 'hai', 'hat', 'hau', 'haw', 'heb',
+                              'her', 'hil', 'him', 'hin', 'hit', 'hmn', 'hmo', 'hrv', 'hun', 'hup', 'iba', 'ibo',
+                              'ice', 'ido', 'iii', 'ijo', 'iku', 'ile', 'ilo', 'ina', 'inc', 'ind', 'ine', 'inh',
+                              'ipk', 'ira', 'iro', 'ita', 'jav', 'jpn', 'jpr', 'jrb', 'kaa', 'kab', 'kac', 'kal',
+                              'kam', 'kan', 'kar', 'kas', 'kau', 'kaw', 'kaz', 'kbd', 'kha', 'khi', 'khm', 'kho',
+                              'kik', 'kin', 'kir', 'kmb', 'kok', 'kom', 'kon', 'kor', 'kos', 'kpe', 'krc', 'kro',
+                              'kru', 'kua', 'kum', 'kur', 'kut', 'lad', 'lah', 'lam', 'lao', 'lat', 'lav', 'lez',
+                              'lim', 'lin', 'lit', 'lol', 'loz', 'ltz', 'lua', 'lub', 'lug', 'lui', 'lun', 'luo',
+                              'lus', 'mac', 'mad', 'mag', 'mah', 'mai', 'mak', 'mal', 'man', 'mao', 'map', 'mar',
+                              'mas', 'may', 'mdf', 'mdr', 'men', 'mga', 'mic', 'min', 'mkh', 'mlg', 'mlt', 'mnc',
+                              'mni', 'mno', 'moh', 'mon', 'mos', 'mun', 'mus', 'mwl', 'mwr', 'myn', 'myv', 'nah',
+                              'nai', 'nap', 'nau', 'nav', 'nbl', 'nde', 'ndo', 'nds', 'nep', 'new', 'nia', 'nic',
+                              'niu', 'nno', 'nob', 'nog', 'non', 'nor', 'nso', 'nub', 'nwc', 'nya', 'nym', 'nyn',
+                              'nyo', 'nzi', 'oci', 'oji', 'ori', 'orm', 'osa', 'oss', 'ota', 'oto', 'paa', 'pag',
+                              'pal', 'pam', 'pan', 'pap', 'pau', 'peo', 'per', 'phi', 'phn', 'pli', 'pol', 'pon',
+                              'por', 'pra', 'pro', 'pus', 'que', 'raj', 'rap', 'rar', 'roa', 'roh', 'rom', 'rum',
+                              'run', 'rup', 'rus', 'sad', 'sag', 'sah', 'sai', 'sal', 'sam', 'san', 'sas', 'sat',
+                              'scn', 'sco', 'sel', 'sem', 'sga', 'sgn', 'shn', 'sid', 'sin', 'sio', 'sit', 'sla',
+                              'slo', 'slv', 'sma', 'sme', 'smi', 'smj', 'smn', 'smo', 'sms', 'sna', 'snd', 'snk',
+                              'sog', 'som', 'son', 'sot', 'spa', 'srd', 'srp', 'srr', 'ssa', 'ssw', 'suk', 'sun',
+                              'sus', 'sux', 'swa', 'swe', 'syr', 'tah', 'tai', 'tam', 'tat', 'tel', 'tem', 'ter',
+                              'tet', 'tgk', 'tgl', 'tha', 'tib', 'tig', 'tir', 'tiv', 'tkl', 'tlh', 'tli', 'tmh',
+                              'tog', 'ton', 'tpi', 'tsi', 'tsn', 'tso', 'tuk', 'tum', 'tup', 'tur', 'tut', 'tvl',
+                              'twi', 'tyv', 'udm', 'uga', 'uig', 'ukr', 'umb', 'urd', 'uzb', 'vai', 'ven', 'vie',
+                              'vol', 'vot', 'wak', 'wal', 'war', 'was', 'wel', 'wen', 'wln', 'wol', 'xal', 'xho',
+                              'yao', 'yap', 'yid', 'yor', 'ypk', 'zap', 'zen', 'zha', 'znd', 'zul', 'zun',
+                              'por-BR', 'rum-MD'])
+    language_map = {'mol': Language('rum-MD'), 'scc': Language('srp'), 'pob': Language('por-BR'),
+                    Language('rum-MD'): 'mol', Language('srp'): 'scc', Language('por-BR'): 'pob'}
+    language_code = 'alpha3'
+    videos = [Episode, Movie]
+    require_video = False
+    confidence_order = ['moviehash', 'imdbid', 'fulltext']
+
+    def __init__(self, config=None):
+        super(OpenSubtitles, self).__init__(config)
+        self.server = xmlrpclib.ServerProxy(self.server_url)
+        self.token = None
+
+    def init(self):
+        super(OpenSubtitles, self).init()
+        result = self.server.LogIn('', '', 'eng', self.user_agent)
+        if result['status'] != '200 OK':
+            raise ServiceError('Login failed')
+        self.token = result['token']
+
+    def terminate(self):
+        super(OpenSubtitles, self).terminate()
+        if self.token:
+            self.server.LogOut(self.token)
+
+    def query(self, filepath, languages, moviehash=None, size=None, imdbid=None, query=None):
+        searches = []
+        if moviehash and size:
+            searches.append({'moviehash': moviehash, 'moviebytesize': size})
+        if imdbid:
+            searches.append({'imdbid': imdbid})
+        if query:
+            searches.append({'query': query})
+        if not searches:
+            raise ServiceError('One or more parameter missing')
+        for search in searches:
+            search['sublanguageid'] = ','.join(self.get_code(l) for l in languages)
+        logger.debug(u'Getting subtitles %r with token %s' % (searches, self.token))
+        results = self.server.SearchSubtitles(self.token, searches)
+        if not results['data']:
+            logger.debug(u'Could not find subtitles for %r with token %s' % (searches, self.token))
+            return []
+        subtitles = []
+        for result in results['data']:
+            language = self.get_language(result['SubLanguageID'])
+            path = get_subtitle_path(filepath, language, self.config.multi)
+            confidence = 1 - float(self.confidence_order.index(result['MatchedBy'])) / float(len(self.confidence_order))
+            subtitle = ResultSubtitle(path, language, self.__class__.__name__.lower(), result['SubDownloadLink'],
+                                      release=to_unicode(result['SubFileName']), confidence=confidence)
+            subtitles.append(subtitle)
+        return subtitles
+
+    def list_checked(self, video, languages):
+        results = []
+        if video.exists:
+            results = self.query(video.path or video.release, languages, moviehash=video.hashes['OpenSubtitles'], size=str(video.size))
+        elif video.imdbid:
+            results = self.query(video.path or video.release, languages, imdbid=video.imdbid)
+        elif isinstance(video, Episode):
+            results = self.query(video.path or video.release, languages, query=video.series)
+        elif isinstance(video, Movie):
+            results = self.query(video.path or video.release, languages, query=video.title)
+        return results
+
+    def download(self, subtitle):
+        #TODO: Use OpenSubtitles DownloadSubtitles method
+        try:
+            self.download_file(subtitle.link, subtitle.path + '.gz')
+            with open(subtitle.path, 'wb') as dump:
+                gz = gzip.open(subtitle.path + '.gz')
+                dump.write(gz.read())
+                gz.close()
+        except Exception as e:
+            if os.path.exists(subtitle.path):
+                os.remove(subtitle.path)
+            raise DownloadFailedError(str(e))
+        finally:
+            if os.path.exists(subtitle.path + '.gz'):
+                os.remove(subtitle.path + '.gz')
+        return subtitle
+
+
+Service = OpenSubtitles

subliminal/services/podnapisi.py

@@ -0,0 +1,110 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from . import ServiceBase
+from ..exceptions import ServiceError, DownloadFailedError
+from ..language import language_set, Language
+from ..subtitles import get_subtitle_path, ResultSubtitle
+from ..utils import to_unicode
+from ..videos import Episode, Movie
+from hashlib import md5, sha256
+import logging
+import xmlrpclib
+
+
+logger = logging.getLogger(__name__)
+
+
+class Podnapisi(ServiceBase):
+    server_url = 'http://ssp.podnapisi.net:8000'
+    api_based = True
+    languages = language_set(['ar', 'be', 'bg', 'bs', 'ca', 'ca', 'cs', 'da', 'de', 'el', 'en',
+                              'es', 'et', 'fa', 'fi', 'fr', 'ga', 'he', 'hi', 'hr', 'hu', 'id',
+                              'is', 'it', 'ja', 'ko', 'lt', 'lv', 'mk', 'ms', 'nl', 'nn', 'pl',
+                              'pt', 'ro', 'ru', 'sk', 'sl', 'sq', 'sr', 'sv', 'th', 'tr', 'uk',
+                              'vi', 'zh', 'es-ar', 'pt-br'])
+    language_map = {'jp': Language('jpn'), Language('jpn'): 'jp',
+                    'gr': Language('gre'), Language('gre'): 'gr',
+                    'pb': Language('por-BR'), Language('por-BR'): 'pb',
+                    'ag': Language('spa-AR'), Language('spa-AR'): 'ag',
+                    'cyr': Language('srp')}
+    videos = [Episode, Movie]
+    require_video = True
+
+    def __init__(self, config=None):
+        super(Podnapisi, self).__init__(config)
+        self.server = xmlrpclib.ServerProxy(self.server_url)
+        self.token = None
+
+    def init(self):
+        super(Podnapisi, self).init()
+        result = self.server.initiate(self.user_agent)
+        if result['status'] != 200:
+            raise ServiceError('Initiate failed')
+        username = 'python_subliminal'
+        password = sha256(md5('XWFXQ6gE5Oe12rv4qxXX').hexdigest() + result['nonce']).hexdigest()
+        self.token = result['session']
+        result = self.server.authenticate(self.token, username, password)
+        if result['status'] != 200:
+            raise ServiceError('Authenticate failed')
+
+    def terminate(self):
+        super(Podnapisi, self).terminate()
+
+    def query(self, filepath, languages, moviehash):
+        results = self.server.search(self.token, [moviehash])
+        if results['status'] != 200:
+            logger.error('Search failed with error code %d' % results['status'])
+            return []
+        if not results['results'] or not results['results'][moviehash]['subtitles']:
+            logger.debug(u'Could not find subtitles for %r with token %s' % (moviehash, self.token))
+            return []
+        subtitles = []
+        for result in results['results'][moviehash]['subtitles']:
+            language = self.get_language(result['lang'])
+            if language not in languages:
+                continue
+            path = get_subtitle_path(filepath, language, self.config.multi)
+            subtitle = ResultSubtitle(path, language, self.__class__.__name__.lower(), result['id'],
+                                      release=to_unicode(result['release']), confidence=result['weight'])
+            subtitles.append(subtitle)
+        if not subtitles:
+            return []
+        # Convert weight to confidence
+        max_weight = float(max([s.confidence for s in subtitles]))
+        min_weight = float(min([s.confidence for s in subtitles]))
+        for subtitle in subtitles:
+            if max_weight == 0 and min_weight == 0:
+                subtitle.confidence = 1.0
+            else:
+                subtitle.confidence = (subtitle.confidence - min_weight) / (max_weight - min_weight)
+        return subtitles
+
+    def list_checked(self, video, languages):
+        results = self.query(video.path, languages, video.hashes['OpenSubtitles'])
+        return results
+
+    def download(self, subtitle):
+        results = self.server.download(self.token, [subtitle.link])
+        if results['status'] != 200:
+            raise DownloadFailedError()
+        subtitle.link = 'http://www.podnapisi.net/static/podnapisi/' + results['names'][0]['filename']
+        self.download_file(subtitle.link, subtitle.path)
+        return subtitle
+
+
+Service = Podnapisi

subliminal/services/subswiki.py

@@ -0,0 +1,99 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from . import ServiceBase
+from ..exceptions import ServiceError
+from ..language import language_set, Language
+from ..subtitles import get_subtitle_path, ResultSubtitle
+from ..utils import get_keywords, split_keyword
+from ..videos import Episode, Movie
+from bs4 import BeautifulSoup
+import logging
+import urllib
+
+
+logger = logging.getLogger(__name__)
+
+
+class SubsWiki(ServiceBase):
+    server_url = 'http://www.subswiki.com'
+    api_based = False
+    languages = language_set(['eng-US', 'eng-GB', 'eng', 'fre', 'por-BR', 'por', 'spa-ES', u'spa', u'ita', u'cat'])
+    language_map = {u'Español': Language('spa'), u'Español (España)': Language('spa'), u'Español (Latinoamérica)': Language('spa'),
+                    u'Català': Language('cat'), u'Brazilian': Language('por-BR'), u'English (US)': Language('eng-US'),
+                    u'English (UK)': Language('eng-GB')}
+    language_code = 'name'
+    videos = [Episode, Movie]
+    require_video = False
+    required_features = ['permissive']
+
+    def list_checked(self, video, languages):
+        results = []
+        if isinstance(video, Episode):
+            results = self.query(video.path or video.release, languages, get_keywords(video.guess), series=video.series, season=video.season, episode=video.episode)
+        elif isinstance(video, Movie) and video.year:
+            results = self.query(video.path or video.release, languages, get_keywords(video.guess), movie=video.title, year=video.year)
+        return results
+
+    def query(self, filepath, languages, keywords=None, series=None, season=None, episode=None, movie=None, year=None):
+        if series and season and episode:
+            request_series = series.lower().replace(' ', '_')
+            if isinstance(request_series, unicode):
+                request_series = request_series.encode('utf-8')
+            logger.debug(u'Getting subtitles for %s season %d episode %d with languages %r' % (series, season, episode, languages))
+            r = self.session.get('%s/serie/%s/%s/%s/' % (self.server_url, urllib.quote(request_series), season, episode))
+            if r.status_code == 404:
+                logger.debug(u'Could not find subtitles for %s season %d episode %d with languages %r' % (series, season, episode, languages))
+                return []
+        elif movie and year:
+            request_movie = movie.title().replace(' ', '_')
+            if isinstance(request_movie, unicode):
+                request_movie = request_movie.encode('utf-8')
+            logger.debug(u'Getting subtitles for %s (%d) with languages %r' % (movie, year, languages))
+            r = self.session.get('%s/film/%s_(%d)' % (self.server_url, urllib.quote(request_movie), year))
+            if r.status_code == 404:
+                logger.debug(u'Could not find subtitles for %s (%d) with languages %r' % (movie, year, languages))
+                return []
+        else:
+            raise ServiceError('One or more parameter missing')
+        if r.status_code != 200:
+            logger.error(u'Request %s returned status code %d' % (r.url, r.status_code))
+            return []
+        soup = BeautifulSoup(r.content, self.required_features)
+        subtitles = []
+        for sub in soup('td', {'class': 'NewsTitle'}):
+            sub_keywords = split_keyword(sub.b.string.lower())
+            if not keywords & sub_keywords:
+                logger.debug(u'None of subtitle keywords %r in %r' % (sub_keywords, keywords))
+                continue
+            for html_language in sub.parent.parent.find_all('td', {'class': 'language'}):
+                language = self.get_language(html_language.string.strip())
+                if language not in languages:
+                    logger.debug(u'Language %r not in wanted languages %r' % (language, languages))
+                    continue
+                html_status = html_language.find_next_sibling('td')
+                status = html_status.strong.string.strip()
+                if status != 'Completado':
+                    logger.debug(u'Wrong subtitle status %s' % status)
+                    continue
+                path = get_subtitle_path(filepath, language, self.config.multi)
+                subtitle = ResultSubtitle(path, language, self.__class__.__name__.lower(), '%s%s' % (self.server_url, html_status.find_next('td').find('a')['href']))
+                subtitles.append(subtitle)
+        return subtitles
+
+
+Service = SubsWiki

subliminal/services/subtitulos.py

@@ -0,0 +1,88 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from . import ServiceBase
+from ..language import language_set, Language
+from ..subtitles import get_subtitle_path, ResultSubtitle
+from ..utils import get_keywords, split_keyword
+from ..videos import Episode
+from bs4 import BeautifulSoup
+import logging
+import re
+import unicodedata
+import urllib
+
+
+logger = logging.getLogger(__name__)
+
+
+class Subtitulos(ServiceBase):
+    server_url = 'http://www.subtitulos.es'
+    api_based = False
+    languages = language_set(['eng-US', 'eng-GB', 'eng', 'fre', 'por-BR', 'por', 'spa-ES', u'spa', u'ita', u'cat'])
+    language_map = {u'Español': Language('spa'), u'Español (España)': Language('spa'), u'Español (Latinoamérica)': Language('spa'),
+                    u'Català': Language('cat'), u'Brazilian': Language('por-BR'), u'English (US)': Language('eng-US'),
+                    u'English (UK)': Language('eng-GB'), 'Galego': Language('glg')}
+    language_code = 'name'
+    videos = [Episode]
+    require_video = False
+    required_features = ['permissive']
+    # the '.+' in the pattern for Version allows us to match both '&oacute;'
+    # and the 'ó' char directly. This is because now BS4 converts the html
+    # code chars into their equivalent unicode char
+    release_pattern = re.compile('Versi.+n (.+) ([0-9]+).([0-9])+ megabytes')
+
+    def list_checked(self, video, languages):
+        return self.query(video.path or video.release, languages, get_keywords(video.guess), video.series, video.season, video.episode)
+
+    def query(self, filepath, languages, keywords, series, season, episode):
+        request_series = series.lower().replace(' ', '_')
+        if isinstance(request_series, unicode):
+            request_series = unicodedata.normalize('NFKD', request_series).encode('ascii', 'ignore')
+        logger.debug(u'Getting subtitles for %s season %d episode %d with languages %r' % (series, season, episode, languages))
+        r = self.session.get('%s/%s/%sx%.2d' % (self.server_url, urllib.quote(request_series), season, episode))
+        if r.status_code == 404:
+            logger.debug(u'Could not find subtitles for %s season %d episode %d with languages %r' % (series, season, episode, languages))
+            return []
+        if r.status_code != 200:
+            logger.error(u'Request %s returned status code %d' % (r.url, r.status_code))
+            return []
+        soup = BeautifulSoup(r.content, self.required_features)
+        subtitles = []
+        for sub in soup('div', {'id': 'version'}):
+            sub_keywords = split_keyword(self.release_pattern.search(sub.find('p', {'class': 'title-sub'}).contents[1]).group(1).lower())
+            if not keywords & sub_keywords:
+                logger.debug(u'None of subtitle keywords %r in %r' % (sub_keywords, keywords))
+                continue
+            for html_language in sub.findAllNext('ul', {'class': 'sslist'}):
+                language = self.get_language(html_language.findNext('li', {'class': 'li-idioma'}).find('strong').contents[0].string.strip())
+                if language not in languages:
+                    logger.debug(u'Language %r not in wanted languages %r' % (language, languages))
+                    continue
+                html_status = html_language.findNext('li', {'class': 'li-estado green'})
+                status = html_status.contents[0].string.strip()
+                if status != 'Completado':
+                    logger.debug(u'Wrong subtitle status %s' % status)
+                    continue
+                path = get_subtitle_path(filepath, language, self.config.multi)
+                subtitle = ResultSubtitle(path, language, self.__class__.__name__.lower(), html_status.findNext('span', {'class': 'descargar green'}).find('a')['href'],
+                                          keywords=sub_keywords)
+                subtitles.append(subtitle)
+        return subtitles
+
+
+Service = Subtitulos

subliminal/services/thesubdb.py

@@ -0,0 +1,63 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from . import ServiceBase
+from ..language import language_set
+from ..subtitles import get_subtitle_path, ResultSubtitle
+from ..videos import Episode, Movie, UnknownVideo
+import logging
+
+
+logger = logging.getLogger(__name__)
+
+
+class TheSubDB(ServiceBase):
+    server_url = 'http://api.thesubdb.com'
+    user_agent = 'SubDB/1.0 (subliminal/0.6; https://github.com/Diaoul/subliminal)'
+    api_based = True
+    # Source: http://api.thesubdb.com/?action=languages
+    languages = language_set(['af', 'cs', 'da', 'de', 'en', 'es', 'fi', 'fr', 'hu', 'id', 'it',
+                              'la', 'nl', 'no', 'oc', 'pl', 'pt', 'ro', 'ru', 'sl', 'sr', 'sv',
+                              'tr'])
+    videos = [Movie, Episode, UnknownVideo]
+    require_video = True
+
+    def list_checked(self, video, languages):
+        return self.query(video.path, video.hashes['TheSubDB'], languages)
+
+    def query(self, filepath, moviehash, languages):
+        r = self.session.get(self.server_url, params={'action': 'search', 'hash': moviehash})
+        if r.status_code == 404:
+            logger.debug(u'Could not find subtitles for hash %s' % moviehash)
+            return []
+        if r.status_code != 200:
+            logger.error(u'Request %s returned status code %d' % (r.url, r.status_code))
+            return []
+        available_languages = language_set(r.content.split(','))
+        languages &= available_languages
+        if not languages:
+            logger.debug(u'Could not find subtitles for hash %s with languages %r (only %r available)' % (moviehash, languages, available_languages))
+            return []
+        subtitles = []
+        for language in languages:
+            path = get_subtitle_path(filepath, language, self.config.multi)
+            subtitle = ResultSubtitle(path, language, self.__class__.__name__.lower(), '%s?action=download&hash=%s&language=%s' % (self.server_url, moviehash, language.alpha2))
+            subtitles.append(subtitle)
+        return subtitles
+
+
+Service = TheSubDB

subliminal/services/tvsubtitles.py

@@ -0,0 +1,142 @@
+# -*- coding: utf-8 -*-
+# Copyright 2012 Nicolas Wack <wackou@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from . import ServiceBase
+from ..cache import cachedmethod
+from ..language import language_set, Language
+from ..subtitles import get_subtitle_path, ResultSubtitle
+from ..utils import get_keywords
+from ..videos import Episode
+from bs4 import BeautifulSoup
+import logging
+import re
+
+
+logger = logging.getLogger(__name__)
+
+
+def match(pattern, string):
+    try:
+        return re.search(pattern, string).group(1)
+    except AttributeError:
+        logger.debug(u'Could not match %r on %r' % (pattern, string))
+        return None
+
+
+class TvSubtitles(ServiceBase):
+    server_url = 'http://www.tvsubtitles.net'
+    api_based = False
+    languages = language_set(['ar', 'bg', 'cs', 'da', 'de', 'el', 'en', 'es', 'fi', 'fr', 'hu',
+                              'it', 'ja', 'ko', 'nl', 'pl', 'pt', 'ro', 'ru', 'sv', 'tr', 'uk',
+                              'zh', 'pt-br'])
+    #TODO: Find more exceptions
+    language_map = {'gr': Language('gre'), 'cz': Language('cze'), 'ua': Language('ukr'),
+                    'cn': Language('chi')}
+    videos = [Episode]
+    require_video = False
+    required_features = ['permissive']
+
+    @cachedmethod
+    def get_likely_series_id(self, name):
+        r = self.session.post('%s/search.php' % self.server_url, data={'q': name})
+        soup = BeautifulSoup(r.content, self.required_features)
+        maindiv = soup.find('div', 'left')
+        results = []
+        for elem in maindiv.find_all('li'):
+            sid = int(match('tvshow-([0-9]+)\.html', elem.a['href']))
+            show_name = match('(.*) \(', elem.a.text)
+            results.append((show_name, sid))
+        #TODO: pick up the best one in a smart way
+        result = results[0]
+        return result[1]
+
+    @cachedmethod
+    def get_episode_id(self, series_id, season, number):
+        """Get the TvSubtitles id for the given episode. Raises KeyError if none
+        could be found."""
+        # download the page of the season, contains ids for all episodes
+        episode_id = None
+        r = self.session.get('%s/tvshow-%d-%d.html' % (self.server_url, series_id, season))
+        soup = BeautifulSoup(r.content, self.required_features)
+        table = soup.find('table', id='table5')
+        for row in table.find_all('tr'):
+            cells = row.find_all('td')
+            if not cells:
+                continue
+            episode_number = match('x([0-9]+)', cells[0].text)
+            if not episode_number:
+                continue
+            episode_number = int(episode_number)
+            episode_id = int(match('episode-([0-9]+)', cells[1].a['href']))
+            # we could just return the id of the queried episode, but as we
+            # already downloaded the whole page we might as well fill in the
+            # information for all the episodes of the season
+            self.cache_for(self.get_episode_id, args=(series_id, season, episode_number), result=episode_id)
+        # raises KeyError if not found
+        return self.cached_value(self.get_episode_id, args=(series_id, season, number))
+
+    # Do not cache this method in order to always check for the most recent
+    # subtitles
+    def get_sub_ids(self, episode_id):
+        subids = []
+        r = self.session.get('%s/episode-%d.html' % (self.server_url, episode_id))
+        epsoup = BeautifulSoup(r.content, self.required_features)
+        for subdiv in epsoup.find_all('a'):
+            if 'href' not in subdiv.attrs or not subdiv['href'].startswith('/subtitle'):
+                continue
+            subid = int(match('([0-9]+)', subdiv['href']))
+            lang = self.get_language(match('flags/(.*).gif', subdiv.img['src']))
+            result = {'subid': subid, 'language': lang}
+            for p in subdiv.find_all('p'):
+                if 'alt' in p.attrs and p['alt'] == 'rip':
+                    result['rip'] = p.text.strip()
+                if 'alt' in p.attrs and p['alt'] == 'release':
+                    result['release'] = p.text.strip()
+            subids.append(result)
+        return subids
+
+    def list_checked(self, video, languages):
+        return self.query(video.path or video.release, languages, get_keywords(video.guess), video.series, video.season, video.episode)
+
+    def query(self, filepath, languages, keywords, series, season, episode):
+        logger.debug(u'Getting subtitles for %s season %d episode %d with languages %r' % (series, season, episode, languages))
+        self.init_cache()
+        sid = self.get_likely_series_id(series.lower())
+        try:
+            ep_id = self.get_episode_id(sid, season, episode)
+        except KeyError:
+            logger.debug(u'Could not find episode id for %s season %d episode %d' % (series, season, episode))
+            return []
+        subids = self.get_sub_ids(ep_id)
+        # filter the subtitles with our queried languages
+        subtitles = []
+        for subid in subids:
+            language = subid['language']
+            if language not in languages:
+                continue
+            path = get_subtitle_path(filepath, language, self.config.multi)
+            subtitle = ResultSubtitle(path, language, self.__class__.__name__.lower(), '%s/download-%d.html' % (self.server_url, subid['subid']),
+                                      keywords=[subid['rip'], subid['release']])
+            subtitles.append(subtitle)
+        return subtitles
+
+    def download(self, subtitle):
+        self.download_zip_file(subtitle.link, subtitle.path)
+        return subtitle
+
+
+Service = TvSubtitles

subliminal/subliminal.py

@@ -1,427 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from itertools import groupby
-import ConfigParser
-import PluginWorker
-import Queue
-import locale
-import logging
-import mimetypes
-import os
-import plugins
-import sys
-import traceback
-import locale
-import encodingKludge as ek
-
-
-SUPPORTED_FORMATS = 'video/x-msvideo', 'video/quicktime', 'video/x-matroska', 'video/mp4'
-logger = logging.getLogger('subliminal')
-SYS_ENCODING = None
-try:
-    locale.setlocale(locale.LC_ALL, "")
-    SYS_ENCODING = locale.getpreferredencoding()
-except (locale.Error, IOError):
-    pass
-# for OSes that are poorly configured I'll just force UTF-8
-if not SYS_ENCODING or SYS_ENCODING in ('ANSI_X3.4-1968', 'US-ASCII', 'ASCII'):
-    SYS_ENCODING = 'UTF-8'
-
-
-class Subliminal(object):
-    """Main Subliminal class"""
-
-    def __init__(self, config=True, cache_dir=True, workers=4, multi=False, force=False, max_depth=3, autostart=False, plugins_config=None, files_mode=-1):
-        # set default values
-        self.multi = multi
-        self.force = force
-        self.max_depth = max_depth
-        self.config = None
-        self.config_file = None
-        self.cache_dir = None
-        self.taskQueue = Queue.Queue()
-        self.resultQueue = Queue.Queue()
-        self._languages = None
-        self._plugins = self.listAPIPlugins()
-        self.workers = workers
-        self.plugins_config = plugins_config
-        self.files_mode = files_mode
-        if autostart:
-            self.startWorkers()
-        # handle configuration file preferences
-        try:
-            if config == True:  # default configuration file
-                import xdg.BaseDirectory as bd
-                self.config = ConfigParser.SafeConfigParser({"languages": "", "plugins": ""})
-                self.config_file = ek.ek(os.path.join, bd.xdg_config_home, "subliminal", "config.ini")
-                if not ek.ek(os.path.exists, self.config_file):  # configuration file doesn't exist, create it
-                    self._createConfigFile()
-                else:  # configuration file exists, load it
-                    self._loadConfigFile()
-            elif config:  # custom configuration file
-                self.config = ConfigParser.SafeConfigParser({"languages": "", "plugins": ""})
-                self.config_file = config
-                if not ek.ek(os.path.isfile, self.config_file):  # custom configuration file doesn't exist, create it
-                    self._createConfigFile()
-                else:
-                    self._loadConfigFile()
-        except:
-            self.config = None
-            self.config_file = None
-            logger.error(u"Failed to use the configuration file, continue without it")
-            raise
-        # handle cache directory preferences
-        try:
-            if cache_dir == True:  # default cache directory
-                import xdg.BaseDirectory as bd
-                self.cache_dir = ek.ek(os.path.join, bd.xdg_config_home, "subliminal", "cache")
-                if not ek.ek(os.path.exists, self.cache_dir):  # cache directory doesn't exist, create it
-                    ek.ek(os.mkdir, self.cache_dir)
-                    logger.debug(u'Creating cache directory: %s' % self.cache_dir)
-            elif cache_dir:  # custom configuration file
-                self.cache_dir = cache_dir
-                if not ek.ek(os.path.isdir, self.cache_dir):  # custom v file doesn't exist, create it
-                    ek.ek(os.mkdir, self.cache_dir)
-                    logger.debug(u'Creating cache directory: %s' % self.cache_dir)
-        except:
-            self.cache_dir = None
-            logger.error(u"Failed to use the cache directory, continue without it")
-
-    def _loadConfigFile(self):
-        """Load a configuration file specified in self.config_file"""
-        self.config.read(self.config_file)
-        self._loadLanguagesFromConfig()
-        self._loadPluginsFromConfig()
-
-    def _createConfigFile(self):
-        """Create a configuration file specified in self.config_file"""
-        folder = ek.ek(os.path.dirname, self.config_file)
-        if not ek.ek(os.path.exists, folder):
-            logger.info(u"Creating folder: %s" % folder)
-            ek.ek(os.mkdir, folder)
-        # try to load a language from system
-        self._loadLanguageFromSystem()
-        self.config.set("DEFAULT", "languages", ",".join(self._languages))
-        self.config.set("DEFAULT", "plugins", ",".join(self._plugins))
-        self.config.add_section("SubtitleSource")
-        self.config.set("SubtitleSource", "key", "")
-        self._writeConfigFile()
-        logger.info(u"Creating configuration file: %s" % self.config_file)
-        logger.debug(u"Languages in created configuration file: %s" % self._languages)
-        logger.debug(u"Plugins in created configuration file: %s" % self._plugins)
-
-    @staticmethod
-    def listExistingPlugins():
-        """List all possible plugins"""
-        return map(lambda x: x.__name__, plugins.PluginBase.PluginBase.__subclasses__())
-
-    @staticmethod
-    def listAPIPlugins():
-        """List plugins that use API"""
-        return filter(Subliminal.isAPIBasedPlugin, Subliminal.listExistingPlugins())
-
-    def _writeConfigFile(self):
-        """Write the configuration file"""
-        configfile = open(self.config_file, "w")
-        self.config.write(configfile)
-        configfile.close()
-
-    def get_languages(self):
-        """Get current languages"""
-        return self._languages
-
-    def set_languages(self, value):
-        """Set languages and save to configuration file if specified by the constructor"""
-        logger.debug(u"Setting languages to %s" % value)
-        self._languages = value
-        if self.config:
-            self._saveLanguagesToConfig()
-
-    @staticmethod
-    def isValidLanguage(language):
-        """Check if a language is valid"""
-        if len(language) != 2:
-            logger.error(u"Language %s is not valid" % language)
-            return False
-        return True
-
-    def _saveLanguagesToConfig(self):
-        """Save languages to configuration file"""
-        logger.debug(u"Saving languages %s to configuration file" % self._languages)
-        self.config.set("DEFAULT", "languages", ",".join(self._languages))
-        self._writeConfigFile()
-
-    def _loadLanguagesFromConfig(self):
-        """Load languages from configuration file"""
-        configLanguages = self.config.get("DEFAULT", "languages")
-        logger.debug(u"Loading languages %s from configuration file" % configLanguages)
-        if not configLanguages:
-            self._languages = None
-            return
-        self._languages = filter(self.isValidLanguage, map(str.strip, configLanguages.split(",")))
-
-    def _loadLanguageFromSystem(self):
-        """Load language from system"""
-        logger.debug(u"Loading language from system")
-        try:
-            self._languages = [locale.getdefaultlocale()[0][:2]]
-            logger.debug(u"Language %s loaded from system" % self._languages)
-        except:
-            logger.warning(u"Could not read language from system")
-
-    def get_plugins(self):
-        """Get current plugins"""
-        return self._plugins
-
-    def set_plugins(self, value):
-        """Set plugins and save to configuration file if specified by the constructor"""
-        logger.debug(u'Setting plugins to %r' % value)
-        self._plugins = filter(self.isValidPlugin, value)
-        if self.config:
-            self._savePluginsToConfig()
-
-    @staticmethod
-    def isValidPlugin(pluginName):
-        """Check if a plugin is valid (exists)"""
-        if pluginName not in Subliminal.listExistingPlugins():
-            logger.error(u"Plugin %s does not exist" % pluginName)
-            return False
-        return True
-
-    @staticmethod
-    def isAPIBasedPlugin(pluginName):
-        """Check if a plugin is API-based"""
-        if not getattr(plugins, pluginName).api_based:
-            return False
-        return True
-
-    def _savePluginsToConfig(self):
-        """Save plugins to configuration file"""
-        logger.debug(u"Saving plugins %s to configuration file" % self._plugins)
-        self.config.set("DEFAULT", "plugins", ",".join(self._plugins))
-        self._writeConfigFile()
-
-    def _loadPluginsFromConfig(self):
-        """Load plugins from configuration file"""
-        configPlugins = self.config.get("DEFAULT", "plugins")
-        logger.debug(u"Loading plugins %s from configuration file" % configPlugins)
-        self._plugins = filter(self.isValidPlugin, map(str.strip, configPlugins.split(",")))
-
-    # getters/setters for the property _languages and _plugins
-    languages = property(get_languages, set_languages)
-    plugins = property(get_plugins, set_plugins)
-
-    def deactivatePlugin(self, plugin):
-        """Deactivate a plugin"""
-        self._plugins.remove(plugin)
-        if self.config:
-            self._savePluginsToConfig()
-
-    def activatePlugin(self, plugin):
-        """Activate a plugin"""
-        if self.isValidPlugin(plugin):
-            self._plugins.append(plugin)
-        if self.config:
-            self._savePluginsToConfig()
-
-    def listSubtitles(self, entries):
-        """
-        Searches subtitles within the active plugins and returns all found matching subtitles.
-        entries can be:
-            - filepaths
-            - folderpaths (N.B. internal recursive search function will be used)
-            - filenames
-        """
-        search_results = []
-        if isinstance(entries, basestring):
-            entries = [ek.fixStupidEncodings(entries)]
-        elif not isinstance(entries, list):
-            raise TypeError('Entries should be a list or a string')
-        for e in entries:
-            search_results.extend(self._recursiveSearch(e))
-        taskCount = 0
-        for (l, f) in search_results:
-            taskCount += self.searchSubtitlesThreaded(f, l)
-        subtitles = []
-        for i in range(taskCount):
-            subtitles.extend(self.resultQueue.get(timeout=10))
-        return subtitles
-
-    @staticmethod
-    def arrangeSubtitles(subtitles):
-        """Arrange subtitles in a handy dict by filename, language and plugin"""
-        arrangedSubtitles = {}
-        for (filename, subsByFilename) in groupby(sorted(subtitles, key=lambda x: x["filename"]), lambda x: x["filename"]):
-            arrangedSubtitles[filename] = {}
-            for (language, subsByFilenameByLanguage) in groupby(sorted(subsByFilename, key=lambda x: x["lang"]), lambda x: x["lang"]):
-                arrangedSubtitles[filename][language] = {}
-                for (plugin, subsByFilenameByLanguageByPlugin) in groupby(sorted(subsByFilenameByLanguage, key=lambda x: x["plugin"]), lambda x: x["plugin"]):
-                    arrangedSubtitles[filename][language][plugin] = sorted(list(subsByFilenameByLanguageByPlugin))
-        return arrangedSubtitles
-
-    def sortSubtitlesRaw(self, subtitles):
-        """Sort subtitles using user defined languages and plugins"""
-        return sorted(subtitles, cmp=self._cmpSubtitles)
-
-    def _cmpSubtitles(self, x, y):
-        """
-        Compares 2 subtitles elements x and y. Returns -1 if x < y, 0 if =, 1 if >
-        Use filename, languages and plugin comparison
-        """
-        filenames = sorted([x['filename'], y['filename']])
-        if x['filename'] != y['filename'] and filenames.index(x['filename']) < filenames(y['filename']):
-            return - 1
-        if x['filename'] != y['filename'] and filenames.index(x['filename']) > filenames(y['filename']):
-            return 1
-        if self._languages and self._languages.index(x['lang']) < self._languages.index(y['lang']):
-            return - 1
-        if self._languages and self._languages.index(x['lang']) > self._languages.index(y['lang']):
-            return 1
-        if self._plugins.index(x['plugin']) < self._plugins.index(y['plugin']):
-            return - 1
-        if self._plugins.index(x['plugin']) > self._plugins.index(y['plugin']):
-            return 1
-        return 0
-
-    def searchSubtitlesThreaded(self, filenames, languages):
-        """
-        Makes workers search for subtitles in different languages for multiple filenames and puts the result in the result queue.
-        Aslo split the work in multiple tasks
-        When the function returns, all the results may not be available yet!
-        """
-        logger.info(u"Searching subtitles for %s with languages %s" % (filenames, languages))
-        tasks = []
-        for pluginName in self._plugins:
-            try:
-                plugin = getattr(plugins, pluginName)(self.getConfigDict())
-            except:
-                logger.debug(traceback.print_exc())
-                continue
-            # split tasks if the plugin can't handle multi-thing queries
-            tasks.extend(plugin.splitTask({'task': 'list', 'plugin': pluginName, 'languages': languages, 'filenames': filenames, 'config': self.getConfigDict()}))
-        for t in tasks:
-            self.taskQueue.put(t)
-        return len(tasks)
-
-    def downloadSubtitlesThreaded(self, subtitles):
-        """
-        Makes workers download subtitles and puts the result in the result queue.
-        When the function returns, all the results may not be available yet!
-        """
-        # 1 task per file if not multi, 1 task per file and per language if multi
-        taskCount = 0
-        for (filename, subsByFilename) in groupby(sorted(subtitles, key=lambda x: x["filename"]), lambda x: x["filename"]):
-            if not self.multi:
-                self.taskQueue.put({'task': 'download', 'subtitle': sorted(list(subsByFilename), cmp=self._cmpSubtitles), 'config': self.getConfigDict()})
-                taskCount += 1
-                continue
-            for (language, subsByFilenameByLanguage) in groupby(sorted(subsByFilename, key=lambda x: x["lang"]), lambda x: x["lang"]):
-                self.taskQueue.put({'task': 'download', 'subtitle': sorted(list(subsByFilenameByLanguage), cmp=self._cmpSubtitles), 'config': self.getConfigDict()})
-                taskCount += 1
-        return taskCount
-
-    def downloadSubtitles(self, entries):
-        """Download subtitles recursivly in entries"""
-        subtitles = self.listSubtitles(entries)
-        taskCount = self.downloadSubtitlesThreaded(subtitles)
-        paths = []
-        for i in range(taskCount):
-            paths.append(self.resultQueue.get(timeout=10))
-        return paths
-
-    def _recursiveSearch(self, entry, depth=0):
-        """
-        Searches files in the entry
-        This will output a list of tuples (filename, languages)
-        """
-        if depth > self.max_depth and self.max_depth != 0:  # we do not want to search the whole file system except if max_depth = 0
-            return []
-        if ek.ek(os.path.isfile, entry):  # a file? scan it
-            if depth != 0:  # only check for valid format if recursing, trust the user
-                mimetypes.add_type("video/x-matroska", ".mkv")
-                mimetype = mimetypes.guess_type(entry)[0]
-                if mimetype not in SUPPORTED_FORMATS:
-                    return []
-            basepath = ek.fixStupidEncodings(ek.ek(os.path.splitext, entry)[0])
-            # check for .xx.srt if needed
-            if self.multi and self.languages:
-                if self.force:
-                    return [(self.languages, [ek.ek(os.path.normpath, entry)])]
-                needed_languages = self.languages[:]
-                for l in self.languages:
-                    if ek.ek(os.path.exists, basepath + '.%s.srt' % l):
-                        logger.info(u"Skipping language %s for file %s as it already exists. Use the --force option to force the download" % (l, entry))
-                        needed_languages.remove(l)
-                if needed_languages:
-                    return [(needed_languages, [ek.ek(os.path.normpath, entry)])]
-                return []
-            # single subtitle download: .srt
-            if self.force or not ek.ek(os.path.exists, basepath + '.srt'):
-                return [(self.languages, [ek.ek(os.path.normpath, entry)])]
-        if ek.ek(os.path.isdir, entry):  # a dir? recurse
-            #TODO if hidden folder, don't keep going (how to handle windows/mac/linux ?)
-            files = []
-            for e in ek.ek(os.listdir, entry):
-                files.extend(self._recursiveSearch(ek.ek(os.path.join, entry, e), depth + 1))
-            files.sort()
-            grouped_files = []
-            for languages, group in groupby(files, lambda t: t[0]):
-                filenames = []
-                for t in group:
-                    filenames.extend(t[1])
-                grouped_files.append((languages, filenames))
-            return grouped_files
-        return []  # anything else, nothing.
-
-    def startWorkers(self):
-        """Create a pool of workers and start them"""
-        self.pool = []
-        for i in range(self.workers):
-            worker = PluginWorker.PluginWorker(self.taskQueue, self.resultQueue)
-            worker.start()
-            self.pool.append(worker)
-            logger.debug(u"Worker %s added to the pool" % worker.name)
-
-    def sendStopSignal(self):
-        """Send a stop signal the pool of workers (poison pill)"""
-        logger.debug(u"Sending %d poison pills into the task queue" % self.workers)
-        for i in range(self.workers):
-            self.taskQueue.put(None)
-
-    def stopWorkers(self):
-        """Stop workers using a stop signal and wait for them to terminate properly"""
-        self.sendStopSignal()
-        for worker in self.pool:
-            worker.join()
-
-    def getConfigDict(self):
-        """Produce a dict with configuration items. Used by plugins to read configuration"""
-        config = {}
-        config['multi'] = self.multi
-        config['cache_dir'] = self.cache_dir
-        if self.config:
-            config['subtitlesource_key'] = self.config.get('SubtitleSource', 'key')
-        if self.plugins_config and 'subtitlesource_key' in self.plugins_config:
-            config['subtitlesource_key'] = self.plugins_config['subtitlesource_key']
-        config['force'] = self.force
-        config['files_mode'] = self.files_mode
-        return config

subliminal/subtitles.py

@@ -0,0 +1,149 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from .language import Language
+from .utils import to_unicode
+import os.path
+
+
+__all__ = ['Subtitle', 'EmbeddedSubtitle', 'ExternalSubtitle', 'ResultSubtitle', 'get_subtitle_path']
+
+#: Subtitles extensions
+EXTENSIONS = ['.srt', '.sub', '.txt', '.ass']
+
+
+class Subtitle(object):
+    """Base class for subtitles
+
+    :param string path: path to the subtitle
+    :param language: language of the subtitle
+    :type language: :class:`~subliminal.language.Language`
+
+    """
+    def __init__(self, path, language):
+        if not isinstance(language, Language):
+            raise TypeError('%r is not an instance of Language')
+        self.path = path
+        self.language = language
+
+    @property
+    def exists(self):
+        """Whether the subtitle exists or not"""
+        if self.path:
+            return os.path.exists(self.path)
+        return False
+
+    def __unicode__(self):
+        return to_unicode(self.path)
+
+    def __str__(self):
+        return unicode(self).encode('utf-8')
+
+    def __repr__(self):
+        return '%s(%s, %s)' % (self.__class__.__name__, self, self.language)
+
+
+class EmbeddedSubtitle(Subtitle):
+    """Subtitle embedded in a container
+
+    :param string path: path to the subtitle
+    :param language: language of the subtitle
+    :type language: :class:`~subliminal.language.Language`
+    :param int track_id: id of the subtitle track in the container
+
+    """
+    def __init__(self, path, language, track_id):
+        super(EmbeddedSubtitle, self).__init__(path, language)
+        self.track_id = track_id
+
+    @classmethod
+    def from_enzyme(cls, path, subtitle):
+        language = Language(subtitle.language, strict=False)
+        return cls(path, language, subtitle.trackno)
+
+
+class ExternalSubtitle(Subtitle):
+    """Subtitle in a file next to the video file"""
+    @classmethod
+    def from_path(cls, path):
+        """Create an :class:`ExternalSubtitle` from path"""
+        extension = None
+        for e in EXTENSIONS:
+            if path.endswith(e):
+                extension = e
+                break
+        if extension is None:
+            raise ValueError('Not a supported subtitle extension')
+        language = Language(os.path.splitext(path[:len(path) - len(extension)])[1][1:], strict=False)
+        return cls(path, language)
+
+
+class ResultSubtitle(ExternalSubtitle):
+    """Subtitle found using :mod:`~subliminal.services`
+
+    :param string path: path to the subtitle
+    :param language: language of the subtitle
+    :type language: :class:`~subliminal.language.Language`
+    :param string service: name of the service
+    :param string link: download link for the subtitle
+    :param string release: release name of the video
+    :param float confidence: confidence that the subtitle matches the video according to the service
+    :param set keywords: keywords that describe the subtitle
+
+    """
+    def __init__(self, path, language, service, link, release=None, confidence=1, keywords=None):
+        super(ResultSubtitle, self).__init__(path, language)
+        self.service = service
+        self.link = link
+        self.release = release
+        self.confidence = confidence
+        self.keywords = keywords or set()
+
+    @property
+    def single(self):
+        """Whether this is a single subtitle or not. A single subtitle does not have
+        a language indicator in its file name
+
+        :rtype: bool
+
+        """
+        return self.language == Language('Undetermined')
+
+    def __repr__(self):
+        if not self.release:
+            return 'ResultSubtitle(%s, %s, %s, %.2f)' % (self.path, self.language, self.service, self.confidence)
+        return 'ResultSubtitle(%s, %s, %s, %.2f, release=%s)' % (self.path, self.language, self.service, self.confidence, self.release.encode('ascii', 'ignore'))
+
+
+def get_subtitle_path(video_path, language, multi):
+    """Create the subtitle path from the given video path using language if multi
+
+    :param string video_path: path to the video
+    :param language: language of the subtitle
+    :type language: :class:`~subliminal.language.Language`
+    :param bool multi: whether to use multi language naming or not
+    :return: path of the subtitle
+    :rtype: string
+
+    """
+    if not os.path.exists(video_path):
+        path = os.path.splitext(os.path.basename(video_path))[0]
+    else:
+        path = os.path.splitext(video_path)[0]
+    if multi and language:
+        return path + '.%s%s' % (language.alpha2, EXTENSIONS[0])
+    return path + '%s' % EXTENSIONS[0]

subliminal/tasks.py

@@ -0,0 +1,68 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+__all__ = ['Task', 'ListTask', 'DownloadTask', 'StopTask']
+
+
+class Task(object):
+    """Base class for tasks to use in subliminal"""
+    pass
+
+
+class ListTask(Task):
+    """List task used by the worker to search for subtitles
+
+    :param video: video to search subtitles for
+    :type video: :class:`~subliminal.videos.Video`
+    :param list languages: languages to search for
+    :param string service: name of the service to use
+    :param config: configuration for the service
+    :type config: :class:`~subliminal.services.ServiceConfig`
+
+    """
+    def __init__(self, video, languages, service, config):
+        super(ListTask, self).__init__()
+        self.video = video
+        self.service = service
+        self.languages = languages
+        self.config = config
+
+    def __repr__(self):
+        return 'ListTask(%r, %r, %s, %r)' % (self.video, self.languages, self.service, self.config)
+
+
+class DownloadTask(Task):
+    """Download task used by the worker to download subtitles
+
+    :param video: video to download subtitles for
+    :type video: :class:`~subliminal.videos.Video`
+    :param subtitles: subtitles to download in order of preference
+    :type subtitles: list of :class:`~subliminal.subtitles.Subtitle`
+
+    """
+    def __init__(self, video, subtitles):
+        super(DownloadTask, self).__init__()
+        self.video = video
+        self.subtitles = subtitles
+
+    def __repr__(self):
+        return 'DownloadTask(%r, %r)' % (self.video, self.subtitles)
+
+
+class StopTask(Task):
+    """Stop task that will stop the worker"""
+    pass

subliminal/test/plugins_unittests.py

@@ -1,206 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import unittest
-import logging
-import os
-
-
-logging.basicConfig(level=logging.DEBUG, format='%(name)-24s %(levelname)-8s %(message)s')
-if not os.path.exists('/tmp/subliminal/cache'):
-    os.mkdir('/tmp/subliminal/cache')
-config = {'multi': True, 'cache_dir': '/tmp/subliminal/cache', 'subtitlesource_key': '', 'force': False}
-
-
-class Addic7edListTestCase1(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import Addic7ed
-        plugin = Addic7ed(config)
-        results = plugin.list(["The.Big.Bang.Theory.S03E13.HDTV.XviD-2HD.mkv"], ["en", "fr"])
-        print results
-        assert len(results) > 0
-
-
-class Addic7edListTestCase2(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import Addic7ed
-        plugin = Addic7ed(config)
-        results = plugin.list(["Dexter.S05E02.720p.HDTV.x264-IMMERSE.mkv"], ["en", "fr"])
-        print results
-        assert len(results) > 0
-
-
-class Addic7edDownloadTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import Addic7ed
-        plugin = Addic7ed(config)
-        results = plugin.download(plugin.list(["/tmp/The.Big.Bang.Theory.S03E13.HDTV.XviD-2HD.mkv"], ["en", "fr"])[0])
-        print results
-        assert len(results) > 0
-
-
-class BierDopjeListTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import BierDopje
-        plugin = BierDopje(config)
-        results = plugin.list(["The.Big.Bang.Theory.S03E13.HDTV.XviD-2HD.mkv"], ["en", "fr"])
-        print results
-        assert len(results) > 0
-
-
-class BierDopjeListExceptionTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import BierDopje
-        plugin = BierDopje(config)
-        results = plugin.list(["The.Office.US.S07E08.Viewing.Party.HDTV.XviD-FQM.[VTV].avi"], ["en", "fr"])
-        print results
-        assert len(results) > 0
-
-
-class BierDopjeListTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import BierDopje
-        plugin = BierDopje(config)
-        results = plugin.list(["The.Big.Bang.Theory.S03E13.HDTV.XviD-2HD.mkv"], ["en", "fr"])
-        print results
-        assert len(results) > 0
-
-
-class OpenSubtitlesQueryTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import OpenSubtitles
-        plugin = OpenSubtitles()
-        results = plugin.query('Night.Watch.2004.CD1.DVDRiP.XViD-FiCO.avi', moviehash="09a2c497663259cb", bytesize="733589504")  # http://trac.opensubtitles.org/projects/opensubtitles/wiki/XMLRPC
-        print results
-        assert len(results) > 0
-
-
-class OpenSubtitlesQueryNoHashTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import OpenSubtitles
-        plugin = OpenSubtitles()
-        results = plugin.query('Night.Watch.2004.CD1.DVDRiP.XViD-FiCO.avi', languages=['en', 'fr'])  # http://trac.opensubtitles.org/projects/opensubtitles/wiki/XMLRPC
-        print results
-        assert len(results) > 0
-
-
-class OpenSubtitlesListTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import OpenSubtitles
-        plugin = OpenSubtitles()
-        results = plugin.download(plugin.query('/tmp/Night.Watch.2004.CD1.DVDRiP.XViD-FiCO.avi', moviehash="09a2c497663259cb", bytesize="733589504")[0])  # http://trac.opensubtitles.org/projects/opensubtitles/wiki/XMLRPC
-        assert len(results) > 0
-
-
-class SubtitulosListTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import Subtitulos
-        plugin = Subtitulos()
-        results = plugin.list(["The.Big.Bang.Theory.S03E13.HDTV.XviD-2HD.mkv"], ['en', 'fr'])
-        print results
-        assert len(results) > 0
-
-
-class SubtitulosDownloadTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import Subtitulos
-        plugin = Subtitulos()
-        results = plugin.download(plugin.list(["/tmp/The.Big.Bang.Theory.S03E13.HDTV.XviD-2HD.mkv"], ['en', 'fr'])[0])
-        print results
-        assert len(results) > 0
-
-
-class TheSubDBQueryTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import TheSubDB
-        plugin = TheSubDB()
-        results = plugin.query("test.mkv", "edc1981d6459c6111fe36205b4aff6c2")
-        print results
-        assert len(results) > 0
-
-
-class TheSubDBDownloadTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import TheSubDB
-        plugin = TheSubDB()
-        results = plugin.download(plugin.query("/tmp/test.mkv", "edc1981d6459c6111fe36205b4aff6c2")[0])
-        print results
-        assert len(results) > 0
-
-
-class SubsWikiListTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import SubsWiki
-        plugin = SubsWiki()
-        results = plugin.list(["The.Big.Bang.Theory.S03E13.HDTV.XviD-2HD.mkv"], ['en', 'es'])
-        print results
-        assert len(results) > 0
-
-
-class SubsWikiDownloadTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import SubsWiki
-        plugin = SubsWiki()
-        results = plugin.download(plugin.list(["/tmp/The.Big.Bang.Theory.S03E13.HDTV.XviD-2HD.mkv"], ['en', 'es'])[0])
-        print results
-        assert len(results) > 0
-'''
-class PodnapisiQueryTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import Podnapisi
-        plugin = Podnapisi()
-        results = plugin.query('09a2c497663259cb', ["en", "fr"])
-        print results
-        assert len(results) > 5
-
-
-class SubSceneListTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import SubScene
-        plugin = SubScene()
-        results = plugin.list(["Dexter.S04E01.HDTV.XviD-NoTV.avi"], ['en', 'fr'])
-        print results
-        assert len(results) > 0, "No result could be found for Dexter.S04E01.HDTV.XviD-NoTV.avi and no languages"
-
-
-class SubSceneDownloadTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import SubScene
-        plugin = SubScene()
-        results = plugin.download(plugin.list(["Dexter.S04E01.HDTV.XviD-NoTV.avi"], ['en', 'fr'])[0])
-        print results
-        assert len(results) > 0, "No result could be found for Dexter.S04E01.HDTV.XviD-NoTV.avi and no languages"
-
-
-class SubtitleSourceListTestCase(unittest.TestCase):
-    def runTest(self):
-        from subliminal.plugins import SubtitleSource
-        plugin = SubtitleSource()
-        results = plugin.list(["PrisM-Inception.2010"], ['en', 'fr'])
-        print results
-        assert len(results) > 0, "No result could be found for PrisM-Inception.2010"
-'''
-
-
-if __name__ == "__main__":
-    unittest.main()

subliminal/utils.py

@@ -0,0 +1,69 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+import re
+
+
+__all__ = ['get_keywords', 'split_keyword', 'to_unicode']
+
+
+def get_keywords(guess):
+    """Retrieve keywords from guessed informations
+
+    :param guess: guessed informations
+    :type guess: :class:`guessit.guess.Guess`
+    :return: lower case alphanumeric keywords
+    :rtype: set
+
+    """
+    keywords = set()
+    for k in ['releaseGroup', 'screenSize', 'videoCodec', 'format']:
+        if k in guess:
+            keywords = keywords | split_keyword(guess[k].lower())
+    return keywords
+
+
+def split_keyword(keyword):
+    """Split a keyword in multiple ones on any non-alphanumeric character
+
+    :param string keyword: keyword
+    :return: keywords
+    :rtype: set
+
+    """
+    split = set(re.findall(r'\w+', keyword))
+    return split
+
+
+def to_unicode(data):
+    """Convert a basestring to unicode
+
+    :param basestring data: data to decode
+    :return: data as unicode
+    :rtype: unicode
+
+    """
+    if not isinstance(data, basestring):
+        raise ValueError('Basestring expected')
+    if isinstance(data, unicode):
+        return data
+    for encoding in ('utf-8', 'latin-1'):
+        try:
+            return unicode(data, encoding)
+        except UnicodeDecodeError:
+            pass
+    return unicode(data, 'utf-8', 'replace')

subliminal/version.py

@@ -1,22 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-__version__ = '0.3'

subliminal/videos.py

@@ -0,0 +1,286 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from . import subtitles
+from .language import Language
+from .utils import to_unicode
+import enzyme.core
+import guessit
+import hashlib
+import logging
+import mimetypes
+import os
+import struct
+
+
+__all__ = ['EXTENSIONS', 'MIMETYPES', 'Video', 'Episode', 'Movie', 'UnknownVideo',
+           'scan', 'hash_opensubtitles', 'hash_thesubdb']
+logger = logging.getLogger(__name__)
+
+#: Video extensions
+EXTENSIONS = ['.avi', '.mkv', '.mpg', '.mp4', '.m4v', '.mov', '.ogm', '.ogv', '.wmv',
+              '.divx', '.asf']
+
+#: Video mimetypes
+MIMETYPES = ['video/mpeg', 'video/mp4', 'video/quicktime', 'video/x-ms-wmv', 'video/x-msvideo',
+             'video/x-flv', 'video/x-matroska', 'video/x-matroska-3d']
+
+
+class Video(object):
+    """Base class for videos
+
+    :param string path: path
+    :param guess: guessed informations
+    :type guess: :class:`~guessit.guess.Guess`
+    :param string imdbid: imdbid
+
+    """
+    def __init__(self, path, guess, imdbid=None):
+        self.release = path
+        self.guess = guess
+        self.imdbid = imdbid
+        self._path = None
+        self.hashes = {}
+        if os.path.exists(path):
+            self._path = path
+            self.size = os.path.getsize(self._path)
+            self._compute_hashes()
+
+    @classmethod
+    def from_path(cls, path):
+        """Create a :class:`Video` subclass guessing all informations from the given path
+
+        :param string path: path
+        :return: video object
+        :rtype: :class:`Episode` or :class:`Movie` or :class:`UnknownVideo`
+
+        """
+        guess = guessit.guess_file_info(path, 'autodetect')
+        result = None
+        if guess['type'] == 'episode' and 'series' in guess and 'season' in guess and 'episodeNumber' in guess:
+            title = None
+            if 'title' in guess:
+                title = guess['title']
+            result = Episode(path, guess['series'], guess['season'], guess['episodeNumber'], title, guess)
+        if guess['type'] == 'movie' and 'title' in guess:
+            year = None
+            if 'year' in guess:
+                year = guess['year']
+            result = Movie(path, guess['title'], year, guess)
+        if not result:
+            result = UnknownVideo(path, guess)
+        if not isinstance(result, cls):
+            raise ValueError('Video is not of requested type')
+        return result
+
+    @property
+    def exists(self):
+        """Whether the video exists or not"""
+        if self._path:
+            return os.path.exists(self._path)
+        return False
+
+    @property
+    def path(self):
+        """Path to the video"""
+        return self._path
+
+    @path.setter
+    def path(self, value):
+        if not os.path.exists(value):
+            raise ValueError('Path does not exists')
+        self._path = value
+        self.size = os.path.getsize(self._path)
+        self._compute_hashes()
+
+    def _compute_hashes(self):
+        """Compute different hashes"""
+        self.hashes['OpenSubtitles'] = hash_opensubtitles(self.path)
+        self.hashes['TheSubDB'] = hash_thesubdb(self.path)
+
+    def scan(self):
+        """Scan and return associated subtitles
+
+        :return: associated subtitles
+        :rtype: list of :class:`~subliminal.subtitles.Subtitle`
+
+        """
+        if not self.exists:
+            return []
+        basepath = os.path.splitext(self.path)[0]
+        results = []
+        video_infos = None
+        try:
+            video_infos = enzyme.parse(self.path)
+            logger.debug(u'Succeeded parsing %s with enzyme: %r' % (self.path, video_infos))
+        except:
+            logger.debug(u'Failed parsing %s with enzyme' % self.path)
+        if isinstance(video_infos, enzyme.core.AVContainer):
+            results.extend([subtitles.EmbeddedSubtitle.from_enzyme(self.path, s) for s in video_infos.subtitles])
+        # cannot use glob here because it chokes if there are any square
+        # brackets inside the filename, so we have to use basic string
+        # startswith/endswith comparisons
+        folder, basename = os.path.split(basepath)
+        if folder == '':
+            folder = '.'
+        existing = [f for f in os.listdir(folder) if f.startswith(basename)]
+        for path in existing:
+            for ext in subtitles.EXTENSIONS:
+                if path.endswith(ext):
+                    language = Language(path[len(basename) + 1:-len(ext)], strict=False)
+                    results.append(subtitles.ExternalSubtitle(path, language))
+        return results
+
+    def __unicode__(self):
+        return to_unicode(self.path or self.release)
+
+    def __str__(self):
+        return unicode(self).encode('utf-8')
+
+    def __repr__(self):
+        return '%s(%s)' % (self.__class__.__name__, self)
+
+    def __hash__(self):
+        return hash(self.path or self.release)
+
+
+class Episode(Video):
+    """Episode :class:`Video`
+
+    :param string path: path
+    :param string series: series
+    :param int season: season number
+    :param int episode: episode number
+    :param string title: title
+    :param guess: guessed informations
+    :type guess: :class:`~guessit.guess.Guess`
+    :param string tvdbid: tvdbid
+    :param string imdbid: imdbid
+
+    """
+    def __init__(self, path, series, season, episode, title=None, guess=None, tvdbid=None, imdbid=None):
+        super(Episode, self).__init__(path, guess, imdbid)
+        self.series = series
+        self.title = title
+        self.season = season
+        self.episode = episode
+        self.tvdbid = tvdbid
+
+
+class Movie(Video):
+    """Movie :class:`Video`
+
+    :param string path: path
+    :param string title: title
+    :param int year: year
+    :param guess: guessed informations
+    :type guess: :class:`~guessit.guess.Guess`
+    :param string imdbid: imdbid
+
+    """
+    def __init__(self, path, title, year=None, guess=None, imdbid=None):
+        super(Movie, self).__init__(path, guess, imdbid)
+        self.title = title
+        self.year = year
+
+
+class UnknownVideo(Video):
+    """Unknown video"""
+    pass
+
+
+def scan(entry, max_depth=3, scan_filter=None, depth=0):
+    """Scan a path for videos and subtitles
+
+    :param string entry: path
+    :param int max_depth: maximum folder depth
+    :param function scan_filter: filter function that takes a path as argument and returns a boolean indicating whether it has to be filtered out (``True``) or not (``False``)
+    :param int depth: starting depth
+    :return: found videos and subtitles
+    :rtype: list of (:class:`Video`, [:class:`~subliminal.subtitles.Subtitle`])
+
+    """
+    if depth > max_depth and max_depth != 0:  # we do not want to search the whole file system except if max_depth = 0
+        return []
+    if os.path.isdir(entry):  # a dir? recurse
+        logger.debug(u'Scanning directory %s with depth %d/%d' % (entry, depth, max_depth))
+        result = []
+        for e in os.listdir(entry):
+            result.extend(scan(os.path.join(entry, e), max_depth, scan_filter, depth + 1))
+        return result
+    if os.path.isfile(entry) or depth == 0:
+        logger.debug(u'Scanning file %s with depth %d/%d' % (entry, depth, max_depth))
+        if depth != 0:  # trust the user: only check for valid format if recursing
+            if mimetypes.guess_type(entry)[0] not in MIMETYPES and os.path.splitext(entry)[1] not in EXTENSIONS:
+                return []
+            if scan_filter is not None and scan_filter(entry):
+                return []
+        video = Video.from_path(entry)
+        return [(video, video.scan())]
+    logger.warning(u'Scanning entry %s failed with depth %d/%d' % (entry, depth, max_depth))
+    return []  # anything else
+
+
+def hash_opensubtitles(path):
+    """Compute a hash using OpenSubtitles' algorithm
+
+    :param string path: path
+    :return: hash
+    :rtype: string
+
+    """
+    longlongformat = 'q'  # long long
+    bytesize = struct.calcsize(longlongformat)
+    with open(path, 'rb') as f:
+        filesize = os.path.getsize(path)
+        filehash = filesize
+        if filesize < 65536 * 2:
+            return None
+        for _ in range(65536 / bytesize):
+            filebuffer = f.read(bytesize)
+            (l_value,) = struct.unpack(longlongformat, filebuffer)
+            filehash += l_value
+            filehash = filehash & 0xFFFFFFFFFFFFFFFF  # to remain as 64bit number
+        f.seek(max(0, filesize - 65536), 0)
+        for _ in range(65536 / bytesize):
+            filebuffer = f.read(bytesize)
+            (l_value,) = struct.unpack(longlongformat, filebuffer)
+            filehash += l_value
+            filehash = filehash & 0xFFFFFFFFFFFFFFFF
+    returnedhash = '%016x' % filehash
+    logger.debug(u'Computed OpenSubtitle hash %s for %s' % (returnedhash, path))
+    return returnedhash
+
+
+def hash_thesubdb(path):
+    """Compute a hash using TheSubDB's algorithm
+
+    :param string path: path
+    :return: hash
+    :rtype: string
+
+    """
+    readsize = 64 * 1024
+    if os.path.getsize(path) < readsize:
+        return None
+    with open(path, 'rb') as f:
+        data = f.read(readsize)
+        f.seek(-readsize, os.SEEK_END)
+        data += f.read(readsize)
+    returnedhash = hashlib.md5(data).hexdigest()
+    logger.debug(u'Computed TheSubDB hash %s for %s' % (returnedhash, path))
+    return returnedhash

tests/__init__.py

@@ -0,0 +1,26 @@
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from . import test_language, test_services, test_subliminal, test_videos
+import unittest
+
+
+suite = unittest.TestSuite([test_language.suite(), test_services.suite(), test_subliminal.suite(), test_videos.suite()])
+
+
+if __name__ == '__main__':
+    unittest.TextTestRunner().run(suite)

tests/test_language.py

@@ -0,0 +1,163 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from subliminal.language import Language, Country, language_set, language_list
+import unittest
+
+
+class LanguageListTestCase(unittest.TestCase):
+    def test_list_contains(self):
+        languages = list([Language('fr'), Language('en-US'), Language('en-GB')])
+        self.assertTrue(Language('fr') in languages)
+        self.assertTrue(Language('en-US') in languages)
+        self.assertTrue(Language('en') not in languages)
+        self.assertTrue(Language('fr-BE') not in languages)
+
+    def test_language_list_contains(self):
+        languages = language_list(['fr', 'en-US', 'en-GB'])
+        self.assertTrue(Language('fr') in languages)
+        self.assertTrue(Language('en-US') in languages)
+        self.assertTrue(Language('en') not in languages)
+        self.assertTrue(Language('fr-BE') in languages)
+
+    def test_list_index(self):
+        languages = [Language('fr'), Language('en-US'), Language('en-GB')]
+        self.assertTrue(languages.index(Language('fr')) == 0)
+        self.assertTrue(languages.index(Language('en-US')) == 1)
+        self.assertTrue(languages.index(Language('en-GB')) == 2)
+        with self.assertRaises(ValueError):
+            languages.index(Language('fr-BE'))
+
+    def test_language_list_index(self):
+        languages = language_list(['fr', 'en-US', 'en-GB'])
+        self.assertTrue(languages.index(Language('fr')) == 0)
+        self.assertTrue(languages.index(Language('en-US')) == 1)
+        self.assertTrue(languages.index(Language('en-GB')) == 2)
+        self.assertTrue(languages.index(Language('fr-BE')) == 0)
+
+
+class LanguageSetTestCase(unittest.TestCase):
+    def test_set_contains(self):
+        languages = set([Language('fr'), Language('en-US'), Language('en-GB')])
+        self.assertTrue(Language('fr') in languages)
+        self.assertTrue(Language('en-US') in languages)
+        self.assertTrue(Language('en') not in languages)
+        self.assertTrue(Language('fr-BE') not in languages)
+
+    def test_language_set_contains(self):
+        languages = language_set(['fr', 'en-US', 'en-GB'])
+        self.assertTrue(Language('fr') in languages)
+        self.assertTrue(Language('en-US') in languages)
+        self.assertTrue(Language('en') not in languages)
+        self.assertTrue(Language('fr-BE') in languages)
+
+    def test_language_set_intersect(self):
+        languages = language_set(['fr', 'en-US', 'en-GB'])
+        self.assertTrue(len(languages & language_set([Language('en')])) == 2)
+        self.assertTrue(len(language_set([Language('en')]) & languages) == 2)
+        self.assertTrue(len(languages & language_set([Language('fr')])) == 1)
+
+    def test_language_set_substract(self):
+        languages = language_set(['fr', 'en-US', 'en-GB'])
+        self.assertTrue(len(languages - language_set(['en'])) == 1)
+        self.assertTrue(len(languages - language_set(['en-US'])) == 2)
+        self.assertTrue(len(languages - language_set(['en-US', 'fr'])) == 1)
+
+
+class LanguageTestCase(unittest.TestCase):
+    def test_attrs(self):
+        language = Language('French')
+        self.assertTrue(language.alpha2 == 'fr')
+        self.assertTrue(language.alpha3 == 'fre')
+        self.assertTrue(language.terminologic == 'fra')
+        self.assertTrue(language.name == 'French')
+        self.assertTrue(language.french_name == u'français')
+
+    def test_eq(self):
+        language = Language('French')
+        self.assertTrue(language == Language('fr'))
+        self.assertTrue(language == Language('fre'))
+        self.assertTrue(language == Language('fra'))
+        self.assertTrue(language == Language('Français'))
+
+    def test_ne(self):
+        self.assertTrue(Language('French') != Language('en'))
+
+    def test_in(self):
+        self.assertTrue(Language('Portuguese (BR)') in Language('Portuguese - Brazil'))
+        self.assertTrue(Language('Portuguese (BR)') in Language('Portuguese'))
+        self.assertTrue(Language('Portuguese') not in Language('Portuguese (BR)'))
+
+    def test_with_country(self):
+        self.assertTrue(Language('Portuguese (BR)').country == Country('Brazil'))
+        self.assertTrue(Language('pt_BR').country == Country('Brazil'))
+        self.assertTrue(Language('fr - France').country == Country('France'))
+        self.assertTrue(Language('fra', country='FR').country == Country('France'))
+        self.assertTrue(Language('fra', country=Country('FRA')).country == Country('France'))
+
+    def test_eq_with_country(self):
+        self.assertTrue(Language('Portuguese (BR)') == Language('Portuguese - Brazil'))
+        self.assertTrue(Language('English') == Language('en'))
+
+    def test_ne_with_country(self):
+        self.assertTrue(Language('Portuguese') != Language('Portuguese (BR)'))
+        self.assertTrue(Language('English (US)') != Language('English (GB)'))
+
+    def test_hash(self):
+        self.assertTrue(hash(Language('French')) == hash('fre'))
+
+    def test_missing(self):
+        with self.assertRaises(ValueError):
+            Language('zzz')
+
+
+class CountryTestCase(unittest.TestCase):
+    def test_attrs(self):
+        country = Country('France')
+        self.assertTrue(country.alpha2 == 'FR')
+        self.assertTrue(country.alpha3 == 'FRA')
+        self.assertTrue(country.name == 'France')
+
+    def test_eq(self):
+        country = Country('France')
+        self.assertTrue(country == Country('FR'))
+        self.assertTrue(country == Country('FRA'))
+        self.assertTrue(country == Country('250'))
+
+    def test_ne(self):
+        self.assertTrue(Country('France') != Country('GB'))
+
+    def test_hash(self):
+        self.assertTrue(hash(Country('France')) == hash('FRA'))
+
+    def test_missing(self):
+        with self.assertRaises(ValueError):
+            Country('ZZ')
+
+
+def suite():
+    suite = unittest.TestSuite()
+    suite.addTest(unittest.TestLoader().loadTestsFromTestCase(CountryTestCase))
+    suite.addTest(unittest.TestLoader().loadTestsFromTestCase(LanguageTestCase))
+    suite.addTest(unittest.TestLoader().loadTestsFromTestCase(LanguageSetTestCase))
+    suite.addTest(unittest.TestLoader().loadTestsFromTestCase(LanguageListTestCase))
+    return suite
+
+
+if __name__ == '__main__':
+    unittest.TextTestRunner().run(suite())

tests/test_services.py

@@ -0,0 +1,501 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from subliminal import videos
+from subliminal.exceptions import ServiceError
+from subliminal.language import language_set, LANGUAGES
+from subliminal.services import ServiceConfig
+from subliminal.services.addic7ed import Addic7ed
+from subliminal.services.bierdopje import BierDopje
+from subliminal.services.opensubtitles import OpenSubtitles
+from subliminal.services.podnapisi import Podnapisi
+from subliminal.services.subswiki import SubsWiki
+from subliminal.services.subtitulos import Subtitulos
+from subliminal.services.thesubdb import TheSubDB
+from subliminal.services.tvsubtitles import TvSubtitles
+import os
+import unittest
+try:
+    import cPickle as pickle
+except ImportError:
+    import pickle
+
+
+cache_dir = u'/tmp/sublicache'
+if not os.path.exists(cache_dir):
+    os.mkdir(cache_dir)
+existing_video = u'/something/The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4'
+
+
+class ServiceTestCase(unittest.TestCase):
+    def setUp(self):
+        self.wrong_languages = language_set(list(language_set(LANGUAGES) - self.service.languages)[:2])
+
+    def tearDown(self):
+        # Setting config to None allows to delete the object, which will in turn save the cache
+        self.config = None
+
+    def test_query_series(self):
+        with self.service(self.config) as service:
+            results = service.query(service, self.fake_file, self.languages, self.episode_keywords, self.series, self.season, self.episode)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_wrong_series(self):
+        with self.service(self.config) as service:
+            results = service.query(service, self.fake_file, self.languages, self.episode_keywords, self.wrong_series, self.season, self.episode)
+        self.assertTrue(len(results) == 0)
+
+    def test_query_wrong_languages(self):
+        with self.service(self.config) as service:
+            results = service.query(service, self.fake_file, self.wrong_languages, self.episode_keywords, self.series, self.season, self.episode)
+        self.assertTrue(len(results) == 0)
+
+    def test_list_episode(self):
+        video = videos.Video.from_path(self.episode_path)
+        with self.service(self.config) as service:
+            results = service.list(video, self.languages)
+        self.assertTrue(len(results) > 0)
+
+    def test_list_movie(self):
+        video = videos.Video.from_path(self.movie_path)
+        with self.service(self.config) as service:
+            results = service.list(video, self.languages)
+        self.assertTrue(len(results) > 0)
+
+    def test_list_wrong_languages(self):
+        video = videos.Video.from_path(self.episode_path)
+        with self.service(self.config) as service:
+            results = service.list(video, self.wrong_languages)
+        self.assertTrue(len(results) == 0)
+
+    def test_download_episode(self):
+        video = videos.Video.from_path(self.episode_path)
+        with self.service(self.config) as service:
+            subtitle = service.list(video, language_set([self.episode_sublanguage]))[0]
+            if os.path.exists(subtitle.path):
+                os.remove(subtitle.path)
+            service.download(subtitle)
+        self.assertTrue(os.path.exists(subtitle.path))
+        self.assertTrue(os.path.getsize(subtitle.path) in self.episode_subfilesizes, msg='Size %d not in %r' % (os.path.getsize(subtitle.path), self.episode_subfilesizes))
+        os.remove(subtitle.path)
+
+    def test_download_movie(self):
+        video = videos.Video.from_path(self.movie_path)
+        with self.service(self.config) as service:
+            subtitle = service.list(video, language_set([self.movie_sublanguage]))[0]
+            if os.path.exists(subtitle.path):
+                os.remove(subtitle.path)
+            service.download(subtitle)
+        self.assertTrue(os.path.exists(subtitle.path))
+        self.assertTrue(os.path.getsize(subtitle.path) in self.movie_subfilesizes, msg='Size %d not in %r' % (os.path.getsize(subtitle.path), self.movie_subfilesizes))
+        os.remove(subtitle.path)
+
+    def test_cached_series(self):
+        with self.service(self.config) as service:
+            service.clear_cache()
+            service.query(self.fake_file, self.languages, self.episode_keywords, self.series, self.season, self.episode)
+            service.save_cache()
+        c = pickle.load(open(os.path.join(cache_dir, 'subliminal_%s.cache' % self.service.__name__)))
+        found = False
+        for _, cached_values in c.items():
+            for args, __ in cached_values.items():
+                if args == (self.series.lower(),):
+                    found = True
+        self.assertTrue(found)
+
+
+class Addic7edTestCase(ServiceTestCase):
+    query_tests = ['test_query_series', 'test_query_wrong_series', 'test_query_wrong_languages']
+    list_tests = ['test_list_episode', 'test_list_wrong_languages']
+    download_tests = ['test_download_episode']
+    cache_tests = ['test_cached_series']
+    service = Addic7ed
+
+    def setUp(self):
+        super(Addic7edTestCase, self).setUp()
+        self.config = ServiceConfig(multi=True, cache_dir=cache_dir)
+        self.fake_file = u'/tmp/fake_file'
+        self.languages = language_set(['en', 'fr'])
+        self.episode_path = u'The Big Bang Theory/Season 05/The.Big.Bang.Theory.S05E06.HDTV.XviD-ASAP.mkv'
+        self.episode_sublanguage = 'en'
+        # FIXME: this is the size of the first subtitle that appears on the page
+        # which is the original one, not the most updated one. We should make
+        # sure the Addic7ed service picks up the most recent one instead
+        self.episode_subfilesizes = [33469]
+        self.episode_keywords = set(['asap', 'hdtv'])
+        self.series = 'The Big Bang Theory'
+        self.wrong_series = 'No Existent Show Name'
+        self.season = 5
+        self.episode = 6
+
+    def test_query_series(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.languages, self.episode_keywords, self.series, self.season, self.episode)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_wrong_series(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.languages, self.episode_keywords, self.wrong_series, self.season, self.episode)
+        self.assertTrue(len(results) == 0)
+
+    def test_query_wrong_languages(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.wrong_languages, self.episode_keywords, self.series, self.season, self.episode)
+        self.assertTrue(len(results) == 0)
+
+
+class BierDopjeTestCase(ServiceTestCase):
+    query_tests = ['test_query_series', 'test_query_wrong_series', 'test_query_wrong_languages',
+                   'test_query_tvdbid', 'test_query_wrong_tvdbid', 'test_query_series_and_tvdbid']
+    list_tests = ['test_list_episode', 'test_list_wrong_languages']
+    download_tests = ['test_download_episode']
+    cache_tests = ['test_cached_series']
+    service = BierDopje
+
+    def setUp(self):
+        super(BierDopjeTestCase, self).setUp()
+        self.config = ServiceConfig(multi=True, cache_dir=cache_dir)
+        self.episode_path = u'The Big Bang Theory/Season 05/S05E06 - The Rhinitis Revelation - HD TV.mkv'
+        self.episode_sublanguage = 'en'
+        self.episode_subfilesizes = [28982]
+        self.movie_path = u'Inception (2010)/Inception - 1080p.mkv'
+        self.movie_sublanguage = 'en'
+        self.movie_subfilesizes = []
+        self.languages = language_set(['en', 'nl'])
+        self.fake_file = u'/tmp/fake_file'
+        self.series = 'The Big Bang Theory'
+        self.episode_keywords = set()
+        self.wrong_series = 'No Existent Show Name'
+        self.season = 5
+        self.episode = 6
+        self.tvdbid = 80379
+        self.wrong_tvdbid = 9999999999
+
+    def test_query_series(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.season, self.episode, self.languages, series=self.series)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_wrong_series(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.season, self.episode, self.languages, series=self.wrong_series)
+        self.assertTrue(len(results) == 0)
+
+    def test_query_wrong_languages(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.season, self.episode, self.wrong_languages, series=self.series)
+        self.assertTrue(len(results) == 0)
+
+    def test_query_tvdbid(self):
+        with BierDopje(self.config) as service:
+            results = service.query(self.fake_file, self.season, self.episode, self.languages, tvdbid=self.tvdbid)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_series_and_tvdbid(self):
+        with BierDopje(self.config) as service:
+            results = service.query(self.fake_file, self.season, self.episode, self.languages, series=self.series, tvdbid=self.tvdbid)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_wrong_tvdbid(self):
+        with BierDopje(self.config) as service:
+            results = service.query(self.fake_file, self.season, self.episode, self.languages, tvdbid=self.wrong_tvdbid)
+        self.assertTrue(len(results) == 0)
+
+    def test_cached_series(self):
+        with self.service(self.config) as service:
+            service.clear_cache()
+            service.query(self.fake_file, self.season, self.episode, self.languages, series=self.series)
+            service.save_cache()
+        c = pickle.load(open(os.path.join(cache_dir, 'subliminal_%s.cache' % self.service.__name__)))
+        found = False
+        for _, cached_values in c.items():
+            for args, __ in cached_values.items():
+                if args == (self.series.lower(),):
+                    found = True
+        self.assertTrue(found)
+
+
+class OpenSubtitlesTestCase(ServiceTestCase):
+    query_tests = ['test_query_query', 'test_query_imdbid', 'test_query_hash', 'test_query_wrong_languages']
+    list_tests = ['test_list_episode', 'test_list_wrong_languages']
+    download_tests = ['test_download_episode']
+    cache_tests = []
+    service = OpenSubtitles
+
+    def setUp(self):
+        super(OpenSubtitlesTestCase, self).setUp()
+        self.config = ServiceConfig(multi=True, cache_dir=cache_dir)
+        self.languages = language_set(['en', 'fr'])
+        self.fake_file = u'/tmp/fake_file'
+        self.episode_path = existing_video
+        self.episode_sublanguage = 'en'
+        self.episode_subfilesizes = [30374, 30358, 33585, 33547, 33563, 33601, 31413, 31429]
+        self.movie = 'Inception'
+        self.imdbid = '1375666'
+        self.wrong_imdbid = '9999999'
+        self.hash = '51e57c4e8fd77990'
+        self.size = 882571264L
+
+    def test_query_query(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.languages, query=self.movie)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_imdbid(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.languages, imdbid=self.imdbid)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_hash(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.languages, moviehash=self.hash, size=self.size)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_wrong_languages(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.wrong_languages, moviehash=self.hash, size=self.size)
+        self.assertTrue(len(results) == 0)
+
+
+class PodnapisiTestCase(ServiceTestCase):
+    query_tests = ['test_query', 'test_query_wrong_languages']
+    list_tests = [] #'test_list', 'test_list_wrong_languages'
+    download_tests = [] #'test_download'
+    cache_tests = []
+    service = Podnapisi
+
+    def setUp(self):
+        super(PodnapisiTestCase, self).setUp()
+        self.config = ServiceConfig(multi=True, cache_dir=cache_dir)
+        self.languages = language_set(['en', 'fr'])
+        self.fake_file = u'/tmp/fake_file'
+        self.path = existing_video
+        self.hash = 'e1b45885346cfa0b'
+
+    def test_query(self):
+        with Podnapisi(self.config) as service:
+            results = service.query(self.fake_file, self.languages, moviehash=self.hash)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_wrong_languages(self):
+        with Podnapisi(self.config) as service:
+            results = service.query(self.fake_file, self.wrong_languages, moviehash=self.hash)
+        self.assertTrue(len(results) == 0)
+
+
+class SubsWikiTestCase(ServiceTestCase):
+    query_tests = ['test_query_series', 'test_query_movie', 'test_query_wrong_parameters', 'test_query_wrong_series', 'test_query_wrong_languages']
+    list_tests = ['test_list_episode', 'test_list_movie', 'test_list_wrong_languages']
+    download_tests = ['test_download_episode', 'test_download_movie']
+    cache_tests = []
+    service = SubsWiki
+
+    def setUp(self):
+        super(SubsWikiTestCase, self).setUp()
+        self.config = ServiceConfig(multi=True, cache_dir=cache_dir)
+        self.fake_file = u'/tmp/fake_file'
+        self.languages = language_set(['en', 'es'])
+        self.movie_path = u'Soul Surfer (2011)/Soul.Surfer.(2011).DVDRip.XviD-TWiZTED.mkv'
+        self.movie_sublanguage = 'es'
+        self.movie_subfilesizes = [87528]
+        self.movie_keywords = set(['twizted'])
+        self.movie = u'Soul Surfer'
+        self.movie_year = 2011
+        self.episode_path = u'The Big Bang Theory/Season 05/The.Big.Bang.Theory.S05E06.HDTV.XviD-ASAP.mkv'
+        self.episode_sublanguage = 'es'
+        self.episode_subfilesizes = [34040]
+        self.episode_keywords = set(['asap', 'hdtv'])
+        self.series = 'The Big Bang Theory'
+        self.wrong_series = 'No Existent Show Name'
+        self.season = 5
+        self.episode = 6
+
+    def test_query_series(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.languages, self.episode_keywords, self.series, self.season, self.episode)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_wrong_series(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.languages, self.episode_keywords, self.wrong_series, self.season, self.episode)
+        self.assertTrue(len(results) == 0)
+
+    def test_query_wrong_languages(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.wrong_languages, self.episode_keywords, self.series, self.season, self.episode)
+        self.assertTrue(len(results) == 0)
+
+    def test_query_movie(self):
+        with SubsWiki(self.config) as service:
+            results = service.query(self.fake_file, self.languages, keywords=self.movie_keywords, movie=self.movie, year=self.movie_year)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_wrong_parameters(self):
+        with SubsWiki(self.config) as service:
+            self.assertRaises(ServiceError, service.query,
+                              self.fake_file, self.languages, keywords=self.movie_keywords, movie=self.movie, series=self.series)
+
+
+class SubtitulosTestCase(ServiceTestCase):
+    query_tests = ['test_query_series', 'test_query_wrong_series', 'test_query_wrong_languages']
+    list_tests = ['test_list_episode', 'test_list_wrong_languages']
+    download_tests = ['test_download_episode']
+    cache_tests = []
+    service = Subtitulos
+
+    def setUp(self):
+        super(SubtitulosTestCase, self).setUp()
+        self.config = ServiceConfig(multi=True, cache_dir=cache_dir)
+        self.fake_file = u'/tmp/fake_file'
+        self.languages = language_set(['en', 'es'])
+        self.episode_path = u'The Big Bang Theory/Season 05/The.Big.Bang.Theory.S05E06.HDTV.XviD-ASAP.mkv'
+        self.episode_sublanguage = 'en'
+        self.episode_subfilesizes = [32986]
+        self.episode_keywords = set(['asap', 'hdtv'])
+        self.series = 'The Big Bang Theory'
+        self.wrong_series = 'No Existent Show Name'
+        self.season = 5
+        self.episode = 6
+
+    def test_query_series(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.languages, self.episode_keywords, self.series, self.season, self.episode)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_wrong_series(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.languages, self.episode_keywords, self.wrong_series, self.season, self.episode)
+        self.assertTrue(len(results) == 0)
+
+    def test_query_wrong_languages(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.wrong_languages, self.episode_keywords, self.series, self.season, self.episode)
+        self.assertTrue(len(results) == 0)
+
+
+class TheSubDBTestCase(ServiceTestCase):
+    query_tests = ['test_query', 'test_query_wrong_languages']
+    list_tests = ['test_list_episode', 'test_list_wrong_languages']
+    download_tests = ['test_download_episode']
+    cache_tests = []
+    service = TheSubDB
+
+    def setUp(self):
+        super(TheSubDBTestCase, self).setUp()
+        self.config = ServiceConfig(multi=True, cache_dir=cache_dir)
+        self.episode_path = existing_video
+        self.episode_sublanguage = 'en'
+        self.episode_subfilesizes = [33536]
+        self.hash = u'edc1981d6459c6111fe36205b4aff6c2'
+        self.languages = language_set(['en', 'nl'])
+        self.fake_file = u'/tmp/fake_file'
+
+    def test_query(self):
+        with TheSubDB(self.config) as service:
+            results = service.query(self.fake_file, self.hash, self.languages)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_wrong_languages(self):
+        with TheSubDB(self.config) as service:
+            results = service.query(self.fake_file, self.hash, self.wrong_languages)
+        self.assertTrue(len(results) == 0)
+
+    @unittest.skipUnless(os.path.exists(existing_video), 'No existing video')
+    def test_list_episode(self):
+        super(TheSubDBTestCase, self).test_list_episode()
+
+    @unittest.skipUnless(os.path.exists(existing_video), 'No existing video')
+    def test_download_episode(self):
+        super(TheSubDBTestCase, self).test_download_episode()
+
+
+class TvSubtitlesTestCase(ServiceTestCase):
+    query_tests = ['test_query_series', 'test_query_wrong_series', 'test_query_wrong_languages']
+    list_tests = ['test_list_episode', 'test_list_wrong_languages']
+    download_tests = ['test_download_episode']
+    cache_tests = ['test_cached_series']
+    service = TvSubtitles
+
+    def setUp(self):
+        super(TvSubtitlesTestCase, self).setUp()
+        self.config = ServiceConfig(multi=True, cache_dir=cache_dir)
+        self.fake_file = u'/tmp/fake_file'
+        self.languages = language_set(['en', 'es'])
+        self.episode_path = u'The Big Bang Theory/Season 05/The.Big.Bang.Theory.S05E06.HDTV.XviD-ASAP.mkv'
+        self.episode_sublanguage = 'en'
+        self.episode_subfilesizes = [33078]
+        self.episode_keywords = set(['asap', 'hdtv'])
+        self.series = 'The Big Bang Theory'
+        self.wrong_series = 'No Existent Show Name'
+        self.season = 5
+        self.episode = 6
+
+    def test_query_series(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.languages, self.episode_keywords, self.series, self.season, self.episode)
+        self.assertTrue(len(results) > 0)
+
+    def test_query_wrong_series(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.languages, self.episode_keywords, self.wrong_series, self.season, self.episode)
+        self.assertTrue(len(results) == 0)
+
+    def test_query_wrong_languages(self):
+        with self.service(self.config) as service:
+            results = service.query(self.fake_file, self.wrong_languages, self.episode_keywords, self.series, self.season, self.episode)
+        self.assertTrue(len(results) == 0)
+
+
+TESTCASES = [Addic7edTestCase, BierDopjeTestCase, OpenSubtitlesTestCase, PodnapisiTestCase, SubsWikiTestCase,
+             SubtitulosTestCase, TheSubDBTestCase, TvSubtitlesTestCase]
+
+
+def query_suite():
+    suite = unittest.TestSuite()
+    for testcase in TESTCASES:
+        suite.addTests(map(testcase, testcase.query_tests))
+    return suite
+
+
+def list_suite():
+    suite = unittest.TestSuite()
+    for testcase in TESTCASES:
+        suite.addTests(map(testcase, testcase.list_tests))
+    return suite
+
+
+def download_suite():
+    suite = unittest.TestSuite()
+    for testcase in TESTCASES:
+        suite.addTests(map(testcase, testcase.download_tests))
+    return suite
+
+
+def cache_suite():
+    suite = unittest.TestSuite()
+    for testcase in TESTCASES:
+        suite.addTests(map(testcase, testcase.cache_tests))
+    return suite
+
+
+def suite():
+    return unittest.TestSuite([query_suite(), list_suite(), download_suite(), cache_suite()])
+
+
+if __name__ == '__main__':
+    unittest.TextTestRunner().run(suite())

tests/test_subliminal.py

@@ -0,0 +1,135 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from subliminal import Pool, list_subtitles, download_subtitles
+import os
+import time
+import unittest
+import requests
+import tarfile
+import StringIO
+
+
+test_dir = 'test_subliminal_files'
+cache_dir = 'test_subliminal_cache'
+test_video = 'The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4'
+
+
+def setUpModule():
+    if not os.path.exists(test_dir):
+        r = requests.get('https://github.com/downloads/Diaoul/subliminal/test_subliminal_files.tar.gz')
+        with tarfile.open(fileobj=StringIO.StringIO(r.content), mode='r:gz') as f:
+            f.extractall(test_dir)
+    if not os.path.exists(cache_dir):
+        os.mkdir(cache_dir)
+
+
+class ApiTestCase(unittest.TestCase):
+    def test_list_subtitles(self):
+        results = list_subtitles(test_video, languages=['en', 'fr'], cache_dir=cache_dir)
+        self.assertTrue(len(results) > 0)
+
+    def test_download_subtitles(self):
+        results = download_subtitles(test_video, languages=['en', 'fr'], cache_dir=cache_dir)
+        self.assertTrue(len(results) == 1)
+        for video, subtitles in results.iteritems():
+            self.assertTrue(video.release == test_video)
+            self.assertTrue(len(subtitles) == 1)
+            for subtitle in subtitles:
+                self.assertTrue(subtitle.path == os.path.splitext(os.path.basename(test_video))[0] + '.srt')
+                self.assertTrue(os.path.exists(subtitle.path))
+                os.remove(subtitle.path)
+
+    def test_download_subtitles_noforce(self):
+        results_first = download_subtitles(test_dir, languages=['en', 'fr'], cache_dir=cache_dir, force=False, services=['thesubdb'])
+        results = download_subtitles(test_dir, languages=['en', 'fr'], cache_dir=cache_dir, force=False, services=['thesubdb'])
+        self.assertTrue(len(results) == 0)
+        for _, subtitles in results_first.iteritems():
+            for subtitle in subtitles:
+                os.remove(subtitle.path)
+
+    def test_download_subtitles_multi(self):
+        results = download_subtitles(test_video, languages=['en', 'fr'], cache_dir=cache_dir, multi=True)
+        self.assertTrue(len(results) == 1)
+        for video, subtitles in results.iteritems():
+            self.assertTrue(video.release == test_video)
+            self.assertTrue(len(subtitles) == 2)
+            for subtitle in subtitles:
+                self.assertTrue(os.path.exists(subtitle.path))
+                os.remove(subtitle.path)
+
+    def test_download_subtitles_multi_noforce(self):
+        results_first = download_subtitles(test_dir, languages=['en', 'fr'], cache_dir=cache_dir, multi=True, force=False, services=['thesubdb'])
+        results = download_subtitles(test_dir, languages=['en', 'fr'], cache_dir=cache_dir, multi=True, force=False, services=['thesubdb'])
+        self.assertTrue(len(results) == 0)
+        for _, subtitles in results_first.iteritems():
+            for subtitle in subtitles:
+                os.remove(subtitle.path)
+
+    def test_download_subtitles_languages(self):
+        results = download_subtitles('Dexter/Season 04/S04E08 - Road Kill - 720p BluRay.mkv', languages=['en'],
+                                     cache_dir=cache_dir, multi=True, force=False, services=['subtitulos', 'tvsubtitles'])
+        self.assertTrue(len(results) == 1)
+        for _, subtitles in results.iteritems():
+            self.assertTrue(len(subtitles) == 1)
+            for subtitle in subtitles:
+                os.remove(subtitle.path)
+
+
+class AsyncTestCase(unittest.TestCase):
+    def test_pool(self):
+        p = Pool(4)
+        self.assertTrue(len(p.workers) == 4)
+        for w in p.workers:
+            self.assertTrue(w.isAlive() == False)
+        p.start()
+        for w in p.workers:
+            self.assertTrue(w.isAlive() == True)
+        p.stop()
+        p.join()
+        time.sleep(0.2)  # so terminate is finished on Worker and proper Thread methods finished
+        for w in p.workers:
+            self.assertTrue(w.isAlive() == False)
+
+    def test_list_subtitles(self):
+        with Pool(4) as p:
+            results = p.list_subtitles(test_video, languages=['en', 'fr'], cache_dir=cache_dir)
+        self.assertTrue(len(results) > 0)
+
+    def test_download_subtitles(self):
+        with Pool(4) as p:
+            results = p.download_subtitles(test_video, languages=['en', 'fr'], cache_dir=cache_dir)
+        self.assertTrue(len(results) == 1)
+        for video, subtitles in results.iteritems():
+            self.assertTrue(video.release == test_video)
+            self.assertTrue(len(subtitles) == 1)
+            for subtitle in subtitles:
+                self.assertTrue(subtitle.path == os.path.splitext(os.path.basename(test_video))[0] + '.srt')
+                self.assertTrue(os.path.exists(subtitle.path))
+                os.remove(subtitle.path)
+
+
+def suite():
+    suite = unittest.TestSuite()
+    suite.addTest(unittest.TestLoader().loadTestsFromTestCase(ApiTestCase))
+    suite.addTest(unittest.TestLoader().loadTestsFromTestCase(AsyncTestCase))
+    return suite
+
+
+if __name__ == '__main__':
+    unittest.TextTestRunner().run(suite())

tests/test_videos.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# Copyright 2011-2012 Antoine Bertin <diaoulael@gmail.com>
+#
+# This file is part of subliminal.
+#
+# subliminal is free software; you can redistribute it and/or modify it under
+# the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# subliminal is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
+from subliminal.subtitles import EmbeddedSubtitle, ExternalSubtitle
+from subliminal.videos import scan
+from subliminal.language import Language
+import StringIO
+import os
+import requests
+import tarfile
+import unittest
+
+
+test_dir = 'test_videos_files'
+
+
+def setUpModule():
+    if not os.path.exists(test_dir):
+        r = requests.get('https://github.com/downloads/Diaoul/subliminal/test_videos_files.tar.gz')
+        with tarfile.open(fileobj=StringIO.StringIO(r.content), mode='r:gz') as f:
+            f.extractall(test_dir)
+
+
+class ScanTestCase(unittest.TestCase):
+    def test_basic(self):
+        results = scan(test_dir)
+        self.assertTrue(len(results) == 1)
+        self.assertTrue(isinstance(results[0], tuple))
+        self.assertTrue(len(results[0]) == 2)
+
+    def test_embedded_subtitles(self):
+        results = [s for s in scan(test_dir)[0][1] if isinstance(s, EmbeddedSubtitle)]
+        self.assertTrue(len(results) == 8)
+        for l in ('fre', 'eng', 'ita', 'spa', 'hun', 'ger', 'jpn', 'und'):
+            self.assertTrue(any([s.language == Language(l) for s in results]))
+
+    def test_external_subtitles(self):
+        results = [s for s in scan(test_dir)[0][1] if isinstance(s, ExternalSubtitle)]
+        self.assertTrue(len(results) == 3)
+        for l in ('fre', 'eng', 'und'):
+            self.assertTrue(any([s.language == Language(l) for s in results]))
+
+
+def suite():
+    suite = unittest.TestSuite()
+    suite.addTest(unittest.TestLoader().loadTestsFromTestCase(ScanTestCase))
+    return suite
+
+
+if __name__ == '__main__':
+    unittest.TextTestRunner().run(suite())