Release 0.7.1

The alpha2 converter might not yet be loaded at this point.
When subliminal's converters are loaded, they import subliminal
which import the video module.

.coveragerc

@@ -0,0 +1,5 @@
+[report]
+exclude_lines =
+    def __repr__
+    raise NotImplementedError
+    if __name__ == .__main__.:

.gitignore

@@ -20,16 +20,24 @@ pip-log.txt
 .coverage
 .tox
 
-#Translations
+# Translations
 *.mo
 
-#Mr Developer
+# Mr Developer
 .mr.developer.cfg
 
-#Pydev
+# Pydev
 .project
 .pydevproject
 .settings
 
-#Sphinx
+# Rope
+.ropeproject
+
+# Sphinx
 docs/_build
+
+# Subliminal unittests
+subliminal/tests/*.srt
+subliminal/tests/*_files
+subliminal/tests/*_cache

.travis.yml

@@ -0,0 +1,24 @@
+language: python
+
+python:
+  - "2.7"
+
+install:
+  - pip install coveralls --use-mirrors
+  - pip install -r requirements.txt --use-mirrors
+
+script:
+  - coverage run --source=subliminal setup.py test
+
+after_success:
+  - coveralls
+
+notifications:
+  email: false
+  irc:
+    channels:
+      - "irc.freenode.org#subliminal"
+    on_success: change
+    on_failure: always
+    use_notice: true
+    skip_join: true

COPYING

@@ -1,674 +0,0 @@
-                    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

@@ -1,165 +0,0 @@
-                   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.

HISTORY.rst

@@ -0,0 +1,127 @@
+Changelog
+=========
+
+0.7.1
+-----
+**release date:** 2013-11-06
+
+* Improve CLI
+* Add login support for Addic7ed
+* Remove lxml dependency
+* Many fixes
+
+
+0.7.0
+-----
+**release date:** 2013-10-29
+
+**WARNING:** Complete rewrite of subliminal with backward incompatible changes
+
+* Use enzyme to parse metadata of videos
+* Use babelfish to handle languages
+* Use dogpile.cache for caching
+* Use charade to detect subtitle encoding
+* Use pysrt for subtitle validation
+* Use entry points for subtitle providers
+* New subtitle score computation
+* Hearing impaired subtitles support
+* Drop async support
+* Drop a few providers
+* And much more...
+
+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

LICENSE

@@ -0,0 +1,20 @@
+The MIT License (MIT)
+
+Copyright (c) 2013 Antoine Bertin
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
+the Software, and to permit persons to whom the Software is furnished to do so,
+subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

MANIFEST.in

@@ -1 +1 @@
-include COPYING COPYING.LESSER NEWS.rst README.rst
+include LICENSE HISTORY.rst requirements.txt

NEWS.rst

@@ -1,43 +0,0 @@
-News
-====
-
-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.rst

@@ -1,43 +1,56 @@
 Subliminal
 ==========
+
 Subliminal is a python library to search and download subtitles.
+It comes with an easy to use CLI (command-line interface) suitable for direct use or cron jobs.
 
-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.
+.. image:: https://travis-ci.org/Diaoul/subliminal.png?branch=develop
+    :target: https://travis-ci.org/Diaoul/subliminal
 
-Features
---------
-Multiple subtitles services are available:
+.. image:: https://coveralls.io/repos/Diaoul/subliminal/badge.png?branch=develop
+    :target: https://coveralls.io/r/Diaoul/subliminal?branch=develop 
 
+
+Providers
+---------
+Subliminal uses multiple providers to give users a vast choice and have a better chance to find the
+best matching subtitles. Providers are extensible through a dedicated entry point.
+
+* Addic7ed
+* BierDopje
 * OpenSubtitles
 * TheSubDB
-* BierDopje
-* SubsWiki
-* Subtitulos
+* TvSubtitles
 
-You can use main subliminal's functions with a **file path**, a **file name** or a **folder path**.
 
+Usage
+-----
 CLI
 ^^^
 Download english subtitles::
 
-    $ subliminal -l en The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4
-    **************************************************
-    Downloaded 1 subtitles
-    (Episode(u'The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4'), ResultSubtitle(en, opensubtitles, 0.33, The.Big.Bang.Theory.S05E18.HDTV-LOL.srt))
-    **************************************************
+    $ subliminal -l en -- The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4
+    1 subtitle downloaded
 
-Module
-^^^^^^
-List english subtitles::
+Library
+^^^^^^^
+Download best subtitles in French and English for videos less than one week old in a video folder,
+skipping videos that already have subtitles whether they are embedded or not::
 
-    >>> subliminal.list_subtitles('The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4', ['en'])
+    from babelfish import Language
+    from datetime import timedelta
+    import subliminal
+    
+    # configure the cache
+    subliminal.cache_region.configure('dogpile.cache.dbm', arguments={'filename': '/path/to/cachefile.dbm'})
 
-Multi-threaded use
-^^^^^^^^^^^^^^^^^^
-Use 4 workers to achieve the same result::
+    # scan for videos in the folder and their subtitles
+    videos = scan_videos(['/path/to/video/folder'], subtitles=True, embedded_subtitles=True) 
 
-    >>> with subliminal.Pool(4) as p:
-    ...     p.list_subtitles('The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4', ['en'])
+    # download
+    subliminal.download_best_subtitles(videos, {Language('eng'), Language('fra')}, age=timedelta(week=1))
+
+
+License
+-------
+MIT

dev-requirements.txt

@@ -0,0 +1,4 @@
+sympy>=0.7.3
+sphinx>=1.1.3
+sphinxcontrib-programoutput>=0.8
+Sphinx-PyPI-upload>=0.2.1

docs/Makefile

@@ -7,6 +7,11 @@ SPHINXBUILD   = sphinx-build
 PAPER         =
 BUILDDIR      = _build
 
+# User-friendly check for sphinx-build
+ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1)
+$(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/)
+endif
+
 # Internal variables.
 PAPEROPT_a4     = -D latex_paper_size=a4
 PAPEROPT_letter = -D latex_paper_size=letter
@@ -29,17 +34,20 @@ help:
 	@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 "  latexpdfja to make LaTeX files and run them through platex/dvipdfmx"
 	@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 "  xml        to make Docutils-native XML files"
+	@echo "  pseudoxml  to make pseudoxml-XML files for display purposes"
 	@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)/*
+	rm -rf $(BUILDDIR)/*
 
 html:
 	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
@@ -108,6 +116,12 @@ latexpdf:
 	$(MAKE) -C $(BUILDDIR)/latex all-pdf
 	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
 
+latexpdfja:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through platex and dvipdfmx..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf-ja
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
 text:
 	$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
 	@echo
@@ -151,3 +165,13 @@ doctest:
 	$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
 	@echo "Testing of doctests in the sources finished, look at the " \
 	      "results in $(BUILDDIR)/doctest/output.txt."
+
+xml:
+	$(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml
+	@echo
+	@echo "Build finished. The XML files are in $(BUILDDIR)/xml."
+
+pseudoxml:
+	$(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
+	@echo
+	@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."

docs/_templates/sidebar-intro.html

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

docs/_templates/sidebar-links.html

@@ -1,6 +0,0 @@
-<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/_templates/sidebar-watch.html

@@ -1,4 +0,0 @@
-<p>
-  <iframe src="http://markdotto.github.com/github-buttons/github-btn.html?user=Diaoul&repo=subliminal&type=watch&count=true&size=large"
-    allowtransparency="true" frameborder="0" scrolling="0" width="200px" height="35px"></iframe>
-</p>

docs/api/api.rst

@@ -0,0 +1,8 @@
+API
+===
+.. module:: subliminal.api
+
+.. autodata:: PROVIDERS_ENTRY_POINT
+.. autofunction:: list_subtitles
+.. autofunction:: download_subtitles
+.. autofunction:: download_best_subtitles

docs/api/cache.rst

@@ -0,0 +1,7 @@
+Cache
+=====
+.. module:: subliminal.cache
+
+.. autodata:: region
+
+Refer to `dogpile.cache's documentation <http://dogpilecache.readthedocs.org>`_ to see how to configure a region

docs/api/cli.rst

@@ -0,0 +1,7 @@
+CLI
+===
+.. module:: subliminal.cli
+
+subliminal
+----------
+.. program-output:: subliminal --help

docs/api/exceptions.rst

@@ -0,0 +1,9 @@
+Exceptions
+==========
+.. module:: subliminal.exceptions
+
+.. autoclass:: Error
+.. autoclass:: ProviderError
+.. autoclass:: ProviderConfigurationError
+.. autoclass:: ProviderNotAvailable
+.. autoclass:: InvalidSubtitle

docs/api/providers.rst

@@ -0,0 +1,6 @@
+Providers
+=========
+.. module:: subliminal.providers
+
+.. autoclass:: Provider
+    :members:

docs/api/score.rst

@@ -0,0 +1,6 @@
+Score
+=====
+.. module:: subliminal.score
+
+.. autofunction:: get_episode_equations
+.. autofunction:: get_movie_equations

docs/api/subtitle.rst

@@ -0,0 +1,9 @@
+Subtitle
+========
+.. module:: subliminal.subtitle
+
+.. autoclass:: Subtitle
+    :members:
+.. autofunction:: get_subtitle_path
+.. autofunction:: is_valid_subtitle
+.. autofunction:: compute_guess_matches

docs/api/video.rst

@@ -0,0 +1,17 @@
+Video
+=====
+.. module:: subliminal.video
+
+.. autodata:: VIDEO_EXTENSIONS
+.. autodata:: SUBTITLE_EXTENSIONS
+.. autoclass:: Video
+    :members:
+.. autoclass:: Episode
+    :members:
+.. autoclass:: Movie
+    :members:
+.. autofunction:: hash_opensubtitles
+.. autofunction:: hash_thesubdb
+.. autofunction:: scan_subtitle_languages
+.. autofunction:: scan_video
+.. autofunction:: scan_videos

docs/conf.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 # subliminal documentation build configuration file, created by
-# sphinx-quickstart on Tue Feb 28 16:33:06 2012.
+# sphinx-quickstart on Wed Oct 23 23:24:28 2013.
 #
 # This file is execfile()d with the current directory set to its containing dir.
 #
@@ -18,7 +18,7 @@ import sys, os
 # 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
+import subliminal
 
 # -- General configuration -----------------------------------------------------
 
@@ -27,7 +27,7 @@ import subliminal.infos
 
 # 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']
+extensions = ['sphinx.ext.autodoc', 'sphinxcontrib.programoutput']
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
@@ -42,17 +42,17 @@ source_suffix = '.rst'
 master_doc = 'index'
 
 # General information about the project.
-project = u'subliminal'
-copyright = u'2012, Antoine Bertin'
+project = subliminal.__title__
+copyright = ' '.join(subliminal.__copyright__.split()[1:])
 
 # 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__
+version = subliminal.__version__
 # The full version, including alpha/beta/rc tags.
-release = version
+release = subliminal.__version__
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
@@ -88,17 +88,29 @@ pygments_style = 'sphinx'
 # A list of ignored prefixes for module index sorting.
 #modindex_common_prefix = []
 
+# If true, keep warnings as "system message" paragraphs in the built documents.
+#keep_warnings = False
+
 
 # -- 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 = 'flask'
+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 = {}
+html_theme_options = {'github_user': 'Diaoul',
+                      'github_repo': 'subliminal',
+                      'github_branch': 'master',
+                      'fork_me': 1,
+                      'flattr': 0,
+                      'gittip': 'Diaoul',
+                      'pypi_downloads': 1,
+                      'pypi_version': 0,
+                      'travis': 0,
+                      'coveralls': 0}
 
 # Add any paths that contain custom themes here, relative to this directory.
 html_theme_path = ['_themes']
@@ -112,7 +124,7 @@ html_theme_path = ['_themes']
 
 # The name of an image file (relative to this directory) to place at the top
 # of the sidebar.
-html_logo = '_static/subliminal-logo.png'
+#html_logo = None
 
 # 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
@@ -134,9 +146,11 @@ html_static_path = ['_static']
 
 # Custom sidebar templates, maps document names to template names.
 html_sidebars = {
-    'index':    ['sidebar-intro.html', 'sidebar-watch.html', 'localtoc.html', 'sidebar-links.html', 'searchbox.html'],
-    '**':       ['localtoc.html', 'relations.html', 'sourcelink.html']
-    }
+    'index': ['sidebar-intro.html', 'sidebar-star.html', 'sidebar-pypi.html', 'sidebar-donate.html',
+              'sourcelink.html', 'searchbox.html'],
+    '**': ['sidebar-intro.html', 'sidebar-star.html', 'sidebar-pypi.html', 'sidebar-donate.html',
+           'localtoc.html', 'relations.html', 'sourcelink.html', 'searchbox.html']
+}
 
 # Additional templates that should be rendered to pages, maps page names to
 # template names.
@@ -245,3 +259,11 @@ texinfo_documents = [
 
 # How to display URL addresses: 'footnote', 'no', or 'inline'.
 #texinfo_show_urls = 'footnote'
+
+# If true, do not generate a @detailmenu in the "Top" node's menu.
+#texinfo_no_detailmenu = False
+
+
+# -- Options for autodoc -------------------------------------------------------
+autodoc_member_order = 'bysource'
+

docs/dev.rst

@@ -1,87 +0,0 @@
-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 don't wanna 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 has a :mod:`~subliminal.languages`
-module that contains utility functions and ISO languages code (639-1 and 639-2)
-
-.. automodule:: subliminal.languages
-    :members:
-
-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

@@ -1,5 +1,5 @@
 .. subliminal documentation master file, created by
-   sphinx-quickstart on Tue Feb 28 16:33:06 2012.
+   sphinx-quickstart on Wed Oct 23 23:24:28 2013.
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
@@ -8,70 +8,95 @@ Subliminal
 Release v\ |version|
 
 Subliminal is a python library to search and download subtitles.
+It comes with an easy to use :abbr:`CLI (command-line interface)` suitable for direct use or cron jobs.
 
-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:
+Providers
+---------
+Subliminal uses multiple providers to give users a vast choice and have a better chance to find the
+best matching subtitles. Providers are extensible through a dedicated entry point.
 
+* Addic7ed
+* BierDopje
 * OpenSubtitles
 * TheSubDB
-* BierDopje
-* SubsWiki
-* Subtitulos
+* TvSubtitles
 
-You can use main subliminal's functions with a **file path**, a **file name** or a **folder path**.
 
+Usage
+-----
 CLI
 ^^^
 Download english subtitles::
 
-    $ subliminal -l en The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4
-    **************************************************
-    Downloaded 1 subtitles
-    (Episode(u'The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4'), ResultSubtitle(en, opensubtitles, 0.33, The.Big.Bang.Theory.S05E18.HDTV-LOL.srt))
-    **************************************************
+    $ subliminal -l en -- The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4
+    1 subtitle downloaded
 
-Module
-^^^^^^
-List english subtitles::
+See :mod:`subliminal.cli`
 
-	>>> subliminal.list_subtitles('The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4', ['en'])
+Library
+^^^^^^^
+Download best subtitles in French and English for videos less than one week old in a video folder,
+skipping videos that already have subtitles whether they are embedded or not::
 
-Multi-threaded use
-^^^^^^^^^^^^^^^^^^
-Use 4 workers to achieve the same result::
+    from babelfish import Language
+    from datetime import timedelta
+    import subliminal
+    
+    # configure the cache
+    subliminal.cache_region.configure('dogpile.cache.dbm', arguments={'filename': '/path/to/cachefile.dbm'})
 
-	>>> with subliminal.Pool(4) as p:
-	... 	p.list_subtitles('The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4', ['en'])
+    # scan for videos in the folder and their subtitles
+    videos = scan_videos(['/path/to/video/folder'], subtitles=True, embedded_subtitles=True) 
 
-User Guide
-----------
-This part of the documentation details how to use subliminal for most common tasks
+    # download
+    subliminal.download_best_subtitles(videos, {Language('eng'), Language('fra')}, age=timedelta(week=1))
 
+See :mod:`subliminal.api`, :func:`~subliminal.video.scan_videos` and :func:`~subliminal.video.scan_video`
+
+How it works
+------------
+Subliminal makes use of various libraries to achieve its goal:
+
+* `enzyme <http://enzyme.readthedocs.org>`_ to detect embedded subtitles in videos and retrieve metadata
+* `guessit <http://guessit.readthedocs.org>`_ to guess informations from filenames
+* `babelfish <http://babelfish.readthedocs.org>`_ to work with languages
+* `requests <http://docs.python-requests.org>`_ to make human readable HTTP requests
+* `BeautifulSoup <http://www.crummy.com/software/BeautifulSoup>`_ to parse HTML and XML
+* `dogpile.cache <http://dogpilecache.readthedocs.org>`_ to cache intermediate search data
+* `charade <https://github.com/sigmavirus24/charade>`_ to detect subtitles' encoding
+* `pysrt <https://github.com/byroot/pysrt>`_ to validate downloaded subtitles
+
+
+License
+-------
+MIT
+
+
+Documentation
+-------------
 .. toctree::
-   :maxdepth: 2
-   
-   user
+    :maxdepth: 2
 
-Developer Guide
----------------
-This part of the documentation explains internal behavior of subliminal and its algorithms
-
-.. toctree::
-   :maxdepth: 2
-   
-   dev
+    provider_guide
 
 
 API Documentation
 -----------------
-Most common subliminal features are listed here
+If you are looking for information on a specific function, class or method,
+this part of the documentation is for you.
 
-.. automodule:: subliminal
-    :members:
-    :noindex:
+.. toctree::
+    :maxdepth: 2
+
+    api/api
+    api/cache
+    api/cli
+    api/exceptions
+    api/providers
+    api/score
+    api/subtitle
+    api/video
+
+
+.. include:: ../HISTORY.rst

docs/provider_guide.rst

@@ -0,0 +1,103 @@
+Provider Guide
+==============
+This guide is going to explain how to add a :class:`~subliminal.providers.Provider` to subliminal
+
+
+Requirements
+------------
+When starting a provider you should be able to answer to the following questions:
+
+* What languages does my provider support?
+* What are the language codes for the supported languages?
+* Does my provider deliver subtitles for episodes? for movies?
+* Does my provider require a video hash?
+
+Each response of these questions will help you set the correct attributes for your
+:class:`~subliminal.providers.Provider`.
+
+
+Video Validation
+----------------
+Not all providers deliver subtitles for :class:`~subliminal.video.Episode`. Some may require a hash.
+The :meth:`~subliminal.providers.Provider.check` method does validation against a :class:`~subliminal.video.Video`
+object and will return `False` if the given :class:`~subliminal.video.Video` isn't suitable. If you're not happy
+with the default implementation, you can override it.
+
+
+Configuration
+-------------
+API keys must not be configurable by the user and must remain linked to subliminal. Hence they must be written
+in the provider module.
+
+Per-user authentication is allowed and must be configured at instantiation as keyword arguments. Configuration
+will be done by the user through the `provider_configs` argument of the :func:`~subliminal.api.list_subtitles` and
+:func:`~subliminal.api.download_best_subtitles` functions. No network operation must be done during instantiation,
+only configuration. Any error in the configuration must raise a
+:class:`~subliminal.exceptions.ProviderConfigurationError`.
+
+
+Beyond this point, if a network error occurs, a :class:`~subliminal.exceptions.ProviderNotAvailable` exception 
+must be raised and an unexpected behavior must raise a :class:`~subliminal.exceptions.ProviderError` exception.
+
+
+Initialization / Termination
+----------------------------
+Actual authentication operations must take place in the :meth:`~subliminal.providers.Provider.initialize` method.
+If you need anything to be executed when the provider isn't used anymore like logout,
+use :meth:`~subliminal.providers.Provider.terminate`.
+
+
+Caching policy
+--------------
+To save bandwidth and improve querying time, intermediate data should be cached when possible. Typical use case is
+when a query to retrieve show ids is required prior to the query to actually search for subtitles. In that case
+the function that gets the show id from the show name must be cached. 
+
+
+Language
+--------
+To be able to handle various language codes, subliminal makes use of `babelfish <http://babelfish.readthedocs.org>`_
+Language and converters. You must set the attribute :attr:`~subliminal.providers.Provider.languages` with a set of
+supported :class:`babelfish.Language`.
+
+If you cannot find a suitable converter for your provider, you can `make one of your own
+<http://babelfish.readthedocs.org/en/latest/#custom-converters>`_.
+
+
+Querying
+--------
+The :meth:`~subliminal.providers.Provider.query` method parameters must include all aspects of provider's querying with
+simple types.
+
+
+Subtitle
+--------
+A custom :class:`~subliminal.subtitle.Subtitle` subclass must be created to represent a subtitle from the provider.
+It must have relevant attributes that can be used to compute the matches of the subtitle against a
+:class:`~subliminal.video.Video` object.
+
+
+Score computation
+-----------------
+
+To be able to compare subtitles coming from different providers between them, the
+:meth:`~subliminal.subtitle.Subtitle.compute_matches` method must be implemented.
+If `guessit <http://guessit.readthedocs.org>`_ is used to extract data from the
+:class:`~subliminal.subtitle.Subtitle` subclass, you can use :func:`~subliminal.subtitle.compute_guess_matches`
+as a helper to compute matches between the :class:`~subliminal.video.Video` and the :class:`guessit.Guess`.
+
+Refer to the `scores` attribute of  :class:`~subliminal.video.Episode` and :class:`~subliminal.video.Movie`
+for a list of possible matches.
+
+
+Unittesting
+-----------
+All possible uses of the :meth:`~subliminal.providers.Provider.query` method must be unittested including the uses
+that produce exceptions other than :class:`~subliminal.exceptions.ProviderNotAvailable`.
+The :meth:`~subliminal.subtitle.Subtitle.compute_matches` is used to validate the unittests.
+
+As it is not possible to unittest all uses of the :meth:`~subliminal.providers.Provider.list_subtitles`
+and :meth:`~subliminal.providers.Provider.download_subtitle` methods, unitests are only required to cover most common
+use cases.
+
+See existing unittests for more details on how to proceed.

docs/user.rst

@@ -1,113 +0,0 @@
-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 that are represented with their extended ISO 639-1 code.
-The current extensions to the ISO 639-1 are:
-
-* *po* for Brazilian Portuguese
-
-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 basic Command Line Interface that allows you to
-download subtitles for one or more videos in a multi-threaded way.
-
-You can have the documentation of the CLI using ``subliminal --help``::
-
-    usage: subliminal [-h] [-l LG] [-s NAME] [-m] [-f] [-w N] [-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)
-      -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
-
-.. note::
-
-    The cache directory defaults to *~/.config/subliminal*. Even on Windows
-
-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'])
-
-
-* from the command line
-* basic functions :func:`~subliminal.list_subtitles` and :func:`~subliminal.download_subtitles`
-* multi-threaded :class:`~subliminal.async.Pool` which implements the abovementioned functions
-* using your own algorithm that produces and gather results of elementary :class:`~subliminal.tasks.Task`

requirements.txt

@@ -1,4 +1,9 @@
-BeautifulSoup>=3.2.0
-guessit>=0.2
-requests
-enzyme>=0.1
+beautifulsoup4>=4.3.2
+guessit>=0.6.1
+requests>=2.0.1
+enzyme>=0.4.0
+html5lib>=0.99
+dogpile.cache>=0.5.1
+babelfish>=0.2.1
+charade>=1.0.3
+pysrt>=0.5.0

scripts/subliminal

@@ -1,79 +0,0 @@
-#!/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/>.
-import argparse
-import subliminal
-import logging
-import os
-import sys
-
-
-def main():
-    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', 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', default=4)
-    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()
-
-    # 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)
-
-    # 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:
-        subtitles = p.download_subtitles(paths, languages=args.languages,
-                             services=args.services, cache_dir=args.cache_dir,
-                             force=args.force, multi=args.multi)
-
-    if not subtitles:
-        if not args.quiet:
-            sys.stderr.write('No subtitles found\n')
-        exit(1)
-    if not args.quiet:
-        print '*' * 50
-        print 'Downloaded %d subtitles' % len(subtitles)
-        for subtitle in subtitles:
-            print subtitle
-        print '*' * 50
-
-
-if __name__ == '__main__':
-    main()

setup.py

@@ -1,46 +1,38 @@
 #!/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/>.
-import os.path
 from setuptools import setup, find_packages
 
 
-def read(fname):
-    return open(os.path.join(os.path.dirname(__file__), fname)).read()
-
-execfile(os.path.join(os.path.dirname(__file__), 'subliminal', 'infos.py'))
 setup(name='subliminal',
-    version=__version__,
-    license='LGPLv3',
+    version='0.7.1',
+    license='MIT',
     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'],
+    long_description=open('README.rst').read() + '\n\n' + open('HISTORY.rst').read(),
     keywords='subtitle subtitles video movie episode tv show',
+    url='https://github.com/Diaoul/subliminal',
     author='Antoine Bertin',
     author_email='diaoulael@gmail.com',
-    url='https://github.com/Diaoul/subliminal',
     packages=find_packages(),
-    scripts=['scripts/subliminal'],
-    install_requires=['BeautifulSoup >= 3.2.0', 'guessit >= 0.2', 'requests', 'enzyme >= 0.1'])
+    classifiers=['Development Status :: 4 - Beta',
+        'Intended Audience :: Developers',
+        'License :: OSI Approved :: MIT License',
+        'Operating System :: OS Independent',
+        'Programming Language :: Python',
+        'Programming Language :: Python :: 2',
+        'Programming Language :: Python :: 2.7',
+        'Programming Language :: Python :: 3',
+        'Programming Language :: Python :: 3.3',
+        'Topic :: Software Development :: Libraries :: Python Modules',
+        'Topic :: Multimedia :: Video'],
+    entry_points={
+        'console_scripts': ['subliminal = subliminal.cli:subliminal'],
+        'subliminal.providers': ['addic7ed = subliminal.providers.addic7ed:Addic7edProvider',
+                                 'bierdopje = subliminal.providers.bierdopje:BierDopjeProvider',
+                                 'opensubtitles = subliminal.providers.opensubtitles:OpenSubtitlesProvider',
+                                 'thesubdb = subliminal.providers.thesubdb:TheSubDBProvider',
+                                 'tvsubtitles = subliminal.providers.tvsubtitles:TVsubtitlesProvider'],
+        'babelfish.converters': ['addic7ed = subliminal.converters.addic7ed:Addic7edConverter',
+                                 'tvsubtitles = subliminal.converters.tvsubtitles:TVsubtitlesConverter']
+    },
+    install_requires=open('requirements.txt').readlines(),
+    test_suite='subliminal.tests.suite')

subliminal/__init__.py

@@ -1,34 +1,16 @@
 # -*- 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 .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__
+__title__ = 'subliminal'
+__version__ = '0.7.1'
+__author__ = 'Antoine Bertin'
+__license__ = 'MIT'
+__copyright__ = 'Copyright 2013 Antoine Bertin'
+
 import logging
-try:
-    from logging import NullHandler
-except ImportError:
-    class NullHandler(logging.Handler):
-        def emit(self, record):
-            pass
+from .api import PROVIDERS_ENTRY_POINT, list_subtitles, download_subtitles, download_best_subtitles
+from .cache import region as cache_region
+from .exceptions import Error, ProviderError, ProviderConfigurationError, ProviderNotAvailable, InvalidSubtitle
+from .subtitle import Subtitle
+from .video import VIDEO_EXTENSIONS, SUBTITLE_EXTENSIONS, Video, Episode, Movie, scan_videos, scan_video
 
 
-__all__ = ['SERVICES', 'LANGUAGE_INDEX', 'SERVICE_INDEX', 'SERVICE_CONFIDENCE',
-           'MATCHING_CONFIDENCE', 'list_subtitles', 'download_subtitles', 'Pool']
-logging.getLogger(__name__).addHandler(NullHandler())
+logging.getLogger(__name__).addHandler(logging.NullHandler())

subliminal/api.py

@@ -1,100 +1,276 @@
 # -*- 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 .languages import list_languages
+from __future__ import unicode_literals
+import collections
+import io
 import logging
+import operator
+import babelfish
+import pkg_resources
+from .exceptions import ProviderNotAvailable, InvalidSubtitle
+from .subtitle import get_subtitle_path
 
 
-__all__ = ['list_subtitles', 'download_subtitles']
 logger = logging.getLogger(__name__)
 
+#: Entry point for the providers
+PROVIDERS_ENTRY_POINT = 'subliminal.providers'
 
-def list_subtitles(paths, languages=None, services=None, force=True, multi=False, cache_dir=None, max_depth=3):
-    """List subtitles in given paths according to the criteria
 
-    :param paths: path(s) to video file or folder
-    :type paths: string or list
-    :param list languages: languages to search for, in preferred order
-    :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
+def list_subtitles(videos, languages, providers=None, provider_configs=None):
+    """List subtitles for `videos` with the given `languages` using the specified `providers`
+
+    :param videos: videos to list subtitles for
+    :type videos: set of :class:`~subliminal.video.Video`
+    :param languages: languages of subtitles to search for
+    :type languages: set of :class:`babelfish.Language`
+    :param providers: providers to use for the search, if not all
+    :type providers: list of string or None
+    :param provider_configs: configuration for providers
+    :type provider_configs: dict of provider name => provider constructor kwargs
     :return: found subtitles
-    :rtype: dict of :class:`~subliminal.videos.Video` => [:class:`~subliminal.subtitles.ResultSubtitle`]
+    :rtype: dict of :class:`~subliminal.video.Video` => [:class:`~subliminal.subtitle.Subtitle`]
 
     """
-    services = services or SERVICES
-    languages = set(languages or list_languages(1))
-    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)
-    for task in tasks:
+    provider_configs = provider_configs or {}
+    subtitles = collections.defaultdict(list)
+    # filter videos
+    videos = [v for v in videos if v.subtitle_languages & languages < languages]
+    if not videos:
+        logger.info('No video to download subtitles for with languages %r', languages)
+        return subtitles
+    subtitle_languages = set.intersection(*[v.subtitle_languages for v in videos])
+    for provider_entry_point in pkg_resources.iter_entry_points(PROVIDERS_ENTRY_POINT):
+        # filter and initialize provider
+        if providers is not None and provider_entry_point.name not in providers:
+            logger.debug('Skipping provider %r: not in the list', provider_entry_point.name)
+            continue
+        Provider = provider_entry_point.load()
+        provider_languages = Provider.languages & languages - subtitle_languages
+        if not provider_languages:
+            logger.debug('Skipping provider %r: no language to search for', provider_entry_point.name)
+            continue
+        provider_videos = [v for v in videos if Provider.check(v)]
+        if not provider_videos:
+            logger.debug('Skipping provider %r: no video to search for', provider_entry_point.name)
+            continue
+
+        # list subtitles with the provider
         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)
+            with Provider(**provider_configs.get(provider_entry_point.name, {})) as provider:
+                for provider_video in provider_videos:
+                    provider_video_languages = provider_languages - provider_video.subtitle_languages
+                    if not provider_video_languages:
+                        logger.debug('Skipping provider %r: no language to search for for video %r',
+                                     provider_entry_point.name, provider_video)
+                        continue
+                    logger.info('Listing subtitles with provider %r for video %r with languages %r',
+                                provider_entry_point.name, provider_video, provider_video_languages)
+                    try:
+                        provider_subtitles = provider.list_subtitles(provider_video, provider_video_languages)
+                    except ProviderNotAvailable:
+                        logger.warning('Provider %r is not available, discarding it', provider_entry_point.name)
+                        break
+                    except:
+                        logger.exception('Unexpected error in provider %r', provider_entry_point.name)
+                        continue
+                    logger.info('Found %d subtitles', len(provider_subtitles))
+                    subtitles[provider_video].extend(provider_subtitles)
+        except ProviderNotAvailable:
+            logger.warning('Provider %r is not available, discarding it', provider_entry_point.name)
+    return subtitles
 
 
-def download_subtitles(paths, languages=None, services=None, force=True, multi=False, cache_dir=None, max_depth=3, order=None):
-    """Download subtitles in given paths according to the criteria
+def download_subtitles(subtitles, provider_configs=None, single=False):
+    """Download subtitles
 
-    :param paths: path(s) to video file or folder
-    :type paths: string or list
-    :param list languages: languages to search for, in preferred order
-    :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 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: found subtitles
-    :rtype: list of (:class:`~subliminal.videos.Video`, [:class:`~subliminal.subtitles.ResultSubtitle`])
+    :param subtitles: subtitles to download
+    :type subtitles: dict of :class:`~subliminal.video.Video` => [:class:`~subliminal.subtitle.Subtitle`]
+    :param provider_configs: configuration for providers
+    :type provider_configs: dict of provider name => provider constructor kwargs
+    :param bool single: download with .srt extension if `True`, add language identifier otherwise
 
     """
-    services = services or SERVICES
-    languages = languages or list_languages(1)
-    if isinstance(paths, basestring):
-        paths = [paths]
-    order = order or [LANGUAGE_INDEX, SERVICE_INDEX, SERVICE_CONFIDENCE, MATCHING_CONFIDENCE]
-    subtitles_by_video = list_subtitles(paths, set(languages), services, force, multi, cache_dir, max_depth)
-    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, multi)
-    for task in tasks:
+    provider_configs = provider_configs or {}
+    discarded_providers = set()
+    providers_by_name = {ep.name: ep.load() for ep in pkg_resources.iter_entry_points(PROVIDERS_ENTRY_POINT)}
+    initialized_providers = {}
+    try:
+        for video, video_subtitles in subtitles.items():
+            languages = {subtitle.language for subtitle in video_subtitles}
+            downloaded_languages = set()
+            for subtitle in video_subtitles:
+                # filter
+                if subtitle.language in downloaded_languages:
+                    continue
+                if subtitle.provider_name in discarded_providers:
+                    logger.debug('Skipping subtitle from discarded provider %r', subtitle.provider_name)
+                    continue
+
+                # initialize provider
+                if subtitle.provider_name in initialized_providers:
+                    provider = initialized_providers[subtitle.provider_name]
+                else:
+                    provider = providers_by_name[subtitle.provider_name](**provider_configs.get(subtitle.provider_name, {}))
+                    try:
+                        provider.initialize()
+                    except ProviderNotAvailable:
+                        logger.warning('Provider %r is not available, discarding it', subtitle.provider_name)
+                        discarded_providers.add(subtitle.provider_name)
+                        continue
+                    initialized_providers[subtitle.provider_name] = provider
+
+                # download subtitles
+                subtitle_path = get_subtitle_path(video.name, None if single else subtitle.language)
+                logger.info('Downloading subtitle %r into %r', subtitle, subtitle_path)
+                try:
+                    subtitle_text = provider.download_subtitle(subtitle)
+                except ProviderNotAvailable:
+                    logger.warning('Provider %r is not available, discarding it', subtitle.provider_name)
+                    discarded_providers.add(subtitle.provider_name)
+                    continue
+                except InvalidSubtitle:
+                    logger.info('Invalid subtitle, skipping it')
+                    continue
+                except:
+                    logger.exception('Unexpected error in provider %r', subtitle.provider_name)
+                    continue
+                with io.open(subtitle_path, 'w', encoding='utf-8') as f:
+                    f.write(subtitle_text)
+                downloaded_languages.add(subtitle.language)
+                if single or downloaded_languages == languages:
+                    break
+    finally:  # terminate providers
+        for (provider_name, provider) in initialized_providers.items():
+            try:
+                provider.terminate()
+            except ProviderNotAvailable:
+                logger.warning('Provider %r is not available, unable to terminate', provider_name)
+            except:
+                logger.exception('Unexpected error in provider %r', provider_name)
+
+
+def download_best_subtitles(videos, languages, providers=None, provider_configs=None, single=False, min_score=0,
+                            hearing_impaired=False):
+    """Download the best subtitles for `videos` with the given `languages` using the specified `providers`
+
+    :param videos: videos to download subtitles for
+    :type videos: set of :class:`~subliminal.video.Video`
+    :param languages: languages of subtitles to download
+    :type languages: set of :class:`babelfish.Language`
+    :param providers: providers to use for the search, if not all
+    :type providers: list of string or None
+    :param provider_configs: configuration for providers
+    :type provider_configs: dict of provider name => provider constructor kwargs
+    :param bool single: download with .srt extension if `True`, add language identifier otherwise
+    :param int min_score: minimum score for subtitles to download
+    :param bool hearing_impaired: download hearing impaired subtitles
+
+    """
+    provider_configs = provider_configs or {}
+    discarded_providers = set()
+    downloaded_subtitles = collections.defaultdict(list)
+    # filter videos
+    videos = [v for v in videos if v.subtitle_languages & languages < languages
+              and (not single or babelfish.Language('und') not in v.subtitle_languages)]
+    if not videos:
+        logger.info('No video to download subtitles for with languages %r', languages)
+        return downloaded_subtitles
+    # filter and initialize providers
+    subtitle_languages = set.intersection(*[v.subtitle_languages for v in videos])
+    initialized_providers = {}
+    for provider_entry_point in pkg_resources.iter_entry_points(PROVIDERS_ENTRY_POINT):
+        if providers is not None and provider_entry_point.name not in providers:
+            logger.debug('Skipping provider %r: not in the list', provider_entry_point.name)
+            continue
+        Provider = provider_entry_point.load()
+        if not Provider.languages & languages - subtitle_languages:
+            logger.debug('Skipping provider %r: no language to search for', provider_entry_point.name)
+            continue
+        if not [v for v in videos if Provider.check(v)]:
+            logger.debug('Skipping provider %r: no video to search for', provider_entry_point.name)
+            continue
+        provider = Provider(**provider_configs.get(provider_entry_point.name, {}))
         try:
-            result = consume_task(task, service_instances)
-            results.append(result)
-        except:
-            logger.error(u'Error consuming task %r' % task, exc_info=True)
-    for service_instance in service_instances.itervalues():
-        service_instance.terminate()
-    return results
+            provider.initialize()
+        except ProviderNotAvailable:
+            logger.warning('Provider %r is not available, discarding it', provider_entry_point.name)
+            continue
+        initialized_providers[provider_entry_point.name] = provider
+    try:
+        for video in videos:
+            # search for subtitles
+            subtitles = []
+            for provider_name, provider in initialized_providers.items():
+                if provider.check(video):
+                    if provider_name in discarded_providers:
+                        logger.debug('Skipping discarded provider %r', provider_name)
+                        continue
+                    provider_video_languages = provider.languages & languages - video.subtitle_languages
+                    if not provider_video_languages:
+                        logger.debug('Skipping provider %r: no language to search for for video %r', provider_name,
+                                     video)
+                        continue
+                    logger.info('Listing subtitles with provider %r for video %r with languages %r',
+                                provider_name, video, provider_video_languages)
+                    try:
+                        provider_subtitles = provider.list_subtitles(video, provider_video_languages)
+                    except ProviderNotAvailable:
+                        logger.warning('Provider %r is not available, discarding it', provider_name)
+                        discarded_providers.add(provider_name)
+                        continue
+                    except:
+                        logger.exception('Unexpected error in provider %r', provider_name)
+                        continue
+                    logger.info('Found %d subtitles', len(provider_subtitles))
+                    subtitles.extend(provider_subtitles)
+
+            # find the best subtitles and download them
+            downloaded_languages = video.subtitle_languages.copy()
+            for subtitle, score in sorted([(s, s.compute_score(video)) for s in subtitles],
+                                          key=operator.itemgetter(1), reverse=True):
+                # filter
+                if subtitle.provider_name in discarded_providers:
+                    logger.debug('Skipping subtitle from discarded provider %r', subtitle.provider_name)
+                    continue
+                if subtitle.hearing_impaired != hearing_impaired:
+                    logger.debug('Skipping subtitle: hearing impaired != %r', hearing_impaired)
+                    continue
+                if score < min_score:
+                    logger.debug('Skipping subtitle: score < %d', min_score)
+                    continue
+                if subtitle.language in downloaded_languages:
+                    logger.debug('Skipping subtitle: %r already downloaded', subtitle.language)
+                    continue
+
+                # download
+                provider = initialized_providers[subtitle.provider_name]
+                subtitle_path = get_subtitle_path(video.name, None if single else subtitle.language)
+                logger.info('Downloading subtitle %r with score %d into %r', subtitle, score, subtitle_path)
+                try:
+                    subtitle_text = provider.download_subtitle(subtitle)
+                    downloaded_subtitles[video].append(subtitle)
+                except ProviderNotAvailable:
+                    logger.warning('Provider %r is not available, discarding it', subtitle.provider_name)
+                    discarded_providers.add(subtitle.provider_name)
+                    continue
+                except InvalidSubtitle:
+                    logger.info('Invalid subtitle, skipping it')
+                    continue
+                except:
+                    logger.exception('Unexpected error in provider %r', subtitle.provider_name)
+                    continue
+                with io.open(subtitle_path, 'w', encoding='utf-8') as f:
+                    f.write(subtitle_text)
+                downloaded_languages.add(subtitle.language)
+                if single or downloaded_languages >= languages:
+                    logger.debug('All languages downloaded')
+                    break
+    finally:  # terminate providers
+        for (provider_name, provider) in initialized_providers.items():
+            try:
+                provider.terminate()
+            except ProviderNotAvailable:
+                logger.warning('Provider %r is not available, unable to terminate', provider_name)
+            except:
+                logger.exception('Unexpected error in provider %r', provider_name)
+    return downloaded_subtitles

subliminal/async.py

@@ -1,141 +0,0 @@
-# -*- 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 .languages import list_languages
-from .tasks import StopTask
-import Queue
-import logging
-import threading
-
-
-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):
-        """See :meth:`subliminal.list_subtitles`"""
-        services = services or SERVICES
-        languages = set(languages or list_languages(1))
-        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)
-        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, cache_dir=None, max_depth=3, force=True, multi=False, order=None):
-        """See :meth:`subliminal.download_subtitles`"""
-        services = services or SERVICES
-        languages = languages or list_languages(1)
-        if isinstance(paths, basestring):
-            paths = [paths]
-        order = order or [LANGUAGE_INDEX, SERVICE_INDEX, SERVICE_CONFIDENCE, MATCHING_CONFIDENCE]
-        subtitles_by_video = self.list_subtitles(paths, set(languages), services, force, multi, cache_dir, max_depth)
-        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, multi)
-        for task in tasks:
-            self.tasks.put(task)
-        self.join()
-        results = self.collect()
-        return results

subliminal/cache.py

@@ -0,0 +1,6 @@
+# -*- coding: utf-8 -*-
+import dogpile.cache
+
+
+#: The subliminal's dogpile.cache region
+region = dogpile.cache.make_region()

subliminal/cli.py

@@ -0,0 +1,166 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals, print_function
+import argparse
+import datetime
+import logging
+import os
+import re
+import sys
+import babelfish
+import guessit
+import pkg_resources
+from subliminal import (__version__, PROVIDERS_ENTRY_POINT, cache_region, Video, Episode, Movie, scan_videos,
+    download_best_subtitles)
+try:
+    import colorlog
+except ImportError:
+    colorlog = None
+
+
+DEFAULT_CACHE_FILE = os.path.join('~', '.config', 'subliminal.cache.dbm')
+
+
+def subliminal():
+    parser = argparse.ArgumentParser(prog='subliminal', description='Subtitles, faster than your thoughts',
+                                     epilog='Suggestions and bug reports are greatly appreciated: '
+                                     'https://github.com/Diaoul/subliminal/issues', add_help=False)
+
+    # required arguments
+    required_arguments_group = parser.add_argument_group('required arguments')
+    required_arguments_group.add_argument('paths', nargs='+', metavar='PATH', help='path to video file or folder')
+    required_arguments_group.add_argument('-l', '--languages', nargs='+', required=True, metavar='LANGUAGE',
+                                          help='wanted languages as alpha2 code (ISO-639-1)')
+
+    # configuration
+    configuration_group = parser.add_argument_group('configuration')
+    configuration_group.add_argument('-s', '--single', action='store_true',
+                                     help='download without language code in subtitle\'s filename i.e. .srt only')
+    configuration_group.add_argument('-c', '--cache-file', default=DEFAULT_CACHE_FILE,
+                                     help='cache file (default: %(default)s)')
+
+    # filtering
+    filtering_group = parser.add_argument_group('filtering')
+    providers = [ep.name for ep in pkg_resources.iter_entry_points(PROVIDERS_ENTRY_POINT)]
+    filtering_group.add_argument('-p', '--providers', nargs='+', metavar='PROVIDER',
+                                 help='providers to use (%s)' % ', '.join(providers))
+    filtering_group.add_argument('-m', '--min-score', type=int,
+                                 help='minimum score for subtitles (0-%d for episodes, 0-%d for movies)'
+                                 % (Episode.scores['hash'], Movie.scores['hash']))
+    filtering_group.add_argument('-a', '--age', help='download subtitles for videos newer than AGE e.g. 12h, 1w2d')
+    filtering_group.add_argument('-h', '--hearing-impaired', action='store_true',
+                                 help='download hearing impaired subtitles')
+    filtering_group.add_argument('-f', '--force', action='store_true',
+                                 help='force subtitle download for videos with existing subtitles')
+
+    # addic7ed
+    addic7ed_group = parser.add_argument_group('addic7ed')
+    addic7ed_group.add_argument('--addic7ed-username', metavar='USERNAME', help='username for addic7ed provider')
+    addic7ed_group.add_argument('--addic7ed-password', metavar='PASSWORD', help='password for addic7ed provider')
+
+    # output
+    output_group = parser.add_argument_group('output')
+    output_exclusive_group = output_group.add_mutually_exclusive_group()
+    output_exclusive_group.add_argument('-q', '--quiet', action='store_true', help='disable output')
+    output_exclusive_group.add_argument('-v', '--verbose', action='store_true', help='verbose output')
+    output_group.add_argument('--color', action='store_true', help='add color to console output (requires colorlog)')
+
+    # troubleshooting
+    troubleshooting_group = parser.add_argument_group('troubleshooting')
+    troubleshooting_group.add_argument('--debug', action='store_true', help='debug output')
+    troubleshooting_group.add_argument('--version', action='version', version=__version__)
+    troubleshooting_group.add_argument('--help', action='help', help='show this help message and exit')
+
+    # parse args
+    args = parser.parse_args()
+
+    # parse paths
+    try:
+        args.paths = [os.path.abspath(os.path.expanduser(p.decode('utf-8'))) for p in args.paths]
+    except UnicodeDecodeError:
+        parser.error('argument paths: encodings is not utf-8: %r' % args.paths)
+
+    # parse languages
+    try:
+        args.languages = {babelfish.Language.fromalpha2(l) for l in args.languages}
+    except babelfish.Error:
+        parser.error('argument -l/--languages: codes are not ISO-639-1: %r' % args.languages)
+
+    # parse age
+    if args.age is not None:
+        match = re.match(r'^(?:(?P<weeks>\d+?)w)?(?:(?P<days>\d+?)d)?(?:(?P<hours>\d+?)h)?$', args.age)
+        if not match:
+            parser.error('argument -a/--age: invalid age: %r' % args.age)
+        args.age = datetime.timedelta(**{k: int(v) for k, v in match.groupdict(0).items()})
+
+    # parse cache-file
+    args.cache_file = os.path.abspath(os.path.expanduser(args.cache_file))
+    if not os.path.exists(os.path.split(args.cache_file)[0]):
+        parser.error('argument -c/--cache-file: directory %r for cache file does not exist'
+                     % os.path.split(args.cache_file)[0])
+
+    # parse provider configs
+    provider_configs = {}
+    if (args.addic7ed_username is not None and args.addic7ed_password is None
+        or args.addic7ed_username is None and args.addic7ed_password is not None):
+        parser.error('argument --addic7ed-username/--addic7ed-password: both arguments are required or none')
+    if args.addic7ed_username is not None and args.addic7ed_password is not None:
+        provider_configs['addic7ed'] = {'username': args.addic7ed_username, 'password': args.addic7ed_password}
+
+    # parse color
+    if args.color and colorlog is None:
+        parser.error('argument --color: colorlog required')
+
+    # setup output
+    if args.debug:
+        handler = logging.StreamHandler()
+        if args.color:
+            handler.setFormatter(colorlog.ColoredFormatter('%(log_color)s%(levelname)-8s%(reset)s [%(blue)s%(name)s-%(funcName)s:%(lineno)d%(reset)s] %(message)s',
+                                                           log_colors=dict(colorlog.default_log_colors.items() + [('DEBUG', 'cyan')])))
+        else:
+            handler.setFormatter(logging.Formatter('%(levelname)-8s [%(name)s-%(funcName)s:%(lineno)d] %(message)s'))
+        logging.getLogger().addHandler(handler)
+        logging.getLogger().setLevel(logging.DEBUG)
+    elif args.verbose:
+        handler = logging.StreamHandler()
+        if args.color:
+            handler.setFormatter(colorlog.ColoredFormatter('%(log_color)s%(levelname)-8s%(reset)s [%(blue)s%(name)s%(reset)s] %(message)s'))
+        else:
+            handler.setFormatter(logging.Formatter('%(levelname)-8s [%(name)s] %(message)s'))
+        logging.getLogger('subliminal').addHandler(handler)
+        logging.getLogger('subliminal').setLevel(logging.INFO)
+    elif not args.quiet:
+        handler = logging.StreamHandler()
+        if args.color:
+            handler.setFormatter(colorlog.ColoredFormatter('[%(log_color)s%(levelname)s%(reset)s] %(message)s'))
+        else:
+            handler.setFormatter(logging.Formatter('%(levelname)s: %(message)s'))
+        logging.getLogger('subliminal.api').addHandler(handler)
+        logging.getLogger('subliminal.api').setLevel(logging.INFO)
+
+    # configure cache
+    cache_region.configure('dogpile.cache.dbm', arguments={'filename': args.cache_file})
+
+    # scan videos
+    videos = scan_videos([p for p in args.paths if os.path.exists(p)], subtitles=not args.force,
+                         embedded_subtitles=not args.force, age=args.age)
+
+    # guess videos
+    videos.extend([Video.fromguess(os.path.split(p)[1], guessit.guess_file_info(p, 'autodetect')) for p in args.paths
+                   if not os.path.exists(p)])
+
+    # download best subtitles
+    subtitles = download_best_subtitles(videos, args.languages, providers=args.providers,
+                                        provider_configs=provider_configs, single=args.single,
+                                        min_score=args.min_score, hearing_impaired=args.hearing_impaired)
+
+    # result output
+    if not subtitles:
+        if not args.quiet:
+            sys.stderr.write('No subtitles downloaded\n')
+        exit(1)
+    if not args.quiet:
+        subtitles_count = sum([len(s) for s in subtitles.values()])
+        if subtitles_count == 1:
+            print('%d subtitle downloaded' % subtitles_count)
+        else:
+            print('%d subtitles downloaded' % subtitles_count)

subliminal/converters/addic7ed.py

@@ -0,0 +1,29 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+from babelfish.converters.name import NameConverter
+
+
+class Addic7edConverter(NameConverter):
+    def __init__(self):
+        super(Addic7edConverter, self).__init__()
+        self.from_addic7ed = {'Català': ('cat', None), 'Chinese (Simplified)': ('zho', None),
+                              'Chinese (Traditional)': ('zho', None), 'Euskera': ('eus', None),
+                              'Galego': ('glg', None), 'Greek': ('ell', None),
+                              'Malay': ('msa', None), 'Portuguese (Brazilian)': ('por', 'BR'),
+                              'Serbian (Cyrillic)': ('srp', None), 'Serbian (Latin)': ('srp', None),
+                              'Spanish (Latin America)': ('spa', None), 'Spanish (Spain)': ('spa', None)}
+        self.to_addic7ed = {('cat', None): 'Català', ('zho', None): 'Chinese (Simplified)',
+                            ('eus', None): 'Euskera', ('glg', None): 'Galego',
+                            ('ell', None): 'Greek', ('msa', None): 'Malay',
+                            ('por', 'BR'): 'Portuguese (Brazilian)', ('srp', None): 'Serbian (Cyrillic)'}
+        self.codes |= set(self.from_addic7ed.keys())
+
+    def convert(self, alpha3, country=None):
+        if (alpha3, country) in self.to_addic7ed:
+            return self.to_addic7ed[(alpha3, country)]
+        return super(Addic7edConverter, self).convert(alpha3, country)
+
+    def reverse(self, addic7ed):
+        if addic7ed in self.from_addic7ed:
+            return self.from_addic7ed[addic7ed]
+        return super(Addic7edConverter, self).reverse(addic7ed)

subliminal/converters/tvsubtitles.py

@@ -0,0 +1,22 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+from babelfish.converters.alpha2 import Alpha2Converter
+
+
+class TVsubtitlesConverter(Alpha2Converter):
+    def __init__(self):
+        super(TVsubtitlesConverter, self).__init__()
+        self.from_tvsubtitles = {'br': ('por', 'BR'), 'ua': ('ukr', None), 'gr': ('ell', None), 'cn': ('zho', None),
+                                 'jp': ('jpn', None), 'cz': ('ces', None)}
+        self.to_tvsubtitles = {v: k for k, v in self.from_tvsubtitles}
+        self.codes |= set(self.from_tvsubtitles.keys())
+
+    def convert(self, alpha3, country=None):
+        if (alpha3, country) in self.to_tvsubtitles:
+            return self.to_tvsubtitles[(alpha3, country)]
+        return super(TVsubtitlesConverter, self).convert(alpha3, country)
+
+    def reverse(self, tvsubtitles):
+        if tvsubtitles in self.from_tvsubtitles:
+            return self.from_tvsubtitles[tvsubtitles]
+        return super(TVsubtitlesConverter, self).reverse(tvsubtitles)

subliminal/core.py

@@ -1,240 +0,0 @@
-# -*- 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 collections import defaultdict
-from itertools import groupby
-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']
-LANGUAGE_INDEX, SERVICE_INDEX, SERVICE_CONFIDENCE, MATCHING_CONFIDENCE = range(4)
-
-
-def create_list_tasks(paths, languages, services, force, multi, cache_dir, max_depth):
-    """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
-    :return: the created tasks
-    :rtype: list of :class:`~subliminal.tasks.ListTask`
-
-    """
-    scan_result = []
-    for p in paths:
-        scan_result.extend(scan(p, max_depth))
-    logger.debug(u'Found %d videos in %r with maximum depth %d' % (len(scan_result), paths, max_depth))
-    tasks = []
-    config = ServiceConfig(multi, cache_dir)
-    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 None 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
-            service_languages = wanted_languages & service.available_languages()
-            if not service_languages:
-                logger.debug(u'Skipping %r: none of wanted languages %r available for service %s' % (video, wanted_languages, service_name))
-                continue
-            if not service.is_valid_video(video):
-                logger.debug(u'Skipping %r: not part of supported videos %r for service %s' % (video, service.videos, service_name))
-                continue
-            task = ListTask(video, service_languages, service_name, config)
-            logger.debug(u'Created task %r' % task)
-            tasks.append(task)
-    return tasks
-
-
-def create_download_tasks(subtitles_by_video, 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 grouped by video and sorted
-    :type subtitles_by_video: dict of :class:`~subliminal.videos.Video` => [:class:`~subliminal.subtitles.Subtitle`]
-    :param order: preferred order for subtitles sorting
-    :type list: list of :data:`LANGUAGE_INDEX`, :data:`SERVICE_INDEX`, :data:`SERVICE_CONFIDENCE`, :data:`MATCHING_CONFIDENCE`
-    :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: 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` or :class:`~subliminal.subtitles.Subtitle`
-
-    """
-    if services is None:
-        services = {}
-    logger.info(u'Consuming %r' % task)
-    result = None
-    if isinstance(task, ListTask):
-        if task.service not in services:
-            mod = __import__('services.' + task.service, globals=globals(), locals=locals(), fromlist=['Service'], level=-1)
-            services[task.service] = mod.Service(task.config)
-            services[task.service].init()
-        subtitles = services[task.service].list(task.video, task.languages)
-        result = subtitles
-    elif isinstance(task, DownloadTask):
-        for subtitle in task.subtitles:
-            if subtitle.service not in services:
-                mod = __import__('services.' + subtitle.service, globals=globals(), locals=locals(), fromlist=['Service'], level=-1)
-                services[subtitle.service] = mod.Service()
-                services[subtitle.service].init()
-            try:
-                services[subtitle.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
-    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:
-        return 0
-    confidence = float(int(matching_format.format(**replacement), 2)) / float(int(best, 2))
-    return confidence
-
-
-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)
-        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
-    return result

subliminal/exceptions.py

@@ -1,20 +1,5 @@
 # -*- 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 __future__ import unicode_literals
 
 
 class Error(Exception):
@@ -22,60 +7,21 @@ class Error(Exception):
     pass
 
 
-class InvalidLanguageError(Error):
-    """Exception raised when invalid language is submitted
-
-    Attributes:
-        language -- language that cause the error
-    """
-    def __init__(self, language):
-        self.language = language
-
-    def __str__(self):
-        return self.language
-
-
-class MissingLanguageError(Error):
-    """Exception raised when a missing language is found
-
-    Attributes:
-        language -- the missing language
-    """
-    def __init__(self, language):
-        self.language = language
-
-    def __str__(self):
-        return self.language
-
-
-class InvalidServiceError(Error):
-    """Exception raised when invalid service is submitted
-
-    :param string service: service that causes the error
-
-    """
-    def __init__(self, service):
-        self.service = service
-
-    def __str__(self):
-        return self.service
-
-
-class ServiceError(Error):
-    """"Exception raised by services"""
+class ProviderError(Error):
+    """Exception raised by providers"""
     pass
 
 
-class WrongTaskError(Error):
-    """"Exception raised when invalid task is submitted"""
+class ProviderConfigurationError(ProviderError):
+    """Exception raised by providers when badly configured"""
     pass
 
 
-class DownloadFailedError(Error):
-    """"Exception raised when a download task has failed in service"""
+class ProviderNotAvailable(ProviderError):
+    """Exception raised by providers when unavailable"""
     pass
 
 
-class UnknownVideoError(Error):
-    """"Exception raised when a video could not be identified"""
+class InvalidSubtitle(ProviderError):
+    """Exception raised by providers when the downloaded subtitle is invalid"""
     pass

subliminal/infos.py

@@ -1,18 +0,0 @@
-# -*- 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__ = '0.5'

subliminal/languages.py

@@ -1,547 +0,0 @@
-# -*- 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__ = ['convert_language', 'list_languages', 'LANGUAGES']
-
-
-def convert_language(language, to_iso, from_iso=None):
-    """Convert a language into another format
-
-    :param string language: language
-    :param int to_iso: convert language to ISO-639-x
-    :param int from_iso: convert language from ISO-639-x
-    :return: converted language
-    :rtype: string
-
-    """
-    if from_iso == None:  # if no from_iso is given, try to guess it
-        if language.startswith(language[:1].upper()):
-            from_iso = 0
-        elif len(language) == 2:
-            from_iso = 1
-        elif len(language) == 3:
-            from_iso = 2
-        else:
-            raise ValueError('Invalid input language format')
-    if isinstance(language, unicode):
-        language = language.encode('utf-8')
-    converted_language = None
-    for language_tuple in LANGUAGES:
-        if language_tuple[from_iso] == language and language_tuple[to_iso]:
-            converted_language = language_tuple[to_iso]
-            break
-    return converted_language
-
-
-def list_languages(iso):
-    """List languages in the given ISO-639-x format
-
-    :param int iso: ISO-639-x format to list
-    :return: languages in the requested format
-    :rtype: list
-
-    """
-    return [l[iso] for l in LANGUAGES if l[iso]]
-
-#: ISO-639-2 languages list from http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
-#: + ('Brazilian', 'po', 'pob')
-LANGUAGES = [('Afar', 'aa', 'aar'),
-             ('Abkhazian', 'ab', 'abk'),
-             ('Achinese', '', 'ace'),
-             ('Acoli', '', 'ach'),
-             ('Adangme', '', 'ada'),
-             ('Adyghe; Adygei', '', 'ady'),
-             ('Afro-Asiatic languages', '', 'afa'),
-             ('Afrihili', '', 'afh'),
-             ('Afrikaans', 'af', 'afr'),
-             ('Ainu', '', 'ain'),
-             ('Akan', 'ak', 'aka'),
-             ('Akkadian', '', 'akk'),
-             ('Albanian', 'sq', 'alb'),
-             ('Aleut', '', 'ale'),
-             ('Algonquian languages', '', 'alg'),
-             ('Southern Altai', '', 'alt'),
-             ('Amharic', 'am', 'amh'),
-             ('English, Old (ca.450-1100)', '', 'ang'),
-             ('Angika', '', 'anp'),
-             ('Apache languages', '', 'apa'),
-             ('Arabic', 'ar', 'ara'),
-             ('Official Aramaic (700-300 BCE); Imperial Aramaic (700-300 BCE)', '', 'arc'),
-             ('Aragonese', 'an', 'arg'),
-             ('Armenian', 'hy', 'arm'),
-             ('Mapudungun; Mapuche', '', 'arn'),
-             ('Arapaho', '', 'arp'),
-             ('Artificial languages', '', 'art'),
-             ('Arawak', '', 'arw'),
-             ('Assamese', 'as', 'asm'),
-             ('Asturian; Bable; Leonese; Asturleonese', '', 'ast'),
-             ('Athapascan languages', '', 'ath'),
-             ('Australian languages', '', 'aus'),
-             ('Avaric', 'av', 'ava'),
-             ('Avestan', 'ae', 'ave'),
-             ('Awadhi', '', 'awa'),
-             ('Aymara', 'ay', 'aym'),
-             ('Azerbaijani', 'az', 'aze'),
-             ('Banda languages', '', 'bad'),
-             ('Bamileke languages', '', 'bai'),
-             ('Bashkir', 'ba', 'bak'),
-             ('Baluchi', '', 'bal'),
-             ('Bambara', 'bm', 'bam'),
-             ('Balinese', '', 'ban'),
-             ('Basque', 'eu', 'baq'),
-             ('Basa', '', 'bas'),
-             ('Baltic languages', '', 'bat'),
-             ('Beja; Bedawiyet', '', 'bej'),
-             ('Belarusian', 'be', 'bel'),
-             ('Bemba', '', 'bem'),
-             ('Bengali', 'bn', 'ben'),
-             ('Berber languages', '', 'ber'),
-             ('Bhojpuri', '', 'bho'),
-             ('Bihari languages', 'bh', 'bih'),
-             ('Bikol', '', 'bik'),
-             ('Bini; Edo', '', 'bin'),
-             ('Bislama', 'bi', 'bis'),
-             ('Siksika', '', 'bla'),
-             ('Bantu (Other)', '', 'bnt'),
-             ('Bosnian', 'bs', 'bos'),
-             ('Braj', '', 'bra'),
-             ('Breton', 'br', 'bre'),
-             ('Batak languages', '', 'btk'),
-             ('Buriat', '', 'bua'),
-             ('Buginese', '', 'bug'),
-             ('Bulgarian', 'bg', 'bul'),
-             ('Burmese', 'my', 'bur'),
-             ('Blin; Bilin', '', 'byn'),
-             ('Caddo', '', 'cad'),
-             ('Central American Indian languages', '', 'cai'),
-             ('Galibi Carib', '', 'car'),
-             ('Catalan; Valencian', 'ca', 'cat'),
-             ('Caucasian languages', '', 'cau'),
-             ('Cebuano', '', 'ceb'),
-             ('Celtic languages', '', 'cel'),
-             ('Chamorro', 'ch', 'cha'),
-             ('Chibcha', '', 'chb'),
-             ('Chechen', 'ce', 'che'),
-             ('Chagatai', '', 'chg'),
-             ('Chinese', 'zh', 'chi'),
-             ('Chuukese', '', 'chk'),
-             ('Mari', '', 'chm'),
-             ('Chinook jargon', '', 'chn'),
-             ('Choctaw', '', 'cho'),
-             ('Chipewyan; Dene Suline', '', 'chp'),
-             ('Cherokee', '', 'chr'),
-             ('Church Slavic; Old Slavonic; Church Slavonic; Old Bulgarian; Old Church Slavonic', 'cu', 'chu'),
-             ('Chuvash', 'cv', 'chv'),
-             ('Cheyenne', '', 'chy'),
-             ('Chamic languages', '', 'cmc'),
-             ('Coptic', '', 'cop'),
-             ('Cornish', 'kw', 'cor'),
-             ('Corsican', 'co', 'cos'),
-             ('Creoles and pidgins, English based', '', 'cpe'),
-             ('Creoles and pidgins, French-based ', '', 'cpf'),
-             ('Creoles and pidgins, Portuguese-based ', '', 'cpp'),
-             ('Cree', 'cr', 'cre'),
-             ('Crimean Tatar; Crimean Turkish', '', 'crh'),
-             ('Creoles and pidgins ', '', 'crp'),
-             ('Kashubian', '', 'csb'),
-             ('Cushitic languages', '', 'cus'),
-             ('Czech', 'cs', 'cze'),
-             ('Dakota', '', 'dak'),
-             ('Danish', 'da', 'dan'),
-             ('Dargwa', '', 'dar'),
-             ('Land Dayak languages', '', 'day'),
-             ('Delaware', '', 'del'),
-             ('Slave (Athapascan)', '', 'den'),
-             ('Dogrib', '', 'dgr'),
-             ('Dinka', '', 'din'),
-             ('Divehi; Dhivehi; Maldivian', 'dv', 'div'),
-             ('Dogri', '', 'doi'),
-             ('Dravidian languages', '', 'dra'),
-             ('Lower Sorbian', '', 'dsb'),
-             ('Duala', '', 'dua'),
-             ('Dutch, Middle (ca.1050-1350)', '', 'dum'),
-             ('Dutch; Flemish', 'nl', 'dut'),
-             ('Dyula', '', 'dyu'),
-             ('Dzongkha', 'dz', 'dzo'),
-             ('Efik', '', 'efi'),
-             ('Egyptian (Ancient)', '', 'egy'),
-             ('Ekajuk', '', 'eka'),
-             ('Elamite', '', 'elx'),
-             ('English', 'en', 'eng'),
-             ('English, Middle (1100-1500)', '', 'enm'),
-             ('Esperanto', 'eo', 'epo'),
-             ('Estonian', 'et', 'est'),
-             ('Ewe', 'ee', 'ewe'),
-             ('Ewondo', '', 'ewo'),
-             ('Fang', '', 'fan'),
-             ('Faroese', 'fo', 'fao'),
-             ('Fanti', '', 'fat'),
-             ('Fijian', 'fj', 'fij'),
-             ('Filipino; Pilipino', '', 'fil'),
-             ('Finnish', 'fi', 'fin'),
-             ('Finno-Ugrian languages', '', 'fiu'),
-             ('Fon', '', 'fon'),
-             ('French', 'fr', 'fre'),
-             ('French, Middle (ca.1400-1600)', '', 'frm'),
-             ('French, Old (842-ca.1400)', '', 'fro'),
-             ('Northern Frisian', '', 'frr'),
-             ('Eastern Frisian', '', 'frs'),
-             ('Western Frisian', 'fy', 'fry'),
-             ('Fulah', 'ff', 'ful'),
-             ('Friulian', '', 'fur'),
-             ('Ga', '', 'gaa'),
-             ('Gayo', '', 'gay'),
-             ('Gbaya', '', 'gba'),
-             ('Germanic languages', '', 'gem'),
-             ('Georgian', 'ka', 'geo'),
-             ('German', 'de', 'ger'),
-             ('Geez', '', 'gez'),
-             ('Gilbertese', '', 'gil'),
-             ('Gaelic; Scottish Gaelic', 'gd', 'gla'),
-             ('Irish', 'ga', 'gle'),
-             ('Galician', 'gl', 'glg'),
-             ('Manx', 'gv', 'glv'),
-             ('German, Middle High (ca.1050-1500)', '', 'gmh'),
-             ('German, Old High (ca.750-1050)', '', 'goh'),
-             ('Gondi', '', 'gon'),
-             ('Gorontalo', '', 'gor'),
-             ('Gothic', '', 'got'),
-             ('Grebo', '', 'grb'),
-             ('Greek, Ancient (to 1453)', '', 'grc'),
-             ('Greek, Modern (1453-)', 'el', 'gre'),
-             ('Guarani', 'gn', 'grn'),
-             ('Swiss German; Alemannic; Alsatian', '', 'gsw'),
-             ('Gujarati', 'gu', 'guj'),
-             ('Gwich\'in', '', 'gwi'),
-             ('Haida', '', 'hai'),
-             ('Haitian; Haitian Creole', 'ht', 'hat'),
-             ('Hausa', 'ha', 'hau'),
-             ('Hawaiian', '', 'haw'),
-             ('Hebrew', 'he', 'heb'),
-             ('Herero', 'hz', 'her'),
-             ('Hiligaynon', '', 'hil'),
-             ('Himachali languages; Western Pahari languages', '', 'him'),
-             ('Hindi', 'hi', 'hin'),
-             ('Hittite', '', 'hit'),
-             ('Hmong; Mong', '', 'hmn'),
-             ('Hiri Motu', 'ho', 'hmo'),
-             ('Croatian', 'hr', 'hrv'),
-             ('Upper Sorbian', '', 'hsb'),
-             ('Hungarian', 'hu', 'hun'),
-             ('Hupa', '', 'hup'),
-             ('Iban', '', 'iba'),
-             ('Igbo', 'ig', 'ibo'),
-             ('Icelandic', 'is', 'ice'),
-             ('Ido', 'io', 'ido'),
-             ('Sichuan Yi; Nuosu', 'ii', 'iii'),
-             ('Ijo languages', '', 'ijo'),
-             ('Inuktitut', 'iu', 'iku'),
-             ('Interlingue; Occidental', 'ie', 'ile'),
-             ('Iloko', '', 'ilo'),
-             ('Interlingua (International Auxiliary Language Association)', 'ia', 'ina'),
-             ('Indic languages', '', 'inc'),
-             ('Indonesian', 'id', 'ind'),
-             ('Indo-European languages', '', 'ine'),
-             ('Ingush', '', 'inh'),
-             ('Inupiaq', 'ik', 'ipk'),
-             ('Iranian languages', '', 'ira'),
-             ('Iroquoian languages', '', 'iro'),
-             ('Italian', 'it', 'ita'),
-             ('Javanese', 'jv', 'jav'),
-             ('Lojban', '', 'jbo'),
-             ('Japanese', 'ja', 'jpn'),
-             ('Judeo-Persian', '', 'jpr'),
-             ('Judeo-Arabic', '', 'jrb'),
-             ('Kara-Kalpak', '', 'kaa'),
-             ('Kabyle', '', 'kab'),
-             ('Kachin; Jingpho', '', 'kac'),
-             ('Kalaallisut; Greenlandic', 'kl', 'kal'),
-             ('Kamba', '', 'kam'),
-             ('Kannada', 'kn', 'kan'),
-             ('Karen languages', '', 'kar'),
-             ('Kashmiri', 'ks', 'kas'),
-             ('Kanuri', 'kr', 'kau'),
-             ('Kawi', '', 'kaw'),
-             ('Kazakh', 'kk', 'kaz'),
-             ('Kabardian', '', 'kbd'),
-             ('Khasi', '', 'kha'),
-             ('Khoisan languages', '', 'khi'),
-             ('Central Khmer', 'km', 'khm'),
-             ('Khotanese; Sakan', '', 'kho'),
-             ('Kikuyu; Gikuyu', 'ki', 'kik'),
-             ('Kinyarwanda', 'rw', 'kin'),
-             ('Kirghiz; Kyrgyz', 'ky', 'kir'),
-             ('Kimbundu', '', 'kmb'),
-             ('Konkani', '', 'kok'),
-             ('Komi', 'kv', 'kom'),
-             ('Kongo', 'kg', 'kon'),
-             ('Korean', 'ko', 'kor'),
-             ('Kosraean', '', 'kos'),
-             ('Kpelle', '', 'kpe'),
-             ('Karachay-Balkar', '', 'krc'),
-             ('Karelian', '', 'krl'),
-             ('Kru languages', '', 'kro'),
-             ('Kurukh', '', 'kru'),
-             ('Kuanyama; Kwanyama', 'kj', 'kua'),
-             ('Kumyk', '', 'kum'),
-             ('Kurdish', 'ku', 'kur'),
-             ('Kutenai', '', 'kut'),
-             ('Ladino', '', 'lad'),
-             ('Lahnda', '', 'lah'),
-             ('Lamba', '', 'lam'),
-             ('Lao', 'lo', 'lao'),
-             ('Latin', 'la', 'lat'),
-             ('Latvian', 'lv', 'lav'),
-             ('Lezghian', '', 'lez'),
-             ('Limburgan; Limburger; Limburgish', 'li', 'lim'),
-             ('Lingala', 'ln', 'lin'),
-             ('Lithuanian', 'lt', 'lit'),
-             ('Mongo', '', 'lol'),
-             ('Lozi', '', 'loz'),
-             ('Luxembourgish; Letzeburgesch', 'lb', 'ltz'),
-             ('Luba-Lulua', '', 'lua'),
-             ('Luba-Katanga', 'lu', 'lub'),
-             ('Ganda', 'lg', 'lug'),
-             ('Luiseno', '', 'lui'),
-             ('Lunda', '', 'lun'),
-             ('Luo (Kenya and Tanzania)', '', 'luo'),
-             ('Lushai', '', 'lus'),
-             ('Macedonian', 'mk', 'mac'),
-             ('Madurese', '', 'mad'),
-             ('Magahi', '', 'mag'),
-             ('Marshallese', 'mh', 'mah'),
-             ('Maithili', '', 'mai'),
-             ('Makasar', '', 'mak'),
-             ('Malayalam', 'ml', 'mal'),
-             ('Mandingo', '', 'man'),
-             ('Maori', 'mi', 'mao'),
-             ('Austronesian languages', '', 'map'),
-             ('Marathi', 'mr', 'mar'),
-             ('Masai', '', 'mas'),
-             ('Malay', 'ms', 'may'),
-             ('Moksha', '', 'mdf'),
-             ('Mandar', '', 'mdr'),
-             ('Mende', '', 'men'),
-             ('Irish, Middle (900-1200)', '', 'mga'),
-             ('Mi\'kmaq; Micmac', '', 'mic'),
-             ('Minangkabau', '', 'min'),
-             ('Uncoded languages', '', 'mis'),
-             ('Mon-Khmer languages', '', 'mkh'),
-             ('Malagasy', 'mg', 'mlg'),
-             ('Maltese', 'mt', 'mlt'),
-             ('Manchu', '', 'mnc'),
-             ('Manipuri', '', 'mni'),
-             ('Manobo languages', '', 'mno'),
-             ('Mohawk', '', 'moh'),
-             ('Mongolian', 'mn', 'mon'),
-             ('Mossi', '', 'mos'),
-             ('Multiple languages', '', 'mul'),
-             ('Munda languages', '', 'mun'),
-             ('Creek', '', 'mus'),
-             ('Mirandese', '', 'mwl'),
-             ('Marwari', '', 'mwr'),
-             ('Mayan languages', '', 'myn'),
-             ('Erzya', '', 'myv'),
-             ('Nahuatl languages', '', 'nah'),
-             ('North American Indian languages', '', 'nai'),
-             ('Neapolitan', '', 'nap'),
-             ('Nauru', 'na', 'nau'),
-             ('Navajo; Navaho', 'nv', 'nav'),
-             ('Ndebele, South; South Ndebele', 'nr', 'nbl'),
-             ('Ndebele, North; North Ndebele', 'nd', 'nde'),
-             ('Ndonga', 'ng', 'ndo'),
-             ('Low German; Low Saxon; German, Low; Saxon, Low', '', 'nds'),
-             ('Nepali', 'ne', 'nep'),
-             ('Nepal Bhasa; Newari', '', 'new'),
-             ('Nias', '', 'nia'),
-             ('Niger-Kordofanian languages', '', 'nic'),
-             ('Niuean', '', 'niu'),
-             ('Norwegian Nynorsk; Nynorsk, Norwegian', 'nn', 'nno'),
-             ('Bokmål, Norwegian; Norwegian Bokmål', 'nb', 'nob'),
-             ('Nogai', '', 'nog'),
-             ('Norse, Old', '', 'non'),
-             ('Norwegian', 'no', 'nor'),
-             ('N\'Ko', '', 'nqo'),
-             ('Pedi; Sepedi; Northern Sotho', '', 'nso'),
-             ('Nubian languages', '', 'nub'),
-             ('Classical Newari; Old Newari; Classical Nepal Bhasa', '', 'nwc'),
-             ('Chichewa; Chewa; Nyanja', 'ny', 'nya'),
-             ('Nyamwezi', '', 'nym'),
-             ('Nyankole', '', 'nyn'),
-             ('Nyoro', '', 'nyo'),
-             ('Nzima', '', 'nzi'),
-             ('Occitan (post 1500); Provençal', 'oc', 'oci'),
-             ('Ojibwa', 'oj', 'oji'),
-             ('Oriya', 'or', 'ori'),
-             ('Oromo', 'om', 'orm'),
-             ('Osage', '', 'osa'),
-             ('Ossetian; Ossetic', 'os', 'oss'),
-             ('Turkish, Ottoman (1500-1928)', '', 'ota'),
-             ('Otomian languages', '', 'oto'),
-             ('Papuan languages', '', 'paa'),
-             ('Pangasinan', '', 'pag'),
-             ('Pahlavi', '', 'pal'),
-             ('Pampanga; Kapampangan', '', 'pam'),
-             ('Panjabi; Punjabi', 'pa', 'pan'),
-             ('Papiamento', '', 'pap'),
-             ('Palauan', '', 'pau'),
-             ('Persian, Old (ca.600-400 B.C.)', '', 'peo'),
-             ('Persian', 'fa', 'per'),
-             ('Philippine languages', '', 'phi'),
-             ('Phoenician', '', 'phn'),
-             ('Pali', 'pi', 'pli'),
-             ('Polish', 'pl', 'pol'),
-             ('Pohnpeian', '', 'pon'),
-             ('Portuguese', 'pt', 'por'),
-             ('Prakrit languages', '', 'pra'),
-             ('Provençal, Old (to 1500)', '', 'pro'),
-             ('Pushto; Pashto', 'ps', 'pus'),
-             ('Reserved for local use', '', 'qaa-qtz'),
-             ('Quechua', 'qu', 'que'),
-             ('Rajasthani', '', 'raj'),
-             ('Rapanui', '', 'rap'),
-             ('Rarotongan; Cook Islands Maori', '', 'rar'),
-             ('Romance languages', '', 'roa'),
-             ('Romansh', 'rm', 'roh'),
-             ('Romany', '', 'rom'),
-             ('Romanian; Moldavian; Moldovan', 'ro', 'rum'),
-             ('Rundi', 'rn', 'run'),
-             ('Aromanian; Arumanian; Macedo-Romanian', '', 'rup'),
-             ('Russian', 'ru', 'rus'),
-             ('Sandawe', '', 'sad'),
-             ('Sango', 'sg', 'sag'),
-             ('Yakut', '', 'sah'),
-             ('South American Indian (Other)', '', 'sai'),
-             ('Salishan languages', '', 'sal'),
-             ('Samaritan Aramaic', '', 'sam'),
-             ('Sanskrit', 'sa', 'san'),
-             ('Sasak', '', 'sas'),
-             ('Santali', '', 'sat'),
-             ('Sicilian', '', 'scn'),
-             ('Scots', '', 'sco'),
-             ('Selkup', '', 'sel'),
-             ('Semitic languages', '', 'sem'),
-             ('Irish, Old (to 900)', '', 'sga'),
-             ('Sign Languages', '', 'sgn'),
-             ('Shan', '', 'shn'),
-             ('Sidamo', '', 'sid'),
-             ('Sinhala; Sinhalese', 'si', 'sin'),
-             ('Siouan languages', '', 'sio'),
-             ('Sino-Tibetan languages', '', 'sit'),
-             ('Slavic languages', '', 'sla'),
-             ('Slovak', 'sk', 'slo'),
-             ('Slovenian', 'sl', 'slv'),
-             ('Southern Sami', '', 'sma'),
-             ('Northern Sami', 'se', 'sme'),
-             ('Sami languages', '', 'smi'),
-             ('Lule Sami', '', 'smj'),
-             ('Inari Sami', '', 'smn'),
-             ('Samoan', 'sm', 'smo'),
-             ('Skolt Sami', '', 'sms'),
-             ('Shona', 'sn', 'sna'),
-             ('Sindhi', 'sd', 'snd'),
-             ('Soninke', '', 'snk'),
-             ('Sogdian', '', 'sog'),
-             ('Somali', 'so', 'som'),
-             ('Songhai languages', '', 'son'),
-             ('Sotho, Southern', 'st', 'sot'),
-             ('Spanish; Castilian', 'es', 'spa'),
-             ('Sardinian', 'sc', 'srd'),
-             ('Sranan Tongo', '', 'srn'),
-             ('Serbian', 'sr', 'srp'),
-             ('Serer', '', 'srr'),
-             ('Nilo-Saharan languages', '', 'ssa'),
-             ('Swati', 'ss', 'ssw'),
-             ('Sukuma', '', 'suk'),
-             ('Sundanese', 'su', 'sun'),
-             ('Susu', '', 'sus'),
-             ('Sumerian', '', 'sux'),
-             ('Swahili', 'sw', 'swa'),
-             ('Swedish', 'sv', 'swe'),
-             ('Classical Syriac', '', 'syc'),
-             ('Syriac', '', 'syr'),
-             ('Tahitian', 'ty', 'tah'),
-             ('Tai languages', '', 'tai'),
-             ('Tamil', 'ta', 'tam'),
-             ('Tatar', 'tt', 'tat'),
-             ('Telugu', 'te', 'tel'),
-             ('Timne', '', 'tem'),
-             ('Tereno', '', 'ter'),
-             ('Tetum', '', 'tet'),
-             ('Tajik', 'tg', 'tgk'),
-             ('Tagalog', 'tl', 'tgl'),
-             ('Thai', 'th', 'tha'),
-             ('Tibetan', 'bo', 'tib'),
-             ('Tigre', '', 'tig'),
-             ('Tigrinya', 'ti', 'tir'),
-             ('Tiv', '', 'tiv'),
-             ('Tokelau', '', 'tkl'),
-             ('Klingon; tlhIngan-Hol', '', 'tlh'),
-             ('Tlingit', '', 'tli'),
-             ('Tamashek', '', 'tmh'),
-             ('Tonga (Nyasa)', '', 'tog'),
-             ('Tonga (Tonga Islands)', 'to', 'ton'),
-             ('Tok Pisin', '', 'tpi'),
-             ('Tsimshian', '', 'tsi'),
-             ('Tswana', 'tn', 'tsn'),
-             ('Tsonga', 'ts', 'tso'),
-             ('Turkmen', 'tk', 'tuk'),
-             ('Tumbuka', '', 'tum'),
-             ('Tupi languages', '', 'tup'),
-             ('Turkish', 'tr', 'tur'),
-             ('Altaic languages', '', 'tut'),
-             ('Tuvalu', '', 'tvl'),
-             ('Twi', 'tw', 'twi'),
-             ('Tuvinian', '', 'tyv'),
-             ('Udmurt', '', 'udm'),
-             ('Ugaritic', '', 'uga'),
-             ('Uighur; Uyghur', 'ug', 'uig'),
-             ('Ukrainian', 'uk', 'ukr'),
-             ('Umbundu', '', 'umb'),
-             ('Undetermined', '', 'und'),
-             ('Urdu', 'ur', 'urd'),
-             ('Uzbek', 'uz', 'uzb'),
-             ('Vai', '', 'vai'),
-             ('Venda', 've', 'ven'),
-             ('Vietnamese', 'vi', 'vie'),
-             ('Volapük', 'vo', 'vol'),
-             ('Votic', '', 'vot'),
-             ('Wakashan languages', '', 'wak'),
-             ('Walamo', '', 'wal'),
-             ('Waray', '', 'war'),
-             ('Washo', '', 'was'),
-             ('Welsh', 'cy', 'wel'),
-             ('Sorbian languages', '', 'wen'),
-             ('Walloon', 'wa', 'wln'),
-             ('Wolof', 'wo', 'wol'),
-             ('Kalmyk; Oirat', '', 'xal'),
-             ('Xhosa', 'xh', 'xho'),
-             ('Yao', '', 'yao'),
-             ('Yapese', '', 'yap'),
-             ('Yiddish', 'yi', 'yid'),
-             ('Yoruba', 'yo', 'yor'),
-             ('Yupik languages', '', 'ypk'),
-             ('Zapotec', '', 'zap'),
-             ('Blissymbols; Blissymbolics; Bliss', '', 'zbl'),
-             ('Zenaga', '', 'zen'),
-             ('Zhuang; Chuang', 'za', 'zha'),
-             ('Zande languages', '', 'znd'),
-             ('Zulu', 'zu', 'zul'),
-             ('Zuni', '', 'zun'),
-             ('No linguistic content; Not applicable', '', 'zxx'),
-             ('Zaza; Dimili; Dimli; Kirdki; Kirmanjki; Zazaki', '', 'zza'),
-             ('Brazilian', 'po', 'pob')]

subliminal/providers/__init__.py

@@ -0,0 +1,131 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import babelfish
+from ..video import Episode, Movie
+
+
+class Provider(object):
+    """Base class for providers
+
+    If any configuration is possible for the provider, like credentials, it must take place during instantiation
+
+    :param \*\*kwargs: configuration
+    :raise: :class:`~subliminal.exceptions.ProviderConfigurationError` if there is a configuration error
+
+    """
+    #: Supported BabelFish languages
+    languages = set()
+
+    #: Supported video types
+    video_types = (Episode, Movie)
+
+    #: Required hash, if any
+    required_hash = None
+
+    def __init__(self, **kwargs):
+        pass
+
+    def __enter__(self):
+        self.initialize()
+        return self
+
+    def __exit__(self, *args):
+        self.terminate()
+
+    def initialize(self):
+        """Initialize the provider
+
+        Must be called when starting to work with the provider. This is the place for network initialization
+        or login operations.
+
+        .. note:
+            This is called automatically if you use the :keyword:`with` statement
+
+
+        :raise: :class:`~subliminal.exceptions.ProviderNotAvailable` if the provider is unavailable
+
+        """
+        pass
+
+    def terminate(self):
+        """Terminate the provider
+
+        Must be called when done with the provider. This is the place for network shutdown or logout operations.
+
+        .. note:
+            This is called automatically if you use the :keyword:`with` statement
+
+        :raise: :class:`~subliminal.exceptions.ProviderNotAvailable` if the provider is unavailable
+        """
+        pass
+
+    @classmethod
+    def check(cls, video):
+        """Check if the `video` can be processed
+
+        The video is considered invalid if not an instance of :attr:`video_types` or if the :attr:`required_hash` is
+        not present in :attr:`~subliminal.video.Video`'s `hashes` attribute.
+
+        :param video: the video to check
+        :type video: :class:`~subliminal.video.Video`
+        :return: `True` if the `video` and `languages` are valid, `False` otherwise
+        :rtype: bool
+
+        """
+        if not isinstance(video, cls.video_types):
+            return False
+        if cls.required_hash is not None and cls.required_hash not in video.hashes:
+            return False
+        return True
+
+    def query(self, languages, *args, **kwargs):
+        """Query the provider for subtitles
+
+        This method arguments match as much as possible the actual parameters for querying the provider
+
+        :param languages: languages to search for
+        :type languages: set of :class:`babelfish.Language`
+        :param \*args: other required arguments
+        :param \*\*kwargs: other optional arguments
+        :return: the subtitles
+        :rtype: list of :class:`~subliminal.subtitle.Subtitle`
+        :raise: :class:`~subliminal.exceptions.ProviderNotAvailable` if the provider is unavailable
+        :raise: :class:`~subliminal.exceptions.ProviderError` if something unexpected occured
+
+        """
+        raise NotImplementedError
+
+    def list_subtitles(self, video, languages):
+        """List subtitles for the `video` with the given `languages`
+
+        This is a proxy for the :meth:`query` method. The parameters passed to the :meth:`query` method may
+        vary depending on the amount of information available in the `video`
+
+        :param video: video to list subtitles for
+        :type video: :class:`~subliminal.video.Video`
+        :param languages: languages to search for
+        :type languages: set of :class:`babelfish.Language`
+        :return: the subtitles
+        :rtype: list of :class:`~subliminal.subtitle.Subtitle`
+        :raise: :class:`~subliminal.exceptions.ProviderNotAvailable` if the provider is unavailable
+        :raise: :class:`~subliminal.exceptions.ProviderError` if something unexpected occured
+
+        """
+        raise NotImplementedError
+
+    def download_subtitle(self, subtitle):
+        """Download the `subtitle`
+
+        :param subtitle: subtitle to download
+        :type subtitle: :class:`~subliminal.subtitle.Subtitle`
+        :return: the subtitle text
+        :rtype: string
+        :raise: :class:`~subliminal.exceptions.ProviderNotAvailable` if the provider is unavailable
+        :raise: :class:`~subliminal.exceptions.InvalidSubtitle` if the downloaded subtitle is invalid
+        :raise: :class:`~subliminal.exceptions.ProviderError` if something unexpected occured
+
+        """
+        raise NotImplementedError
+
+    def __repr__(self):
+        return '<%s [%r]>' % (self.__class__.__name__, self.video_types)

subliminal/providers/addic7ed.py

@@ -0,0 +1,191 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import logging
+import babelfish
+import bs4
+import charade
+import requests
+from . import Provider
+from .. import __version__
+from ..cache import region
+from ..exceptions import ProviderConfigurationError, ProviderNotAvailable, InvalidSubtitle
+from ..subtitle import Subtitle, is_valid_subtitle
+from ..video import Episode
+
+
+logger = logging.getLogger(__name__)
+
+
+class Addic7edSubtitle(Subtitle):
+    provider_name = 'addic7ed'
+
+    def __init__(self, language, series, season, episode, title, version, hearing_impaired, download_link, referer):
+        super(Addic7edSubtitle, self).__init__(language, hearing_impaired)
+        self.series = series
+        self.season = season
+        self.episode = episode
+        self.title = title
+        self.version = version
+        self.download_link = download_link
+        self.referer = referer
+
+    def compute_matches(self, video):
+        matches = set()
+        # series
+        if video.series and self.series == video.series:
+            matches.add('series')
+        # season
+        if video.season and self.season == video.season:
+            matches.add('season')
+        # episode
+        if video.episode and self.episode == video.episode:
+            matches.add('episode')
+        # title
+        if video.title and self.title.lower() == video.title.lower():
+            matches.add('title')
+        # release_group
+        if video.release_group and self.version and video.release_group.lower() in self.version.lower():
+            matches.add('release_group')
+        # resolution
+        if video.resolution and self.version and video.resolution in self.version.lower():
+            matches.add('resolution')
+        return matches
+
+
+class Addic7edProvider(Provider):
+    languages = {babelfish.Language('por', 'BR')} | {babelfish.Language(l)
+                 for l in ['ara', 'aze', 'ben', 'bos', 'bul', 'cat', 'ces', 'dan', 'deu', 'ell', 'eng', 'eus', 'fas',
+                           'fin', 'fra', 'glg', 'heb', 'hrv', 'hun', 'hye', 'ind', 'ita', 'jpn', 'kor', 'mkd', 'msa',
+                           'nld', 'nor', 'pol', 'por', 'ron', 'rus', 'slk', 'slv', 'spa', 'sqi', 'srp', 'swe', 'tha',
+                           'tur', 'ukr', 'vie', 'zho']}
+    video_types = (Episode,)
+    server = 'http://www.addic7ed.com'
+
+    def __init__(self, username=None, password=None):
+        if username is not None and password is None or username is None and password is not None:
+            raise ProviderConfigurationError('Username and password must be specified')
+        self.username = username
+        self.password = password
+        self.logged_in = False
+
+    def initialize(self):
+        self.session = requests.Session()
+        self.session.headers = {'User-Agent': 'Subliminal/%s' % __version__}
+        # login
+        if self.username is not None and self.password is not None:
+            logger.debug('Logging in')
+            data = {'username': self.username, 'password': self.password, 'Submit': 'Log in'}
+            try:
+                r = self.session.post(self.server + '/dologin.php', data, timeout=10, allow_redirects=False)
+            except requests.Timeout:
+                raise ProviderNotAvailable('Timeout after 10 seconds')
+            if r.status_code == 302:
+                logger.info('Logged in')
+                self.logged_in = True
+            else:
+                logger.error('Failed to login')
+
+    def terminate(self):
+        # logout
+        if self.logged_in:
+            try:
+                r = self.session.get(self.server + '/logout.php', timeout=10)
+                logger.info('Logged out')
+            except requests.Timeout:
+                raise ProviderNotAvailable('Timeout after 10 seconds')
+            if r.status_code != 200:
+                raise ProviderNotAvailable('Request failed with status code %d' % r.status_code)
+        self.session.close()
+
+    def get(self, url, params=None):
+        """Make a GET request on `url` with the given parameters
+
+        :param string url: part of the URL to reach with the leading slash
+        :param params: params of the request
+        :return: the response
+        :rtype: :class:`bs4.BeautifulSoup`
+        :raise: :class:`~subliminal.exceptions.ProviderNotAvailable`
+
+        """
+        try:
+            r = self.session.get(self.server + url, params=params, timeout=10)
+        except requests.Timeout:
+            raise ProviderNotAvailable('Timeout after 10 seconds')
+        if r.status_code != 200:
+            raise ProviderNotAvailable('Request failed with status code %d' % r.status_code)
+        return bs4.BeautifulSoup(r.content, ['permissive'])
+
+    @region.cache_on_arguments()
+    def get_show_ids(self):
+        """Load the shows page with default series to show ids mapping
+
+        :return: series to show ids
+        :rtype: dict
+
+        """
+        soup = self.get('/shows.php')
+        show_ids = {}
+        for html_show in soup.select('td.version > h3 > a[href^="/show/"]'):
+            show_ids[html_show.string.lower()] = int(html_show['href'][6:])
+        return show_ids
+
+    @region.cache_on_arguments()
+    def find_show_id(self, series):
+        """Find a show id from the series
+
+        Use this only if the series is not in the dict returned by :meth:`get_show_ids`
+
+        :param string series: series of the episode
+        :return: the show id, if any
+        :rtype: int or None
+
+        """
+        params = {'search': series, 'Submit': 'Search'}
+        logger.debug('Searching series %r', params)
+        suggested_shows = self.get('/search.php', params).select('span.titulo > a[href^="/show/"]')
+        if not suggested_shows:
+            logger.info('Series %r not found', series)
+            return None
+        return int(suggested_shows[0]['href'][6:])
+
+    def query(self, series, season):
+        show_ids = self.get_show_ids()
+        if series.lower() in show_ids:
+            show_id = show_ids[series.lower()]
+        else:
+            show_id = self.find_show_id(series.lower())
+            if show_id is None:
+                return []
+        params = {'show_id': show_id, 'season': season}
+        logger.debug('Searching subtitles %r', params)
+        link = '/show/{show_id}&season={season}'.format(**params)
+        soup = self.get(link)
+        subtitles = []
+        for row in soup('tr', class_='epeven completed'):
+            cells = row('td')
+            if cells[5].string != 'Completed':
+                logger.debug('Skipping incomplete subtitle')
+                continue
+            subtitles.append(Addic7edSubtitle(babelfish.Language.fromaddic7ed(cells[3].string), series, season,
+                                              int(cells[1].string), cells[2].string, cells[4].string,
+                                              bool(cells[6].string), cells[9].a['href'], link))
+        return subtitles
+
+    def list_subtitles(self, video, languages):
+        return [s for s in self.query(video.series, video.season)
+                if s.language in languages and s.episode == video.episode]
+
+    def download_subtitle(self, subtitle):
+        try:
+            r = self.session.get(self.server + subtitle.download_link, timeout=10,
+                                 headers={'Referer': self.server + subtitle.referer})
+        except requests.Timeout:
+            raise ProviderNotAvailable('Timeout after 10 seconds')
+        if r.status_code != 200:
+            raise ProviderNotAvailable('Request failed with status code %d' % r.status_code)
+        if r.headers['Content-Type'] == 'text/html':
+            raise ProviderNotAvailable('Download limit exceeded')
+        subtitle_text = r.content.decode(charade.detect(r.content)['encoding'], 'replace')
+        if not is_valid_subtitle(subtitle_text):
+            raise InvalidSubtitle
+        return subtitle_text

subliminal/providers/bierdopje.py

@@ -0,0 +1,138 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import logging
+import urllib
+import babelfish
+import charade
+import guessit
+import requests
+import xml.etree.ElementTree
+from . import Provider
+from .. import __version__
+from ..cache import region
+from ..exceptions import InvalidSubtitle, ProviderNotAvailable, ProviderError
+from ..subtitle import Subtitle, is_valid_subtitle, compute_guess_matches
+from ..video import Episode
+
+
+logger = logging.getLogger(__name__)
+
+
+class BierDopjeSubtitle(Subtitle):
+    provider_name = 'bierdopje'
+
+    def __init__(self, language, season, episode, tvdb_id, series, filename, download_link):
+        super(BierDopjeSubtitle, self).__init__(language)
+        self.season = season
+        self.episode = episode
+        self.tvdb_id = tvdb_id
+        self.series = series
+        self.filename = filename
+        self.download_link = download_link
+
+    def compute_matches(self, video):
+        matches = set()
+        # tvdb_id
+        if video.tvdb_id and self.tvdb_id == video.tvdb_id:
+            matches.add('tvdb_id')
+        # series
+        if video.series and self.series == video.series:
+            matches.add('series')
+        # season
+        if video.season and self.season == video.season:
+            matches.add('season')
+        # episode
+        if video.episode and self.episode == video.episode:
+            matches.add('episode')
+        matches |= compute_guess_matches(video, guessit.guess_episode_info(self.filename + '.mkv'))
+        return matches
+
+
+class BierDopjeProvider(Provider):
+    languages = {babelfish.Language(l) for l in ['eng', 'nld']}
+    video_types = (Episode,)
+
+    def initialize(self):
+        self.session = requests.Session()
+        self.session.headers = {'User-Agent': 'Subliminal/%s' % __version__}
+
+    def terminate(self):
+        self.session.close()
+
+    def get(self, url, **params):
+        """Make a GET request on the `url` formatted with `**params`
+
+        :param string url: API part of the URL to reach without the leading slash
+        :param \*\*params: format specs for the `url`
+        :return: the response
+        :rtype: :class:`xml.etree.ElementTree.Element`
+        :raise: :class:`~subliminal.exceptions.ProviderNotAvailable`
+
+        """
+        try:
+            r = self.session.get('http://api.bierdopje.com/A2B638AC5D804C2E/' + url.format(**params), timeout=10)
+        except requests.Timeout:
+            raise ProviderNotAvailable('Timeout after 10 seconds')
+        if r.status_code == 429:
+            raise ProviderNotAvailable('Too Many Requests')
+        elif r.status_code != 200:
+            raise ProviderError('Request failed with status code %d' % r.status_code)
+        return xml.etree.ElementTree.fromstring(r.content)
+
+    @region.cache_on_arguments()
+    def find_show_id(self, series):
+        """Find the show id from series name
+
+        :param string series: series of the episode
+        :return: show id
+        :rtype: int
+
+        """
+        logger.debug('Searching for series %r', series)
+        root = self.get('FindShowByName/{series}', series=urllib.quote(series))
+        if root.find('response/status').text == 'false':
+            logger.info('Series %r not found', series)
+            return None
+        return int(root.find('response/results/result[1]/showid').text)
+
+    def query(self, language, season, episode, tvdb_id=None, series=None):
+        params = {'language': language.alpha2, 'season': season, 'episode': episode}
+        if tvdb_id is not None:
+            params['showid'] = tvdb_id
+            params['istvdbid'] = 'true'
+        elif series is not None:
+            show_id = self.find_show_id(series)
+            if show_id is None:
+                return []
+            params['showid'] = show_id
+            params['istvdbid'] = 'false'
+        else:
+            raise ValueError('Missing parameter tvdb_id or series')
+        logger.debug('Searching subtitles %r', params)
+        root = self.get('GetAllSubsFor/{showid}/{season}/{episode}/{language}/{istvdbid}', **params)
+        if root.find('response/status').text == 'false':
+            logger.debug('No subtitle found')
+            return []
+        logger.debug('Found subtitles %r', root.find('response/results'))
+        return [BierDopjeSubtitle(language, season, episode, tvdb_id, series, result.find('filename').text,
+                                  result.find('downloadlink').text) for result in root.find('response/results')]
+
+    def list_subtitles(self, video, languages):
+        subtitles = []
+        for language in languages:
+            subtitles.extend(self.query(language, video.season, video.episode, video.tvdb_id, video.series))
+        return subtitles
+
+    def download_subtitle(self, subtitle):
+        try:
+            r = self.session.get(subtitle.download_link, timeout=10)
+        except requests.Timeout:
+            raise ProviderNotAvailable('Timeout after 10 seconds')
+        if r.status_code == 429:
+            raise ProviderNotAvailable('Too Many Requests')
+        elif r.status_code != 200:
+            raise ProviderError('Request failed with status code %d' % r.status_code)
+        subtitle_text = r.content.decode(charade.detect(r.content)['encoding'], 'replace')
+        if not is_valid_subtitle(subtitle_text):
+            raise InvalidSubtitle
+        return subtitle_text

subliminal/providers/opensubtitles.py

@@ -0,0 +1,159 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import base64
+import logging
+import os
+import re
+import xmlrpclib
+import zlib
+import babelfish
+import charade
+import guessit
+from . import Provider
+from .. import __version__
+from ..exceptions import ProviderError, ProviderNotAvailable, InvalidSubtitle
+from ..subtitle import Subtitle, is_valid_subtitle, compute_guess_matches
+from ..video import Episode, Movie
+
+
+logger = logging.getLogger(__name__)
+
+
+class OpenSubtitlesSubtitle(Subtitle):
+    provider_name = 'opensubtitles'
+    series_re = re.compile('^"(?P<series_name>.*)" (?P<series_title>.*)$')
+
+    def __init__(self, language, hearing_impaired, id, matched_by, movie_kind, hash, movie_name, movie_release_name, movie_year,
+                 movie_imdb_id, series_season, series_episode):
+        super(OpenSubtitlesSubtitle, self).__init__(language, hearing_impaired)
+        self.id = id
+        self.matched_by = matched_by
+        self.movie_kind = movie_kind
+        self.hash = hash
+        self.movie_name = movie_name
+        self.movie_release_name = movie_release_name
+        self.movie_year = movie_year
+        self.movie_imdb_id = movie_imdb_id
+        self.series_season = series_season
+        self.series_episode = series_episode
+
+    @property
+    def series_name(self):
+        return self.series_re.match(self.movie_name).group('series_name')
+
+    @property
+    def series_title(self):
+        return self.series_re.match(self.movie_name).group('series_title')
+
+    def compute_matches(self, video):
+        matches = set()
+        # episode
+        if isinstance(video, Episode) and self.movie_kind == 'episode':
+            # series
+            if video.series and self.series_name.lower() == video.series.lower():
+                matches.add('series')
+            # season
+            if video.season and self.series_season == video.season:
+                matches.add('season')
+            # episode
+            if video.episode and self.series_episode == video.episode:
+                matches.add('episode')
+            # guess
+            matches |= compute_guess_matches(video, guessit.guess_episode_info(self.movie_release_name + '.mkv'))
+        # movie
+        elif isinstance(video, Movie) and self.movie_kind == 'movie':
+            # year
+            if video.year and self.movie_year == video.year:
+                matches.add('year')
+            # guess
+            matches |= compute_guess_matches(video, guessit.guess_movie_info(self.movie_release_name + '.mkv'))
+        else:
+            logger.info('%r is not a valid movie_kind for %r', self.movie_kind, video)
+            return matches
+        # hash
+        if 'opensubtitles' in video.hashes and self.hash == video.hashes['opensubtitles']:
+            matches.add('hash')
+        # imdb_id
+        if video.imdb_id and self.movie_imdb_id == video.imdb_id:
+            matches.add('imdb_id')
+        # title
+        if video.title and self.movie_name.lower() == video.title.lower():
+            matches.add('title')
+        return matches
+
+
+class OpenSubtitlesProvider(Provider):
+    languages = {babelfish.Language.fromopensubtitles(l) for l in babelfish.CONVERTERS['opensubtitles'].codes}
+
+    def __init__(self):
+        self.server = xmlrpclib.ServerProxy('http://api.opensubtitles.org/xml-rpc')
+        self.token = None
+
+    def initialize(self):
+        try:
+            response = self.server.LogIn('', '', 'eng', 'subliminal v%s' % __version__)
+        except xmlrpclib.ProtocolError:
+            raise ProviderNotAvailable
+        if response['status'] != '200 OK':
+            raise ProviderError('Login failed with status %r' % response['status'])
+        self.token = response['token']
+
+    def terminate(self):
+        try:
+            response = self.server.LogOut(self.token)
+        except xmlrpclib.ProtocolError:
+            raise ProviderNotAvailable
+        if response['status'] != '200 OK':
+            raise ProviderError('Logout failed with status %r' % response['status'])
+
+    def query(self, languages, hash=None, size=None, imdb_id=None, query=None):
+        searches = []
+        if hash and size:
+            searches.append({'moviehash': hash, 'moviebytesize': str(size)})
+        if imdb_id:
+            searches.append({'imdbid': imdb_id})
+        if query:
+            searches.append({'query': query})
+        if not searches:
+            raise ValueError('One or more parameter missing')
+        for search in searches:
+            search['sublanguageid'] = ','.join(l.opensubtitles for l in languages)
+        logger.debug('Searching subtitles %r', searches)
+        try:
+            response = self.server.SearchSubtitles(self.token, searches)
+        except xmlrpclib.ProtocolError:
+            raise ProviderNotAvailable
+        if response['status'] != '200 OK':
+            raise ProviderError('Search failed with status %r' % response['status'])
+        if not response['data']:
+            logger.debug('No subtitle found')
+            return []
+        logger.debug('Found subtitles %r', response['data'])
+        return [OpenSubtitlesSubtitle(babelfish.Language.fromopensubtitles(r['SubLanguageID']),
+                                      bool(int(r['SubHearingImpaired'])), r['IDSubtitleFile'], r['MatchedBy'],
+                                      r['MovieKind'], r['MovieHash'], r['MovieName'], r['MovieReleaseName'],
+                                      int(r['MovieYear']) if r['MovieYear'] else None, int(r['IDMovieImdb']),
+                                      int(r['SeriesSeason']) if r['SeriesSeason'] else None,
+                                      int(r['SeriesEpisode']) if r['SeriesEpisode'] else None)
+                for r in response['data']]
+
+    def list_subtitles(self, video, languages):
+        query = None
+        if ('opensubtitles' not in video.hashes or not video.size) and not video.imdb_id:
+            query = video.name.split(os.sep)[-1]
+        return self.query(languages, hash=video.hashes.get('opensubtitles'), size=video.size, imdb_id=video.imdb_id, query=query)
+
+    def download_subtitle(self, subtitle):
+        try:
+            response = self.server.DownloadSubtitles(self.token, [subtitle.id])
+        except xmlrpclib.ProtocolError:
+            raise ProviderNotAvailable
+        if response['status'] != '200 OK':
+            raise ProviderError('Download failed with status %r' % response['status'])
+        if not response['data']:
+            raise ProviderError('Nothing to download')
+        subtitle_bytes = zlib.decompress(base64.b64decode(response['data'][0]['data']), 47)
+        subtitle_text = subtitle_bytes.decode(charade.detect(subtitle_bytes)['encoding'], 'replace')
+        if not is_valid_subtitle(subtitle_text):
+            raise InvalidSubtitle
+        return subtitle_text

subliminal/providers/thesubdb.py

@@ -0,0 +1,81 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import logging
+import babelfish
+import charade
+import requests
+from . import Provider
+from .. import __version__
+from ..exceptions import InvalidSubtitle, ProviderNotAvailable, ProviderError
+from ..subtitle import Subtitle, is_valid_subtitle
+
+
+logger = logging.getLogger(__name__)
+
+
+class TheSubDBSubtitle(Subtitle):
+    provider_name = 'thesubdb'
+
+    def __init__(self, language, hash):
+        super(TheSubDBSubtitle, self).__init__(language)
+        self.hash = hash
+
+    def compute_matches(self, video):
+        matches = set()
+        # hash
+        if 'thesubdb' in video.hashes and video.hashes['thesubdb'] == self.hash:
+            matches.add('hash')
+        return matches
+
+
+class TheSubDBProvider(Provider):
+    languages = {babelfish.Language.fromalpha2(l) for l in ['en', 'es', 'fr', 'it', 'nl', 'pl', 'pt', 'ro', 'sv', 'tr']}
+    required_hash = 'thesubdb'
+
+    def initialize(self):
+        self.session = requests.Session()
+        self.session.headers = {'User-Agent': 'SubDB/1.0 (subliminal/%s; https://github.com/Diaoul/subliminal)' %
+                                __version__}
+
+    def terminate(self):
+        self.session.close()
+
+    def get(self, params):
+        """Make a GET request on the server with the given parameters
+
+        :param params: params of the request
+        :return: the response
+        :rtype: :class:`requests.Response`
+        :raise: :class:`~subliminal.exceptions.ProviderNotAvailable`
+
+        """
+        try:
+            r = self.session.get('http://api.thesubdb.com', params=params, timeout=10)
+        except requests.Timeout:
+            raise ProviderNotAvailable('Timeout after 10 seconds')
+        return r
+
+    def query(self, hash):
+        params = {'action': 'search', 'hash': hash}
+        logger.debug('Searching subtitles %r', params)
+        r = self.get(params)
+        if r.status_code == 404:
+            logger.debug('No subtitle found')
+            return []
+        elif r.status_code != 200:
+            raise ProviderError('Request failed with status code %d' % r.status_code)
+        return [TheSubDBSubtitle(language, hash) for language in
+                {babelfish.Language.fromalpha2(l) for l in r.content.split(',')}]
+
+    def list_subtitles(self, video, languages):
+        return [s for s in self.query(video.hashes['thesubdb']) if s.language in languages]
+
+    def download_subtitle(self, subtitle):
+        params = {'action': 'download', 'hash': subtitle.hash, 'language': subtitle.language.alpha2}
+        r = self.get(params)
+        if r.status_code != 200:
+            raise ProviderError('Request failed with status code %d' % r.status_code)
+        subtitle_text = r.content.decode(charade.detect(r.content)['encoding'], 'replace')
+        if not is_valid_subtitle(subtitle_text):
+            raise InvalidSubtitle
+        return subtitle_text

subliminal/providers/tvsubtitles.py

@@ -0,0 +1,166 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import io
+import logging
+import re
+import zipfile
+import babelfish
+import bs4
+import charade
+import requests
+from . import Provider
+from .. import __version__
+from ..cache import region
+from ..exceptions import InvalidSubtitle, ProviderNotAvailable, ProviderError
+from ..subtitle import Subtitle, is_valid_subtitle
+from ..video import Episode
+
+
+logger = logging.getLogger(__name__)
+
+
+class TVsubtitlesSubtitle(Subtitle):
+    provider_name = 'tvsubtitles'
+
+    def __init__(self, language, series, season, episode, id, rip, release):
+        super(TVsubtitlesSubtitle, self).__init__(language)
+        self.series = series
+        self.season = season
+        self.episode = episode
+        self.id = id
+        self.rip = rip
+        self.release = release
+
+    def compute_matches(self, video):
+        matches = set()
+        # series
+        if video.series and self.series == video.series:
+            matches.add('series')
+        # season
+        if video.season and self.season == video.season:
+            matches.add('season')
+        # episode
+        if video.episode and self.episode == video.episode:
+            matches.add('episode')
+        # release_group
+        if video.release_group and self.release and video.release_group.lower() in self.release.lower():
+            matches.add('release_group')
+        # video_codec
+        if video.video_codec and self.release and (video.video_codec in self.release.lower()
+                                                   or video.video_codec == 'h264' and 'x264' in self.release.lower()):
+            matches.add('video_codec')
+        # resolution
+        if video.resolution and self.rip and video.resolution in self.rip.lower():
+            matches.add('resolution')
+        return matches
+
+
+class TVsubtitlesProvider(Provider):
+    languages = {babelfish.Language('por', 'BR')} | {babelfish.Language(l)
+                 for l in ['ara', 'bul', 'ces', 'dan', 'deu', 'ell', 'eng', 'fin', 'fra', 'hun', 'ita', 'jpn', 'kor',
+                           'nld', 'pol', 'por', 'ron', 'rus', 'spa', 'swe', 'tur', 'ukr', 'zho']}
+    video_types = (Episode,)
+    server = 'http://www.tvsubtitles.net'
+    episode_id_re = re.compile('^episode-(\d+)\.html$')
+    subtitle_re = re.compile('^\/subtitle-(\d+)\.html$')
+
+    def initialize(self):
+        self.session = requests.Session()
+        self.session.headers = {'User-Agent': 'Subliminal/%s' % __version__}
+
+    def terminate(self):
+        self.session.close()
+
+    def request(self, url, params=None, data=None, method='GET'):
+        """Make a `method` request on `url` with the given parameters
+
+        :param string url: part of the URL to reach with the leading slash
+        :param dict params: params of the request
+        :param dict data: data of the request
+        :return: the response
+        :rtype: :class:`bs4.BeautifulSoup`
+        :raise: :class:`~subliminal.exceptions.ProviderNotAvailable`
+
+        """
+        try:
+            r = self.session.request(method, self.server + url, params=params, data=data, timeout=10)
+        except requests.Timeout:
+            raise ProviderNotAvailable('Timeout after 10 seconds')
+        if r.status_code != 200:
+            raise ProviderNotAvailable('Request failed with status code %d' % r.status_code)
+        return bs4.BeautifulSoup(r.content, ['permissive'])
+
+    @region.cache_on_arguments()
+    def find_show_id(self, series):
+        """Find a show id from the series
+
+        :param string series: series of the episode
+        :return: the show id, if any
+        :rtype: int or None
+
+        """
+        data = {'q': series}
+        logger.debug('Searching series %r', data)
+        soup = self.request('/search.php', data=data, method='POST')
+        links = soup.select('div.left li div a[href^="/tvshow-"]')
+        if not links:
+            logger.info('Series %r not found', series)
+            return None
+        return int(links[0]['href'][8:-5])
+
+    @region.cache_on_arguments()
+    def find_episode_ids(self, show_id, season):
+        """Find episode ids from the show id and the season
+
+        :param int show_id: show id
+        :param int season: season of the episode
+        :return: episode ids per episode number
+        :rtype: dict
+
+        """
+        params = {'show_id': show_id, 'season': season}
+        logger.debug('Searching episodes %r', params)
+        soup = self.request('/tvshow-{show_id}-{season}.html'.format(**params))
+        episode_ids = {}
+        for row in soup.select('table#table5 tr'):
+            if not row('a', href=self.episode_id_re):
+                continue
+            cells = row('td')
+            episode_ids[int(cells[0].string.split('x')[1])] = int(cells[1].a['href'][8:-5])
+        return episode_ids
+
+    def query(self, series, season, episode):
+        show_id = self.find_show_id(series.lower())
+        if show_id is None:
+            return []
+        episode_ids = self.find_episode_ids(show_id, season)
+        if episode not in episode_ids:
+            logger.info('Episode %d not found', episode)
+            return []
+        params = {'episode_id': episode_ids[episode]}
+        logger.debug('Searching episode %r', params)
+        soup = self.request('/episode-{episode_id}.html'.format(**params))
+        return [TVsubtitlesSubtitle(babelfish.Language.fromtvsubtitles(row.h5.img['src'][13:-4]), series, season,
+                                    episode, row['href'][10:-5], row.find('p', title='rip').text.strip() or None,
+                                    row.find('p', title='release').text.strip() or None)
+                for row in soup('a', href=self.subtitle_re)]
+
+    def list_subtitles(self, video, languages):
+        return [s for s in self.query(video.series, video.season, video.episode) if s.language in languages]
+
+    def download_subtitle(self, subtitle):
+        try:
+            r = self.session.get(self.server + '/download-{subtitle_id}.html'.format(subtitle_id=subtitle.id),
+                                 timeout=10)
+        except requests.Timeout:
+            raise ProviderNotAvailable('Timeout after 10 seconds')
+        if r.status_code != 200:
+            raise ProviderNotAvailable('Request failed with status code %d' % r.status_code)
+        with zipfile.ZipFile(io.BytesIO(r.content)) as zf:
+            if len(zf.namelist()) > 1:
+                raise ProviderError('More than one file to unzip')
+            subtitle_bytes = zf.read(zf.namelist()[0])
+        subtitle_text = subtitle_bytes.decode(charade.detect(subtitle_bytes)['encoding'], 'replace')
+        if not is_valid_subtitle(subtitle_text):
+            raise InvalidSubtitle
+        return subtitle_text

subliminal/score.py

@@ -0,0 +1,84 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+from __future__ import print_function, unicode_literals
+from sympy import Eq, symbols, solve
+
+
+# Symbols
+release_group, resolution, video_codec, audio_codec = symbols('release_group resolution video_codec audio_codec')
+imdb_id, hash, title, series, tvdb_id, season, episode = symbols('imdb_id hash title series tvdb_id season episode')
+year = symbols('year')
+
+
+def get_episode_equations():
+    """Get the score equations for a :class:`~subliminal.video.Episode`
+
+    The equations are the following:
+
+    1. hash = resolution + video_codec + audio_codec + series + season + episode + release_group
+    2. series = resolution + video_codec + audio_codec + season + episode + 1
+    3. tvdb_id = series
+    4. season = resolution + video_codec + audio_codec + 1
+    5. imdb_id = series + season + episode
+    6. resolution = video_codec
+    7. video_codec = 2 * audio_codec
+    8. title = season + episode
+    9. season = episode
+    10. release_group = season
+    11. audio_codec = 1
+
+    :return: the score equations for an episode
+    :rtype: list of :class:`sympy.Eq`
+
+    """
+    equations = []
+    equations.append(Eq(hash, resolution + video_codec + audio_codec + series + season + episode + release_group))
+    equations.append(Eq(series, resolution + video_codec + audio_codec + season + episode + release_group))
+    equations.append(Eq(tvdb_id, series))
+    equations.append(Eq(season, resolution + video_codec + audio_codec + 1))
+    equations.append(Eq(imdb_id, series + season + episode))
+    equations.append(Eq(resolution, video_codec))
+    equations.append(Eq(video_codec, 2 * audio_codec))
+    equations.append(Eq(title, season + episode))
+    equations.append(Eq(season, episode))
+    equations.append(Eq(release_group, season))
+    equations.append(Eq(audio_codec, 1))
+    return equations
+
+
+def get_movie_equations():
+    """Get the score equations for a :class:`~subliminal.video.Movie`
+
+    The equations are the following:
+
+    1. hash = resolution + video_codec + audio_codec + title + year + release_group
+    2. imdb_id = hash
+    3. resolution = video_codec
+    4. video_codec = 2 * audio_codec
+    5. title = resolution + video_codec + audio_codec + year + 1
+    6. release_group = resolution + video_codec + audio_codec + 1
+    7. year = release_group + 1
+    8. audio_codec = 1
+
+    :return: the score equations for a movie
+    :rtype: list of :class:`sympy.Eq`
+
+    """
+    equations = []
+    equations.append(Eq(hash, resolution + video_codec + audio_codec + title + year + release_group))
+    equations.append(Eq(imdb_id, hash))
+    equations.append(Eq(resolution, video_codec))
+    equations.append(Eq(video_codec, 2 * audio_codec))
+    equations.append(Eq(title, resolution + video_codec + audio_codec + year + 1))
+    equations.append(Eq(video_codec, 2 * audio_codec))
+    equations.append(Eq(release_group, resolution + video_codec + audio_codec + 1))
+    equations.append(Eq(year, release_group + 1))
+    equations.append(Eq(audio_codec, 1))
+    return equations
+
+
+if __name__ == '__main__':
+    print(solve(get_episode_equations(), [release_group, resolution, video_codec, audio_codec, imdb_id,
+                                          hash, series, tvdb_id, season, episode, title]))
+    print(solve(get_movie_equations(), [release_group, resolution, video_codec, audio_codec, imdb_id,
+                                        hash, title, year]))

subliminal/services/__init__.py

@@ -1,214 +0,0 @@
-# -*- 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 MissingLanguageError, DownloadFailedError
-import logging
-import os
-import requests
-import threading
-
-
-__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 v0.5'
-
-    #: Whether based on an API or not
-    api_based = False
-
-    #: Timeout for web requests
-    timeout = 5
-
-    #: Lock for cache interactions
-    lock = threading.Lock()
-
-    #: Mapping to Service's language codes and subliminal's
-    languages = {}
-
-    #: Whether the mapping is reverted or not
-    reverted_languages = False
-
-    #: 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
-
-    def __init__(self, config=None):
-        self.config = config or ServiceConfig()
-
-    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 terminate(self):
-        """Terminate connection"""
-        logger.debug(u'Terminating %s' % self.__class__.__name__)
-
-    def query(self, *args):
-        """Make the actual query"""
-        pass
-
-    def list(self, video, languages):
-        """List subtitles"""
-        pass
-
-    def download(self, subtitle):
-        """Download a subtitle"""
-        self.download_file(subtitle.link, subtitle.path)
-
-    @classmethod
-    def available_languages(cls):
-        """Available languages in the Service
-
-        :return: available languages
-        :rtype: set
-
-        """
-        if not cls.reverted_languages:
-            return set(cls.languages.keys())
-        return set(cls.languages.values())
-
-    @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 set languages: languages to check
-        :rtype: bool
-
-        """
-        languages &= cls.available_languages()
-        if not languages:
-            logger.debug(u'No language available for service %s' % cls.__class__.__name__.lower())
-            return False
-        if not cls.is_valid_video(video):
-            logger.debug(u'%r is not valid for service %s' % (video, cls.__class__.__name__.lower()))
-            return False
-        return True
-
-    @classmethod
-    def is_valid_video(cls, video):
-        """Check if video is valid in the Service
-
-        :param video: the video to check
-        :type video: :class:`~subliminal.videos.Video`
-        :rtype: bool
-
-        """
-        if cls.require_video and not video.exists:
-            return False
-        if not isinstance(video, tuple(cls.videos)):
-            return False
-        return True
-
-    @classmethod
-    def is_valid_language(cls, language):
-        """Check if language is valid in the Service
-
-        :param string language: the language to check
-        :rtype: bool
-
-        """
-        if language in cls.available_languages():
-            return True
-        return False
-
-    @classmethod
-    def get_revert_language(cls, language):
-        """ISO-639-1 language code from service language code
-
-        :param string language: service language code
-        :return: ISO-639-1 language code
-        :rtype: string
-
-        """
-        if not cls.reverted_languages and language in cls.languages.values():
-            return [k for k, v in cls.languages.iteritems() if v == language][0]
-        if cls.reverted_languages and language in cls.languages.keys():
-            return cls.languages[language]
-        raise MissingLanguageError(language)
-
-    @classmethod
-    def get_language(cls, language):
-        """Service language code from ISO-639-1 language code
-
-        :param string language: ISO-639-1 language code
-        :return: service language code
-        :rtype: string
-
-        """
-        if not cls.reverted_languages and language in cls.languages.keys():
-            return cls.languages[language]
-        if cls.reverted_languages and language in cls.languages.values():
-            return [k for k, v in cls.languages.iteritems() if v == language][0]
-        raise MissingLanguageError(language)
-
-    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' % url)
-        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 %s failed: %s' % (url, e))
-            if os.path.exists(filepath):
-                os.remove(filepath)
-            raise DownloadFailedError(str(e))
-        logger.debug(u'Download finished for file %s. Size: %s' % (filepath, os.path.getsize(filepath)))
-
-
-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
-
-    def __repr__(self):
-        return 'ServiceConfig(%r, %s)' % (self.multi, self.cache_dir)

subliminal/services/bierdopje.py

@@ -1,122 +0,0 @@
-# -*- 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 ..subtitles import get_subtitle_path, ResultSubtitle
-from ..videos import Episode
-from ..utils import to_unicode
-import BeautifulSoup
-import logging
-import os.path
-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/'
-    api_based = True
-    languages = {'en': 'en', 'nl': 'nl'}
-    reverted_languages = False
-    videos = [Episode]
-    require_video = False
-
-    def __init__(self, config=None):
-        super(BierDopje, self).__init__(config)
-        self.showids = {}
-        if self.config and self.config.cache_dir:
-            self.init_cache()
-
-    def init_cache(self):
-        logger.debug(u'Initializing cache...')
-        if not self.config or not self.config.cache_dir:
-            raise ServiceError('Cache directory is required')
-        self.showids_cache = os.path.join(self.config.cache_dir, 'bierdopje_showids.cache')
-        if not os.path.exists(self.showids_cache):
-            self.save_cache()
-
-    def save_cache(self):
-        logger.debug(u'Saving showids to cache...')
-        with self.lock:
-            with open(self.showids_cache, 'w') as f:
-                pickle.dump(self.showids, f)
-
-    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, season, episode, languages, filepath, tvdbid=None, series=None):
-        self.load_cache()
-        if series:
-            if series.lower() in self.showids:  # from cache
-                request_id = self.showids[series.lower()]
-                logger.debug(u'Retreived showid %d for %s from cache' % (request_id, series))
-            else:  # query to get showid
-                logger.debug(u'Getting showid from show name %s...' % 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 []
-                soup = BeautifulSoup.BeautifulStoneSoup(r.content)
-                if soup.status.contents[0] == 'false':
-                    logger.debug(u'Could not find show %s' % series)
-                    return []
-                request_id = int(soup.showid.contents[0])
-                self.showids[series.lower()] = request_id
-                self.save_cache()
-            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))
-            r = self.session.get('%sGetAllSubsFor/%s/%s/%s/%s/%s' % (self.server_url, request_id, season, episode, language, 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.BeautifulStoneSoup(r.content)
-            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))
-                continue
-            path = get_subtitle_path(filepath, language, self.config.multi)
-            for result in soup.results('result'):
-                subtitle = ResultSubtitle(path, language, service=self.__class__.__name__.lower(), link=result.downloadlink.contents[0],
-                                          release=to_unicode(result.filename.contents[0]))
-                subtitles.append(subtitle)
-        return subtitles
-
-    def list(self, video, languages):
-        if not self.check_validity(video, languages):
-            return []
-        results = self.query(video.season, video.episode, languages, video.path or video.release, video.tvdbid, video.series)
-        return results
-
-
-Service = BierDopje

subliminal/services/opensubtitles.py

@@ -1,143 +0,0 @@
-# -*- 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 ..subtitles import get_subtitle_path, ResultSubtitle
-from ..videos import Episode, Movie
-from ..utils import to_unicode
-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
-    languages = {'aa': 'aar', 'ab': 'abk', 'af': 'afr', 'ak': 'aka', 'sq': 'alb', 'am': 'amh', 'ar': 'ara',
-                 'an': 'arg', 'hy': 'arm', 'as': 'asm', 'av': 'ava', 'ae': 'ave', 'ay': 'aym', 'az': 'aze',
-                 'ba': 'bak', 'bm': 'bam', 'eu': 'baq', 'be': 'bel', 'bn': 'ben', 'bh': 'bih', 'bi': 'bis',
-                 'bs': 'bos', 'br': 'bre', 'bg': 'bul', 'my': 'bur', 'ca': 'cat', 'ch': 'cha', 'ce': 'che',
-                 'zh': 'chi', 'cu': 'chu', 'cv': 'chv', 'kw': 'cor', 'co': 'cos', 'cr': 'cre', 'cs': 'cze',
-                 'da': 'dan', 'dv': 'div', 'nl': 'dut', 'dz': 'dzo', 'en': 'eng', 'eo': 'epo', 'et': 'est',
-                 'ee': 'ewe', 'fo': 'fao', 'fj': 'fij', 'fi': 'fin', 'fr': 'fre', 'fy': 'fry', 'ff': 'ful',
-                 'ka': 'geo', 'de': 'ger', 'gd': 'gla', 'ga': 'gle', 'gl': 'glg', 'gv': 'glv', 'el': 'ell',
-                 'gn': 'grn', 'gu': 'guj', 'ht': 'hat', 'ha': 'hau', 'he': 'heb', 'hz': 'her', 'hi': 'hin',
-                 'ho': 'hmo', 'hr': 'hrv', 'hu': 'hun', 'ig': 'ibo', 'is': 'ice', 'io': 'ido', 'ii': 'iii',
-                 'iu': 'iku', 'ie': 'ile', 'ia': 'ina', 'id': 'ind', 'ik': 'ipk', 'it': 'ita', 'jv': 'jav',
-                 'ja': 'jpn', 'kl': 'kal', 'kn': 'kan', 'ks': 'kas', 'kr': 'kau', 'kk': 'kaz', 'km': 'khm',
-                 'ki': 'kik', 'rw': 'kin', 'ky': 'kir', 'kv': 'kom', 'kg': 'kon', 'ko': 'kor', 'kj': 'kua',
-                 'ku': 'kur', 'lo': 'lao', 'la': 'lat', 'lv': 'lav', 'li': 'lim', 'ln': 'lin', 'lt': 'lit',
-                 'lb': 'ltz', 'lu': 'lub', 'lg': 'lug', 'mk': 'mac', 'mh': 'mah', 'ml': 'mal', 'mi': 'mao',
-                 'mr': 'mar', 'ms': 'may', 'mg': 'mlg', 'mt': 'mlt', 'mo': 'mol', 'mn': 'mon', 'na': 'nau',
-                 'nv': 'nav', 'nr': 'nbl', 'nd': 'nde', 'ng': 'ndo', 'ne': 'nep', 'nn': 'nno', 'nb': 'nob',
-                 'no': 'nor', 'ny': 'nya', 'oc': 'oci', 'oj': 'oji', 'or': 'ori', 'om': 'orm', 'os': 'oss',
-                 'pa': 'pan', 'fa': 'per', 'pi': 'pli', 'pl': 'pol', 'pt': 'por', 'ps': 'pus', 'qu': 'que',
-                 'rm': 'roh', 'rn': 'run', 'ru': 'rus', 'sg': 'sag', 'sa': 'san', 'sr': 'scc', 'si': 'sin',
-                 'sk': 'slo', 'sl': 'slv', 'se': 'sme', 'sm': 'smo', 'sn': 'sna', 'sd': 'snd', 'so': 'som',
-                 'st': 'sot', 'es': 'spa', 'sc': 'srd', 'ss': 'ssw', 'su': 'sun', 'sw': 'swa', 'sv': 'swe',
-                 'ty': 'tah', 'ta': 'tam', 'tt': 'tat', 'te': 'tel', 'tg': 'tgk', 'tl': 'tgl', 'th': 'tha',
-                 'bo': 'tib', 'ti': 'tir', 'to': 'ton', 'tn': 'tsn', 'ts': 'tso', 'tk': 'tuk', 'tr': 'tur',
-                 'tw': 'twi', 'ug': 'uig', 'uk': 'ukr', 'ur': 'urd', 'uz': 'uzb', 've': 'ven', 'vi': 'vie',
-                 'vo': 'vol', 'cy': 'wel', 'wa': 'wln', 'wo': 'wol', 'xh': 'xho', 'yi': 'yid', 'yo': 'yor',
-                 'za': 'zha', 'zu': 'zul', 'ro': 'rum', 'po': 'pob', 'un': 'unk', 'ay': 'ass'}
-    reverted_languages = False
-    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_language(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_revert_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, service=self.__class__.__name__.lower(), link=result['SubDownloadLink'],
-                                      release=to_unicode(result['SubFileName']), confidence=confidence)
-            subtitles.append(subtitle)
-        return subtitles
-
-    def list(self, video, languages):
-        if not self.check_validity(video, languages):
-            return []
-        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/subswiki.py

@@ -1,99 +0,0 @@
-# -*- 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 ..subtitles import get_subtitle_path, ResultSubtitle
-from ..videos import Episode, Movie
-from subliminal.utils import get_keywords, split_keyword
-import BeautifulSoup
-import logging
-import re
-import urllib
-
-
-logger = logging.getLogger(__name__)
-
-
-class SubsWiki(ServiceBase):
-    server_url = 'http://www.subswiki.com'
-    api_based = False
-    languages = {u'English (US)': 'en', u'English (UK)': 'en', u'English': 'en', u'French': 'fr', u'Brazilian': 'po',
-                 u'Portuguese': 'pt', u'Español (Latinoamérica)': 'es', u'Español (España)': 'es', u'Español': 'es',
-                 u'Italian': 'it', u'Català': 'ca'}
-    reverted_languages = True
-    videos = [Episode, Movie]
-    require_video = False
-    release_pattern = re.compile('\nVersion (.+), ([0-9]+).([0-9])+ MBs')
-
-    def list(self, video, languages):
-        if not self.check_validity(video, languages):
-            return []
-        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.BeautifulSoup(r.content)
-        subtitles = []
-        for sub in soup('td', {'class': 'NewsTitle'}):
-            sub_keywords = split_keyword(self.release_pattern.search(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.parent.parent.findAll('td', {'class': 'language'}):
-                language = self.get_revert_language(html_language.string.strip())
-                if not language in languages:
-                    logger.debug(u'Language %r not in wanted languages %r' % (language, languages))
-                    continue
-                html_status = html_language.findNextSibling('td')
-                status = html_status.find('strong').string.strip()
-                if status != 'Completed':
-                    logger.debug(u'Wrong subtitle status %s' % status)
-                    continue
-                path = get_subtitle_path(filepath, language, self.config.multi)
-                subtitle = ResultSubtitle(path, language, service=self.__class__.__name__.lower(), link='%s%s' % (self.server_url, html_status.findNext('td').find('a')['href']))
-                subtitles.append(subtitle)
-        return subtitles
-
-Service = SubsWiki

subliminal/services/subtitulos.py

@@ -1,83 +0,0 @@
-# -*- 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 ..subtitles import get_subtitle_path, ResultSubtitle
-from ..videos import Episode
-from subliminal.utils import get_keywords, split_keyword
-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 = {u'English (US)': 'en', u'English (UK)': 'en', u'English': 'en', u'French': 'fr', u'Brazilian': 'po',
-                 u'Portuguese': 'pt', u'Español (Latinoamérica)': 'es', u'Español (España)': 'es', u'Español': 'es',
-                 u'Italian': 'it', u'Català': 'ca'}
-    reverted_languages = True
-    videos = [Episode]
-    require_video = False
-    release_pattern = re.compile('Versi&oacute;n (.+) ([0-9]+).([0-9])+ megabytes')
-
-    def list(self, video, languages):
-        if not self.check_validity(video, languages):
-            return []
-        results = self.query(video.path or video.release, languages, get_keywords(video.guess), video.series, video.season, video.episode)
-        return results
-
-    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.BeautifulSoup(r.content)
-        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_revert_language(html_language.findNext('li', {'class': 'li-idioma'}).find('strong').contents[0].string.strip())
-                if not language 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, service=self.__class__.__name__.lower(), link=html_status.findNext('span', {'class': 'descargar green'}).find('a')['href'], keywords=sub_keywords)
-                subtitles.append(subtitle)
-        return subtitles
-
-Service = Subtitulos

subliminal/services/thesubdb.py

@@ -1,65 +0,0 @@
-# -*- 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 ..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/'  # for testing purpose, use http://sandbox.thesubdb.com/ instead
-    user_agent = 'SubDB/1.0 (subliminal/0.5; https://github.com/Diaoul/subliminal)'  # defined by the API
-    api_based = True
-    languages = {'af': 'af', 'cs': 'cs', 'da': 'da', 'de': 'de', 'en': 'en', 'es': 'es', 'fi': 'fi',
-                 'fr': 'fr', 'hu': 'hu', 'id': 'id', 'it': 'it', 'la': 'la', 'nl': 'nl', 'no': 'no',
-                 'oc': 'oc', 'pl': 'pl', 'pt': 'pt', 'ro': 'ro', 'ru': 'ru', 'sl': 'sl', 'sr': 'sr',
-                 'sv': 'sv', 'tr': 'tr'}  # list available with the API at http://sandbox.thesubdb.com/?action=languages
-    reverted_languages = False
-    videos = [Movie, Episode, UnknownVideo]
-    require_video = True
-
-    def list(self, video, languages):
-        if not self.check_validity(video, languages):
-            return []
-        results = self.query(video.path, video.hashes['TheSubDB'], languages)
-        return results
-
-    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 = set([self.get_revert_language(l) for l in 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, service=self.__class__.__name__.lower(), link='%s?action=download&hash=%s&language=%s' % (self.server_url, moviehash, self.get_language(language)))
-            subtitles.append(subtitle)
-        return subtitles
-
-Service = TheSubDB

subliminal/subtitle.py

@@ -0,0 +1,153 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import logging
+import os.path
+import babelfish
+import pysrt
+from .video import Episode, Movie
+
+
+logger = logging.getLogger(__name__)
+
+
+class Subtitle(object):
+    """Base class for subtitle
+
+    :param language: language of the subtitle
+    :type language: :class:`babelfish.Language`
+    :param bool hearing_impaired: `True` if the subtitle is hearing impaired, `False` otherwise
+
+    """
+    def __init__(self, language, hearing_impaired=False):
+        self.language = language
+        self.hearing_impaired = hearing_impaired
+
+    def compute_matches(self, video):
+        """Compute the matches of the subtitle against the `video`
+
+        :param video: the video to compute the matches against
+        :type video: :class:`~subliminal.video.Video`
+        :return: matches of the subtitle
+        :rtype: set
+
+        """
+        raise NotImplementedError
+
+    def compute_score(self, video):
+        """Compute the score of the subtitle against the `video`
+
+        There are equivalent matches so that a provider can match one element or its equivalent. This is
+        to give all provider a chance to have a score in the same range without hurting quality.
+
+        * Matching :class:`~subliminal.video.Video`'s `hashes` is equivalent to matching everything else
+        * Matching :class:`~subliminal.video.Episode`'s `season` and `episode`
+          is equivalent to matching :class:`~subliminal.video.Episode`'s `title`
+        * Matching :class:`~subliminal.video.Episode`'s `tvdb_id` is equivalent to matching
+          :class:`~subliminal.video.Episode`'s `series`
+
+        :param video: the video to compute the score against
+        :type video: :class:`~subliminal.video.Video`
+        :return: score of the subtitle
+        :rtype: int
+
+        """
+        score = 0
+        # compute matches
+        initial_matches = self.compute_matches(video)
+        matches = initial_matches.copy()
+        # hash is the perfect match
+        if 'hash' in matches:
+            score = video.scores['hash']
+        else:
+            # remove equivalences
+            if isinstance(video, Episode):
+                if 'imdb_id' in matches:
+                    matches -= {'series', 'tvdb_id', 'season', 'episode', 'title'}
+                if 'tvdb_id' in matches:
+                    matches -= {'series'}
+                if 'title' in matches:
+                    matches -= {'season', 'episode'}
+            # add other scores
+            score += sum((video.scores[match] for match in matches))
+        logger.info('Computed score %d with matches %r', score, initial_matches)
+        return score
+
+    def __repr__(self):
+        return '<%s [%r]>' % (self.__class__.__name__, self.language)
+
+
+def get_subtitle_path(video_path, language=None):
+    """Create the subtitle path from the given `video_path` and `language`
+
+    :param string video_path: path to the video
+    :param language: language of the subtitle to put in the path
+    :type language: :class:`babelfish.Language` or None
+    :return: path of the subtitle
+    :rtype: string
+
+    """
+    subtitle_path = os.path.splitext(video_path)[0]
+    if language is not None:
+        try:
+            return subtitle_path + '.%s.%s' % (language.alpha2, 'srt')
+        except babelfish.ConvertError:
+            return subtitle_path + '.%s.%s' % (language.alpha3, 'srt')
+    return subtitle_path + '.srt'
+
+
+def is_valid_subtitle(subtitle_text):
+    """Check if a subtitle text is a valid SubRip format
+
+    :return: `True` if the subtitle is valid, `False` otherwise
+    :rtype: bool
+
+    """
+    try:
+        pysrt.from_string(subtitle_text, error_handling=pysrt.ERROR_RAISE)
+        return True
+    except pysrt.Error:
+        return False
+
+
+def compute_guess_matches(video, guess):
+    """Compute matches between a `video` and a `guess`
+
+    :param video: the video to compute the matches on
+    :type video: :class:`~subliminal.video.Video`
+    :param guess: the guess to compute the matches on
+    :type guess: :class:`guessit.Guess`
+    :return: matches of the `guess`
+    :rtype: set
+
+    """
+    matches = set()
+    if isinstance(video, Episode):
+        # Series
+        if video.series and 'series' in guess and guess['series'].lower() == video.series.lower():
+            matches.add('series')
+        # Season
+        if video.season and 'seasonNumber' in guess and guess['seasonNumber'] == video.season:
+            matches.add('season')
+        # Episode
+        if video.episode and 'episodeNumber' in guess and guess['episodeNumber'] == video.episode:
+            matches.add('episode')
+    elif isinstance(video, Movie):
+        # Year
+        if video.year and 'year' in guess and guess['year'] == video.year:
+            matches.add('year')
+    # Title
+    if video.title and 'title' in guess and guess['title'].lower() == video.title.lower():
+        matches.add('title')
+    # Release group
+    if video.release_group and 'releaseGroup' in guess and guess['releaseGroup'].lower() == video.release_group.lower():
+        matches.add('release_group')
+    # Screen size
+    if video.resolution and 'screenSize' in guess and guess['screenSize'] == video.resolution:
+        matches.add('resolution')
+    # Video codec
+    if video.video_codec and 'videoCodec' in guess and guess['videoCodec'] == video.video_codec:
+        matches.add('video_codec')
+    # Audio codec
+    if video.audio_codec and 'audioCodec' in guess and guess['audioCodec'] == video.audio_codec:
+        matches.add('audio_codec')
+    return matches

subliminal/subtitles.py

@@ -1,130 +0,0 @@
-# -*- 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 .languages import list_languages, convert_language
-import os.path
-
-
-__all__ = ['Subtitle', 'EmbeddedSubtitle', 'ExternalSubtitle', 'ResultSubtitle', 'get_subtitle_path']
-
-
-#: Subtitles extensions
-EXTENSIONS = ['.srt', '.sub', '.txt']
-
-
-class Subtitle(object):
-    """Base class for subtitles
-
-    :param string path: path to the subtitle
-    :param string language: language of the subtitle (second element of :class:`~subliminal.languages.LANGUAGES`)
-
-    """
-    def __init__(self, path, 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
-
-
-class EmbeddedSubtitle(Subtitle):
-    """Subtitle embedded in a container
-
-    :param string path: path to the subtitle
-    :param string language: language of the subtitle (second element of :class:`~subliminal.languages.LANGUAGES`)
-    :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 = convert_language(subtitle.language, 1, 2)
-        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 = ''
-        for e in EXTENSIONS:
-            if path.endswith(e):
-                extension = e
-                break
-        if not extension:
-            raise ValueError('Not a supported subtitle extension')
-        language = os.path.splitext(path[:len(path) - len(extension)])[1][1:]
-        if not language in list_languages(1):
-            language = None
-        return cls(path, language)
-
-
-class ResultSubtitle(ExternalSubtitle):
-    """Subtitle found using :mod:`~subliminal.services`
-
-    :param string path: path to the subtitle
-    :param string language: language of the subtitle (second element of :class:`~subliminal.languages.LANGUAGES`)
-    :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=set()):
-        super(ResultSubtitle, self).__init__(path, language)
-        self.service = service
-        self.link = link
-        self.release = release
-        self.confidence = confidence
-        self.keywords = keywords
-
-    @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
-
-        """
-        extension = os.path.splitext(self.path)[0]
-        language = os.path.splitext(self.path[:len(self.path) - len(extension)])[1][1:]
-        if not language in list_languages(1):
-            return True
-        return False
-
-    def __repr__(self):
-        return 'ResultSubtitle(%s, %s, %.2f, %s)' % (self.language, self.service, self.confidence, self.release)
-
-
-def get_subtitle_path(video_path, language, multi):
-    """Create the subtitle path from the given video path using language if multi"""
-    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, EXTENSIONS[0])
-    return path + '%s' % EXTENSIONS[0]

subliminal/tasks.py

@@ -1,66 +0,0 @@
-# -*- 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):
-        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):
-        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/tests/__init__.py

@@ -0,0 +1,14 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+from unittest import TextTestRunner, TestSuite
+from subliminal import cache_region
+from . import test_providers, test_subliminal
+
+
+cache_region.configure('dogpile.cache.memory', expiration_time=60 * 30)
+suite = TestSuite([test_providers.suite(), test_subliminal.suite()])
+
+
+if __name__ == '__main__':
+    TextTestRunner().run(suite)

subliminal/tests/common.py

@@ -0,0 +1,19 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+from subliminal import Movie, Episode
+
+
+MOVIES = [Movie('Man of Steel (2013)/man.of.steel.2013.720p.bluray.x264-felony.mkv', 'Man of Steel',
+                release_group='felony', resolution='720p', video_codec='h264', audio_codec='DTS', imdb_id=770828,
+                size=7033732714, year=2013,
+                hashes={'opensubtitles': '5b8f8f4e41ccb21e', 'thesubdb': 'ad32876133355929d814457537e12dc2'})]
+
+EPISODES = [Episode('The Big Bang Theory/Season 07/The.Big.Bang.Theory.S07E05.720p.HDTV.X264-DIMENSION.mkv',
+                    'The Big Bang Theory', 7, 5, release_group='DIMENSION', resolution='720p', video_codec='h264',
+                    audio_codec='AC3', imdb_id=3229392, size=501910737, title='The Workplace Proximity',
+                    tvdb_id=80379,
+                    hashes={'opensubtitles': '6878b3ef7c1bd19e', 'thesubdb': '9dbbfb7ba81c9a6237237dae8589fccc'}),
+            Episode('Game of Thrones/Season 03/Game.of.Thrones.S03E10.Mhysa.720p.WEB-DL.DD5.1.H.264-NTb.mkv',
+                    'Game of Thrones', 3, 10, release_group='NTb', resolution='720p', video_codec='h264',
+                    audio_codec='AC3', imdb_id=2178796, size=2142810931, title='Mhysa', tvdb_id=121361,
+                    hashes={'opensubtitles': 'b850baa096976c22', 'thesubdb': 'b1f899c77f4c960b84b8dbf840d4e42d'})]

subliminal/tests/test_providers.py

@@ -0,0 +1,389 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import os
+from unittest import TestCase, TestSuite, TestLoader, TextTestRunner
+from babelfish import Language
+from pkg_resources import iter_entry_points
+from subliminal import PROVIDERS_ENTRY_POINT
+from subliminal.subtitle import is_valid_subtitle
+from subliminal.tests.common import MOVIES, EPISODES
+
+
+class ProviderTestCase(TestCase):
+    provider_name = ''
+
+    def setUp(self):
+        for provider_entry_point in iter_entry_points(PROVIDERS_ENTRY_POINT, self.provider_name):
+            self.Provider = provider_entry_point.load()
+            break
+
+
+class Addic7edProviderTestCase(ProviderTestCase):
+    provider_name = 'addic7ed'
+
+    def test_find_show_id(self):
+        with self.Provider() as provider:
+            show_id = provider.find_show_id('The Big Bang')
+        self.assertTrue(show_id == 126)
+
+    def test_find_show_id_error(self):
+        with self.Provider() as provider:
+            show_id = provider.find_show_id('the big how i met your mother')
+        self.assertTrue(show_id is None)
+
+    def test_get_show_ids(self):
+        with self.Provider() as provider:
+            show_ids = provider.get_show_ids()
+        self.assertTrue('the big bang theory' in show_ids and show_ids['the big bang theory'] == 126)
+
+    def test_query_episode_0(self):
+        video = EPISODES[0]
+        languages = {Language('tur'), Language('rus'), Language('heb'), Language('ita'), Language('fra'),
+                     Language('ron'), Language('nld'), Language('eng'), Language('deu'), Language('ell'),
+                     Language('por', 'BR'), Language('bul')}
+        matches = {frozenset(['episode', 'release_group', 'title', 'series', 'resolution', 'season']),
+                   frozenset(['series', 'resolution', 'season']),
+                   frozenset(['series', 'episode', 'season', 'title']),
+                   frozenset(['series', 'release_group', 'season']),
+                   frozenset(['series', 'episode', 'season', 'release_group', 'title']),
+                   frozenset(['series', 'season'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(video.series, video.season)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_query_episode_1(self):
+        video = EPISODES[1]
+        languages = {Language('ind'), Language('spa'), Language('hrv'), Language('ita'), Language('fra'),
+                     Language('cat'), Language('ell'), Language('nld'), Language('eng'), Language('fas'),
+                     Language('por'), Language('nor'), Language('deu'), Language('ron'), Language('por', 'BR'),
+                     Language('bul')}
+        matches = {frozenset(['series', 'episode', 'resolution', 'season', 'title']),
+                   frozenset(['series', 'resolution', 'season']),
+                   frozenset(['series', 'episode', 'season', 'title']),
+                   frozenset(['series', 'release_group', 'season']),
+                   frozenset(['series', 'resolution', 'release_group', 'season']),
+                   frozenset(['series', 'episode', 'season', 'release_group', 'title']),
+                   frozenset(['series', 'season'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(video.series, video.season)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_list_subtitles(self):
+        video = EPISODES[0]
+        languages = {Language('eng'), Language('fra')}
+        matches = {frozenset(['series', 'episode', 'season', 'release_group', 'title']),
+                   frozenset(['series', 'episode', 'season', 'title'])}
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_download_subtitle(self):
+        video = EPISODES[0]
+        languages = {Language('eng'), Language('fra')}
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+            subtitle_text = provider.download_subtitle(subtitles[0])
+        self.assertTrue(is_valid_subtitle(subtitle_text))
+
+
+class BierDopjeProviderTestCase(ProviderTestCase):
+    provider_name = 'bierdopje'
+
+    def test_find_show_id(self):
+        with self.Provider() as provider:
+            show_id = provider.find_show_id('The Big Bang')
+        self.assertTrue(show_id == 9203)
+
+    def test_find_show_id_error(self):
+        with self.Provider() as provider:
+            show_id = provider.find_show_id('the big how i met your mother')
+        self.assertTrue(show_id is None)
+
+    def test_query_episode_0(self):
+        video = EPISODES[0]
+        language = Language('eng')
+        matches = {frozenset(['series', 'video_codec', 'resolution', 'episode', 'season']),
+                   frozenset(['season', 'video_codec', 'episode', 'series']),
+                   frozenset(['episode', 'video_codec', 'season', 'series', 'resolution', 'release_group'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(language, video.season, video.episode, series=video.series)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == {language})
+
+    def test_query_episode_1(self):
+        video = EPISODES[1]
+        language = Language('nld')
+        matches = {frozenset(['series', 'video_codec', 'resolution', 'episode', 'season']),
+                   frozenset(['season', 'video_codec', 'episode', 'series']),
+                   frozenset(['series', 'episode', 'season']),
+                   frozenset(['season', 'video_codec', 'episode', 'release_group', 'series']),
+                   frozenset(['episode', 'video_codec', 'season', 'series', 'resolution', 'release_group'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(language, video.season, video.episode, series=video.series)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == {language})
+
+    def test_query_episode_0_tvdb_id(self):
+        video = EPISODES[0]
+        language = Language('eng')
+        matches = {frozenset(['video_codec', 'tvdb_id', 'episode', 'season', 'series']),
+                   frozenset(['episode', 'video_codec', 'series', 'season', 'tvdb_id', 'resolution', 'release_group']),
+                   frozenset(['episode', 'series', 'video_codec', 'tvdb_id', 'resolution', 'season'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(language, video.season, video.episode, tvdb_id=video.tvdb_id)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == {language})
+
+    def test_list_subtitles(self):
+        video = EPISODES[1]
+        languages = {Language('eng'), Language('nld')}
+        matches = {frozenset(['series', 'video_codec', 'tvdb_id', 'episode', 'season']),
+                   frozenset(['episode', 'video_codec', 'season', 'series', 'tvdb_id', 'resolution', 'release_group']),
+                   frozenset(['season', 'tvdb_id', 'episode', 'series']),
+                   frozenset(['episode', 'video_codec', 'season', 'series', 'tvdb_id', 'resolution']),
+                   frozenset(['episode', 'video_codec', 'season', 'series', 'tvdb_id', 'release_group'])}
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_download_subtitle(self):
+        video = EPISODES[0]
+        languages = {Language('eng'), Language('nld')}
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+            subtitle_text = provider.download_subtitle(subtitles[0])
+        self.assertTrue(is_valid_subtitle(subtitle_text))
+
+
+class OpenSubtitlesProviderTestCase(ProviderTestCase):
+    provider_name = 'opensubtitles'
+
+    def test_query_movie_0_query(self):
+        video = MOVIES[0]
+        languages = {Language('eng')}
+        matches = {frozenset([]), frozenset(['imdb_id', 'resolution', 'title', 'year']),
+                   frozenset(['imdb_id', 'title', 'year']),
+                   frozenset(['imdb_id', 'video_codec', 'title', 'year']),
+                   frozenset(['imdb_id', 'resolution', 'title', 'video_codec', 'year']),
+                   frozenset(['imdb_id', 'title', 'year', 'video_codec', 'resolution', 'release_group'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(languages, query=video.title)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_query_episode_0_query(self):
+        video = EPISODES[0]
+        languages = {Language('eng')}
+        matches = {frozenset(['series', 'episode', 'season', 'imdb_id']),
+                   frozenset(['series', 'imdb_id', 'video_codec', 'episode', 'season']),
+                   frozenset(['episode', 'title', 'series', 'imdb_id', 'video_codec', 'season'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(languages, query=video.name.split(os.sep)[-1])
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_query_episode_1_query(self):
+        video = EPISODES[1]
+        languages = {Language('eng'), Language('fra')}
+        matches = {frozenset(['episode', 'title', 'series', 'imdb_id', 'video_codec', 'season']),
+                   frozenset(['series', 'imdb_id', 'title', 'episode', 'season']),
+                   frozenset(['series', 'imdb_id', 'video_codec', 'episode', 'season']),
+                   frozenset(['episode', 'video_codec', 'series', 'imdb_id', 'resolution', 'season']),
+                   frozenset(['series', 'imdb_id', 'resolution', 'episode', 'season']),
+                   frozenset(['series', 'episode', 'season', 'imdb_id'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(languages, query=video.name.split(os.sep)[-1])
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_query_movie_0_imdb_id(self):
+        video = MOVIES[0]
+        languages = {Language('eng'), Language('fra')}
+        matches = {frozenset(['imdb_id', 'video_codec', 'title', 'year']),
+                   frozenset(['imdb_id', 'resolution', 'title', 'video_codec', 'year']),
+                   frozenset(['imdb_id', 'title', 'year', 'video_codec', 'resolution', 'release_group']),
+                   frozenset(['imdb_id', 'title', 'year']),
+                   frozenset(['imdb_id', 'resolution', 'title', 'year'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(languages, imdb_id=video.imdb_id)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_query_episode_0_imdb_id(self):
+        video = EPISODES[0]
+        languages = {Language('eng'), Language('fra')}
+        matches = {frozenset(['series', 'episode', 'season', 'imdb_id']),
+                   frozenset(['episode', 'release_group', 'video_codec', 'series', 'imdb_id', 'resolution', 'season']),
+                   frozenset(['series', 'imdb_id', 'video_codec', 'episode', 'season']),
+                   frozenset(['episode', 'title', 'series', 'imdb_id', 'video_codec', 'season'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(languages, imdb_id=video.imdb_id)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_query_movie_0_hash(self):
+        video = MOVIES[0]
+        languages = {Language('eng')}
+        matches = {frozenset(['hash', 'title', 'video_codec', 'year', 'resolution', 'imdb_id']),
+                   frozenset(['hash', 'title', 'video_codec', 'year', 'resolution', 'release_group', 'imdb_id']),
+                   frozenset(['year', 'video_codec', 'imdb_id', 'hash', 'title']),
+                   frozenset(['year', 'resolution', 'imdb_id', 'hash', 'title']),
+                   frozenset(['year', 'imdb_id', 'hash', 'title'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(languages, hash=video.hashes['opensubtitles'], size=video.size)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_query_episode_0_hash(self):
+        video = EPISODES[0]
+        languages = {Language('eng')}
+        matches = {frozenset(['series', 'hash']),
+                   frozenset(['episode', 'season', 'series', 'imdb_id', 'video_codec', 'hash']),
+                   frozenset(['series', 'episode', 'season', 'hash', 'imdb_id']),
+                   frozenset(['series', 'resolution', 'hash', 'video_codec'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(languages, hash=video.hashes['opensubtitles'], size=video.size)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_list_subtitles(self):
+        video = MOVIES[0]
+        languages = {Language('eng'), Language('fra')}
+        matches = {frozenset(['title', 'video_codec', 'year', 'resolution', 'release_group', 'imdb_id']),
+                   frozenset(['imdb_id', 'year', 'title']),
+                   frozenset(['year', 'video_codec', 'imdb_id', 'resolution', 'title']),
+                   frozenset(['hash', 'title', 'video_codec', 'year', 'resolution', 'release_group', 'imdb_id']),
+                   frozenset(['year', 'video_codec', 'imdb_id', 'hash', 'title']),
+                   frozenset(['year', 'resolution', 'imdb_id', 'hash', 'title']),
+                   frozenset(['hash', 'title', 'video_codec', 'year', 'resolution', 'imdb_id']),
+                   frozenset(['year', 'imdb_id', 'hash', 'title']),
+                   frozenset(['video_codec', 'imdb_id', 'year', 'title']),
+                   frozenset(['year', 'imdb_id', 'resolution', 'title'])}
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_download_subtitle(self):
+        video = MOVIES[0]
+        languages = {Language('eng'), Language('fra')}
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+            subtitle_text = provider.download_subtitle(subtitles[0])
+        self.assertTrue(is_valid_subtitle(subtitle_text))
+
+
+class TheSubDBProviderTestCase(ProviderTestCase):
+    provider_name = 'thesubdb'
+
+    def test_query_episode_0(self):
+        video = EPISODES[0]
+        languages = {Language('eng'), Language('spa'), Language('por')}
+        matches = {frozenset(['hash'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(video.hashes['thesubdb'])
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_query_episode_1(self):
+        video = EPISODES[1]
+        languages = {Language('eng'), Language('por')}
+        matches = {frozenset(['hash'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(video.hashes['thesubdb'])
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_list_subtitles(self):
+        video = MOVIES[0]
+        languages = {Language('eng'), Language('por')}
+        matches = {frozenset(['hash'])}
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_download_subtitle(self):
+        video = MOVIES[0]
+        languages = {Language('eng'), Language('por')}
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+            subtitle_text = provider.download_subtitle(subtitles[0])
+        self.assertTrue(is_valid_subtitle(subtitle_text))
+
+
+class TVsubtitlesProviderTestCase(ProviderTestCase):
+    provider_name = 'tvsubtitles'
+
+    def test_find_show_id(self):
+        with self.Provider() as provider:
+            show_id = provider.find_show_id('The Big Bang')
+        self.assertTrue(show_id == 154)
+
+    def test_find_show_id_error(self):
+        with self.Provider() as provider:
+            show_id = provider.find_show_id('the big gaming')
+        self.assertTrue(show_id is None)
+
+    def test_find_episode_ids(self):
+        with self.Provider() as provider:
+            episode_ids = provider.find_episode_ids(154, 5)
+        self.assertTrue(set(episode_ids.keys()) == set(range(1, 25)))
+
+    def test_query_episode_0(self):
+        video = EPISODES[0]
+        languages = {Language('fra'), Language('por'), Language('hun'), Language('ron'), Language('eng')}
+        matches = {frozenset(['series', 'episode', 'season', 'video_codec']),
+                   frozenset(['series', 'episode', 'season'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(video.series, video.season, video.episode)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_query_episode_1(self):
+        video = EPISODES[1]
+        languages = {Language('fra'), Language('ell'), Language('ron'), Language('eng'), Language('hun'),
+                     Language('por'), Language('por', 'BR')}
+        matches = {frozenset(['series', 'episode', 'resolution', 'season']),
+                   frozenset(['series', 'episode', 'season', 'video_codec']),
+                   frozenset(['series', 'episode', 'season'])}
+        with self.Provider() as provider:
+            subtitles = provider.query(video.series, video.season, video.episode)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_list_subtitles(self):
+        video = EPISODES[0]
+        languages = {Language('eng'), Language('fra')}
+        matches = {frozenset(['series', 'episode', 'season'])}
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+        self.assertTrue({frozenset(subtitle.compute_matches(video)) for subtitle in subtitles} == matches)
+        self.assertTrue({subtitle.language for subtitle in subtitles} == languages)
+
+    def test_download_subtitle(self):
+        video = EPISODES[0]
+        languages = {Language('hun')}
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+            subtitle_text = provider.download_subtitle(subtitles[0])
+        self.assertTrue(is_valid_subtitle(subtitle_text))
+
+
+def suite():
+    suite = TestSuite()
+    suite.addTest(TestLoader().loadTestsFromTestCase(Addic7edProviderTestCase))
+    suite.addTest(TestLoader().loadTestsFromTestCase(BierDopjeProviderTestCase))
+    suite.addTest(TestLoader().loadTestsFromTestCase(OpenSubtitlesProviderTestCase))
+    suite.addTest(TestLoader().loadTestsFromTestCase(TheSubDBProviderTestCase))
+    suite.addTest(TestLoader().loadTestsFromTestCase(TVsubtitlesProviderTestCase))
+    return suite
+
+
+if __name__ == '__main__':
+    TextTestRunner().run(suite())

subliminal/tests/test_subliminal.py

@@ -0,0 +1,172 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import os
+import shutil
+from unittest import TestCase, TestSuite, TestLoader, TextTestRunner
+from babelfish import Language
+from subliminal import list_subtitles, download_subtitles, download_best_subtitles, scan_video, scan_videos
+from subliminal.tests.common import MOVIES, EPISODES
+
+
+TEST_DIR = 'test_data'
+
+
+class ApiTestCase(TestCase):
+    def setUp(self):
+        os.mkdir(TEST_DIR)
+
+    def tearDown(self):
+        shutil.rmtree(TEST_DIR)
+
+    def test_list_subtitles_movie_0(self):
+        videos = [MOVIES[0]]
+        languages = {Language('eng')}
+        subtitles = list_subtitles(videos, languages)
+        self.assertTrue(len(subtitles) == len(videos))
+        self.assertTrue(len(subtitles[videos[0]]) > 0)
+
+    def test_list_subtitles_movie_0_por_br(self):
+        videos = [MOVIES[0]]
+        languages = {Language('por', 'BR')}
+        subtitles = list_subtitles(videos, languages)
+        self.assertTrue(len(subtitles) == len(videos))
+        self.assertTrue(len(subtitles[videos[0]]) > 0)
+
+    def test_list_subtitles_episodes(self):
+        videos = [EPISODES[0], EPISODES[1]]
+        languages = {Language('eng'), Language('fra')}
+        subtitles = list_subtitles(videos, languages)
+        self.assertTrue(len(subtitles) == len(videos))
+        self.assertTrue(len(subtitles[videos[0]]) > 0)
+
+    def test_download_subtitles(self):
+        videos = [EPISODES[0], EPISODES[1]]
+        for video in videos:
+            video.name = os.path.join(TEST_DIR, video.name.split(os.sep)[-1])
+        languages = {Language('eng'), Language('fra')}
+        subtitles = list_subtitles(videos, languages)
+        download_subtitles(subtitles)
+        for video in videos:
+            self.assertTrue(os.path.exists(os.path.splitext(video.name)[0] + '.en.srt'))
+            self.assertTrue(os.path.exists(os.path.splitext(video.name)[0] + '.fr.srt'))
+
+    def test_download_subtitles_single(self):
+        videos = [EPISODES[0], EPISODES[1]]
+        for video in videos:
+            video.name = os.path.join(TEST_DIR, video.name.split(os.sep)[-1])
+        languages = {Language('eng'), Language('fra')}
+        subtitles = list_subtitles(videos, languages)
+        download_subtitles(subtitles, single=True)
+        for video in videos:
+            self.assertTrue(os.path.exists(os.path.splitext(video.name)[0] + '.srt'))
+
+    def test_download_best_subtitles(self):
+        videos = [EPISODES[0], EPISODES[1]]
+        for video in videos:
+            video.name = os.path.join(TEST_DIR, video.name.split(os.sep)[-1])
+        languages = {Language('eng'), Language('fra')}
+        subtitles = download_best_subtitles(videos, languages)
+        for video in videos:
+            self.assertTrue(video in subtitles and len(subtitles[video]) == 2)
+            self.assertTrue(os.path.exists(os.path.splitext(video.name)[0] + '.en.srt'))
+            self.assertTrue(os.path.exists(os.path.splitext(video.name)[0] + '.fr.srt'))
+
+    def test_download_best_subtitles_single(self):
+        videos = [EPISODES[0], EPISODES[1]]
+        for video in videos:
+            video.name = os.path.join(TEST_DIR, video.name.split(os.sep)[-1])
+        languages = {Language('eng'), Language('fra')}
+        subtitles = download_best_subtitles(videos, languages, single=True)
+        for video in videos:
+            self.assertTrue(video in subtitles and len(subtitles[video]) == 1)
+            self.assertTrue(os.path.exists(os.path.splitext(video.name)[0] + '.srt'))
+
+    def test_download_best_subtitles_min_score(self):
+        videos = [MOVIES[0]]
+        for video in videos:
+            video.name = os.path.join(TEST_DIR, video.name.split(os.sep)[-1])
+        languages = {Language('eng'), Language('fra')}
+        subtitles = download_best_subtitles(videos, languages, min_score=1000)
+        self.assertTrue(len(subtitles) == 0)
+
+    def test_download_best_subtitles_hearing_impaired(self):
+        videos = [MOVIES[0]]
+        for video in videos:
+            video.name = os.path.join(TEST_DIR, video.name.split(os.sep)[-1])
+        languages = {Language('eng')}
+        subtitles = download_best_subtitles(videos, languages, hearing_impaired=True)
+        self.assertTrue(subtitles[videos[0]][0].hearing_impaired == True)
+
+
+class VideoTestCase(TestCase):
+    def setUp(self):
+        os.mkdir(TEST_DIR)
+        for video in MOVIES + EPISODES:
+            open(os.path.join(TEST_DIR, os.path.split(video.name)[1]), 'w').close()
+
+    def tearDown(self):
+        shutil.rmtree(TEST_DIR)
+
+    def test_scan_video_movie(self):
+        video = MOVIES[0]
+        scanned_video = scan_video(os.path.join(TEST_DIR, os.path.split(video.name)[1]))
+        self.assertTrue(scanned_video.name == os.path.join(TEST_DIR, os.path.split(video.name)[1]))
+        self.assertTrue(scanned_video.title.lower() == video.title.lower())
+        self.assertTrue(scanned_video.year == video.year)
+        self.assertTrue(scanned_video.video_codec == video.video_codec)
+        self.assertTrue(scanned_video.resolution == video.resolution)
+        self.assertTrue(scanned_video.release_group == video.release_group)
+        self.assertTrue(scanned_video.subtitle_languages == set())
+        self.assertTrue(scanned_video.hashes == {})
+        self.assertTrue(scanned_video.audio_codec is None)
+        self.assertTrue(scanned_video.imdb_id is None)
+        self.assertTrue(scanned_video.size == 0)
+
+    def test_scan_video_episode(self):
+        video = EPISODES[0]
+        scanned_video = scan_video(os.path.join(TEST_DIR, os.path.split(video.name)[1]))
+        self.assertTrue(scanned_video.name == os.path.join(TEST_DIR, os.path.split(video.name)[1]))
+        self.assertTrue(scanned_video.series == video.series)
+        self.assertTrue(scanned_video.season == video.season)
+        self.assertTrue(scanned_video.episode == video.episode)
+        self.assertTrue(scanned_video.video_codec == video.video_codec)
+        self.assertTrue(scanned_video.resolution == video.resolution)
+        self.assertTrue(scanned_video.release_group == video.release_group)
+        self.assertTrue(scanned_video.subtitle_languages == set())
+        self.assertTrue(scanned_video.hashes == {})
+        self.assertTrue(scanned_video.title is None)
+        self.assertTrue(scanned_video.tvdb_id is None)
+        self.assertTrue(scanned_video.imdb_id is None)
+        self.assertTrue(scanned_video.audio_codec is None)
+        self.assertTrue(scanned_video.size == 0)
+
+    def test_scan_video_subtitle_language_und(self):
+        video = EPISODES[0]
+        open(os.path.join(TEST_DIR, os.path.splitext(os.path.split(video.name)[1])[0]) + '.srt', 'w').close()
+        scanned_video = scan_video(os.path.join(TEST_DIR, os.path.split(video.name)[1]))
+        self.assertTrue(scanned_video.subtitle_languages == {Language('und')})
+
+    def test_scan_video_subtitles_language_eng(self):
+        video = EPISODES[0]
+        open(os.path.join(TEST_DIR, os.path.splitext(os.path.split(video.name)[1])[0]) + '.en.srt', 'w').close()
+        scanned_video = scan_video(os.path.join(TEST_DIR, os.path.split(video.name)[1]))
+        self.assertTrue(scanned_video.subtitle_languages == {Language('eng')})
+
+    def test_scan_video_subtitles_languages(self):
+        video = EPISODES[0]
+        open(os.path.join(TEST_DIR, os.path.splitext(os.path.split(video.name)[1])[0]) + '.en.srt', 'w').close()
+        open(os.path.join(TEST_DIR, os.path.splitext(os.path.split(video.name)[1])[0]) + '.fr.srt', 'w').close()
+        open(os.path.join(TEST_DIR, os.path.splitext(os.path.split(video.name)[1])[0]) + '.srt', 'w').close()
+        scanned_video = scan_video(os.path.join(TEST_DIR, os.path.split(video.name)[1]))
+        self.assertTrue(scanned_video.subtitle_languages == {Language('eng'), Language('fra'), Language('und')})
+
+def suite():
+    suite = TestSuite()
+    suite.addTest(TestLoader().loadTestsFromTestCase(ApiTestCase))
+    suite.addTest(TestLoader().loadTestsFromTestCase(VideoTestCase))
+    return suite
+
+
+if __name__ == '__main__':
+    TextTestRunner().run(suite())

subliminal/utils.py

@@ -1,64 +0,0 @@
-# -*- 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
-    return unicode(data, 'utf-8', 'replace')

subliminal/video.py

@@ -0,0 +1,371 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import datetime
+import hashlib
+import logging
+import os
+import struct
+import babelfish
+import enzyme
+import guessit
+
+
+logger = logging.getLogger(__name__)
+
+#: Video extensions
+VIDEO_EXTENSIONS = ('.3g2', '.3gp', '.3gp2', '.3gpp', '.60d', '.ajp', '.asf', '.asx', '.avchd', '.avi', '.bik',
+                    '.bix', '.box', '.cam', '.dat', '.divx', '.dmf', '.dv', '.dvr-ms', '.evo', '.flc', '.fli',
+                    '.flic', '.flv', '.flx', '.gvi', '.gvp', '.h264', '.m1v', '.m2p', '.m2ts', '.m2v', '.m4e',
+                    '.m4v', '.mjp', '.mjpeg', '.mjpg', '.mkv', '.moov', '.mov', '.movhd', '.movie', '.movx', '.mp4',
+                    '.mpe', '.mpeg', '.mpg', '.mpv', '.mpv2', '.mxf', '.nsv', '.nut', '.ogg', '.ogm', '.omf', '.ps',
+                    '.qt', '.ram', '.rm', '.rmvb', '.swf', '.ts', '.vfw', '.vid', '.video', '.viv', '.vivo', '.vob',
+                    '.vro', '.wm', '.wmv', '.wmx', '.wrap', '.wvx', '.wx', '.x264', '.xvid')
+
+#: Subtitle extensions
+SUBTITLE_EXTENSIONS = ('.srt', '.sub', '.smi', '.txt', '.ssa', '.ass', '.mpl')
+
+
+class Video(object):
+    """Base class for videos
+
+    Represent a video, existing or not, with various properties that defines it.
+    Each property has an associated score based on equations that are described in
+    subclasses.
+
+    :param string name: name or path of the video
+    :param string release_group: release group of the video
+    :param string resolution: screen size of the video stream (480p, 720p, 1080p or 1080i)
+    :param string video_codec: codec of the video stream
+    :param string audio_codec: codec of the main audio stream
+    :param int imdb_id: IMDb id of the video
+    :param dict hashes: hashes of the video file by provider names
+    :param int size: byte size of the video file
+    :param set subtitle_languages: existing subtitle languages
+
+    """
+    scores = {}
+
+    def __init__(self, name, release_group=None, resolution=None, video_codec=None, audio_codec=None, imdb_id=None,
+                 hashes=None, size=None, subtitle_languages=None):
+        self.name = name
+        self.release_group = release_group
+        self.resolution = resolution
+        self.video_codec = video_codec
+        self.audio_codec = audio_codec
+        self.imdb_id = imdb_id
+        self.hashes = hashes or {}
+        self.size = size
+        self.subtitle_languages = subtitle_languages or set()
+
+    @classmethod
+    def fromguess(cls, name, guess):
+        if guess['type'] == 'episode':
+            return Episode.fromguess(name, guess)
+        if guess['type'] == 'movie':
+            return Movie.fromguess(name, guess)
+        raise ValueError('The guess must be an episode or a movie guess')
+
+    def __repr__(self):
+        return '<%s [%r]>' % (self.__class__.__name__, self.name)
+
+    def __hash__(self):
+        return hash(self.name)
+
+
+class Episode(Video):
+    """Episode :class:`Video`
+
+    Scores are defined by a set of equations, see :func:`~subliminal.score.get_episode_equations`
+
+    :param string series: series of the episode
+    :param int season: season number of the episode
+    :param int episode: episode number of the episode
+    :param string title: title of the episode
+    :param int tvdb_id: TheTVDB id of the episode
+
+    """
+    scores = {'title': 12, 'video_codec': 2, 'imdb_id': 35, 'audio_codec': 1, 'tvdb_id': 23, 'resolution': 2,
+              'season': 6, 'release_group': 6, 'series': 23, 'episode': 6, 'hash': 46}
+
+    def __init__(self, name, series, season, episode, release_group=None, resolution=None, video_codec=None,
+                 audio_codec=None, imdb_id=None, hashes=None, size=None, subtitle_languages=None, title=None,
+                 tvdb_id=None):
+        super(Episode, self).__init__(name, release_group, resolution, video_codec, audio_codec, imdb_id, hashes,
+                                      size, subtitle_languages)
+        self.series = series
+        self.season = season
+        self.episode = episode
+        self.title = title
+        self.tvdb_id = tvdb_id
+
+    @classmethod
+    def fromguess(cls, name, guess):
+        if guess['type'] != 'episode':
+            raise ValueError('The guess must be an episode guess')
+        if 'series' not in guess or 'season' not in guess or 'episodeNumber' not in guess:
+            raise ValueError('Insufficient data to process the guess')
+        return cls(name, guess['series'], guess['season'], guess['episodeNumber'],
+                   release_group=guess.get('releaseGroup'), resolution=guess.get('screenSize'),
+                   video_codec=guess.get('videoCodec'), audio_codec=guess.get('audioCodec'),
+                   title=guess.get('title'))
+
+    def __repr__(self):
+        return '<%s [%r, %rx%r]>' % (self.__class__.__name__, self.series, self.season, self.episode)
+
+
+class Movie(Video):
+    """Movie :class:`Video`
+
+    Scores are defined by a set of equations, see :func:`~subliminal.score.get_movie_equations`
+
+    :param string title: title of the movie
+    :param int year: year of the movie
+
+    """
+    scores = {'title': 13, 'video_codec': 2, 'resolution': 2, 'audio_codec': 1, 'year': 7, 'imdb_id': 31,
+              'release_group': 6, 'hash': 31}
+
+    def __init__(self, name, title, release_group=None, resolution=None, video_codec=None, audio_codec=None,
+                 imdb_id=None, hashes=None, size=None, subtitle_languages=None, year=None):
+        super(Movie, self).__init__(name, release_group, resolution, video_codec, audio_codec, imdb_id, hashes,
+                                    size, subtitle_languages)
+        self.title = title
+        self.year = year
+
+    @classmethod
+    def fromguess(cls, name, guess):
+        if guess['type'] != 'movie':
+            raise ValueError('The guess must be a movie guess')
+        if 'title' not in guess:
+            raise ValueError('Insufficient data to process the guess')
+        return cls(name, guess['title'], release_group=guess.get('releaseGroup'), resolution=guess.get('screenSize'),
+                   video_codec=guess.get('videoCodec'), audio_codec=guess.get('audioCodec'),
+                   year=guess.get('year'))
+
+    def __repr__(self):
+        if self.year is None:
+            return '<%s [%r]>' % (self.__class__.__name__, self.title)
+        return '<%s [%r, %r]>' % (self.__class__.__name__, self.title, self.year)
+
+
+def scan_subtitle_languages(path):
+    """Search for subtitles with alpha2 extension from a video `path` and return their language
+
+    :param string path: path to the video
+    :return: found subtitle languages
+    :rtype: set
+
+    """
+    language_extensions = tuple('.' + c for c in babelfish.CONVERTERS['alpha2'].codes)
+    dirpath, filename = os.path.split(path)
+    subtitles = set()
+    for p in os.listdir(dirpath):
+        if not isinstance(p, bytes) and p.startswith(os.path.splitext(filename)[0]) and p.endswith(SUBTITLE_EXTENSIONS):
+            if os.path.splitext(p)[0].endswith(language_extensions):
+                subtitles.add(babelfish.Language.fromalpha2(os.path.splitext(p)[0][-2:]))
+            else:
+                subtitles.add(babelfish.Language('und'))
+    logger.debug('Found subtitles %r', subtitles)
+    return subtitles
+
+
+def scan_video(path, subtitles=True, embedded_subtitles=True):
+    """Scan a video and its subtitle languages from a video `path`
+
+    :param string path: absolute path to the video
+    :param bool subtitles: scan for subtitles with the same name
+    :param bool embedded_subtitles: scan for embedded subtitles
+    :return: the scanned video
+    :rtype: :class:`Video`
+    :raise: ValueError if cannot guess enough information from the path
+
+    """
+    dirpath, filename = os.path.split(path)
+    logger.info('Scanning video %r in %r', filename, dirpath)
+    video = Video.fromguess(path, guessit.guess_file_info(path, 'autodetect'))
+    video.size = os.path.getsize(path)
+    if video.size > 10485760:
+        logger.debug('Size is %d', video.size)
+        video.hashes['opensubtitles'] = hash_opensubtitles(path)
+        video.hashes['thesubdb'] = hash_thesubdb(path)
+        logger.debug('Computed hashes %r', video.hashes)
+    else:
+        logger.warning('Size is lower than 10MB: hashes not computed')
+    if subtitles:
+        video.subtitle_languages |= scan_subtitle_languages(path)
+    # enzyme
+    try:
+        if filename.endswith('.mkv'):
+            with open(path, 'rb') as f:
+                mkv = enzyme.MKV(f)
+            if mkv.video_tracks:
+                video_track = mkv.video_tracks[0]
+                # resolution
+                if video_track.height in (480, 720, 1080):
+                    if video_track.interlaced:
+                        video.resolution = '%di' % video_track.height
+                        logger.debug('Found resolution %s with enzyme', video.resolution)
+                    else:
+                        video.resolution = '%dp' % video_track.height
+                        logger.debug('Found resolution %s with enzyme', video.resolution)
+                # video codec
+                if video_track.codec_id == 'V_MPEG4/ISO/AVC':
+                    video.video_codec = 'h264'
+                    logger.debug('Found video_codec %s with enzyme', video.video_codec)
+                elif video_track.codec_id == 'V_MPEG4/ISO/SP':
+                    video.video_codec = 'DivX'
+                    logger.debug('Found video_codec %s with enzyme', video.video_codec)
+                elif video_track.codec_id == 'V_MPEG4/ISO/ASP':
+                    video.video_codec = 'XviD'
+                    logger.debug('Found video_codec %s with enzyme', video.video_codec)
+            else:
+                logger.warning('MKV has no video track')
+            if mkv.audio_tracks:
+                audio_track = mkv.audio_tracks[0]
+                # audio codec
+                if audio_track.codec_id == 'A_AC3':
+                    video.audio_codec = 'AC3'
+                    logger.debug('Found audio_codec %s with enzyme', video.audio_codec)
+                elif audio_track.codec_id == 'A_DTS':
+                    video.audio_codec = 'DTS'
+                    logger.debug('Found audio_codec %s with enzyme', video.audio_codec)
+                elif audio_track.codec_id == 'A_AAC':
+                    video.audio_codec = 'AAC'
+                    logger.debug('Found audio_codec %s with enzyme', video.audio_codec)
+            else:
+                logger.warning('MKV has no audio track')
+            if mkv.subtitle_tracks:
+                # embedded subtitles
+                if embedded_subtitles:
+                    embedded_subtitle_languages = set()
+                    for st in mkv.subtitle_tracks:
+                        try:
+                            embedded_subtitle_languages.add(babelfish.Language.fromalpha3b(st.language or 'und'))
+                        except babelfish.Error:
+                            logger.error('Embedded subtitle language %r is not a valid language', st.language)
+                    logger.debug('Found embedded subtitle %r with enzyme', embedded_subtitle_languages)
+                    video.subtitle_languages |= embedded_subtitle_languages
+            else:
+                logger.info('MKV has no subtitle track')
+    except enzyme.Error:
+        logger.error('Parsing video metadata with enzyme failed')
+    return video
+
+
+def scan_videos(paths, subtitles=True, embedded_subtitles=True, age=None):
+    """Scan `paths` for videos and their subtitle languages
+
+    :params paths: absolute paths to scan for videos
+    :type paths: list of string
+    :param bool subtitles: scan for subtitles with the same name
+    :param bool embedded_subtitles: scan for embedded subtitles
+    :param age: age of the video, if any
+    :type age: datetime.timedelta or None
+    :return: the scanned videos
+    :rtype: list of :class:`Video`
+
+    """
+    videos = []
+    # scan files
+    for filepath in [p for p in paths if os.path.isfile(p)]:
+        if age and datetime.datetime.now() - datetime.datetime.fromtimestamp(os.path.getmtime(filepath)) > age:
+            logger.info('Skipping video %r: older than %r', filepath, age)
+            continue
+        try:
+            videos.append(scan_video(filepath, subtitles, embedded_subtitles))
+        except ValueError as e:
+            logger.error('Skipping video: %s', e)
+            continue
+    # scan directories
+    for path in [p for p in paths if os.path.isdir(p)]:
+        logger.info('Scanning directory %r', path)
+        for dirpath, dirnames, filenames in os.walk(path):
+            # skip badly encoded directories
+            if isinstance(dirpath, bytes):
+                logger.error('Skipping badly encoded directory %r', dirpath.decode('utf-8', errors='replace'))
+                continue
+            # skip badly encoded and hidden sub directories
+            for dirname in list(dirnames):
+                if isinstance(dirname, bytes):
+                    logger.error('Skipping badly encoded dirname %r in %r', dirname.decode('utf-8', errors='replace'),
+                                 dirpath)
+                    dirnames.remove(dirname)
+                elif dirname.startswith('.'):
+                    logger.debug('Skipping hidden dirname %r in %r', dirname, dirpath)
+                    dirnames.remove(dirname)
+            # scan for videos
+            for filename in filenames:
+                # skip badly encoded files
+                if isinstance(filename, bytes):
+                    logger.error('Skipping badly encoded filename %r in %r', filename.decode('utf-8', errors='replace'),
+                                 dirpath)
+                    continue
+                # filter videos
+                if not filename.endswith(VIDEO_EXTENSIONS):
+                    continue
+                # skip hidden files
+                if filename.startswith('.'):
+                    logger.debug('Skipping hidden filename %r in %r', filename, dirpath)
+                    continue
+                filepath = os.path.join(dirpath, filename)
+                # skip links
+                if os.path.islink(filepath):
+                    logger.debug('Skipping link %r in %r', filename, dirpath)
+                    continue
+                if age and datetime.datetime.now() - datetime.datetime.fromtimestamp(os.path.getmtime(filepath)) > age:
+                    logger.info('Skipping video %r: older than %r', filepath, age)
+                    continue
+                try:
+                    video = scan_video(filepath, subtitles, embedded_subtitles)
+                except ValueError as e:
+                    logger.error('Skipping video: %s', e)
+                    continue
+                videos.append(video)
+    return videos
+
+
+def hash_opensubtitles(video_path):
+    """Compute a hash using OpenSubtitles' algorithm
+
+    :param string video_path: path of the video
+    :return: the hash
+    :rtype: string
+
+    """
+    bytesize = struct.calcsize(b'q')
+    with open(video_path, 'rb') as f:
+        filesize = os.path.getsize(video_path)
+        filehash = filesize
+        if filesize < 65536 * 2:
+            return None
+        for _ in range(65536 / bytesize):
+            filebuffer = f.read(bytesize)
+            (l_value,) = struct.unpack(b'q', 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(b'q', filebuffer)
+            filehash += l_value
+            filehash = filehash & 0xFFFFFFFFFFFFFFFF
+    returnedhash = '%016x' % filehash
+    return returnedhash
+
+
+def hash_thesubdb(video_path):
+    """Compute a hash using TheSubDB's algorithm
+
+    :param string video_path: path of the video
+    :return: the hash
+    :rtype: string
+
+    """
+    readsize = 64 * 1024
+    if os.path.getsize(video_path) < readsize:
+        return None
+    with open(video_path, 'rb') as f:
+        data = f.read(readsize)
+        f.seek(-readsize, os.SEEK_END)
+        data += f.read(readsize)
+    return hashlib.md5(data).hexdigest().decode('ascii')

subliminal/videos.py

@@ -1,269 +0,0 @@
-# -*- 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 .languages import list_languages
-import enzyme
-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 enzyme.ParseError:
-            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])
-        for l in list_languages(1):
-            for e in subtitles.EXTENSIONS:
-                single_path = basepath + '%s' % e
-                if os.path.exists(single_path):
-                    results.append(subtitles.ExternalSubtitle(single_path, None))
-                multi_path = basepath + '.%s%s' % (l, e)
-                if os.path.exists(multi_path):
-                    results.append(subtitles.ExternalSubtitle(multi_path, l))
-        return results
-
-    def __repr__(self):
-        return '%s(%r)' % (self.__class__.__name__, 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, depth=0):
-    """Scan a path for videos and subtitles
-
-    :param string entry: path
-    :param int max_depth: maximum folder depth
-    :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 depth == 0:
-        entry = os.path.abspath(entry)
-    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, 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 []
-        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
-    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/test_async.py

@@ -1,58 +0,0 @@
-#!/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
-import os
-import time
-import unittest
-
-
-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 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(existing_video, languages=['en', 'fr'], cache_dir=cache_dir, max_depth=3)
-        self.assertTrue(len(results) > 0)
-
-    def test_download_subtitles(self):
-        with Pool(4) as p:
-            results = p.download_subtitles(existing_video, languages=['en', 'fr'], cache_dir=cache_dir, max_depth=3)
-        self.assertTrue(len(results) > 0)
-
-
-if __name__ == '__main__':
-    unittest.main()

tests/test_services.py

@@ -1,392 +0,0 @@
-#!/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 MissingLanguageError, ServiceError
-from subliminal.services import ServiceConfig
-from subliminal.services.bierdopje import BierDopje
-from subliminal.services.opensubtitles import OpenSubtitles
-from subliminal.services.subswiki import SubsWiki
-from subliminal.services.subtitulos import Subtitulos
-from subliminal.services.thesubdb import TheSubDB
-from subliminal.subtitles import Subtitle
-import os
-import unittest
-
-
-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 BierDopjeTestCase(unittest.TestCase):
-    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_movie', 'test_list_wrong_languages']
-    download_tests = ['test_download']
-
-    def setUp(self):
-        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.movie_path = u'Inception (2010)/Inception - 1080p.mkv'
-        self.languages = set(['en', 'nl'])
-        self.wrong_languages = set(['zz', 'es'])
-        self.fake_file = u'/tmp/fake_file'
-        self.series = 'The Big Bang Theory'
-        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 BierDopje(self.config) as service:
-            results = service.query(self.season, self.episode, self.languages, self.fake_file, series=self.series)
-        self.assertTrue(len(results) > 0)
-
-    def test_query_wrong_series(self):
-        with BierDopje(self.config) as service:
-            results = service.query(self.season, self.episode, self.languages, self.fake_file, series=self.wrong_series)
-        self.assertTrue(len(results) == 0)
-
-    def test_query_wrong_languages(self):
-        with BierDopje(self.config) as service:
-            results = service.query(self.season, self.episode, self.wrong_languages, self.fake_file, series=self.series)
-        self.assertTrue(len(results) == 0)
-
-    def test_query_tvdbid(self):
-        with BierDopje(self.config) as service:
-            results = service.query(self.season, self.episode, self.languages, self.fake_file, 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.season, self.episode, self.languages, self.fake_file, 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.season, self.episode, self.languages, self.fake_file, tvdbid=self.wrong_tvdbid)
-        self.assertTrue(len(results) == 0)
-
-    def test_list_episode(self):
-        episode = videos.Video.from_path(self.episode_path)
-        with BierDopje(self.config) as service:
-            results = service.list(episode, self.languages)
-        self.assertTrue(len(results) > 0)
-
-    def test_list_movie(self):
-        movie = videos.Video.from_path(self.movie_path)
-        with BierDopje(self.config) as service:
-            results = service.list(movie, self.languages)
-        self.assertTrue(len(results) == 0)
-
-    def test_list_wrong_languages(self):
-        episode = videos.Video.from_path(self.episode_path)
-        with BierDopje(self.config) as service:
-            results = service.list(episode, self.wrong_languages)
-        self.assertTrue(len(results) == 0)
-
-    def test_download(self):
-        episode = videos.Video.from_path(self.episode_path)
-        with BierDopje(self.config) as service:
-            subtitle = service.list(episode, self.languages)[0]
-            if os.path.exists(subtitle.path):
-                os.remove(subtitle.path)
-            service.download(subtitle)
-        self.assertTrue(os.path.exists(subtitle.path))
-
-
-class OpenSubtitlesTestCase(unittest.TestCase):
-    query_tests = ['test_query_query', 'test_query_imdbid', 'test_query_hash', 'test_query_wrong_languages']
-    list_tests = ['test_list', 'test_list_wrong_languages']
-    download_tests = ['test_download']
-
-    def setUp(self):
-        self.config = ServiceConfig(multi=True, cache_dir=cache_dir)
-        self.languages = set(['en', 'fr'])
-        self.wrong_languages = set(['zz', 'yy'])
-        self.fake_file = u'/tmp/fake_file'
-        self.path = existing_video
-        self.series = 'The Big Bang Theory'
-        self.movie = 'Inception'
-        self.wrong_series = 'No Existent Show Name'
-        self.imdbid = 'tt1375666'
-        self.wrong_imdbid = 'tt9999999'
-        self.hash = '51e57c4e8fd77990'
-        self.size = 882571264L
-
-    def test_query_query(self):
-        with OpenSubtitles(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 OpenSubtitles(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 OpenSubtitles(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 OpenSubtitles(self.config) as service:
-            with self.assertRaises(MissingLanguageError):
-                service.query(self.fake_file, self.wrong_languages, moviehash=self.hash, size=self.size)
-
-    def test_list(self):
-        video = videos.Video.from_path(self.path)
-        with OpenSubtitles(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.path)
-        with OpenSubtitles(self.config) as service:
-            results = service.list(video, self.wrong_languages)
-        self.assertTrue(len(results) == 0)
-
-    def test_download(self):
-        video = videos.Video.from_path(self.path)
-        with OpenSubtitles(self.config) as service:
-            subtitle = service.list(video, self.languages)[0]
-            if os.path.exists(subtitle.path):
-                os.remove(subtitle.path)
-            result = service.download(subtitle)
-        self.assertTrue(isinstance(result, Subtitle))
-        self.assertTrue(os.path.exists(subtitle.path))
-
-
-class TheSubDBTestCase(unittest.TestCase):
-    query_tests = ['test_query', 'test_query_wrong_hash', 'test_query_wrong_languages']
-    list_tests = ['test_list', 'test_list_wrong_languages']
-    download_tests = ['test_download']
-
-    def setUp(self):
-        self.config = ServiceConfig(multi=True, cache_dir=cache_dir)
-        self.path = existing_video
-        self.hash = u'edc1981d6459c6111fe36205b4aff6c2'
-        self.wrong_hash = u'ffffffffffffffffffffffffffffffff'
-        self.languages = set(['en', 'nl'])
-        self.wrong_languages = set(['zz', 'cs'])
-        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_hash(self):
-        with TheSubDB(self.config) as service:
-            results = service.query(self.fake_file, self.wrong_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)
-
-    def test_list(self):
-        video = videos.Video.from_path(self.path)
-        with TheSubDB(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.path)
-        with TheSubDB(self.config) as service:
-            results = service.list(video, self.wrong_languages)
-        self.assertTrue(len(results) == 0)
-
-    def test_download(self):
-        video = videos.Video.from_path(self.path)
-        with TheSubDB(self.config) as service:
-            subtitle = service.list(video, self.languages)[0]
-            if os.path.exists(subtitle.path):
-                os.remove(subtitle.path)
-            service.download(subtitle)
-        self.assertTrue(os.path.exists(subtitle.path))
-
-
-class SubsWikiTestCase(unittest.TestCase):
-    query_tests = ['test_query_series', 'test_query_movie', 'test_query_wrong_parameters', 'test_query_wrong_series', 'test_query_wrong_languages']
-    list_tests = ['test_list_series', 'test_list_movie', 'test_list_series_wrong_languages']
-    download_tests = ['test_download']
-
-    def setUp(self):
-        self.config = ServiceConfig(multi=True, cache_dir=cache_dir)
-        self.fake_file = u'/tmp/fake_file'
-        self.languages = set(['en', 'es'])
-        self.wrong_languages = set(['zz', 'ay'])
-        self.movie_path = u'Soul Surfer (2011)/Soul.Surfer.(2011).DVDRip.XviD-TWiZTED.mkv'
-        self.movie_keywords = set(['twizted'])
-        self.movie = u'Soul Surfer'
-        self.movie_year = 2011
-        self.series_path = u'The Big Bang Theory/Season 05/The.Big.Bang.Theory.S05E06.HDTV.XviD-ASAP.mkv'
-        self.series_keywords = set(['asap', 'hdtv'])
-        self.series = 'The Big Bang Theory'
-        self.wrong_series = 'No Existent Show Name'
-        self.series_season = 5
-        self.series_episode = 6
-
-    def test_query_series(self):
-        with SubsWiki(self.config) as service:
-            results = service.query(self.fake_file, self.languages, keywords=self.series_keywords, series=self.series, season=self.series_season, episode=self.series_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:
-            with self.assertRaises(ServiceError):
-                service.query(self.fake_file, self.languages, keywords=self.movie_keywords, movie=self.movie, series=self.series)
-
-    def test_query_wrong_series(self):
-        with SubsWiki(self.config) as service:
-            results = service.query(self.fake_file, self.languages, keywords=self.series_keywords, series=self.wrong_series, season=self.series_season, episode=self.series_episode)
-        self.assertTrue(len(results) == 0)
-
-    def test_query_wrong_languages(self):
-        with SubsWiki(self.config) as service:
-            results = service.query(self.fake_file, self.wrong_languages, keywords=self.series_keywords, series=self.series, season=self.series_season, episode=self.series_episode)
-        self.assertTrue(len(results) == 0)
-
-    def test_list_series(self):
-        video = videos.Video.from_path(self.series_path)
-        with SubsWiki(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 SubsWiki(self.config) as service:
-            results = service.list(video, self.languages)
-        self.assertTrue(len(results) > 0)
-
-    def test_list_series_wrong_languages(self):
-        video = videos.Video.from_path(self.series_path)
-        with SubsWiki(self.config) as service:
-            results = service.list(video, self.wrong_languages)
-        self.assertTrue(len(results) == 0)
-
-    def test_download(self):
-        video = videos.Video.from_path(self.series_path)
-        with SubsWiki(self.config) as service:
-            subtitle = service.list(video, self.languages)[0]
-            if os.path.exists(subtitle.path):
-                os.remove(subtitle.path)
-            service.download(subtitle)
-        self.assertTrue(os.path.exists(subtitle.path))
-
-
-class SubtitulosTestCase(unittest.TestCase):
-    query_tests = ['test_query', 'test_query_wrong_series', 'test_query_wrong_languages']
-    list_tests = ['test_list', 'test_list_wrong_languages']
-    download_tests = ['test_download']
-
-    def setUp(self):
-        self.config = ServiceConfig(multi=True, cache_dir=cache_dir)
-        self.fake_file = u'/tmp/fake_file'
-        self.languages = set(['en', 'es'])
-        self.wrong_languages = set(['zz', 'ay'])
-        self.path = u'The Big Bang Theory/Season 05/The.Big.Bang.Theory.S05E06.HDTV.XviD-ASAP.mkv'
-        self.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(self):
-        with Subtitulos(self.config) as service:
-            results = service.query(self.fake_file, self.languages, self.keywords, self.series, self.season, self.episode)
-        self.assertTrue(len(results) > 0)
-
-    def test_query_wrong_series(self):
-        with Subtitulos(self.config) as service:
-            results = service.query(self.fake_file, self.languages, self.keywords, self.wrong_series, self.season, self.episode)
-        self.assertTrue(len(results) == 0)
-
-    def test_query_wrong_languages(self):
-        with Subtitulos(self.config) as service:
-            results = service.query(self.fake_file, self.wrong_languages, self.keywords, self.series, self.season, self.episode)
-        self.assertTrue(len(results) == 0)
-
-    def test_list(self):
-        video = videos.Video.from_path(self.path)
-        with Subtitulos(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.path)
-        with Subtitulos(self.config) as service:
-            results = service.list(video, self.wrong_languages)
-        self.assertTrue(len(results) == 0)
-
-    def test_download(self):
-        video = videos.Video.from_path(self.path)
-        with Subtitulos(self.config) as service:
-            subtitle = service.list(video, self.languages)[0]
-            if os.path.exists(subtitle.path):
-                os.remove(subtitle.path)
-            result = service.download(subtitle)
-        self.assertTrue(os.path.exists(subtitle.path))
-
-
-def query_suite():
-    suite = unittest.TestSuite()
-    suite.addTests(map(BierDopjeTestCase, BierDopjeTestCase.query_tests))
-    suite.addTests(map(OpenSubtitlesTestCase, OpenSubtitlesTestCase.query_tests))
-    suite.addTests(map(TheSubDBTestCase, TheSubDBTestCase.query_tests))
-    suite.addTests(map(SubsWikiTestCase, SubsWikiTestCase.query_tests))
-    suite.addTests(map(SubtitulosTestCase, SubtitulosTestCase.query_tests))
-    return suite
-
-
-def list_suite():
-    suite = unittest.TestSuite()
-    suite.addTests(map(BierDopjeTestCase, BierDopjeTestCase.list_tests))
-    suite.addTests(map(OpenSubtitlesTestCase, OpenSubtitlesTestCase.list_tests))
-    suite.addTests(map(TheSubDBTestCase, TheSubDBTestCase.list_tests))
-    suite.addTests(map(SubsWikiTestCase, SubsWikiTestCase.list_tests))
-    suite.addTests(map(SubtitulosTestCase, SubtitulosTestCase.list_tests))
-    return suite
-
-
-def download_suite():
-    suite = unittest.TestSuite()
-    suite.addTests(map(BierDopjeTestCase, BierDopjeTestCase.download_tests))
-    suite.addTests(map(OpenSubtitlesTestCase, OpenSubtitlesTestCase.download_tests))
-    suite.addTests(map(TheSubDBTestCase, TheSubDBTestCase.download_tests))
-    suite.addTests(map(SubsWikiTestCase, SubsWikiTestCase.download_tests))
-    suite.addTests(map(SubtitulosTestCase, SubtitulosTestCase.download_tests))
-    return suite
-
-
-if __name__ == '__main__':
-    suites = []
-    suites.append(query_suite())
-    suites.append(list_suite())
-    suites.append(download_suite())
-    unittest.TextTestRunner(verbosity=2).run(unittest.TestSuite(suites))