Update documentation

0.7.x

.coveragerc

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

.gitignore

@@ -1,8 +1,46 @@
-build
+*.py[co]
+
+# Packages
+*.egg
+*.egg-info
 dist
-subliminal.egg-info
-*.pyc
-.settings
+build
+eggs
+parts
+bin
+var
+sdist
+develop-eggs
+.installed.cfg
+
+# Installer logs
+pip-log.txt
+
+# Unit test / coverage reports
+.coverage
+.tox
+
+# Translations
+*.mo
+
+# Mr Developer
+.mr.developer.cfg
+
+# Pydev
 .project
 .pydevproject
-*~
+.settings
+
+# Rope
+.ropeproject
+
+# PyCharm
+.idea
+
+# Sphinx
+docs/_build
+
+# Subliminal unittests
+subliminal/tests/*.srt
+subliminal/tests/*_files
+subliminal/tests/*_cache

.gitmodules

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

.travis.yml

@@ -0,0 +1,25 @@
+language: python
+
+python:
+  - "2.6"
+  - "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

HISTORY.rst

@@ -0,0 +1,167 @@
+Changelog
+=========
+
+0.7.5
+-----
+**release date:** 2015-03-04
+
+* Update requirements
+* Remove BierDopje provider
+* Add pre-guessed video optional argument in scan_video
+* Improve hearing impaired support
+* Fix TVSubtitles and Podnapisi providers
+
+0.7.4
+-----
+**release date:** 2014-01-27
+
+* Fix requirements for guessit and babelfish
+
+
+0.7.3
+-----
+**release date:** 2013-11-22
+
+* Fix windows compatibility
+* Improve subtitle validation
+* Improve embedded subtitle languages detection
+* Improve unittests
+
+
+0.7.2
+-----
+**release date:** 2013-11-10
+
+* Fix TVSubtitles for ambiguous series
+* Add a CACHE_VERSION to force cache reloading on version change
+* Set CLI default cache expiration time to 30 days
+* Add podnapisi provider
+* Support script for languages e.g. Latn, Cyrl
+* Improve logging levels
+* Fix subtitle validation in some rare cases
+
+
+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

@@ -0,0 +1 @@
+include LICENSE HISTORY.rst requirements.txt

README.md

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

README.rst

@@ -0,0 +1,56 @@
+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.
+
+.. image:: https://travis-ci.org/Diaoul/subliminal.png?branch=develop
+    :target: https://travis-ci.org/Diaoul/subliminal
+
+.. 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
+* OpenSubtitles
+* Podnapisi
+* TheSubDB
+* TvSubtitles
+
+
+Usage
+-----
+CLI
+^^^
+Download english subtitles::
+
+    $ subliminal -l en -- The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4
+    1 subtitle downloaded
+
+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::
+
+    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'})
+
+    # scan for videos in the folder and their subtitles
+    videos = subliminal.scan_videos(['/path/to/video/folder'], subtitles=True, embedded_subtitles=True, age=timedelta(weeks=1))
+
+    # download
+    subliminal.download_best_subtitles(videos, {Language('eng'), Language('fra')}, age=timedelta(week=1))
+
+
+License
+-------
+MIT

dev-requirements.txt

@@ -0,0 +1,5 @@
+sympy>=0.7.3
+sphinx>=1.1.3
+sphinxcontrib-programoutput>=0.8
+Sphinx-PyPI-upload>=0.2.1
+setuptools>=1.4

docs/Makefile

@@ -0,0 +1,177 @@
+# Makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+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
+ALLSPHINXOPTS   = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+# the i18n builder cannot share the environment and doctrees with the others
+I18NSPHINXOPTS  = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+
+.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext
+
+help:
+	@echo "Please use \`make <target>' where <target> is one of"
+	@echo "  html       to make standalone HTML files"
+	@echo "  dirhtml    to make HTML files named index.html in directories"
+	@echo "  singlehtml to make a single large HTML file"
+	@echo "  pickle     to make pickle files"
+	@echo "  json       to make JSON files"
+	@echo "  htmlhelp   to make HTML files and a HTML help project"
+	@echo "  qthelp     to make HTML files and a qthelp project"
+	@echo "  devhelp    to make HTML files and a Devhelp project"
+	@echo "  epub       to make an epub"
+	@echo "  latex      to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
+	@echo "  latexpdf   to make LaTeX files and run them through pdflatex"
+	@echo "  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)/*
+
+html:
+	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
+
+dirhtml:
+	$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
+
+singlehtml:
+	$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
+	@echo
+	@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
+
+pickle:
+	$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
+	@echo
+	@echo "Build finished; now you can process the pickle files."
+
+json:
+	$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
+	@echo
+	@echo "Build finished; now you can process the JSON files."
+
+htmlhelp:
+	$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
+	@echo
+	@echo "Build finished; now you can run HTML Help Workshop with the" \
+	      ".hhp project file in $(BUILDDIR)/htmlhelp."
+
+qthelp:
+	$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
+	@echo
+	@echo "Build finished; now you can run "qcollectiongenerator" with the" \
+	      ".qhcp project file in $(BUILDDIR)/qthelp, like this:"
+	@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/subliminal.qhcp"
+	@echo "To view the help file:"
+	@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/subliminal.qhc"
+
+devhelp:
+	$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
+	@echo
+	@echo "Build finished."
+	@echo "To view the help file:"
+	@echo "# mkdir -p $$HOME/.local/share/devhelp/subliminal"
+	@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/subliminal"
+	@echo "# devhelp"
+
+epub:
+	$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
+	@echo
+	@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
+
+latex:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo
+	@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
+	@echo "Run \`make' in that directory to run these through (pdf)latex" \
+	      "(use \`make latexpdf' here to do that automatically)."
+
+latexpdf:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through pdflatex..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+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
+	@echo "Build finished. The text files are in $(BUILDDIR)/text."
+
+man:
+	$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
+	@echo
+	@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
+
+texinfo:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo
+	@echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
+	@echo "Run \`make' in that directory to run these through makeinfo" \
+	      "(use \`make info' here to do that automatically)."
+
+info:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo "Running Texinfo files through makeinfo..."
+	make -C $(BUILDDIR)/texinfo info
+	@echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
+
+gettext:
+	$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
+	@echo
+	@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
+
+changes:
+	$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
+	@echo
+	@echo "The overview file is in $(BUILDDIR)/changes."
+
+linkcheck:
+	$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
+	@echo
+	@echo "Link check complete; look for any errors in the above output " \
+	      "or in $(BUILDDIR)/linkcheck/output.txt."
+
+doctest:
+	$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
+	@echo "Testing of doctests in the sources finished, look at the " \
+	      "results in $(BUILDDIR)/doctest/output.txt."
+
+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

@@ -0,0 +1,4 @@
+<h3>Subliminal</h3>
+<p>
+    Subliminal is a Python library to search and download subtitles.
+</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 +1,11 @@
+Cache
+=====
+.. module:: subliminal.cache
+
+.. autodata:: CACHE_VERSION
+.. autofunction:: subliminal_key_generator
+.. data:: region
+
+    The dogpile.cache region
+
+Refer to `dogpile.cache's documentation <http://dogpilecache.readthedocs.org>`_ to see how to configure the 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

@@ -0,0 +1,269 @@
+# -*- coding: utf-8 -*-
+#
+# subliminal documentation build configuration file, created by
+# sphinx-quickstart on Wed Oct 23 23:24:28 2013.
+#
+# This file is execfile()d with the current directory set to its containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+import sys, os
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+sys.path.insert(0, os.path.abspath('..'))
+sys.path.append(os.path.abspath('_themes'))
+import subliminal
+
+# -- General configuration -----------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be extensions
+# coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
+extensions = ['sphinx.ext.autodoc', 'sphinxcontrib.programoutput']
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix of source filenames.
+source_suffix = '.rst'
+
+# The encoding of source files.
+#source_encoding = 'utf-8-sig'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = 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.__version__
+# The full version, including alpha/beta/rc tags.
+release = subliminal.__version__
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#language = None
+
+# There are two options for replacing |today|: either, you set today to some
+# non-false value, then it is used:
+#today = ''
+# Else, today_fmt is used as the format for a strftime call.
+#today_fmt = '%B %d, %Y'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+exclude_patterns = ['_build']
+
+# The reST default role (used for this markup: `text`) to use for all documents.
+#default_role = None
+
+# If true, '()' will be appended to :func: etc. cross-reference text.
+#add_function_parentheses = True
+
+# If true, the current module name will be prepended to all description
+# unit titles (such as .. function::).
+#add_module_names = True
+
+# If true, sectionauthor and moduleauthor directives will be shown in the
+# output. They are ignored by default.
+#show_authors = False
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# A list of ignored prefixes for module index sorting.
+#modindex_common_prefix = []
+
+# 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 = 'diaoul'
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+html_theme_options = {'github_user': 'Diaoul',
+                      'github_repo': 'subliminal',
+                      'github_branch': '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']
+
+# The name for this set of Sphinx documents.  If None, it defaults to
+# "<project> v<release> documentation".
+#html_title = None
+
+# A shorter title for the navigation bar.  Default is the same as html_title.
+#html_short_title = None
+
+# The name of an image file (relative to this directory) to place at the top
+# of the sidebar.
+#html_logo = 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
+# pixels large.
+#html_favicon = None
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
+# using the given strftime format.
+#html_last_updated_fmt = '%b %d, %Y'
+
+# If true, SmartyPants will be used to convert quotes and dashes to
+# typographically correct entities.
+#html_use_smartypants = True
+
+# Custom sidebar templates, maps document names to template names.
+html_sidebars = {
+    'index': ['sidebar-intro.html', 'sidebar-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.
+#html_additional_pages = {}
+
+# If false, no module index is generated.
+#html_domain_indices = True
+
+# If false, no index is generated.
+#html_use_index = True
+
+# If true, the index is split into individual pages for each letter.
+#html_split_index = False
+
+# If true, links to the reST sources are added to the pages.
+#html_show_sourcelink = True
+
+# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
+#html_show_sphinx = True
+
+# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
+#html_show_copyright = True
+
+# If true, an OpenSearch description file will be output, and all pages will
+# contain a <link> tag referring to it.  The value of this option must be the
+# base URL from which the finished HTML is served.
+#html_use_opensearch = ''
+
+# This is the file name suffix for HTML files (e.g. ".xhtml").
+#html_file_suffix = None
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'subliminaldoc'
+
+
+# -- Options for LaTeX output --------------------------------------------------
+
+latex_elements = {
+# The paper size ('letterpaper' or 'a4paper').
+#'papersize': 'letterpaper',
+
+# The font size ('10pt', '11pt' or '12pt').
+#'pointsize': '10pt',
+
+# Additional stuff for the LaTeX preamble.
+#'preamble': '',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title, author, documentclass [howto/manual]).
+latex_documents = [
+  ('index', 'subliminal.tex', u'subliminal Documentation',
+   u'Antoine Bertin', 'manual'),
+]
+
+# The name of an image file (relative to this directory) to place at the top of
+# the title page.
+#latex_logo = None
+
+# For "manual" documents, if this is true, then toplevel headings are parts,
+# not chapters.
+#latex_use_parts = False
+
+# If true, show page references after internal links.
+#latex_show_pagerefs = False
+
+# If true, show URL addresses after external links.
+#latex_show_urls = False
+
+# Documents to append as an appendix to all manuals.
+#latex_appendices = []
+
+# If false, no module index is generated.
+#latex_domain_indices = True
+
+
+# -- Options for manual page output --------------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    ('index', 'subliminal', u'subliminal Documentation',
+     [u'Antoine Bertin'], 1)
+]
+
+# If true, show URL addresses after external links.
+#man_show_urls = False
+
+
+# -- Options for Texinfo output ------------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+  ('index', 'subliminal', u'subliminal Documentation',
+   u'Antoine Bertin', 'subliminal', 'One line description of project.',
+   'Miscellaneous'),
+]
+
+# Documents to append as an appendix to all manuals.
+#texinfo_appendices = []
+
+# If false, no module index is generated.
+#texinfo_domain_indices = True
+
+# How to display URL addresses: 'footnote', 'no', or 'inline'.
+#texinfo_show_urls = 'footnote'
+
+# 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/index.rst

@@ -0,0 +1,102 @@
+.. subliminal documentation master file, created by
+   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.
+
+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.
+
+
+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
+* OpenSubtitles
+* Podnapisi
+* TheSubDB
+* TvSubtitles
+
+
+Usage
+-----
+CLI
+^^^
+Download english subtitles::
+
+    $ subliminal -l en -- The.Big.Bang.Theory.S05E18.HDTV.x264-LOL.mp4
+    1 subtitle downloaded
+
+See :mod:`subliminal.cli`
+
+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::
+
+    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'})
+
+    # scan for videos in the folder and their subtitles
+    videos = subliminal.scan_videos(['/path/to/video/folder'], subtitles=True, embedded_subtitles=True, age=timedelta(weeks=1))
+
+    # 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
+
+    provider_guide
+
+
+API Documentation
+-----------------
+If you are looking for information on a specific function, class or method,
+this part of the documentation is for you.
+
+.. 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.

requirements.txt

@@ -0,0 +1,9 @@
+beautifulsoup4>=4.3.2
+guessit>=0.7,<0.10
+requests>=2.0.1
+enzyme>=0.4.0
+html5lib>=0.99
+dogpile.cache>=0.5.2
+babelfish>=0.5.0
+charade>=1.0.3
+pysrt>=0.5.0

scripts/subliminal

@@ -1,80 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import argparse
-import subliminal
-import logging
-import mimetypes
-import os
-import os.path
-import sys
-
-
-def main():
-    '''Download subtitles'''
-    # parse command line options
-    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('-p', '--plugin', action='append', dest='plugins', help='plugin 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)
-    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 plugins may not work)')
-    parser.add_argument('--version', action='version', version=subliminal.__version__)
-    parser.add_argument('paths', nargs='+', help='path to video files or folders', 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')
-
-    # Initialize the instance
-    subli = subliminal.Subliminal(cache_dir=args.cache_dir, workers=args.workers, multi=args.multi, force=args.force, max_depth=3, files_mode=-1)
-    if args.plugins:
-        subli.plugins = args.plugins
-    if args.languages:
-        subli.languages = args.languages
-    try:
-        subtitles = subli.downloadSubtitles([unicode(x) for x in args.paths])
-    finally:
-        subli.stopWorkers()
-    if len(subtitles) == 0:
-        if not args.quiet:
-            sys.stderr.write('No subtitles found\n')
-        exit(1)
-    if not args.quiet:
-        print '*' * 50
-        print 'Downloaded %s subtitles' % len(subtitles)
-        for subtitle in subtitles:
-            print subtitle
-        print '*' * 50
-
-if __name__ == '__main__':
-    main()

setup.cfg

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

setup.py

@@ -1,45 +1,40 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from setuptools import setup
+from setuptools import setup, find_packages
 
 
-execfile('subliminal/version.py')
 setup(name='subliminal',
-    version=__version__,
-    license='LGPLv3',
-    description='Subliminal - Subtitles, faster than your thoughts',
-    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',
-        'Topic :: Software Development :: Libraries :: Python Modules',
-        'Topic :: Multimedia :: Video'],
-    keywords='subliminal video movie subtitle python library',
+    version='0.7.5',
+    license='MIT',
+    description='Subtitles, faster than your thoughts',
+    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=['subliminal', 'subliminal/plugins'],
-    scripts=['scripts/subliminal'],
-    py_modules=['subliminal'],
-    install_requires=['BeautifulSoup>=3.2.0', 'guessit>=0.2'])
+    packages=find_packages(),
+    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 :: 2.6',
+        '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',
+                                 'opensubtitles = subliminal.providers.opensubtitles:OpenSubtitlesProvider',
+                                 'podnapisi = subliminal.providers.podnapisi:PodnapisiProvider',
+                                 'thesubdb = subliminal.providers.thesubdb:TheSubDBProvider',
+                                 'tvsubtitles = subliminal.providers.tvsubtitles:TVsubtitlesProvider'],
+        'babelfish.language_converters': ['addic7ed = subliminal.converters.addic7ed:Addic7edConverter',
+                                          'podnapisi = subliminal.converters.podnapisi:PodnapisiConverter',
+                                          'tvsubtitles = subliminal.converters.tvsubtitles:TVsubtitlesConverter']
+    },
+    install_requires=open('requirements.txt').readlines(),
+    test_suite='subliminal.tests.suite')

subliminal/__init__.py

@@ -1,25 +1,19 @@
 # -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
+__title__ = 'subliminal'
+__version__ = '0.7.5'
+__author__ = 'Antoine Bertin'
+__license__ = 'MIT'
+__copyright__ = 'Copyright 2013 Antoine Bertin'
 
-__all__ = ['FORMATS', 'LANGUAGES', 'PLUGINS', 'API_PLUGINS', 'Subliminal', 'Subtitle']
-from classes import *
-from subliminal import *
-from version import __version__
+import logging
+from .api import PROVIDERS_ENTRY_POINT, list_subtitles, download_subtitles, download_best_subtitles
+from .cache import MutexLock, 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
+
+class NullHandler(logging.Handler):
+    def emit(self, record):
+        pass
+
+logging.getLogger(__name__).addHandler(NullHandler())

subliminal/api.py

@@ -0,0 +1,334 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import collections
+import io
+import logging
+import operator
+import babelfish
+import pkg_resources
+from os.path import basename
+from .exceptions import ProviderNotAvailable, InvalidSubtitle
+from .subtitle import get_subtitle_path
+from socket import error as socket_error
+
+logger = logging.getLogger(__name__)
+
+#: Entry point for the providers
+PROVIDERS_ENTRY_POINT = 'subliminal.providers'
+
+
+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.video.Video` => [:class:`~subliminal.subtitle.Subtitle`]
+
+    """
+    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.info('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.info('Skipping provider %r: no video to search for', provider_entry_point.name)
+            continue
+
+        # list subtitles with the provider
+        try:
+            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 as err:
+                        logger.warning('Provider %r is not available, discarding it', provider_entry_point.name)
+                        logger.debug('ProviderNotAvailable error: %r', str(err))
+                        break
+                    except:
+                        logger.exception('Unexpected error in provider %r', provider_entry_point.name)
+                        continue
+                    logger.info('Found %d subtitle(s) on %s' % (
+                        len(provider_subtitles),
+                        provider_entry_point.name,
+                    ))
+                    subtitles[provider_video].extend(provider_subtitles)
+        except ProviderNotAvailable as err:
+            logger.warning('Provider %r is not available, discarding it', provider_entry_point.name)
+            logger.debug('ProviderNotAvailable error: %r', str(err))
+    return subtitles
+
+
+def download_subtitles(subtitles, provider_configs=None, single=False):
+    """Download subtitles
+
+    :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
+
+    """
+    provider_configs = provider_configs or {}
+    discarded_providers = set()
+    providers_by_name = dict([(ep.name, ep.load()) for ep in pkg_resources.iter_entry_points(PROVIDERS_ENTRY_POINT)])
+
+    initialized_providers = {}
+    downloaded_subtitles = collections.defaultdict(list)
+    fetched_subtitles = set()
+    try:
+        for video, video_subtitles in subtitles.items():
+            languages = set([subtitle.language for subtitle in video_subtitles])
+            downloaded_languages = set()
+            for subtitle in video_subtitles:
+                # filter
+                if subtitle.language in downloaded_languages:
+                    logger.debug('Skipping subtitle: %r already downloaded', subtitle.language)
+                    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 as err:
+                        logger.warning('Provider %r is not available, discarding it', subtitle.provider_name)
+                        logger.debug('ProviderNotAvailable error: %r', str(err))
+                        discarded_providers.add(subtitle.provider_name)
+                        continue
+                    except socket_error as err:
+                        logger.warning('Provider %r is not responding, discarding it', subtitle.provider_name)
+                        logger.debug('Provider socket error: %r', str(err))
+                        discarded_providers.add(subtitle.provider_name)
+                        continue
+                    except:
+                        logger.exception('Unexpected error in provider %r', 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)
+                if basename(subtitle_path) in fetched_subtitles:
+                    logger.debug('Skipping subtitle already retrieved %r', basename(subtitle_path))
+                    continue
+
+                logger.info('Downloading subtitle %r into %r', subtitle, subtitle_path)
+                try:
+                    subtitle_text = provider.download_subtitle(subtitle)
+                    downloaded_subtitles[video].append(subtitle)
+                except ProviderNotAvailable as err:
+                    logger.warning('Provider %r is not available, discarding it', subtitle.provider_name)
+                    logger.debug('ProviderNotAvailable error: %r', str(err))
+                    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)
+                    fetched_subtitles.add(basename(subtitle_path))
+                if single or sorted(downloaded_languages) == sorted(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)
+    return downloaded_subtitles
+
+
+def download_best_subtitles(videos, languages, providers=None, provider_configs=None, single=False, min_score=0,
+                            hearing_impaired=False, hi_score_adjust=0):
+    """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
+    :param int hi_score_adjust: Adjust hearing_impaired_scores if matched.
+
+    """
+    provider_configs = provider_configs or {}
+    discarded_providers = set()
+    downloaded_subtitles = collections.defaultdict(list)
+    fetched_subtitles = set()
+    # 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: video type not hosted here.', provider_entry_point.name)
+            continue
+        provider = Provider(**provider_configs.get(provider_entry_point.name, {}))
+        try:
+            provider.initialize()
+        except ProviderNotAvailable as err:
+            logger.warning('Provider %r is not available, discarding it', provider_entry_point.name)
+            logger.debug('ProviderNotAvailable error: %r', str(err))
+            continue
+        except socket_error as err:
+            logger.warning('Provider %r is not responding, discarding it', provider_entry_point.name)
+            logger.debug('Provider socket error: %r', str(err))
+            continue
+        except:
+            logger.exception('Unexpected error in provider %r', provider_entry_point.name)
+            continue
+        initialized_providers[provider_entry_point.name] = provider
+    try:
+        for video in videos:
+            # search for subtitles
+            subtitles = []
+            downloaded_languages = set()
+            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 as err:
+                        logger.warning('Provider %r is not available, discarding it', provider_name)
+                        logger.debug('ProviderNotAvailable error: %r', str(err))
+                        discarded_providers.add(provider_name)
+                        continue
+                    except:
+                        logger.exception('Unexpected error in provider %r', provider_name)
+                        continue
+                    logger.info('Found %d subtitle(s) on %s' % (
+                        len(provider_subtitles),
+                        provider_name,
+                    ))
+                    subtitles.extend(provider_subtitles)
+
+            # find the best subtitles and download them
+            for subtitle, score in sorted([(s, s.compute_score(video, hi_score_adjust)) \
+                    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 hearing_impaired is not None:
+                    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)
+                if basename(subtitle_path) in fetched_subtitles:
+                    logger.debug('Skipping subtitle already retrieved %r', basename(subtitle_path))
+                    continue
+
+                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 as err:
+                    logger.warning('Provider %r is not available, discarding it', subtitle.provider_name)
+                    logger.debug('ProviderNotAvailable error: %r', str(err))
+                    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)
+                    fetched_subtitles.add(basename(subtitle_path))
+                if single or sorted(downloaded_languages) == sorted(languages):
+                    break
+
+    finally:  # terminate providers
+        for (provider_name, provider) in initialized_providers.items():
+            try:
+                provider.terminate()
+            except ProviderNotAvailable as err:
+                logger.warning('Provider %r is not available, unable to terminate', provider_name)
+                logger.debug('ProviderNotAvailable error: %r', str(err))
+            except socket_error as err:
+                logger.warning('Provider %r is not available, unable to terminate', provider_name)
+                logger.debug('Provider socket error: %r', str(err))
+            except:
+                logger.exception('Unexpected error in provider %r', provider_name)
+    return downloaded_subtitles

subliminal/cache.py

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+import inspect
+from dogpile.cache import make_region  # @UnresolvedImport
+from dogpile.cache.backends.file import AbstractFileLock  # @UnresolvedImport
+from dogpile.cache.compat import string_type  # @UnresolvedImport
+from dogpile.core.readwrite_lock import ReadWriteMutex  # @UnresolvedImport
+
+
+#: Subliminal's cache version
+CACHE_VERSION = 2
+
+
+def subliminal_key_generator(namespace, fn, to_str=string_type):
+    """Add a :data:`CACHE_VERSION` to dogpile.cache's default function_key_generator"""
+    if namespace is None:
+        namespace = '%d:%s:%s' % (CACHE_VERSION, fn.__module__, fn.__name__)
+    else:
+        namespace = '%d:%s:%s|%s' % (CACHE_VERSION, fn.__module__, fn.__name__, namespace)
+
+    args = inspect.getargspec(fn)
+    has_self = args[0] and args[0][0] in ('self', 'cls')
+
+    def generate_key(*args, **kw):
+        if kw:
+            raise ValueError('Keyword arguments not supported')
+        if has_self:
+            args = args[1:]
+        return namespace + '|' + ' '.join(map(to_str, args))
+    return generate_key
+
+
+class MutexLock(AbstractFileLock):
+    """:class:`MutexLock` is a thread-based rw lock based on :class:`dogpile.core.ReadWriteMutex`"""
+    def __init__(self, filename):
+        self.mutex = ReadWriteMutex()
+
+    def acquire_read_lock(self, wait):
+        ret = self.mutex.acquire_read_lock(wait)
+        return wait or ret
+
+    def acquire_write_lock(self, wait):
+        ret = self.mutex.acquire_write_lock(wait)
+        return wait or ret
+
+    def release_read_lock(self):
+        return self.mutex.release_read_lock()
+
+    def release_write_lock(self):
+        return self.mutex.release_write_lock()
+
+
+#: The dogpile.cache region (long-lived)
+region = make_region(function_key_generator=subliminal_key_generator)
+
+#: The dogpile.cache region for :meth:`~subliminal.providers.Provider.query` (short-lived)
+query_region = make_region(function_key_generator=subliminal_key_generator)

subliminal/classes.py

@@ -1,127 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-
-class Error(Exception):
-    """Base class for exceptions in subliminal"""
-    pass
-
-
-class BadStateError(Error):
-    """Exception raised when an invalid action is asked
-
-    Attributes:
-        current  -- current state of Subliminal instance
-        expected -- expected state of Subliminal instance
-    """
-    def __init__(self, current, expected):
-        self.current = current
-        self.expected = expected
-
-    def __str__(self):
-        return 'Expected state %d but current state is %d' % (self.expected, self.current)
-
-
-class LanguageError(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 PluginError(Error):
-    """"Exception raised when invalid plugin is submitted
-
-    Attributes:
-        plugin -- plugin that cause the error
-    """
-    def __init__(self, plugin):
-        self.plugin = plugin
-
-    def __str__(self):
-        return self.plugin
-
-
-class WrongTaskError(Error):
-    """"Exception raised when invalid task is submitted"""
-    pass
-
-
-class DownloadFailedError(Error):
-    """"Exception raised when a download task has failed in plugin"""
-    pass
-
-
-class Subtitle(object):
-    """Subtitle class
-
-    Attributes:
-        video_path -- path to the video file
-        path       -- path to the subtitle file
-        plugin     -- plugin used
-        language   -- language of the subtitle
-        link       -- download link
-        release    -- release group identified by guessit
-        teams      -- identified by subliminal
-    """
-    def __init__(self, video_path=None, path=None, plugin=None, language=None, link=None, release=None, teams=None):
-        self.video_path = video_path
-        self.path = path
-        self.plugin = plugin
-        self.language = language
-        self.link = link
-        self.release = release
-        self.teams = teams
-
-    def __repr__(self):
-        return repr({'video_path': self.video_path, 'path': self.path, 'plugin': self.plugin,
-            'language': self.language, 'link': self.link, 'release': self.release, 'teams': self.teams})
-
-
-class Task(object):
-    """Base class for tasks to use in subliminal"""
-    pass
-
-
-class ListTask(Task):
-    """List task to list subtitles"""
-    def __init__(self, filepath, languages, plugin, config):
-        self.filepath = filepath
-        self.plugin = plugin
-        self.languages = languages
-        self.config = config
-
-
-class DownloadTask(Task):
-    """Download task to download subtitles"""
-    def __init__(self, subtitles):
-        self.subtitles = subtitles
-
-
-class StopTask(Task):
-    """Stop task to stop workers"""
-    pass

subliminal/cli.py

@@ -0,0 +1,157 @@
+# -*- 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, MutexLock, 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 IETF codes e.g. fr, pt-BR, sr-Cyrl ')
+
+    # 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')
+
+    # 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 = set( babelfish.Language.fromietf(l) for l in args.languages )
+    except babelfish.Error:
+        parser.error('argument -l/--languages: codes are not IETF: %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(**dict([(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 = {}
+
+    # 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', expiration_time=datetime.timedelta(days=30),  # @UndefinedVariable
+                           arguments={'filename': args.cache_file, 'lock_factory': MutexLock})
+
+    # 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, info=['filename'])) 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 +1,31 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+from babelfish import LanguageReverseConverter, language_converters
+
+
+class Addic7edConverter(LanguageReverseConverter):
+    def __init__(self):
+        self.name_converter = language_converters['name']
+        self.from_addic7ed = {'Català': ('cat',), 'Chinese (Simplified)': ('zho',), 'Chinese (Traditional)': ('zho',),
+                              'Euskera': ('eus',), 'Galego': ('glg',), 'Greek': ('ell',), 'Malay': ('msa',),
+                              'Portuguese (Brazilian)': ('por', 'BR'), 'Serbian (Cyrillic)': ('srp', None, 'Cyrl'),
+                              'Serbian (Latin)': ('srp',), 'Spanish (Latin America)': ('spa',),
+                              'Spanish (Spain)': ('spa',)}
+        self.to_addic7ed = {('cat',): 'Català', ('zho',): 'Chinese (Simplified)', ('eus',): 'Euskera',
+                            ('glg',): 'Galego', ('ell',): 'Greek', ('msa',): 'Malay',
+                            ('por', 'BR'): 'Portuguese (Brazilian)', ('srp', None, 'Cyrl'): 'Serbian (Cyrillic)'}
+        self.codes = self.name_converter.codes | set(self.from_addic7ed.keys())
+
+    def convert(self, alpha3, country=None, script=None):
+        if (alpha3, country, script) in self.to_addic7ed:
+            return self.to_addic7ed[(alpha3, country, script)]
+        if (alpha3, country) in self.to_addic7ed:
+            return self.to_addic7ed[(alpha3, country)]
+        if (alpha3,) in self.to_addic7ed:
+            return self.to_addic7ed[(alpha3,)]
+        return self.name_converter.convert(alpha3, country, script)
+
+    def reverse(self, addic7ed):
+        if addic7ed in self.from_addic7ed:
+            return self.from_addic7ed[addic7ed]
+        return self.name_converter.reverse(addic7ed)

subliminal/converters/podnapisi.py

@@ -0,0 +1,32 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+from babelfish import LanguageReverseConverter, LanguageConvertError, LanguageReverseError
+
+
+class PodnapisiConverter(LanguageReverseConverter):
+    def __init__(self):
+        self.from_podnapisi = {2: ('eng',), 28: ('spa',), 26: ('pol',), 36: ('srp',), 1: ('slv',), 38: ('hrv',),
+                               9: ('ita',), 8: ('fra',), 48: ('por', 'BR'), 23: ('nld',), 12: ('ara',), 13: ('ron',),
+                               33: ('bul',), 32: ('por',), 16: ('ell',), 15: ('hun',), 31: ('fin',), 30: ('tur',),
+                               7: ('ces',), 25: ('swe',), 27: ('rus',), 24: ('dan',), 22: ('heb',), 51: ('vie',),
+                               52: ('fas',), 5: ('deu',), 14: ('spa', 'AR'), 54: ('ind',), 47: ('srp', None, 'Cyrl'),
+                               3: ('nor',), 20: ('est',), 10: ('bos',), 17: ('zho',), 37: ('slk',), 35: ('mkd',),
+                               11: ('jpn',), 4: ('kor',), 29: ('sqi',), 6: ('isl',), 19: ('lit',), 46: ('ukr',),
+                               44: ('tha',), 53: ('cat',), 56: ('sin',), 21: ('lav',), 40: ('cmn',), 55: ('msa',),
+                               42: ('hin',), 50: ('bel',)}
+        self.to_podnapisi = dict([(v, k) for k, v in self.from_podnapisi.items()])
+        self.codes = set(self.from_podnapisi.keys())
+
+    def convert(self, alpha3, country=None, script=None):
+        if (alpha3,) in self.to_podnapisi:
+            return self.to_podnapisi[(alpha3,)]
+        if (alpha3, country) in self.to_podnapisi:
+            return self.to_podnapisi[(alpha3, country)]
+        if (alpha3, country, script) in self.to_podnapisi:
+            return self.to_podnapisi[(alpha3, country, script)]
+        raise LanguageConvertError(alpha3, country, script)
+
+    def reverse(self, podnapisi):
+        if podnapisi not in self.from_podnapisi:
+            raise LanguageReverseError(podnapisi)
+        return self.from_podnapisi[podnapisi]

subliminal/converters/tvsubtitles.py

@@ -0,0 +1,24 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+from babelfish import LanguageReverseConverter, language_converters
+
+
+class TVsubtitlesConverter(LanguageReverseConverter):
+    def __init__(self):
+        self.alpha2_converter = language_converters['alpha2']
+        self.from_tvsubtitles = {'br': ('por', 'BR'), 'ua': ('ukr',), 'gr': ('ell',), 'cn': ('zho',), 'jp': ('jpn',),
+                                 'cz': ('ces',)}
+        self.to_tvsubtitles = set([(v, k) for k, v in self.from_tvsubtitles])
+        self.codes = self.alpha2_converter.codes | set(self.from_tvsubtitles.keys())
+
+    def convert(self, alpha3, country=None, script=None):
+        if (alpha3, country) in self.to_tvsubtitles:
+            return self.to_tvsubtitles[(alpha3, country)]
+        if (alpha3,) in self.to_tvsubtitles:
+            return self.to_tvsubtitles[(alpha3,)]
+        return self.alpha2_converter.convert(alpha3, country, script)
+
+    def reverse(self, tvsubtitles):
+        if tvsubtitles in self.from_tvsubtitles:
+            return self.from_tvsubtitles[tvsubtitles]
+        return self.alpha2_converter.reverse(tvsubtitles)

subliminal/exceptions.py

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+
+class Error(Exception):
+    """Base class for exceptions in subliminal"""
+    pass
+
+
+class ProviderError(Error):
+    """Exception raised by providers"""
+    pass
+
+
+class ProviderConfigurationError(ProviderError):
+    """Exception raised by providers when badly configured"""
+    pass
+
+
+class ProviderNotAvailable(ProviderError):
+    """Exception raised by providers when unavailable"""
+    pass
+
+
+class InvalidSubtitle(ProviderError):
+    """Exception raised by providers when the downloaded subtitle is invalid"""
+    pass

subliminal/plugins/Addic7ed.py

@@ -1,134 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from BeautifulSoup import BeautifulSoup
-from subliminal.classes import Subtitle
-import guessit
-import PluginBase
-import urllib2
-import re
-
-
-class Addic7ed(PluginBase.PluginBase):
-    site_url = 'http://www.addic7ed.com'
-    site_name = 'Addic7ed'
-    server_url = 'http://www.addic7ed.com'
-    api_based = False
-    _plugin_languages = {u'English': 'en',
-            u'English (US)': 'en',
-            u'English (UK)': 'en',
-            u'Italian': 'it',
-            u'Portuguese': 'pt',
-            u'Portuguese (Brazilian)': 'pt-br',
-            u'Romanian': 'ro',
-            u'Español (Latinoamérica)': 'es',
-            u'Español (España)': 'es',
-            u'Spanish (Latin America)': 'es',
-            u'Español': 'es',
-            u'Spanish': 'es',
-            u'Spanish (Spain)': 'es',
-            u'French': 'fr',
-            u'Greek': 'el',
-            u'Arabic': 'ar',
-            u'German': 'de',
-            u'Croatian': 'hr',
-            u'Indonesian': 'id',
-            u'Hebrew': 'he',
-            u'Russian': 'ru',
-            u'Turkish': 'tr',
-            u'Swedish': 'se',
-            u'Czech': 'cs',
-            u'Dutch': 'nl',
-            u'Hungarian': 'hu',
-            u'Norwegian': 'no',
-            u'Polish': 'pl',
-            u'Persian': 'fa'}
-
-    def __init__(self, config_dict=None):
-        super(Addic7ed, self).__init__(self._plugin_languages, config_dict, isRevert=True)
-        #http://www.addic7ed.com/serie/Smallville/9/11/Absolute_Justice
-        self.release_pattern = re.compile(' \nVersion (.+), ([0-9]+).([0-9])+ MBs')
-
-    def list(self, filepath, languages):
-        if not self.checkLanguages(languages):
-            return []
-        guess = guessit.guess_file_info(filepath, 'autodetect')
-        if guess['type'] != 'episode':
-            self.logger.debug(u'Not an episode')
-            return []
-        # add multiple things to the release group set
-        release_group = set()
-        if 'releaseGroup' in guess:
-            release_group.add(guess['releaseGroup'].lower())
-        else:
-            if 'title' in guess:
-                release_group.add(guess['title'].lower())
-            if 'screenSize' in guess:
-                release_group.add(guess['screenSize'].lower())
-        if 'series' not in guess or len(release_group) == 0:
-            self.logger.debug(u'Not enough information to proceed')
-            return []
-        self.release_group = release_group  # used to sort results
-        return self.query(guess['series'], guess['season'], guess['episodeNumber'], release_group, filepath, languages)
-
-    def query(self, name, season, episode, release_group, filepath, languages=None):
-        searchname = name.lower().replace(' ', '_')
-        if isinstance(searchname, unicode):
-            searchname = searchname.encode('utf-8')
-        searchurl = '%s/serie/%s/%s/%s/%s' % (self.server_url, urllib2.quote(searchname), season, episode, urllib2.quote(searchname))
-        self.logger.debug(u'Searching in %s' % searchurl)
-        try:
-            req = urllib2.Request(searchurl, headers={'User-Agent': self.user_agent})
-            page = urllib2.urlopen(req, timeout=self.timeout)
-        except urllib2.HTTPError as inst:
-            self.logger.info(u'Error: %s - %s' % (searchurl, inst))
-            return []
-        except urllib2.URLError as inst:
-            self.logger.info(u'TimeOut: %s' % inst)
-            return []
-        soup = BeautifulSoup(page.read())
-        sublinks = []
-        for html_sub in soup('td', {'class': 'NewsTitle', 'colspan': '3'}):
-            if not self.release_pattern.match(str(html_sub.contents[1])):  # On not needed soup td result
-                continue
-            sub_teams = self.listTeams([self.release_pattern.match(str(html_sub.contents[1])).groups()[0].lower()], ['.', '_', ' ', '/', '-'])
-            if not release_group.intersection(sub_teams):  # On wrong team
-                continue
-            html_language = html_sub.findNext('td', {'class': 'language'})
-            sub_language = self.getRevertLanguage(html_language.contents[0].strip().replace('&nbsp;', ''))
-            if languages and not sub_language in languages:  # On wrong language
-                continue
-            html_status = html_language.findNextSibling('td')
-            sub_status = html_status.find('b').string.strip()
-            if not sub_status == 'Completed':  # On not completed subtitles
-                continue
-            sub_link = self.server_url + html_status.findNextSibling('td', {'colspan': '3'}).find('a')['href']
-            self.logger.debug(u'Found a match with teams: %s' % sub_teams)
-            result = Subtitle(filepath, self.getSubtitlePath(filepath, sub_language), self.__class__.__name__, sub_language, sub_link, teams=sub_teams)
-            sublinks.append(result)
-        sublinks.sort(self._cmpReleaseGroup)
-        return sublinks
-
-    def download(self, subtitle):
-        self.downloadFile(subtitle.link, subtitle.path)
-        return subtitle
-

subliminal/plugins/BierDopje.py

@@ -1,154 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from xml.dom import minidom
-import guessit
-import PluginBase
-import os
-try:
-    import cPickle as pickle
-except ImportError:
-    import pickle
-import urllib2
-from subliminal.classes import Subtitle
-
-
-class BierDopje(PluginBase.PluginBase):
-    site_url = 'http://bierdopje.com'
-    site_name = 'BierDopje'
-    server_url = 'http://api.bierdopje.com/A2B638AC5D804C2E/'
-    api_based = True
-    exceptions = {'the office': 10358,
-        'the office us': 10358,
-        'greys anatomy': 3733,
-        'sanctuary us': 7904,
-        'human target 2010': 12986,
-        'csi miami': 2187,
-        'castle 2009': 12708,
-        'chase 2010': 14228,
-        'the defenders 2010': 14225,
-        'hawaii five-0 2010': 14211}
-    _plugin_languages = {'en': 'en', 'nl': 'nl'}
-
-    def __init__(self, config_dict=None):
-        super(BierDopje, self).__init__(self._plugin_languages, config_dict)
-        #http://api.bierdopje.com/23459DC262C0A742/GetShowByName/30+Rock
-        #http://api.bierdopje.com/23459DC262C0A742/GetAllSubsFor/94/5/1/en (30 rock, season 5, episode 1)
-        if config_dict and config_dict['cache_dir']:
-            self.showid_cache = os.path.join(config_dict['cache_dir'], 'bierdopje_showid.cache')
-            with self.lock:
-                if not os.path.exists(self.showid_cache):
-                    if not os.path.exists(os.path.dirname(self.showid_cache)):
-                        raise Exception('Cache directory does not exist')
-                    f = open(self.showid_cache, 'w')
-                    pickle.dump({}, f)
-                    f.close()
-                f = open(self.showid_cache, 'r')
-                self.showids = pickle.load(f)
-                self.logger.debug(u'Reading showids from cache: %s' % self.showids)
-                f.close()
-
-    def list(self, filepath, languages):
-        if not self.config_dict['cache_dir']:
-            raise Exception('Cache directory is required for this plugin')
-        possible_languages = self.possible_languages(languages)
-        if not possible_languages:
-            return []
-        guess = guessit.guess_file_info(filepath, 'autodetect')
-        if guess['type'] != 'episode':
-            self.logger.debug(u'Not an episode')
-            return []
-        # add multiple things to the release group set
-        release_group = set()
-        if 'releaseGroup' in guess:
-            release_group.add(guess['releaseGroup'].lower())
-        else:
-            if 'title' in guess:
-                release_group.add(guess['title'].lower())
-            if 'screenSize' in guess:
-                release_group.add(guess['screenSize'].lower())
-        if 'series' not in guess or len(release_group) == 0:
-            self.logger.debug(u'Not enough information to proceed')
-            return []
-        self.release_group = release_group  # used to sort results
-        return self.query(guess['series'], guess['season'], guess['episodeNumber'], release_group, filepath, possible_languages)
-
-    def download(self, subtitle):
-        self.downloadFile(subtitle.link, subtitle.path)
-        return subtitle
-
-    def query(self, name, season, episode, release_group, filepath, languages):
-        sublinks = []
-        # get the show id
-        show_name = name.lower()
-        if show_name in self.exceptions:  # get it from exceptions
-            show_id = self.exceptions[show_name]
-        elif show_name in self.showids:  # get it from cache
-            show_id = self.showids[show_name]
-        else:  # retrieve it
-            show_name_encoded = show_name
-            if isinstance(show_name_encoded, unicode):
-                show_name_encoded = show_name_encoded.encode('utf-8')
-            show_id_url = '%sGetShowByName/%s' % (self.server_url, urllib2.quote(show_name_encoded))
-            self.logger.debug(u'Retrieving show id from web at %s' % show_id_url)
-            page = urllib2.urlopen(show_id_url)
-            dom = minidom.parse(page)
-            if not dom or len(dom.getElementsByTagName('showid')) == 0:  # no proper result
-                page.close()
-                return []
-            show_id = dom.getElementsByTagName('showid')[0].firstChild.data
-            self.showids[show_name] = show_id
-            with self.lock:
-                f = open(self.showid_cache, 'w')
-                self.logger.debug(u'Writing showid %s to cache file' % show_id)
-                pickle.dump(self.showids, f)
-                f.close()
-            page.close()
-
-        # get the subs for the show id we have
-        for language in languages:
-            subs_url = '%sGetAllSubsFor/%s/%s/%s/%s' % (self.server_url, show_id, season, episode, language)
-            self.logger.debug(u'Getting subtitles at %s' % subs_url)
-            page = urllib2.urlopen(subs_url)
-            dom = minidom.parse(page)
-            page.close()
-            for sub in dom.getElementsByTagName('result'):
-                sub_release = sub.getElementsByTagName('filename')[0].firstChild.data
-                if sub_release.endswith('.srt'):
-                    sub_release = sub_release[:-4]
-                sub_release = sub_release + '.avi'  # put a random extension for guessit not to fail guessing that file
-                # guess information from subtitle
-                sub_guess = guessit.guess_file_info(sub_release, 'episode')
-                sub_release_group = set()
-                if 'releaseGroup' in sub_guess:
-                    sub_release_group.add(sub_guess['releaseGroup'].lower())
-                else:
-                    if 'title' in sub_guess:
-                        sub_release_group.add(sub_guess['title'].lower())
-                    if 'screenSize' in sub_guess:
-                        sub_release_group.add(sub_guess['screenSize'].lower())
-                sub_link = sub.getElementsByTagName('downloadlink')[0].firstChild.data
-                result = Subtitle(filepath, self.getSubtitlePath(filepath, language), self.__class__.__name__, language, sub_link, sub_release, sub_release_group)
-                sublinks.append(result)
-        sublinks.sort(self._cmpReleaseGroup)
-        return sublinks
-

subliminal/plugins/OpenSubtitles.py

@@ -1,172 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import PluginBase
-import gzip
-import os
-import socket
-import xmlrpclib
-import guessit
-import unicodedata
-from subliminal.classes import Subtitle, DownloadFailedError
-
-
-class OpenSubtitles(PluginBase.PluginBase):
-    site_url = 'http://www.opensubtitles.org'
-    site_name = 'OpenSubtitles'
-    server_url = 'http://api.opensubtitles.org/xml-rpc'
-    user_agent = 'Subliminal v0.4'
-    api_based = True
-    _plugin_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', 'pb': 'pob', 'un': 'unk', 'ay': 'ass'}
-
-    def __init__(self, config_dict=None):
-        super(OpenSubtitles, self).__init__(self._plugin_languages, config_dict)
-
-    def list(self, filepath, languages):
-        possible_languages = self.possible_languages(languages)
-        if not possible_languages:
-            return []
-        if os.path.isfile(filepath):
-            filehash = self.hashFile(filepath)
-            size = os.path.getsize(filepath)
-            return self.query(moviehash=filehash, languages=possible_languages, bytesize=size, filepath=filepath)
-        else:
-            return self.query(languages=possible_languages, filepath=filepath)
-
-    def download(self, subtitle):
-        try:
-            self.downloadFile(subtitle.link, subtitle.path + '.gz')
-            with open(subtitle.path, 'wb') as dump:
-                gz = gzip.open(subtitle.path + '.gz')
-                dump.write(gz.read())
-                gz.close()
-                self.adjustPermissions(subtitle.path)
-            os.remove(subtitle.path + '.gz')
-        except Exception as e:
-            if os.path.exists(subtitle.path):
-                os.remove(subtitle.path)
-            raise DownloadFailedError(str(e))
-        return subtitle
-
-    def query(self, filepath, imdbID=None, moviehash=None, bytesize=None, languages=None):
-        """Makes a query on OpenSubtitles and returns info about found subtitles.
-            Note: if using moviehash, bytesize is required. """
-        # prepare the search
-        search = {}
-        if moviehash:
-            search['moviehash'] = moviehash
-        if imdbID:
-            search['imdbid'] = imdbID
-        if bytesize:
-            search['moviebytesize'] = str(bytesize)
-        if languages:
-            search['sublanguageid'] = ','.join([self.getLanguage(l) for l in languages])
-        if not imdbID and not moviehash and not bytesize:
-            self.logger.debug(u'No search term, using the filename')
-            guess = guessit.guess_file_info(filepath, 'autodetect')
-            if guess['type'] == 'episode' and 'series' in guess:
-                search['query'] = guess['series'].lower()
-            elif guess['type'] == 'movie':
-                search['query'] = guess['title'].lower()
-            else:  # we don't know what we have
-                return[]
-        # login
-        self.server = xmlrpclib.Server(self.server_url)
-        socket.setdefaulttimeout(self.timeout)
-        try:
-            log_result = self.server.LogIn('', '', 'eng', self.user_agent)
-            if not log_result['status'] or log_result['status'] != '200 OK' or not log_result['token']:
-                raise Exception('OpenSubtitles login failed')
-            token = log_result['token']
-        except Exception:
-            self.logger.error(u'Cannot login')
-            token = None
-            socket.setdefaulttimeout(None)
-            return []
-        # search
-        sublinks = self.get_results(token, search, filepath)
-        # logout
-        try:
-            self.server.LogOut(token)
-        except:
-            self.logger.error(u'Cannot logout')
-        socket.setdefaulttimeout(None)
-        return sublinks
-
-    def get_results(self, token, search, filepath):
-        self.logger.debug(u'Query uses token %s and search parameters %s' % (token, search))
-        try:
-            results = self.server.SearchSubtitles(token, [search])
-        except Exception:
-            self.logger.debug(u'Cannot query the server')
-            return []
-        if not results['data']:  # no subtitle found
-            return []
-        sublinks = []
-        self.filename = self.getFileName(filepath)
-        for r in sorted(results['data'], self._cmpSubFileName):
-            result = Subtitle(filepath, self.getSubtitlePath(filepath, self.getRevertLanguage(r['SubLanguageID'])), self.__class__.__name__, self.getRevertLanguage(r['SubLanguageID']), r['SubDownloadLink'], r['SubFileName'])
-            if 'query' in search:  # query mode search, filter results
-                query_encoded = search['query']
-                if isinstance(query_encoded, unicode):
-                    query_encoded = unicodedata.normalize('NFKD', query_encoded).encode('ascii', 'ignore')
-                if not r['MovieReleaseName'].replace('.', ' ').lower().startswith(query_encoded):
-                    self.logger.debug(u'Skipping %s it does not start with %s' % (r['MovieReleaseName'].replace('.', ' ').lower(), query_encoded))
-                    continue
-            sublinks.append(result)
-        return sublinks
-
-    def _cmpSubFileName(self, x, y):
-        """Sort based on the SubFileName name tag """
-        #TODO add also support for subtitles release
-        xmatch = x['SubFileName'] and (x['SubFileName'].find(self.filename) > -1 or self.filename.find(x['SubFileName']) > -1)
-        ymatch = y['SubFileName'] and (y['SubFileName'].find(self.filename) > -1 or self.filename.find(y['SubFileName']) > -1)
-        if xmatch and ymatch:
-            if x['SubFileName'] == self.filename or x['SubFileName'].startswith(self.filename):
-                return - 1
-            return 0
-        if not xmatch and not ymatch:
-            return 0
-        if xmatch and not ymatch:
-            return - 1
-        if not xmatch and ymatch:
-            return 1
-        return 0
-

subliminal/plugins/PluginBase.py

@@ -1,163 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import abc
-import logging
-import os
-import urllib2
-import struct
-import threading
-import socket
-from subliminal.classes import DownloadFailedError
-
-
-class PluginBase(object):
-    __metaclass__ = abc.ABCMeta
-    api_based = True
-    timeout = 3
-    user_agent = 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.3)'
-    lock = threading.Lock()
-
-    @abc.abstractmethod
-    def __init__(self, pluginLanguages, config_dict=None, isRevert=False):
-        self.config_dict = config_dict
-        if not pluginLanguages:
-            self.pluginLanguages = None
-            self.revertPluginLanguages = None
-        elif not isRevert:
-            self.pluginLanguages = pluginLanguages
-            self.revertPluginLanguages = dict((v, k) for k, v in self.pluginLanguages.iteritems())
-        else:
-            self.revertPluginLanguages = pluginLanguages
-            self.pluginLanguages = dict((v, k) for k, v in self.revertPluginLanguages.iteritems())
-        self.logger = logging.getLogger('subliminal.%s' % self.__class__.__name__)
-
-    @staticmethod
-    def getFileName(filepath):
-        filename = filepath
-        if os.path.isfile(filename):
-            filename = os.path.basename(filename)
-        if filename.endswith(('.avi', '.wmv', '.mov', '.mp4', '.mpeg', '.mpg', '.mkv')):
-            filename = filename.rsplit('.', 1)[0]
-        return filename
-
-    def possible_languages(self, languages):
-        possible_languages = languages & set(self.pluginLanguages.keys())
-        if not possible_languages:
-            self.logger.debug(u'Languages %r are not in supported languages' % languages)
-        return possible_languages
-
-    def hashFile(self, filename):
-        """Hash a file like OpenSubtitles"""
-        longlongformat = 'q'  # long long
-        bytesize = struct.calcsize(longlongformat)
-        f = open(filename, 'rb')
-        filesize = os.path.getsize(filename)
-        hash = filesize
-        if filesize < 65536 * 2:
-            self.logger.error(u'File %s is too small (SizeError < 2**16)' % filename)
-            return []
-        for _ in range(65536 / bytesize):
-            buffer = f.read(bytesize)
-            (l_value,) = struct.unpack(longlongformat, buffer)
-            hash += l_value
-            hash = hash & 0xFFFFFFFFFFFFFFFF  # to remain as 64bit number
-        f.seek(max(0, filesize - 65536), 0)
-        for _ in range(65536 / bytesize):
-            buffer = f.read(bytesize)
-            (l_value,) = struct.unpack(longlongformat, buffer)
-            hash += l_value
-            hash = hash & 0xFFFFFFFFFFFFFFFF
-        f.close()
-        returnedhash = '%016x' % hash
-        return returnedhash
-
-    def downloadFile(self, url, filepath, data=None):
-        """Download a subtitle file"""
-        self.logger.info(u'Downloading %s' % url)
-        socket.setdefaulttimeout(self.timeout)
-        try:
-            req = urllib2.Request(url, headers={'Referer': url, 'User-Agent': self.user_agent})
-            with open(filepath, 'wb') as dump:
-                f = urllib2.urlopen(req, data=data)
-                dump.write(f.read())
-                self.adjustPermissions(filepath)
-                f.close()
-        except Exception as e:
-            self.logger.error(u'Download %s failed: %s' % (url, e))
-            if os.path.exists(filepath):
-                os.remove(filepath)
-            raise DownloadFailedError(str(e))
-        finally:
-            socket.setdefaulttimeout(self.timeout)
-        self.logger.debug(u'Download finished for file %s. Size: %s' % (filepath, os.path.getsize(filepath)))
-
-    def adjustPermissions(self, filepath):
-        if self.config_dict and 'files_mode' in self.config_dict and self.config_dict['files_mode'] != -1:
-            os.chmod(filepath, self.config_dict['files_mode'])
-
-    @abc.abstractmethod
-    def list(self, filepath, languages):
-        """List subtitles"""
-
-    @abc.abstractmethod
-    def download(self, subtitle):
-        """Download a subtitle"""
-
-    def getRevertLanguage(self, language):
-        """ISO-639-1 language code from plugin language code"""
-        try:
-            return self.revertPluginLanguages[language]
-        except KeyError:
-            self.logger.warn(u'Ooops, you found a missing language in the configuration file of %s: %s. Send a bug report to have it added.' % (self.__class__.__name__, language))
-
-    def getLanguage(self, language):
-        """Plugin language code from ISO-639-1 language code"""
-        try:
-            return self.pluginLanguages[language]
-        except KeyError:
-            self.logger.warn(u'Ooops, you found a missing language in the configuration file of %s: %s. Send a bug report to have it added.' % (self.__class__.__name__, language))
-    
-    def getSubtitlePath(self, video_path, language):
-        if not os.path.exists(video_path):
-            video_path = os.path.split(video_path)[1]
-        path = video_path.rsplit('.', 1)[0]
-        if self.config_dict and self.config_dict['multi']:
-            return path + '.%s.srt' % language
-        return path + '.srt'
-
-    def listTeams(self, sub_teams, separators):
-        """List teams of a given string using separators"""
-        for sep in separators:
-            sub_teams = self.splitTeam(sub_teams, sep)
-        return set(sub_teams)
-
-    def splitTeam(self, sub_teams, sep):
-        """Split teams of a given string using separators"""
-        teams = []
-        for t in sub_teams:
-            teams += t.split(sep)
-        return teams
-
-    def _cmpReleaseGroup(self, x, y):
-        """Sort based on teams matching"""
-        return -cmp(len(x.teams.intersection(self.release_group)), len(y.teams.intersection(self.release_group)))
-

subliminal/plugins/Podnapisi.py

@@ -1,135 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from hashlib import md5, sha256
-import PluginBase
-import xmlrpclib
-import socket
-import os
-
-
-class Podnapisi(PluginBase.PluginBase):
-    site_url = "http://www.podnapisi.net"
-    site_name = "Podnapisi"
-    server_url = 'http://ssp.podnapisi.net:8000'
-    api_based = True
-    _plugin_languages = {"sl": "1",
-            "en": "2",
-            "no": "3",
-            "ko": "4",
-            "de": "5",
-            "is": "6",
-            "cs": "7",
-            "fr": "8",
-            "it": "9",
-            "bs": "10",
-            "ja": "11",
-            "ar": "12",
-            "ro": "13",
-            "es-ar": "14",
-            "hu": "15",
-            "el": "16",
-            "zh": "17",
-            "lt": "19",
-            "et": "20",
-            "lv": "21",
-            "he": "22",
-            "nl": "23",
-            "da": "24",
-            "se": "25",
-            "pl": "26",
-            "ru": "27",
-            "es": "28",
-            "sq": "29",
-            "tr": "30",
-            "fi": "31",
-            "pt": "32",
-            "bg": "33",
-            "mk": "35",
-            "sk": "37",
-            "hr": "38",
-            "zh": "40",
-            "hi": "42",
-            "th": "44",
-            "uk": "46",
-            "sr": "47",
-            "pt-br": "48",
-            "ga": "49",
-            "be": "50",
-            "vi": "51",
-            "fa": "52",
-            "ca": "53",
-            "id": "54"}
-
-    def __init__(self, config_dict=None):
-        super(Podnapisi, self).__init__(self._plugin_languages, config_dict)
-        # Podnapisi uses two reference for latin serbian and cyrillic serbian (36 and 47)
-        # add the 36 manually as cyrillic seems to be more used
-        self.revertPluginLanguages["36"] = "sr"
-
-    def list(self, filenames, languages):
-        """Main method to call when you want to list subtitles"""
-        filepath = filenames[0]
-        if not os.path.isfile(filepath):
-            return []
-        return self.query(self.hashFile(filepath), languages)
-
-    def download(self, subtitle):
-        return []
-
-    def query(self, moviehash, languages=None):
-        """Makes a query on podnapisi and returns info (link, lang) about found subtitles"""
-        # login
-        self.server = xmlrpclib.Server(self.server_url)
-        socket.setdefaulttimeout(self.timeout)
-        try:
-            log_result = self.server.initiate(self.user_agent)
-            self.logger.debug(u"Result: %s" % log_result)
-            token = log_result["session"]
-            nonce = log_result["nonce"]
-        except Exception:
-            self.logger.error(u"Cannot login" % log_result)
-            socket.setdefaulttimeout(None)
-            return []
-        username = 'getmesubs'
-        password = '99D31$$'
-        hash = md5()
-        hash.update(password)
-        password = hash.hexdigest()
-        hash = sha256()
-        hash.update(password)
-        hash.update(nonce)
-        password = hash.hexdigest()
-        self.server.authenticate(token, username, password)
-        self.logger.debug(u'Authenticated')
-        #if languages:
-        #    self.logger.debug([self.getLanguage(l) for l in languages])
-        #    self.server.setFilters(token, [self.getLanguage(l) for l in languages])
-        #    self.logger.debug('Filers set for languages %s' % languages)
-        self.logger.debug(u"Starting search with token %s and hashs %s" % (token, [moviehash]))
-        results = self.server.search(token, [moviehash])
-        return results
-        subs = []
-        for sub in results['results']:
-            subs.append(sub)
-        self.server.terminate(token)
-        return subs

subliminal/plugins/SubScene.py

@@ -1,168 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from BeautifulSoup import BeautifulSoup
-import PluginBase
-import zipfile
-import os
-import urllib2
-
-
-class SubScene(PluginBase.PluginBase):
-    site_url = 'http://subscene.com'
-    site_name = 'SubScene'
-    server_url = 'http://subscene.com/s.aspx?subtitle='
-    api_based = False
-    _plugin_languages = {"en": "English",
-            "se": "Swedish",
-            "da": "Danish",
-            "fi": "Finnish",
-            "no": "Norwegian",
-            "fr": "French",
-            "es": "Spanish",
-            "is": "Icelandic",
-            "cs": "Czech",
-            "bg": "Bulgarian",
-            "de": "German",
-            "ar": "Arabic",
-            "el": "Greek",
-            "fa": "Farsi/Persian",
-            "nl": "Dutch",
-            "he": "Hebrew",
-            "id": "Indonesian",
-            "ja": "Japanese",
-            "vi": "Vietnamese",
-            "pt": "Portuguese",
-            "ro": "Romanian",
-            "tr": "Turkish",
-            "sr": "Serbian",
-            "pt-br": "Brazillian Portuguese",
-            "ru": "Russian",
-            "hr": "Croatian",
-            "sl": "Slovenian",
-            "zh": "Chinese BG code",
-            "it": "Italian",
-            "pl": "Polish",
-            "ko": "Korean",
-            "hu": "Hungarian",
-            "ku": "Kurdish",
-            "et": "Estonian"}
-
-    def __init__(self, config_dict=None):
-        super(SubScene, self).__init__(self._plugin_languages, config_dict)
-        #http://subscene.com/s.aspx?subtitle=Dexter.S04E01.HDTV.XviD-NoTV
-
-    def list(self, filenames, languages):
-        """Main method to call when you want to list subtitles"""
-        filepath = filenames[0]
-        fname = self.getFileName(filepath)
-        subs = self.query(fname, filepath, languages)
-        if not subs and fname.rfind(".[") > 0:
-            # Try to remove the [VTV] or [EZTV] at the end of the file
-            teamless_filename = fname[0:fname.rfind(".[")]
-            subs = self.query(teamless_filename, filepath, languages)
-            return subs
-        else:
-            return subs
-
-    def download(self, subtitle):
-        """Main method to call when you want to download a subtitle"""
-        subpage = subtitle["page"]
-        page = urllib2.urlopen(subpage)
-        soup = BeautifulSoup(page)
-        dlhref = soup.find("div", {"class": "download"}).find("a")["href"]
-        subtitle["link"] = self.site_url + dlhref.split('"')[7]
-        format = "zip"
-        archivefilename = subtitle["filename"].rsplit(".", 1)[0] + '.' + format
-        self.downloadFile(subtitle["link"], archivefilename)
-        subtitlefilename = None
-        if zipfile.is_zipfile(archivefilename):
-            self.logger.debug(u"Unzipping file " + archivefilename)
-            zf = zipfile.ZipFile(archivefilename, "r")
-            for el in zf.infolist():
-                extension = el.orig_filename.rsplit(".", 1)[1]
-                if extension in ("srt", "sub", "txt"):
-                    subtitlefilename = srtbasefilename + "." + extension
-                    outfile = open(subtitlefilename, "wb")
-                    outfile.write(zf.read(el.orig_filename))
-                    outfile.flush()
-                    self.adjustPermissions(subtitlefilename)
-                    outfile.close()
-                else:
-                    self.logger.info(u"File %s does not seem to be valid " % el.orig_filename)
-            # Deleting the zip file
-            zf.close()
-            os.remove(archivefilename)
-            return subtitlefilename
-        elif archivefilename.endswith('.rar'):
-            self.logger.warn(u'Rar is not really supported yet. Trying to call unrar')
-            import subprocess
-            try:
-                args = ['unrar', 'lb', archivefilename]
-                output = subprocess.Popen(args, stdout=subprocess.PIPE).communicate()[0]
-                for el in output.splitlines():
-                    extension = el.rsplit(".", 1)[1]
-                    if extension in ("srt", "sub"):
-                        args = ['unrar', 'e', archivefilename, el, os.path.dirname(archivefilename)]
-                        subprocess.Popen(args)
-                        tmpsubtitlefilename = os.path.join(os.path.dirname(archivefilename), el)
-                        subtitlefilename = os.path.join(os.path.dirname(archivefilename), srtbasefilename + "." + extension)
-                        if os.path.exists(tmpsubtitlefilename):
-                            # rename it to match the file
-                            os.rename(tmpsubtitlefilename, subtitlefilename)
-                            # exit
-                        return subtitlefilename
-            except OSError as e:
-                self.logger.error(u"Execution failed: %s" % e)
-                return None
-        else:
-            self.logger.info(u"Unexpected file type (not zip) for %s" % archivefilename)
-            return None
-
-    def downloadFile(self, url, filename):
-        """Downloads the given url to the given filename"""
-        #FIXME: Not working
-
-    def query(self, token, filepath, langs=None):
-        """Make a query on SubScene and returns info about found subtitles"""
-        sublinks = []
-        searchurl = "%s%s" % (self.server_url, urllib2.quote(token))
-        self.logger.debug(u"Query: %s" % searchurl)
-        page = urllib2.urlopen(searchurl)
-        soup = BeautifulSoup(page.read())
-        for subs in soup("a", {"class": "a1"}):
-            lang_span = subs.find("span")
-            lang = self.getRevertLanguage(lang_span.contents[0].strip())
-            release_span = lang_span.findNext("span")
-            release = release_span.contents[0].strip().split(" (")[0]
-            sub_page = subs["href"]
-            #http://subscene.com//s-dlpath-260016/78348/rar.zipx
-            if release.lower().startswith(token.lower()) and (not langs or lang in langs):
-                result = {}
-                result["release"] = release
-                result["lang"] = lang
-                result["link"] = None
-                result["page"] = self.site_url + sub_page
-                result["filename"] = filepath
-                result["plugin"] = self.__class__.__name__
-                sublinks.append(result)
-        return sublinks

subliminal/plugins/SubsWiki.py

@@ -1,116 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from BeautifulSoup import BeautifulSoup
-import PluginBase
-import urllib2
-import re
-import guessit
-from subliminal.classes import Subtitle
-
-
-class SubsWiki(PluginBase.PluginBase):
-    site_url = 'http://www.subswiki.com'
-    site_name = 'SubsWiki'
-    server_url = 'http://www.subswiki.com'
-    api_based = False
-    _plugin_languages = {u'English (US)': 'en',
-            u'English (UK)': 'en',
-            u'English': 'en',
-            u'French': 'fr',
-            u'Brazilian': 'pt-br',
-            u'Portuguese': 'pt',
-            u'Español (Latinoamérica)': 'es',
-            u'Español (España)': 'es',
-            u'Español': 'es',
-            u'Italian': 'it',
-            u'Català': 'ca'}
-
-    def __init__(self, config_dict=None):
-        super(SubsWiki, self).__init__(self._plugin_languages, config_dict, True)
-        self.release_pattern = re.compile('\nVersion (.+), ([0-9]+).([0-9])+ MBs')
-
-    def list(self, filepath, languages):
-        possible_languages = self.possible_languages(languages)
-        if not possible_languages:
-            return []
-        guess = guessit.guess_file_info(filepath, 'autodetect')
-        if guess['type'] != 'episode':
-            self.logger.debug(u'Not an episode')
-            return []
-        # add multiple things to the release group set
-        release_group = set()
-        if 'releaseGroup' in guess:
-            release_group.add(guess['releaseGroup'].lower())
-        else:
-            if 'title' in guess:
-                release_group.add(guess['title'].lower())
-            if 'screenSize' in guess:
-                release_group.add(guess['screenSize'].lower())
-        if 'series' not in guess or len(release_group) == 0:
-            self.logger.debug(u'Not enough information to proceed')
-            return []
-        self.release_group = release_group  # used to sort results
-        return self.query(guess['series'], guess['season'], guess['episodeNumber'], release_group, filepath, possible_languages)
-
-    def query(self, name, season, episode, release_group, filepath, languages):
-        sublinks = []
-        searchname = name.lower().replace(' ', '_')
-        if isinstance(searchname, unicode):
-            searchname = searchname.encode('utf-8')
-        searchurl = '%s/serie/%s/%s/%s/' % (self.server_url, urllib2.quote(searchname), season, episode)
-        self.logger.debug(u'Searching in %s' % searchurl)
-        try:
-            req = urllib2.Request(searchurl, headers={'User-Agent': self.user_agent})
-            page = urllib2.urlopen(req, timeout=self.timeout)
-        except urllib2.HTTPError as inst:
-            self.logger.info(u'Error: %s - %s' % (searchurl, inst))
-            return []
-        except urllib2.URLError as inst:
-            self.logger.info(u'TimeOut: %s' % inst)
-            return []
-        soup = BeautifulSoup(page.read())
-        for subs in soup('td', {'class': 'NewsTitle'}):
-            sub_teams = self.listTeams([self.release_pattern.search('%s' % subs.contents[1]).group(1).lower()], ['.', '_', ' ', '/', '-'])
-            if not release_group.intersection(sub_teams):  # On wrong team
-                continue
-            self.logger.debug(u'Team from website: %s' % sub_teams)
-            self.logger.debug(u'Team from file: %s' % release_group)
-            for html_language in subs.parent.parent.findAll('td', {'class': 'language'}):
-                sub_language = self.getRevertLanguage(html_language.string.strip())
-                self.logger.debug(u'Subtitle reverted language: %s' % sub_language)
-                if not sub_language in languages:  # On wrong language
-                    continue
-                html_status = html_language.findNextSibling('td')
-                sub_status = html_status.find('strong').string.strip()
-                if not sub_status == 'Completed':  # On not completed subtitles
-                    continue
-                sub_link = html_status.findNext('td').find('a')['href']
-                result = Subtitle(filepath, self.getSubtitlePath(filepath, sub_language), self.__class__.__name__, sub_language, self.server_url + sub_link, teams=sub_teams)
-                sublinks.append(result)
-        sublinks.sort(self._cmpReleaseGroup)
-        return sublinks
-
-    def download(self, subtitle):
-        self.downloadFile(subtitle.link, subtitle.path)
-        return subtitle
-

subliminal/plugins/Subtitulos.py

@@ -1,109 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-from BeautifulSoup import BeautifulSoup
-import guessit
-import urllib2
-import unicodedata
-import re
-import PluginBase
-from subliminal.classes import Subtitle
-
-
-class Subtitulos(PluginBase.PluginBase):
-    site_url = 'http://www.subtitulos.es'
-    site_name = 'Subtitulos'
-    server_url = 'http://www.subtitulos.es'
-    api_based = False
-    _plugin_languages = {u'English (US)': 'en', u'English (UK)': 'en', u'English': 'en', u'French': 'fr', u'Brazilian': 'pt-br',
-            u'Portuguese': 'pt', u'Español (Latinoamérica)': 'es', u'Español (España)': 'es', u'Español': 'es', u'Italian': 'it',
-            u'Català': 'ca'}
-
-    def __init__(self, config_dict=None):
-        super(Subtitulos, self).__init__(self._plugin_languages, config_dict, True)
-        self.release_pattern = re.compile('Versi&oacute;n (.+) ([0-9]+).([0-9])+ megabytes')
-
-    def list(self, filepath, languages):
-        possible_languages = self.possible_languages(languages)
-        if not possible_languages:
-            return []
-        guess = guessit.guess_file_info(filepath, 'autodetect')
-        if guess['type'] != 'episode':
-            self.logger.debug(u'Not an episode')
-            return []
-        # add multiple things to the release group set
-        release_group = set()
-        if 'releaseGroup' in guess:
-            release_group.add(guess['releaseGroup'].lower())
-        else:
-            if 'title' in guess:
-                release_group.add(guess['title'].lower())
-            if 'screenSize' in guess:
-                release_group.add(guess['screenSize'].lower())
-        if 'series' not in guess or len(release_group) == 0:
-            self.logger.debug(u'Not enough information to proceed')
-            return []
-        self.release_group = release_group  # used to sort results
-        return self.query(guess['series'], guess['season'], guess['episodeNumber'], release_group, filepath, possible_languages)
-
-    def query(self, name, season, episode, release_group, filepath, languages):
-        sublinks = []
-        searchname = name.lower().replace(' ', '-')
-        if isinstance(searchname, unicode):
-            searchname = unicodedata.normalize('NFKD', searchname).encode('ascii','ignore')
-        searchurl = '%s/%s/%sx%.2d' % (self.server_url, urllib2.quote(searchname), season, episode)
-        self.logger.debug(u'Searching in %s' % searchurl)
-        try:
-            req = urllib2.Request(searchurl, headers={'User-Agent': self.user_agent})
-            page = urllib2.urlopen(req, timeout=self.timeout)
-        except urllib2.HTTPError as inst:
-            self.logger.info(u'Error: %s - %s' % (searchurl, inst))
-            return []
-        except urllib2.URLError as inst:
-            self.logger.info(u'TimeOut: %s' % inst)
-            return []
-        soup = BeautifulSoup(page.read())
-        for subs in soup('div', {'id': 'version'}):
-            version = subs.find('p', {'class': 'title-sub'})
-            sub_teams = self.listTeams([self.release_pattern.search('%s' % version.contents[1]).group(1).lower()], ['.', '_', ' ', '/', '-'])
-            self.logger.debug(u'Team from website: %s' % sub_teams)
-            self.logger.debug(u'Team from file: %s' % release_group)
-            if not release_group.intersection(sub_teams):  # On wrong team
-                continue
-            for html_language in subs.findAllNext('ul', {'class': 'sslist'}):
-                sub_language = self.getRevertLanguage(html_language.findNext('li', {'class': 'li-idioma'}).find('strong').contents[0].string.strip())
-                if not sub_language in languages:  # On wrong language
-                    continue
-                html_status = html_language.findNext('li', {'class': 'li-estado green'})
-                sub_status = html_status.contents[0].string.strip()
-                if not sub_status == 'Completado':  # On not completed subtitles
-                    continue
-                sub_link = html_status.findNext('span', {'class': 'descargar green'}).find('a')['href']
-                result = Subtitle(filepath, self.getSubtitlePath(filepath, sub_language), self.__class__.__name__, sub_language, sub_link, teams=sub_teams)
-                sublinks.append(result)
-        sublinks.sort(self._cmpReleaseGroup)
-        return sublinks
-
-    def download(self, subtitle):
-        self.downloadFile(subtitle.link, subtitle.path)
-        return subtitle
-

subliminal/plugins/TheSubDB.py

@@ -1,87 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2008-2011 Patrick Dessalle <patrick@dessalle.be>
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import PluginBase
-import hashlib
-import os
-import urllib2
-from subliminal.classes import Subtitle
-
-
-class TheSubDB(PluginBase.PluginBase):
-    site_url = 'http://thesubdb.com'
-    site_name = 'SubDB'
-    server_url = 'http://api.thesubdb.com'  # for testing purpose, use http://sandbox.thesubdb.com instead
-    api_based = True
-    user_agent = 'SubDB/1.0 (Subliminal/0.4; https://github.com/Diaoul/subliminal)'  # defined by the API
-    _plugin_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
-
-
-    def __init__(self, config_dict=None):
-        super(TheSubDB, self).__init__(self._plugin_languages, config_dict)
-
-    def list(self, filepath, languages):
-        possible_languages = self.possible_languages(languages)
-        if not possible_languages:
-            return []
-        if not os.path.isfile(filepath):
-            return []
-        return self.query(filepath, self.hashFile(filepath), possible_languages)
-
-    def query(self, filepath, moviehash, languages):
-        searchurl = '%s/?action=%s&hash=%s' % (self.server_url, 'search', moviehash)
-        self.logger.debug(u'Query URL: %s' % searchurl)
-        try:
-            req = urllib2.Request(searchurl, headers={'User-Agent': self.user_agent})
-            page = urllib2.urlopen(req, timeout=self.timeout)
-        except urllib2.HTTPError as inst:
-            if inst.code == 404:  # no result found
-                return []
-            self.logger.error(u'Error: %s - %s' % (searchurl, inst))
-            return []
-        except urllib2.URLError as inst:
-            self.logger.error(u'TimeOut: %s' % inst)
-            return []
-        available_languages = page.readlines()[0].split(',')
-        self.logger.debug(u'Available languages: %s' % available_languages)
-        subs = []
-        for l in available_languages:
-            if l in languages:
-                result = Subtitle(filepath, self.getSubtitlePath(filepath, l), self.__class__.__name__, l, '%s/?action=download&hash=%s&language=%s' % (self.server_url, moviehash, l))
-                subs.append(result)
-        return subs
-
-    def hashFile(self, filepath):
-        """TheSubDB specific hash function"""
-        readsize = 64 * 1024
-        with open(filepath, 'rb') as f:
-            data = f.read(readsize)
-            f.seek(-readsize, os.SEEK_END)
-            data += f.read(readsize)
-        return hashlib.md5(data).hexdigest()
-
-    def download(self, subtitle):
-        self.downloadFile(subtitle.link, subtitle.path)
-        return subtitle
-

subliminal/plugins/__init__.py

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

subliminal/providers/__init__.py

@@ -0,0 +1,156 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import babelfish
+from ..video import Episode, Movie
+from .. import __version__
+from random import randint
+
+# Agent List
+AGENT_LIST = (
+    'Mozilla/5.0 (Windows NT 6.3; rv:36.0) Gecko/20100101 Firefox/36.0',
+    'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.1 Safari/537.36',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10; rv:33.0) Gecko/20100101 Firefox/33.0',
+    'Mozilla/5.0 (X11; Linux i586; rv:31.0) Gecko/20100101 Firefox/31.0',
+    'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20130401 Firefox/31.0',
+    'Mozilla/5.0 (Windows NT 5.1; rv:31.0) Gecko/20100101 Firefox/31.0',
+    'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36',
+    'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36',
+    'Mozilla/5.0 (compatible, MSIE 11, Windows NT 6.3; Trident/7.0; rv:11.0) like Gecko',
+    'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/7046A194A',
+    'Mozilla/5.0 (iPad; CPU OS 6_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/6.0 Mobile/10A5355d Safari/8536.25',
+)
+
+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
+
+    # Returns a random agent to use from the list above
+    random_user_agent = AGENT_LIST[randint(0, len(AGENT_LIST)-1)]
+
+    # Defines the ideal user agent to use for all providers otherwise
+    primary_user_agent = 'Subliminal/%s' % __version__
+
+
+    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 +1,166 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import logging
+import babelfish
+import bs4
+import charade
+import requests
+from . import Provider
+from ..cache import region
+from ..exceptions import ProviderConfigurationError, ProviderNotAvailable, InvalidSubtitle
+from ..subtitle import Subtitle, is_valid_subtitle, sanitize_string
+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 = set([babelfish.Language('por', 'BR')]) | set([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 initialize(self):
+        self.session = requests.Session()
+        self.session.headers = {
+            'User-Agent': self.random_user_agent,
+            'Referer': self.server,
+        }
+
+    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[sanitize_string(html_show.string)] = \
+                    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()
+        sanitized_series = sanitize_string(series)
+        if sanitized_series in show_ids:
+            show_id = show_ids[sanitized_series]
+        else:
+            show_id = self.find_show_id(sanitized_series)
+            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
+            if not cells[3].string:
+                logger.debug('Skipping empty language')
+                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/opensubtitles.py

@@ -0,0 +1,164 @@
+# -*- 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 ..subtitle import sanitize_string
+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,  # @ReservedAssignment
+                 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 \
+                    sanitize_string(self.series_name) == \
+                    sanitize_string(video.series):
+                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 \
+                sanitize_string(self.movie_name) == \
+                sanitize_string(video.title):
+            matches.add('title')
+        return matches
+
+
+class OpenSubtitlesProvider(Provider):
+    languages = set([babelfish.Language.fromopensubtitles(l) for l in babelfish.language_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):  # @ReservedAssignment
+        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 []
+        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/podnapisi.py

@@ -0,0 +1,208 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import io
+import logging
+import re
+import contextlib
+import xml.etree.ElementTree
+import zipfile
+import babelfish
+import bs4
+import charade
+import guessit
+import requests
+from . import Provider
+from ..exceptions import InvalidSubtitle, ProviderNotAvailable, ProviderError
+from ..subtitle import Subtitle, is_valid_subtitle, compute_guess_matches
+from ..subtitle import sanitize_string
+from ..video import Episode, Movie
+
+
+logger = logging.getLogger(__name__)
+URL_RE = re.compile(
+    '^((http[s]?|ftp):\/)?\/?([^:\/\s]+)(:([^\/]*))?((\/\w+)*\/)' + \
+    '([\w\-\.]+[^#?\s]+)(\?([^#]*))?(#(.*))?$',
+)
+
+class PodnapisiSubtitle(Subtitle):
+    provider_name = 'podnapisi'
+
+    def __init__(self, language, id, releases, hearing_impaired, link, series=None, season=None, episode=None,  # @ReservedAssignment
+                 title=None, year=None):
+        super(PodnapisiSubtitle, self).__init__(language, hearing_impaired)
+        self.id = id
+        self.releases = releases
+        self.hearing_impaired = hearing_impaired
+        self.link = '/ppodnapisi' + link
+        self.series = series
+        self.season = season
+        self.episode = episode
+        self.title = title
+        self.year = year
+
+    def compute_matches(self, video):
+        matches = set()
+        # episode
+        if isinstance(video, Episode):
+            # series
+            if video.series and \
+                sanitize_string(self.series) == \
+                sanitize_string(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')
+            # guess
+            for release in self.releases:
+                matches |= compute_guess_matches(video, guessit.guess_episode_info(release + '.mkv'))
+        # movie
+        elif isinstance(video, Movie):
+            # title
+            if video.title and \
+                sanitize_string(self.title) == \
+                sanitize_string(video.title):
+                matches.add('title')
+            # year
+            if video.year and self.year == video.year:
+                matches.add('year')
+            # guess
+            for release in self.releases:
+                matches |= compute_guess_matches(video, guessit.guess_movie_info(release + '.mkv'))
+        return matches
+
+
+class PodnapisiProvider(Provider):
+    languages = set([babelfish.Language.frompodnapisi(l) for l in babelfish.language_converters['podnapisi'].codes])
+    video_types = (Episode, Movie)
+    server = 'http://simple.podnapisi.net'
+    pre_link_re = re.compile('^.*(?P<link>/ppodnapisi/predownload/i/\d+/k/.*$)')
+    link_re = re.compile('^.*(?P<link>/[a-zA-Z]{2}/ppodnapisi/download/i/\d+/k/.*$)')
+
+    def initialize(self):
+        self.session = requests.Session()
+        self.session.headers = {'User-Agent': self.primary_user_agent }
+
+    def terminate(self):
+        self.session.close()
+
+    def get(self, url, params=None, headers=None, is_xml=True):
+        """Make a GET 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 headers: headers of the request
+        :param bool xml: whether the response content is XML or not
+        :return: the response
+        :rtype: :class:`xml.etree.ElementTree.Element` or :class:`bs4.BeautifulSoup`
+        :raise: :class:`~subliminal.exceptions.ProviderNotAvailable`
+
+        """
+
+        prefix_url = ''
+        url_result = URL_RE.search(url)
+        if url_result and url_result.group(2) is None:
+            prefix_url = self.server
+
+        try:
+            r = self.session.get(
+                prefix_url + url, params=params,
+                headers=headers,
+                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)
+        if is_xml:
+            return xml.etree.ElementTree.fromstring(r.content)
+        else:
+            return bs4.BeautifulSoup(r.content, ['permissive'])
+
+    def query(self, language, series=None, season=None, episode=None, title=None, year=None):
+        params = {'sXML': 1, 'sJ': language.podnapisi}
+        if series and season and episode:
+            params['sK'] = series
+            params['sTS'] = season
+            params['sTE'] = episode
+        elif title:
+            params['sK'] = title
+            if year:
+                params['sY'] = year
+        else:
+            raise ValueError('Missing parameters series and season and episode or title')
+        logger.debug('Searching episode %r', params)
+        subtitles = []
+        while True:
+            root = self.get('/ppodnapisi/search', params)
+            if not int(root.find('pagination/results').text):
+                logger.debug('No subtitle found')
+                break
+            if series and season and episode:
+                try:
+                    subtitles.extend([PodnapisiSubtitle(language, int(s.find('id').text), s.find('release').text.split(),
+                                                    'h' in (s.find('flags').text or ''), s.find('url').text[38:],
+                                                    series=series, season=season, episode=episode)
+                                  for s in root.findall('subtitle')])
+                except AttributeError:
+                    # there simply wasn't enough information in the TV Show
+                    # gracefully handle this instead of crashing :)
+                    break
+            elif title:
+                try:
+                    subtitles.extend([PodnapisiSubtitle(language, int(s.find('id').text), s.find('release').text.split(),
+                                                    'h' in (s.find('flags').text or ''), s.find('url').text[38:],
+                                                    title=title, year=year)
+                                  for s in root.findall('subtitle')])
+                except AttributeError:
+                    # there simply wasn't enough information in the movie
+                    # gracefully handle this instead of crashing :)
+                    break
+            if int(root.find('pagination/current').text) >= int(root.find('pagination/count').text):
+                break
+            params['page'] = int(root.find('pagination/current').text) + 1
+        return subtitles
+
+    def list_subtitles(self, video, languages):
+        if isinstance(video, Episode):
+            return [s for l in languages for s in self.query(l, series=video.series, season=video.season,
+                                                             episode=video.episode)]
+        elif isinstance(video, Movie):
+            return [s for l in languages for s in self.query(l, title=video.title, year=video.year)]
+
+    def download_subtitle(self, subtitle):
+        soup = self.get(subtitle.link, is_xml=False)
+        pre_link = soup.find('a', href=self.pre_link_re)
+        if not pre_link:
+            raise ProviderError('Cannot find the pre-download link')
+        pre_link = self.server + \
+            self.pre_link_re.match(pre_link['href']).group('link')
+
+        # Continue following the link
+        soup = self.get(
+            pre_link,
+            headers={
+                'Referer': self.server,
+            },
+            is_xml=False,
+        )
+
+        link = soup.find('a', href=self.link_re)
+        if not link:
+            raise ProviderError('Cannot find the download link')
+        try:
+            r = self.session.get(self.server + self.link_re.match(link['href']).group('link'), 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 contextlib.closing(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/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):  # @ReservedAssignment
+        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 = set([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):  # @ReservedAssignment
+        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
+                set([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 +1,195 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import io
+import logging
+import re
+import contextlib
+import zipfile
+import babelfish
+import bs4
+import charade
+import requests
+from . import Provider
+from ..cache import region
+from ..exceptions import InvalidSubtitle, ProviderNotAvailable, ProviderError
+from ..subtitle import Subtitle, is_valid_subtitle, sanitize_string
+from ..video import Episode
+
+IGNORE_DATEMATCH=re.compile('^(.*)[ \t0-9-._)(]*$')
+
+logger = logging.getLogger(__name__)
+
+
+class TVsubtitlesSubtitle(Subtitle):
+    provider_name = 'tvsubtitles'
+
+    def __init__(self, language, series, season, episode, id, rip, release):  # @ReservedAssignment
+        super(TVsubtitlesSubtitle, self).__init__(language)
+        self.series = series
+        self.season = season
+        self.episode = episode
+        self.id = id
+        self.rip = rip
+        self.release = release
+
+    def compute_matches(self, video):
+        matches = set()
+        # series
+        if video.series and self.series == video.series:
+            matches.add('series')
+        # season
+        if video.season and self.season == video.season:
+            matches.add('season')
+        # episode
+        if video.episode and self.episode == video.episode:
+            matches.add('episode')
+        # release_group
+        if video.release_group and self.release and video.release_group.lower() in self.release.lower():
+            matches.add('release_group')
+        # video_codec
+        if video.video_codec and self.release and (video.video_codec in self.release.lower()
+                                                   or video.video_codec == 'h264' and 'x264' in self.release.lower()):
+            matches.add('video_codec')
+        # resolution
+        if video.resolution and self.rip and video.resolution in self.rip.lower():
+            matches.add('resolution')
+        return matches
+
+
+class TVsubtitlesProvider(Provider):
+    languages = set([babelfish.Language('por', 'BR')]) | set([babelfish.Language(l)
+                 for l in ['ara', 'bul', 'ces', 'dan', 'deu', 'ell', 'eng', 'fin', 'fra', 'hun', 'ita', 'jpn', 'kor',
+                           'nld', 'pol', 'por', 'ron', 'rus', 'spa', 'swe', 'tur', 'ukr', 'zho']])
+    video_types = (Episode,)
+    server = 'http://www.tvsubtitles.net'
+    episode_id_re = re.compile('^episode-\d+\.html$')
+    subtitle_re = re.compile('^\/subtitle-\d+\.html$')
+    link_re = re.compile('^(?P<series>.+) \(\d{4}-\d{4}\)$')
+
+    def initialize(self):
+        self.session = requests.Session()
+        self.session.headers = {'User-Agent': self.primary_user_agent }
+
+    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
+        :param string method: method 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-"]')
+        sanitized_series = IGNORE_DATEMATCH.match(
+            sanitize_string(series).replace('.', ' ').strip(),
+        )
+        if not sanitized_series:
+            sanitized_series = sanitize_string(series)\
+                        .replace('.', ' ').strip()
+        else:
+            sanitized_series = sanitized_series.group(1)
+
+        if not links:
+            logger.info('Series %r not found', series)
+            return None
+
+        for link in links:
+            match = self.link_re.match(link.string)
+            if not match:
+                logger.warning('Could not parse %r', link.string)
+                continue
+            show = IGNORE_DATEMATCH.match(
+                sanitize_string(match.group('series'))\
+                        .replace('.', ' ').strip(),
+            )
+            if not show:
+                logger.warning('Could not postparse %r', match.group('series'))
+                continue
+            show = show.group(1)
+
+            if show == sanitized_series:
+                return int(link['href'][8:-5])
+        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)
+        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 contextlib.closing(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')  # @ReservedAssignment
+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/subliminal.py

@@ -1,325 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import threading
-from itertools import groupby
-from classes import DownloadTask, ListTask, StopTask, LanguageError, PluginError, BadStateError, WrongTaskError, DownloadFailedError
-import Queue
-import logging
-import mimetypes
-import os
-import plugins
-
-
-# be nice
-try:
-    from logging import NullHandler
-except ImportError:
-
-    class NullHandler(logging.Handler):
-        def emit(self, record):
-            pass
-logger = logging.getLogger('subliminal')
-logger.addHandler(NullHandler())
-
-# const
-FORMATS = ['video/x-msvideo', 'video/quicktime', 'video/x-matroska', 'video/mp4']
-EXTENSIONS = set(['srt', 'sub'])
-LANGUAGES = set(['aa', 'ab', 'ae', 'af', 'ak', 'am', 'an', 'ar', 'as', 'av', 'ay', 'az', 'ba', 'be', 'bg', 'bh', 'bi',
-                 'bm', 'bn', 'bo', 'br', 'bs', 'ca', 'ce', 'ch', 'co', 'cr', 'cs', 'cu', 'cv', 'cy', 'da', 'de', 'dv',
-                 'dz', 'ee', 'el', 'en', 'eo', 'es', 'et', 'eu', 'fa', 'ff', 'fi', 'fj', 'fo', 'fr', 'fy', 'ga', 'gd',
-                 'gl', 'gn', 'gu', 'gv', 'ha', 'he', 'hi', 'ho', 'hr', 'ht', 'hu', 'hy', 'hz', 'ia', 'id', 'ie', 'ig',
-                 'ii', 'ik', 'io', 'is', 'it', 'iu', 'ja', 'jv', 'ka', 'kg', 'ki', 'kj', 'kk', 'kl', 'km', 'kn', 'ko',
-                 'kr', 'ks', 'ku', 'kv', 'kw', 'ky', 'la', 'lb', 'lg', 'li', 'ln', 'lo', 'lt', 'lu', 'lv', 'mg', 'mh',
-                 'mi', 'mk', 'ml', 'mn', 'mo', 'mr', 'ms', 'mt', 'my', 'na', 'nb', 'nd', 'ne', 'ng', 'nl', 'nn', 'no',
-                 'nr', 'nv', 'ny', 'oc', 'oj', 'om', 'or', 'os', 'pa', 'pi', 'pl', 'ps', 'pt', 'qu', 'rm', 'rn', 'ro',
-                 'ru', 'rw', 'sa', 'sc', 'sd', 'se', 'sg', 'si', 'sk', 'sl', 'sm', 'sn', 'so', 'sq', 'sr', 'ss', 'st',
-                 'su', 'sv', 'sw', 'ta', 'te', 'tg', 'th', 'ti', 'tk', 'tl', 'tn', 'to', 'tr', 'ts', 'tt', 'tw', 'ty',
-                 'ug', 'uk', 'ur', 'uz', 've', 'vi', 'vo', 'wa', 'wo', 'xh', 'yi', 'yo', 'za', 'zh', 'zu'])  # ISO 639-1
-PLUGINS = ['BierDopje', 'OpenSubtitles', 'SubsWiki', 'Subtitulos', 'TheSubDB']
-API_PLUGINS = filter(lambda p: getattr(plugins, p).api_based, PLUGINS)
-IDLE = 0
-RUNNING = 1
-PAUSED = 2
-
-
-class Subliminal(object):
-    """Main Subliminal class"""
-
-    def __init__(self, cache_dir=None, workers=4, multi=False, force=False, max_depth=3, files_mode=-1):
-        self.multi = multi
-        self.force = force
-        self.max_depth = max_depth
-        self.cache_dir = None
-        self.taskQueue = Queue.PriorityQueue()
-        self.listResultQueue = Queue.Queue()
-        self.downloadResultQueue = Queue.Queue()
-        self._languages = []
-        self._plugins = API_PLUGINS
-        self.workers = workers
-        self.files_mode = files_mode
-        self.state = IDLE
-        try:
-            if cache_dir:
-                self.cache_dir = cache_dir
-                if not os.path.isdir(self.cache_dir):
-                    os.makedirs(self.cache_dir)
-                    logger.debug(u'Creating cache directory: %r' % self.cache_dir)
-        except:
-            self.cache_dir = None
-            logger.error(u'Failed to use the cache directory, continue without it')
-
-    @property
-    def languages(self):
-        """Getter for languages"""
-        return self._languages
-
-    @languages.setter
-    def languages(self, languages):
-        """Setter for languages"""
-        logger.debug(u'Setting languages to %r' % languages)
-        self._languages = []
-        for l in languages:
-            if l not in LANGUAGES:
-                raise LanguageError(l)
-            if not l in self._languages:
-                self._languages.append(l)
-
-    @property
-    def plugins(self):
-        """Getter for plugins"""
-        return self._plugins
-
-    @plugins.setter
-    def plugins(self, plugins):
-        """Setter for plugins"""
-        logger.debug(u'Setting plugins to %r' % plugins)
-        self._plugins = []
-        for p in plugins:
-            if p not in PLUGINS:
-                raise PluginError(p)
-            if not p in self._plugins:
-                self._plugins.append(p)
-
-    def listSubtitles(self, entries, auto=True):
-        """
-        Search subtitles within the plugins and return all found subtitles in a list of Subtitle object.
-
-        Attributes:
-            entries -- filepath or folderpath of video file or a list of that
-            auto    -- automaticaly manage workers"""
-        if auto:
-            if self.state != IDLE:
-                raise BadStateError(self.state, IDLE)
-            self.startWorkers()
-        if isinstance(entries, basestring):
-            entries = [entries]
-        scan_result = []
-        for e in entries:
-            if not isinstance(e, unicode):
-                logger.warning(u'Entry %r is not unicode' % e)
-            if not os.path.exists(e):
-                scan_result.append((e, set(), False))
-                continue
-            scan_result.extend(scan(e))
-        task_count = 0
-        for filepath, languages, has_single in scan_result:
-            wanted_languages = set(self._languages)
-            if not wanted_languages:
-                wanted_languages = LANGUAGES
-            if not self.force and self.multi:
-                wanted_languages = set(wanted_languages) - languages
-                if not wanted_languages:
-                    logger.debug(u'No need to list multi subtitles %r for %r because %r subtitles detected' % (self._languages, filepath, languages))
-                    continue
-            if not self.force and not self.multi and has_single:
-                logger.debug(u'No need to list single subtitles %r for %r because one detected' % (self._languages, filepath))
-                continue
-            logger.debug(u'Listing subtitles %r for %r with %r' % (wanted_languages, filepath, self._plugins))
-            for plugin in self._plugins:
-                self.taskQueue.put((5, ListTask(filepath, wanted_languages, plugin, self.getConfigDict())))
-                task_count += 1
-        subtitles = []
-        for _ in range(task_count):
-            subtitles.extend(self.listResultQueue.get())
-        if auto:
-            self.stopWorkers()
-        return subtitles
-
-    def downloadSubtitles(self, entries, auto=True):
-        """
-        Download subtitles using the plugins preferences and languages. Also use internal algorithm to find
-        the best match inside a plugin.
-
-        Attributes:
-            entries -- filepath or folderpath of video file or a list of that
-            auto    -- automaticaly manage workers"""
-        if auto:
-            if self.state != IDLE:
-                raise BadStateError(self.state, IDLE)
-            self.startWorkers()
-        subtitles = self.listSubtitles(entries, False)
-        task_count = 0
-        for _, subsByVideoPath in groupby(sorted(subtitles, key=lambda x: x.video_path), lambda x: x.video_path):
-            if not self.multi:
-                self.taskQueue.put((5, DownloadTask(sorted(list(subsByVideoPath), cmp=self.cmpSubtitles))))
-                task_count += 1
-                continue
-            for __, subsByVideoPathByLanguage in groupby(sorted(subsByVideoPath, key=lambda x: x.language), lambda x: x.language):
-                self.taskQueue.put((5, DownloadTask(sorted(list(subsByVideoPathByLanguage), cmp=self.cmpSubtitles))))
-                task_count += 1
-        downloaded = []
-        for _ in range(task_count):
-            downloaded.extend(self.downloadResultQueue.get())
-        if auto:
-            self.stopWorkers()
-        return downloaded
-
-    def cmpSubtitles(self, x, y):
-        """Compares 2 subtitles elements x and y using video_path, languages and plugin"""
-        video_paths = sorted([x.video_path, y.video_path])
-        if x.video_path != y.video_path and video_paths.index(x.video_path) < video_paths(y.video_path):
-            return - 1
-        if x.video_path != y.video_path and video_paths.index(x.video_path) > video_paths(y.video_path):
-            return 1
-        if self._languages and self._languages.index(x.language) < self._languages.index(y.language):
-            return - 1
-        if self._languages and self._languages.index(x.language) > self._languages.index(y.language):
-            return 1
-        if self._plugins.index(x.plugin) < self._plugins.index(y.plugin):
-            return - 1
-        if self._plugins.index(x.plugin) > self._plugins.index(y.plugin):
-            return 1
-        return 0
-
-    def startWorkers(self):
-        """Create a pool of workers and start them"""
-        self.pool = []
-        for _ in range(self.workers):
-            worker = PluginWorker(self.taskQueue, self.listResultQueue, self.downloadResultQueue)
-            worker.start()
-            self.pool.append(worker)
-            logger.debug(u'Worker %s added to the pool' % worker.name)
-        self.state = RUNNING
-
-    def stopWorkers(self):
-        """Stop workers using a lowest priority stop signal and wait for them to terminate properly"""
-        for _ in range(self.workers):
-            self.taskQueue.put((10, StopTask()))
-        for worker in self.pool:
-            worker.join()
-        self.state = IDLE
-
-    def pauseWorkers(self):
-        """Pause workers using a highest priority stop signal and wait for them to terminate properly"""
-        for _ in range(self.workers):
-            self.taskQueue.put((0, StopTask()))
-        for worker in self.pool:
-            worker.join()
-        self.state = PAUSED
-        if self.taskQueue.empty():
-            self.state = STOPPED
-
-    def getConfigDict(self):
-        """Produce a dict with configuration items. Used by plugins to read configuration"""
-        config = {}
-        config['multi'] = self.multi
-        config['cache_dir'] = self.cache_dir
-        config['files_mode'] = self.files_mode
-        return config
-
-    def addTask(self, task):
-        if not isinstance(task, Task) or isinstance(task, StopTask):
-            raise WrongTaskError()
-        self.taskQueue.put((5, task))
-
-
-class PluginWorker(threading.Thread):
-    """Threaded plugin worker"""
-    def __init__(self, taskQueue, listResultQueue, downloadResultQueue):
-        threading.Thread.__init__(self)
-        self.taskQueue = taskQueue
-        self.listResultQueue = listResultQueue
-        self.downloadResultQueue = downloadResultQueue
-        self.logger = logging.getLogger('subliminal.worker')
-
-    def run(self):
-        while True:
-            task = self.taskQueue.get()[1]
-            if isinstance(task, StopTask):
-                self.logger.debug(u'Poison pill received, terminating thread %s' % self.name)
-                self.taskQueue.task_done()
-                break
-            result = []
-            try:
-                if isinstance(task, ListTask):
-                    plugin = getattr(plugins, task.plugin)(task.config)
-                    result = plugin.list(task.filepath, task.languages)
-                elif isinstance(task, DownloadTask):
-                    for subtitle in task.subtitles:
-                        plugin = getattr(plugins, subtitle.plugin)()
-                        try:
-                            result = [plugin.download(subtitle)]
-                            break
-                        except DownloadFailedError as e:
-                            self.logger.warning(u'Could not download subtitle %r, trying next' % subtitle)
-                            continue
-                    if not result:
-                        self.logger.error(u'No subtitles could be downloaded for file %r' % subtitle.video_path)
-            except:
-                self.logger.error(u'Exception raised in worker %s' % self.name, exc_info=True)
-            finally:
-                if isinstance(task, ListTask):
-                    self.listResultQueue.put(result)
-                elif isinstance(task, DownloadTask):
-                    self.downloadResultQueue.put(result)
-                self.taskQueue.task_done()
-        self.logger.debug(u'Thread %s terminated' % self.name)
-
-
-def scan(entry, depth=0, max_depth=3):
-    """Scan a path and return a list of tuples (filepath, set(languages), has single)"""
-    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.isfile(entry):  # a file? scan it
-        if depth != 0:  # trust the user: only check for valid format if recursing
-            mimetypes.add_type('video/x-matroska', '.mkv')
-            if mimetypes.guess_type(entry)[0] not in FORMATS:
-                return []
-        # check for .lg.ext and .ext
-        available_languages = set()
-        has_single = False
-        basepath = os.path.splitext(entry)[0]
-        for l in LANGUAGES:
-            for e in EXTENSIONS:
-                if os.path.exists(basepath + '.%s.%s' % (l, e)):
-                    available_languages.add(l)
-                if os.path.exists(basepath + '.%s' % e):
-                    has_single = True
-        return [(os.path.normpath(entry), available_languages, has_single)]
-    if os.path.isdir(entry):  # a dir? recurse
-        result = []
-        for e in os.listdir(entry):
-            result.extend(scan(os.path.join(entry, e), depth + 1))
-        return result
-    return []  # anything else

subliminal/subtitle.py

@@ -0,0 +1,187 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+import logging
+import os.path
+import babelfish
+import pysrt
+import re
+from .video import Episode, Movie
+
+
+logger = logging.getLogger(__name__)
+
+#:  The following characters are always stripped
+IGNORED_CHARACTERS_RE = re.compile('[!@#$\'"]')
+
+
+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, hi_score_adjust=0):
+        """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`
+        :param hi_score_adjust: adjust hearing impaired matched videos by this value
+        :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 -= set(['series', 'tvdb_id', 'season', 'episode', 'title'])
+                if 'tvdb_id' in matches:
+                    matches -= set(['series',])
+                if 'title' in matches:
+                    matches -= set(['season', 'episode'])
+            # add other scores
+            score += sum([video.scores[match] for match in matches])
+
+            # Adjust scoring if hearing impaired subtitles are detected
+            if self.hearing_impaired and hi_score_adjust != 0:
+                logger.debug('Hearing impaired subtitle score adjusted ' + \
+                             'by %d' % hi_score_adjust)
+                # Priortization (adjust score)
+                score += hi_score_adjust
+
+        logger.debug('Computed score %d with matches %r', score, initial_matches)
+        return score
+
+    def __repr__(self):
+        return '<%s [%s]>' % (self.__class__.__name__, self.language)
+
+
+def sanitize_string(str_in):
+    """
+    Sanitizes a string passed into it by eliminating characters that might
+    otherwise cause issues when attempting to locate a match on websites by
+    striping out any special characters and forcing a consistent string that
+    can be used for caching too.
+
+    :param string str_in: the string to sanitize
+    :return: sanitized string
+    :rtype: string
+    """
+    if not isinstance(str_in, basestring):
+        # handle int, float, etc
+        str_in = str(str_in)
+
+    return IGNORED_CHARACTERS_RE.sub('', str_in).lower().strip()
+
+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.LanguageConvertError:
+            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 as e:
+        if e.args[0] > 80:
+            return True
+    except:
+        logger.exception('Unexpected error when validating subtitle')
+    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/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)  # @UndefinedVariable
+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 +1,383 @@
+#!/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.assertEqual(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.assertEqual(show_id, 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)
+        self.assertEqual(show_ids['the big bang theory'], 126)
+
+    def test_query_episode_0(self):
+        video = EPISODES[0]
+        languages = set([Language('rus'), Language('heb'), Language('ita'), Language('fra'),
+                     Language('ron'), Language('nld'), Language('eng'), Language('deu'), Language('ell'),
+                     Language('por', 'BR'), Language('bul')])
+        matches = set([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(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_query_episode_1(self):
+        video = EPISODES[1]
+        languages = set([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 = set([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(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_list_subtitles(self):
+        video = EPISODES[0]
+        languages = set([Language('eng'), Language('fra')])
+        matches = set([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(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_download_subtitle(self):
+        video = EPISODES[0]
+        languages = set([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 OpenSubtitlesProviderTestCase(ProviderTestCase):
+    provider_name = 'opensubtitles'
+
+    def test_query_movie_0_query(self):
+        video = MOVIES[0]
+        languages = set([Language('eng'), ])
+        matches = set([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(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_query_episode_0_query(self):
+        video = EPISODES[0]
+        languages = set([Language('eng'), ])
+        matches = set([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(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_query_episode_1_query(self):
+        video = EPISODES[1]
+        languages = set([Language('eng'), Language('fra')])
+        matches = set([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(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_query_movie_0_imdb_id(self):
+        video = MOVIES[0]
+        languages = set([Language('eng'), Language('fra')])
+        matches = set([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(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_query_episode_0_imdb_id(self):
+        video = EPISODES[0]
+        languages = set([Language('eng'), Language('fra')])
+        matches = set([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(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_query_movie_0_hash(self):
+        video = MOVIES[0]
+        languages = set([Language('eng'), ])
+        matches = set([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([]),
+                   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(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_query_episode_0_hash(self):
+        video = EPISODES[0]
+        languages = set([Language('eng'), ])
+        matches = set([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(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_list_subtitles(self):
+        video = MOVIES[0]
+        languages = set([Language('eng'), Language('fra')])
+        matches = set([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([]),
+                   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(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_download_subtitle(self):
+        video = MOVIES[0]
+        languages = set([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 PodnapisiProviderTestCase(ProviderTestCase):
+    provider_name = 'podnapisi'
+
+    def test_query_movie_0(self):
+        video = MOVIES[0]
+        language = Language('eng')
+        matches = set([frozenset(['video_codec', 'title', 'resolution', 'year']),
+                   frozenset(['title', 'resolution', 'year']),
+                   frozenset(['video_codec', 'title', 'year']),
+                   frozenset(['title', 'year']),
+                   frozenset(['video_codec', 'title', 'resolution', 'release_group', 'year']),
+                   frozenset(['video_codec', 'title', 'resolution', 'audio_codec', 'year'])])
+        with self.Provider() as provider:
+            subtitles = provider.query(language, title=video.title, year=video.year)
+        self.assertTrue(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue([Language, ], [subtitle.language for subtitle in subtitles])
+
+    def test_query_episode_0(self):
+        video = EPISODES[0]
+        language = Language('eng')
+        matches = set([frozenset(['episode', 'series', 'season', 'video_codec', 'resolution', 'release_group']),
+                   frozenset(['season', 'video_codec', 'episode', 'resolution', 'series'])])
+        with self.Provider() as provider:
+            subtitles = provider.query(language, series=video.series, season=video.season, episode=video.episode)
+        self.assertTrue(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue([Language, ], [subtitle.language for subtitle in subtitles])
+
+    def test_list_subtitles(self):
+        video = MOVIES[0]
+        languages = set([Language('eng'), Language('fra')])
+        matches = set([frozenset(['video_codec', 'title', 'resolution', 'year']),
+                   frozenset(['title', 'resolution', 'year']),
+                   frozenset(['video_codec', 'title', 'year']),
+                   frozenset(['title', 'year']),
+                   frozenset(['video_codec', 'title', 'resolution', 'release_group', 'year']),
+                   frozenset(['video_codec', 'title', 'resolution', 'audio_codec', 'year'])])
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+        self.assertTrue(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_download_subtitle(self):
+        video = MOVIES[0]
+        languages = set([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 = set([Language('eng'), Language('spa'), Language('por')])
+        matches = set([frozenset(['hash']), ])
+        with self.Provider() as provider:
+            subtitles = provider.query(video.hashes['thesubdb'])
+        self.assertTrue(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_query_episode_1(self):
+        video = EPISODES[1]
+        languages = set([Language('eng'), Language('por')])
+        matches = set([frozenset(['hash']), ])
+        with self.Provider() as provider:
+            subtitles = provider.query(video.hashes['thesubdb'])
+        self.assertTrue(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_list_subtitles(self):
+        video = MOVIES[0]
+        languages = set([Language('eng'), Language('por')])
+        matches = set([frozenset(['hash']), ])
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+        self.assertTrue(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    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.assertEqual(show_id, 154)
+
+    def test_find_show_id_ambiguous(self):
+        with self.Provider() as provider:
+            show_id = provider.find_show_id('New Girl')
+        self.assertEqual(show_id, 977)
+
+    def test_find_show_id_no_dots(self):
+        with self.Provider() as provider:
+            show_id = provider.find_show_id('Marvel\'s Agents of S H I E L D')
+        self.assertEqual(show_id, 1340)
+
+    def test_find_show_id_error(self):
+        with self.Provider() as provider:
+            show_id = provider.find_show_id('the big gaming')
+        self.assertEqual(show_id, None)
+
+    def test_find_episode_ids(self):
+        with self.Provider() as provider:
+            episode_ids = provider.find_episode_ids(154, 5)
+        self.assertEqual(set(episode_ids.keys()), set(range(1, 25)))
+
+    def test_query_episode_0(self):
+        video = EPISODES[0]
+        languages = set([Language('fra'), Language('por'), Language('hun'), Language('ron'), Language('eng')])
+        matches = set([frozenset(['series', 'episode', 'resolution', 'season']),
+                   frozenset(['series', 'episode', 'season'])])
+        with self.Provider() as provider:
+            subtitles = provider.query(video.series, video.season, video.episode)
+        self.assertTrue(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_query_episode_1(self):
+        video = EPISODES[1]
+        languages = set([Language('fra'), Language('ell'), Language('ron'), Language('eng'), Language('hun'),
+                     Language('por'), Language('por', 'BR')])
+        matches = set([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(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    def test_list_subtitles(self):
+        video = EPISODES[0]
+        languages = set([Language('eng'), Language('fra')])
+        matches = set([frozenset(['series', 'episode', 'resolution', 'season']),
+                      frozenset([u'series', u'episode', u'season'])])
+        with self.Provider() as provider:
+            subtitles = provider.list_subtitles(video, languages)
+        self.assertTrue(matches - set([frozenset(subtitle.compute_matches(video)) for subtitle in subtitles]) == set([]))
+        self.assertTrue(languages - set([subtitle.language for subtitle in subtitles]) == set([]))
+
+    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(OpenSubtitlesProviderTestCase))
+    suite.addTest(TestLoader().loadTestsFromTestCase(PodnapisiProviderTestCase))
+    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 +1,175 @@
+#!/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
+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 = set([ Language('eng'), ])
+        subtitles = list_subtitles(videos, languages)
+        self.assertEqual(len(subtitles), len(videos))
+        self.assertTrue(len(subtitles[videos[0]]) > 0)
+
+    def test_list_subtitles_movie_0_por_br(self):
+        videos = [MOVIES[0]]
+        languages = set([Language('por', 'BR'), ])
+        subtitles = list_subtitles(videos, languages)
+        self.assertEqual(len(subtitles), len(videos))
+        self.assertTrue(len(subtitles[videos[0]]) > 0)
+
+    def test_list_subtitles_episodes(self):
+        videos = [EPISODES[0], EPISODES[1]]
+        languages = set([Language('eng'), Language('fra')])
+        subtitles = list_subtitles(videos, languages)
+        self.assertEqual(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 = set([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 = set([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 = set([Language('eng'), Language('fra')])
+        subtitles = download_best_subtitles(videos, languages)
+        for video in videos:
+            self.assertTrue(video in subtitles)
+            self.assertTrue(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 = set([Language('eng'), Language('fra')])
+        subtitles = download_best_subtitles(videos, languages, single=True)
+        for video in videos:
+            self.assertTrue(video in subtitles)
+            self.assertEqual(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 = set([Language('eng'), Language('fra')])
+        subtitles = download_best_subtitles(videos, languages, min_score=1000)
+        self.assertEqual(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 = set([Language('eng'), ])
+        subtitles = download_best_subtitles(videos, languages, hearing_impaired=True)
+        self.assertTrue(subtitles[videos[0]][0].hearing_impaired)
+
+
+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.assertEqual(scanned_video.name, os.path.join(TEST_DIR, os.path.split(video.name)[1]))
+        self.assertEqual(scanned_video.title.lower(), video.title.lower())
+        self.assertEqual(scanned_video.year, video.year)
+        self.assertEqual(scanned_video.video_codec, video.video_codec)
+        self.assertEqual(scanned_video.resolution, video.resolution)
+        self.assertEqual(scanned_video.release_group, video.release_group)
+        self.assertEqual(scanned_video.subtitle_languages, set())
+        self.assertEqual(scanned_video.hashes, {})
+        self.assertEqual(scanned_video.audio_codec, None)
+        self.assertEqual(scanned_video.imdb_id, None)
+        self.assertEqual(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.assertEqual(scanned_video.name, os.path.join(TEST_DIR, os.path.split(video.name)[1]))
+        self.assertEqual(scanned_video.series, video.series)
+        self.assertEqual(scanned_video.season, video.season)
+        self.assertEqual(scanned_video.episode, video.episode)
+        self.assertEqual(scanned_video.video_codec, video.video_codec)
+        self.assertEqual(scanned_video.resolution, video.resolution)
+        self.assertEqual(scanned_video.release_group, video.release_group)
+        self.assertEqual(scanned_video.subtitle_languages, set())
+        self.assertEqual(scanned_video.hashes, {})
+        self.assertEqual(scanned_video.title, None)
+        self.assertEqual(scanned_video.tvdb_id, None)
+        self.assertEqual(scanned_video.imdb_id, None)
+        self.assertEqual(scanned_video.audio_codec, None)
+        self.assertEqual(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.assertEqual(scanned_video.subtitle_languages, set([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.assertEqual(scanned_video.subtitle_languages, set([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.assertEqual(scanned_video.subtitle_languages, set([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/version.py

@@ -1,22 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-__version__ = '0.4'

subliminal/video.py

@@ -0,0 +1,416 @@
+# -*- 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)
+
+    def __eq__(self, other):
+        return self.__class__.__name__ == other.__class__.__name__\
+                and self.name == other.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)
+
+    def __hash__(self):
+        return hash((
+            self.series,
+            self.season,
+            self.episode,
+        ))
+
+    def __eq__(self, other):
+        return self.__class__.__name__ == other.__class__.__name__\
+                and self.series == other.series\
+                and self.season == other.season\
+                and self.episode == other.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 __hash__(self):
+        if self.year is None:
+            return hash((
+                self.title,
+                self.year,
+            ))
+        return hash(self.title)
+
+    def __eq__(self, other):
+        return self.__class__.__name__ == other.__class__.__name__\
+                and self.title == other.title\
+                and self.year == other.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.language_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, video=None):
+    """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
+    :parm :class:`Video`: optionally specify a video if you've already detected on
+                          by other means.
+    :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)
+    if not video:
+        video = Video.fromguess(
+            path,
+            guessit.guess_file_info(path, info=['filename']),
+        )
+
+    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:
+                        if st.language:
+                            try:
+                                embedded_subtitle_languages.add(babelfish.Language.fromalpha3b(st.language))
+                            except babelfish.Error:
+                                logger.error('Embedded subtitle track language %r is not a valid language', st.language)
+                                embedded_subtitle_languages.add(babelfish.Language('und'))
+                        elif st.name:
+                            try:
+                                embedded_subtitle_languages.add(babelfish.Language.fromname(st.name))
+                            except babelfish.Error:
+                                logger.error('Embedded subtitle track name %r is not a valid language', st.name)
+                                embedded_subtitle_languages.add(babelfish.Language('und'))
+                        else:
+                            embedded_subtitle_languages.add(babelfish.Language('und'))
+                    logger.debug('Found embedded subtitle %r with enzyme', embedded_subtitle_languages)
+                    video.subtitle_languages |= embedded_subtitle_languages
+            else:
+                logger.debug('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', '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', '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', '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')

test/test_plugins.py

@@ -1,152 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import unittest
-import logging
-import os
-
-
-logging.basicConfig(level=logging.DEBUG, format='%(name)-24s %(levelname)-8s %(message)s')
-test_folder = u'/your/path/here/videos/'
-test_file = u'/your/path/here/videos/the.big.bang.theory.s04e01.hdtv.xvid-fqm.avi'
-cache_dir = u'/tmp/sublicache'
-if not os.path.exists(cache_dir):
-    os.mkdir(cache_dir)
-
-
-class Addic7edTestCase(unittest.TestCase):
-    def setUp(self):
-        from subliminal.plugins import Addic7ed
-        self.config = {'multi': True, 'cache_dir': cache_dir, 'files_mode': -1}
-        self.plugin = Addic7ed(self.config)
-        self.languages = set(['en', 'fr'])
-
-    def test_list(self):
-        list = self.plugin.list(test_file, self.languages)
-        assert list
-
-    def test_download(self):
-        subtitle = self.plugin.list(test_file, self.languages)[0]
-        if os.path.exists(subtitle.path):
-            os.remove(subtitle.path)
-        download = self.plugin.download(subtitle)
-        assert download
-
-
-class BierDopjeTestCase(unittest.TestCase):
-    def setUp(self):
-        from subliminal.plugins import BierDopje
-        self.config = {'multi': True, 'cache_dir': cache_dir, 'files_mode': -1}
-        self.plugin = BierDopje(self.config)
-        self.languages = set(['en', 'fr'])
-
-    def test_list(self):
-        list = self.plugin.list(test_file, self.languages)
-        assert list
-
-    def test_download(self):
-        subtitle = self.plugin.list(test_file, self.languages)[0]
-        if os.path.exists(subtitle.path):
-            os.remove(subtitle.path)
-        download = self.plugin.download(subtitle)
-        assert download
-
-
-class OpenSubtitlesTestCase(unittest.TestCase):
-    def setUp(self):
-        from subliminal.plugins import OpenSubtitles
-        self.config = {'multi': True, 'cache_dir': cache_dir, 'files_mode': -1}
-        self.plugin = OpenSubtitles(self.config)
-        self.languages = set(['en', 'fr'])
-
-    def test_list(self):
-        list = self.plugin.list(test_file, self.languages)
-        assert list
-
-    def test_download(self):
-        subtitle = self.plugin.list(test_file, self.languages)[0]
-        if os.path.exists(subtitle.path):
-            os.remove(subtitle.path)
-        download = self.plugin.download(subtitle)
-        assert download
-
-
-class SubsWikiTestCase(unittest.TestCase):
-    def setUp(self):
-        from subliminal.plugins import SubsWiki
-        self.config = {'multi': True, 'cache_dir': cache_dir, 'files_mode': -1}
-        self.plugin = SubsWiki(self.config)
-        self.languages = set(['en', 'fr', 'es', 'pt'])
-
-    def test_list(self):
-        list = self.plugin.list(test_file, self.languages)
-        assert list
-
-    def test_download(self):
-        subtitle = self.plugin.list(test_file, self.languages)[0]
-        if os.path.exists(subtitle.path):
-            os.remove(subtitle.path)
-        download = self.plugin.download(subtitle)
-        assert download
-
-
-class SubtitulosTestCase(unittest.TestCase):
-    def setUp(self):
-        from subliminal.plugins import Subtitulos
-        self.config = {'multi': True, 'cache_dir': cache_dir, 'files_mode': -1}
-        self.plugin = Subtitulos(self.config)
-        self.languages = set(['en', 'fr', 'es', 'pt'])
-
-    def test_list(self):
-        list = self.plugin.list(test_file, self.languages)
-        assert list
-
-    def test_download(self):
-        subtitle = self.plugin.list(test_file, self.languages)[0]
-        if os.path.exists(subtitle.path):
-            os.remove(subtitle.path)
-        download = self.plugin.download(subtitle)
-        assert download
-
-
-class TheSubDBTestCase(unittest.TestCase):
-    def setUp(self):
-        from subliminal.plugins import TheSubDB
-        self.config = {'multi': True, 'cache_dir': cache_dir, 'files_mode': -1}
-        self.plugin = TheSubDB(self.config)
-        self.languages = set(['en', 'fr', 'es', 'pt'])
-
-    def test_list(self):
-        list = self.plugin.list(test_file, self.languages)
-        assert list
-
-    def test_download(self):
-        subtitle = self.plugin.list(test_file, self.languages)[0]
-        if os.path.exists(subtitle.path):
-            os.remove(subtitle.path)
-        download = self.plugin.download(subtitle)
-        assert download
-
-
-if __name__ == "__main__":
-    unittest.main()
-

test/test_subliminal.py

@@ -1,90 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-#
-# Subliminal - Subtitles, faster than your thoughts
-# Copyright (c) 2011 Antoine Bertin <diaoulael@gmail.com>
-#
-# This file is part of Subliminal.
-#
-# Subliminal is free software; you can redistribute it and/or modify it under
-# the terms of the Lesser GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# Subliminal is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# Lesser GNU General Public License for more details.
-#
-# You should have received a copy of the Lesser GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-
-import unittest
-import logging
-import os
-import subliminal
-
-
-logging.basicConfig(level=logging.DEBUG, format='%(name)-24s %(levelname)-8s %(message)s')
-test_folder = u'/your/path/here/videos/'
-test_file = u'/your/path/here/videos/the.big.bang.theory.s04e01.hdtv.xvid-fqm.avi'
-cache_dir = u'/tmp/sublicache'
-if not os.path.exists(cache_dir):
-    os.mkdir(cache_dir)
-
-
-class FileTestCase(unittest.TestCase):
-    def setUp(self):
-        self.subli = subliminal.Subliminal(cache_dir=cache_dir, workers=4, multi=False, force=True, max_depth=3, files_mode=-1)
-        self.subli.languages = ['en', 'fr', 'es', 'pt']
-        self.subli.plugins = subliminal.PLUGINS
-
-    def test_list(self):
-        results = self.subli.listSubtitles(test_file)
-        self.assertTrue(len(results) > 0)
-
-    def test_download(self):
-        results = self.subli.downloadSubtitles(test_file)
-        self.assertTrue(len(results) > 0)
-
-
-class ErrorTestCase(unittest.TestCase):
-    def setUp(self):
-        self.subli = subliminal.Subliminal(cache_dir=cache_dir, workers=4, multi=False, force=True, max_depth=3, files_mode=-1)
-
-    def test_language(self):
-        with self.assertRaises(subliminal.classes.LanguageError):
-            self.subli.languages = ['en', 'fr', 'zz', 'pt']
-
-    def test_plugin(self):
-        with self.assertRaises(subliminal.classes.PluginError):
-            self.subli.plugins = ['WrongPlugin']
-
-
-class PriorityQueueTestCase(unittest.TestCase):
-    def setUp(self):
-        self.subli = subliminal.Subliminal(cache_dir=cache_dir, workers=4, multi=False, force=True, max_depth=3, files_mode=-1)
-        self.subli.languages = ['en', 'fr', 'es', 'pt']
-        self.subli.plugins = subliminal.PLUGINS
-
-    def test_bad_state_error(self):
-        with self.assertRaises(subliminal.classes.BadStateError):
-            self.subli.startWorkers()
-            results = self.subli.listSubtitles(test_folder)
-        self.subli.stopWorkers()
-
-    def test_manual_list(self):
-        self.subli.taskQueue.put((5, subliminal.classes.ListTask(test_file, set(self.subli.languages), 'OpenSubtitles', self.subli.getConfigDict())))
-        self.subli.startWorkers()
-        # parallel stuff...
-        self.subli.stopWorkers()
-        result = self.subli.listResultQueue.get()
-        self.assertTrue(len(result) > 0)
-        
-
-
-
-if __name__ == "__main__":
-    unittest.main()
-