Update subliminal

libs/subliminal/services/__init__.py

@@ -15,10 +15,10 @@
 #
 # You should have received a copy of the GNU Lesser General Public License
 # along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
-from .. import cache
-from ..exceptions import MissingLanguageError, DownloadFailedError, ServiceError
+from ..cache import Cache
+from ..exceptions import DownloadFailedError, ServiceError
+from ..language import language_set, Language
 from ..subtitles import EXTENSIONS
-from guessit.language import lang_set, UNDETERMINED
 import logging
 import os
 import requests
@@ -49,8 +49,14 @@ class ServiceBase(object):
     #: Timeout for web requests
     timeout = 5
 
-    #: Mapping to Service's language codes and subliminal's
-    languages = {}
+    #: :class:`~subliminal.language.language_set` of available languages
+    languages = language_set()
+
+    #: Map between language objects and language codes used in the service
+    language_map = {}
+
+    #: Default attribute of a :class:`~subliminal.language.Language` to get with :meth:`get_code`
+    language_code = 'alpha2'
 
     #: Accepted video classes (:class:`~subliminal.videos.Episode`, :class:`~subliminal.videos.Movie`, :class:`~subliminal.videos.UnknownVideo`)
     videos = []
@@ -63,6 +69,7 @@ class ServiceBase(object):
 
     def __init__(self, config=None):
         self.config = config or ServiceConfig()
+        self.session = None
 
     def __enter__(self):
         self.init()
@@ -80,33 +87,60 @@ class ServiceBase(object):
         """Initialize cache, make sure it is loaded from disk"""
         if not self.config or not self.config.cache:
             raise ServiceError('Cache directory is required')
-
-        service_name = self.__class__.__name__
-        self.config.cache.load(service_name)
+        self.config.cache.load(self.__class__.__name__)
 
     def save_cache(self):
-        service_name = self.__class__.__name__
-        self.config.cache.save(service_name)
+        self.config.cache.save(self.__class__.__name__)
 
     def clear_cache(self):
-        service_name = self.__class__.__name__
-        self.config.cache.clear(service_name)
+        self.config.cache.clear(self.__class__.__name__)
 
     def cache_for(self, func, args, result):
-        service_name = self.__class__.__name__
-        return self.config.cache.cache_for(service_name, func, args, result)
+        return self.config.cache.cache_for(self.__class__.__name__, func, args, result)
 
     def cached_value(self, func, args):
-        service_name = self.__class__.__name__
-        return self.config.cache.cached_value(service_name, func, args)
+        return self.config.cache.cached_value(self.__class__.__name__, func, args)
 
     def terminate(self):
         """Terminate connection"""
         logger.debug(u'Terminating %s' % self.__class__.__name__)
 
+    def get_code(self, language):
+        """Get the service code for a :class:`~subliminal.language.Language`
+
+        It uses the :data:`language_map` and if there's no match, falls back
+        on the :data:`language_code` attribute of the given :class:`~subliminal.language.Language`
+
+        """
+        if language in self.language_map:
+            return self.language_map[language]
+        if self.language_code is None:
+            raise ValueError('%r has no matching code' % language)
+        return getattr(language, self.language_code)
+
+    def get_language(self, code):
+        """Get a :class:`~subliminal.language.Language` from a service code
+
+        It uses the :data:`language_map` and if there's no match, uses the
+        given code as ``language`` parameter for the :class:`~subliminal.language.Language`
+        constructor
+
+        .. note::
+
+            A warning is emitted if the generated :class:`~subliminal.language.Language`
+            is "Undetermined"
+
+        """
+        if code in self.language_map:
+            return self.language_map[code]
+        language = Language(code, strict=False)
+        if language == Language('Undetermined'):
+            logger.warning(u'Code %s could not be identified as a language for %s' % (code, self.__class__.__name__))
+        return language
+
     def query(self, *args):
         """Make the actual query"""
-        pass
+        raise NotImplementedError()
 
     def list(self, video, languages):
         """List subtitles
@@ -119,6 +153,10 @@ class ServiceBase(object):
             return []
         return self.list_checked(video, languages)
 
+    def list_checked(self, video, languages):
+        """List subtitles without having to check parameters for validity"""
+        raise NotImplementedError()
+
     def download(self, subtitle):
         """Download a subtitle"""
         self.download_file(subtitle.link, subtitle.path)
@@ -129,11 +167,12 @@ class ServiceBase(object):
 
         :param video: the video to check
         :type video: :class:`~subliminal.videos.video`
-        :param set languages: languages to check
+        :param languages: languages to check
+        :type languages: :class:`~subliminal.language.Language`
         :rtype: bool
 
         """
-        languages = (lang_set(languages) & cls.languages) - set([UNDETERMINED])
+        languages = (languages & cls.languages) - language_set(['Undetermined'])
         if not languages:
             logger.debug(u'No language available for service %s' % cls.__name__.lower())
             return False
@@ -211,7 +250,7 @@ class ServiceConfig(object):
         self.cache_dir = cache_dir
         self.cache = None
         if cache_dir is not None:
-            self.cache = cache.Cache(cache_dir)
+            self.cache = Cache(cache_dir)
 
     def __repr__(self):
         return 'ServiceConfig(%r, %s)' % (self.multi, self.cache.cache_dir)

libs/subliminal/services/addic7ed.py

@@ -17,12 +17,11 @@
 # along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
 from . import ServiceBase
 from ..cache import cachedmethod
+from ..language import Language, language_set
 from ..subtitles import get_subtitle_path, ResultSubtitle
+from ..utils import get_keywords
 from ..videos import Episode
 from bs4 import BeautifulSoup
-from guessit.language import lang_set
-from subliminal.utils import get_keywords
-import guessit
 import logging
 import re
 
@@ -49,13 +48,10 @@ def matches(pattern, string):
 class Addic7ed(ServiceBase):
     server_url = 'http://www.addic7ed.com'
     api_based = False
-    languages = lang_set([u'English', u'Italian', u'Portuguese',
-                          u'Portuguese (Brazilian)', u'Romanian',
-                          u'Spanish', u'French', u'Greek', u'Arabic',
-                          u'German', u'Croatian', u'Indonesian', u'Hebrew',
-                          u'Russian', u'Turkish', u'Swedish', u'Czech',
-                          u'Dutch', u'Hungarian', u'Norwegian', u'Polish',
-                          u'Persian'], strict=True)
+    #TODO: Complete this
+    languages = language_set(['ar', 'ca', 'de', 'el', 'en', 'es', 'eu', 'fr', 'ga', 'he', 'hr', 'hu', 'it',
+                              'pl', 'pt', 'ro', 'ru', 'se', 'pt-br'])
+    language_map = {'Portuguese (Brazilian)': Language('por-BR'), 'Greek': Language('gre')}
     videos = [Episode]
     require_video = False
     required_features = ['permissive']
@@ -119,7 +115,7 @@ class Addic7ed(ServiceBase):
                 if 'href' not in link.attrs or not (link['href'].startswith('/original') or link['href'].startswith('/updated')):
                     continue
                 suburl = link['href']
-                lang = guessit.Language(row.find('td', 'language').text.strip())
+                lang = self.get_language(row.find('td', 'language').text.strip())
                 result = {'suburl': suburl, 'language': lang, 'release': release}
                 suburls.append(result)
         return suburls
@@ -135,21 +131,18 @@ class Addic7ed(ServiceBase):
         except KeyError:
             logger.debug(u'Could not find series id for %s' % series)
             return []
-
         try:
             ep_url = self.get_episode_url(sid, season, episode)
         except KeyError:
             logger.debug(u'Could not find episode id for %s season %d episode %d' % (series, season, episode))
             return []
         suburls = self.get_sub_urls(ep_url)
-
         # filter the subtitles with our queried languages
         subtitles = []
         for suburl in suburls:
             language = suburl['language']
             if language not in languages:
                 continue
-
             path = get_subtitle_path(filepath, language, self.config.multi)
             subtitle = ResultSubtitle(path, language, self.__class__.__name__.lower(),
                                       '%s/%s' % (self.server_url, suburl['suburl']),

libs/subliminal/services/bierdopje.py

@@ -18,11 +18,11 @@
 from . import ServiceBase
 from ..cache import cachedmethod
 from ..exceptions import ServiceError
+from ..language import language_set
 from ..subtitles import get_subtitle_path, ResultSubtitle
 from ..utils import to_unicode
 from ..videos import Episode
 from bs4 import BeautifulSoup
-from guessit.language import lang_set
 import logging
 import urllib
 try:
@@ -37,7 +37,7 @@ logger = logging.getLogger(__name__)
 class BierDopje(ServiceBase):
     server_url = 'http://api.bierdopje.com/A2B638AC5D804C2E/'
     api_based = True
-    languages = lang_set(['en', 'nl'])
+    languages = language_set(['eng', 'dut'])
     videos = [Episode]
     require_video = False
     required_features = ['xml']
@@ -52,7 +52,6 @@ class BierDopje(ServiceBase):
         if soup.status.contents[0] == 'false':
             logger.debug(u'Could not find show %s' % series)
             return None
-
         return int(soup.showid.contents[0])
 
     def load_cache(self):

libs/subliminal/services/opensubtitles.py

@@ -17,11 +17,10 @@
 # along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
 from . import ServiceBase
 from ..exceptions import ServiceError, DownloadFailedError
+from ..language import Language, language_set
 from ..subtitles import get_subtitle_path, ResultSubtitle
 from ..utils import to_unicode
 from ..videos import Episode, Movie
-from guessit.language import lang_set
-import guessit
 import gzip
 import logging
 import os.path
@@ -34,71 +33,50 @@ logger = logging.getLogger(__name__)
 class OpenSubtitles(ServiceBase):
     server_url = 'http://api.opensubtitles.org/xml-rpc'
     api_based = True
-    # language list fetched from:
-    # http://www.opensubtitles.org/addons/export_languages.php
-    languages = lang_set(['aar', 'abk', 'ace', 'ach', 'ada', 'ady', 'afa', 'afh',
-                          'afr', 'ain', 'aka', 'akk', 'alb', 'ale', 'alg', 'alt',
-                          'amh', 'ang', 'apa', 'ara', 'arc', 'arg', 'arm', 'arn',
-                          'arp', 'art', 'arw', 'asm', 'ast', 'ath', 'aus', 'ava',
-                          'ave', 'awa', 'aym', 'aze', 'bad', 'bai', 'bak', 'bal',
-                          'bam', 'ban', 'baq', 'bas', 'bat', 'bej', 'bel', 'bem',
-                          'ben', 'ber', 'bho', 'bih', 'bik', 'bin', 'bis', 'bla',
-                          'bnt', 'bod', 'bos', 'bra', 'bre', 'btk', 'bua', 'bug',
-                          'bul', 'bur', 'byn', 'cad', 'cai', 'car', 'cat', 'cau',
-                          'ceb', 'cel', 'cha', 'chb', 'che', 'chg', 'chi', 'chk',
-                          'chm', 'chn', 'cho', 'chp', 'chr', 'chu', 'chv', 'chy',
-                          'cmc', 'cop', 'cor', 'cos', 'cpe', 'cpf', 'cpp', 'cre',
-                          'crh', 'crp', 'csb', 'cus', 'cym', 'cze', 'dak', 'dan',
-                          'dar', 'day', 'del', 'den', 'deu', 'dgr', 'din', 'div',
-                          'doi', 'dra', 'dua', 'dum', 'dut', 'dyu', 'dzo', 'efi',
-                          'egy', 'eka', 'elx', 'eng', 'enm', 'epo', 'est', 'eus',
-                          'ewe', 'ewo', 'fan', 'fao', 'fas', 'fat', 'fij', 'fil',
-                          'fin', 'fiu', 'fon', 'fra', 'fre', 'frm', 'fro', 'fry',
-                          'ful', 'fur', 'gaa', 'gay', 'gba', 'gem', 'geo', 'ger',
-                          'gez', 'gil', 'gla', 'gle', 'glg', 'glv', 'gmh', 'goh',
-                          'gon', 'gor', 'got', 'grb', 'grc', 'ell', 'grn', 'guj',
-                          'gwi', 'hai', 'hat', 'hau', 'haw', 'heb', 'her', 'hil',
-                          'him', 'hin', 'hit', 'hmn', 'hmo', 'hrv', 'hun', 'hup',
-                          'hye', 'iba', 'ibo', 'ice', 'ido', 'iii', 'ijo', 'iku',
-                          'ile', 'ilo', 'ina', 'inc', 'ind', 'ine', 'inh', 'ipk',
-                          'ira', 'iro', 'isl', 'ita', 'jav', 'jpn', 'jpr', 'jrb',
-                          'kaa', 'kab', 'kac', 'kal', 'kam', 'kan', 'kar', 'kas',
-                          'kat', 'kau', 'kaw', 'kaz', 'kbd', 'kha', 'khi', 'khm',
-                          'kho', 'kik', 'kin', 'kir', 'kmb', 'kok', 'kom', 'kon',
-                          'kor', 'kos', 'kpe', 'krc', 'kro', 'kru', 'kua', 'kum',
-                          'kur', 'kut', 'lad', 'lah', 'lam', 'lao', 'lat', 'lav',
-                          'lez', 'lim', 'lin', 'lit', 'lol', 'loz', 'ltz', 'lua',
-                          'lub', 'lug', 'lui', 'lun', 'luo', 'lus', 'mac', 'mad',
-                          'mag', 'mah', 'mai', 'mak', 'mal', 'man', 'mao', 'map',
-                          'mar', 'mas', 'may', 'mdf', 'mdr', 'men', 'mga', 'mic',
-                          'min', 'mis', 'mkd', 'mkh', 'mlg', 'mlt', 'mnc', 'mni',
-                          'mno', 'moh', 'mol', 'mon', 'mos', 'mri', 'msa', 'mwl',
-                          'mul', 'mun', 'mus', 'mwr', 'mya', 'myn', 'myv', 'nah',
-                          'nai', 'nap', 'nau', 'nav', 'nbl', 'nde', 'ndo', 'nds',
-                          'nep', 'new', 'nia', 'nic', 'niu', 'nld', 'nno', 'nob',
-                          'nog', 'non', 'nor', 'nso', 'nub', 'nwc', 'nya', 'nym',
-                          'nyn', 'nyo', 'nzi', 'oci', 'oji', 'ori', 'orm', 'osa',
-                          'oss', 'ota', 'oto', 'paa', 'pag', 'pal', 'pam', 'pan',
-                          'pap', 'pau', 'peo', 'per', 'phi', 'phn', 'pli', 'pol',
-                          'pon', 'por', 'pra', 'pro', 'pus', 'que', 'raj', 'rap',
-                          'rar', 'roa', 'roh', 'rom', 'ron', 'run', 'rup', 'rus',
-                          'sad', 'sag', 'sah', 'sai', 'sal', 'sam', 'san', 'sas',
-                          'sat', 'scc', 'scn', 'sco', 'scr', 'sel', 'sem', 'sga',
-                          'sgn', 'shn', 'sid', 'sin', 'sio', 'sit', 'sla', 'slk',
-                          'slo', 'slv', 'sma', 'sme', 'smi', 'smj', 'smn', 'smo',
-                          'sms', 'sna', 'snd', 'snk', 'sog', 'som', 'son', 'sot',
-                          'spa', 'sqi', 'srd', 'srp', 'srr', 'ssa', 'ssw', 'suk',
-                          'sun', 'sus', 'sux', 'swa', 'swe', 'syr', 'tah', 'tai',
-                          'tam', 'tat', 'tel', 'tem', 'ter', 'tet', 'tgk', 'tgl',
-                          'tha', 'tib', 'tig', 'tir', 'tiv', 'tkl', 'tlh', 'tli',
-                          'tmh', 'tog', 'ton', 'tpi', 'tsi', 'tsn', 'tso', 'tuk',
-                          'tum', 'tup', 'tur', 'tut', 'tvl', 'twi', 'tyv', 'udm',
-                          'uga', 'uig', 'ukr', 'umb', 'und', 'urd', 'uzb', 'vai',
-                          'ven', 'vie', 'vol', 'vot', 'wak', 'wal', 'war', 'was',
-                          'wel', 'wen', 'wln', 'wol', 'xal', 'xho', 'yao', 'yap',
-                          'yid', 'yor', 'ypk', 'zap', 'zen', 'zha', 'zho', 'znd',
-                          'zul', 'zun', 'rum', 'pob', 'unk', 'ass'])
-
+    # Source: http://www.opensubtitles.org/addons/export_languages.php
+    languages = language_set(['aar', 'abk', 'ace', 'ach', 'ada', 'ady', 'afa', 'afh', 'afr', 'ain', 'aka', 'akk',
+                              'alb', 'ale', 'alg', 'alt', 'amh', 'ang', 'apa', 'ara', 'arc', 'arg', 'arm', 'arn',
+                              'arp', 'art', 'arw', 'asm', 'ast', 'ath', 'aus', 'ava', 'ave', 'awa', 'aym', 'aze',
+                              'bad', 'bai', 'bak', 'bal', 'bam', 'ban', 'baq', 'bas', 'bat', 'bej', 'bel', 'bem',
+                              'ben', 'ber', 'bho', 'bih', 'bik', 'bin', 'bis', 'bla', 'bnt', 'bos', 'bra', 'bre',
+                              'btk', 'bua', 'bug', 'bul', 'bur', 'byn', 'cad', 'cai', 'car', 'cat', 'cau', 'ceb',
+                              'cel', 'cha', 'chb', 'che', 'chg', 'chi', 'chk', 'chm', 'chn', 'cho', 'chp', 'chr',
+                              'chu', 'chv', 'chy', 'cmc', 'cop', 'cor', 'cos', 'cpe', 'cpf', 'cpp', 'cre', 'crh',
+                              'crp', 'csb', 'cus', 'cze', 'dak', 'dan', 'dar', 'day', 'del', 'den', 'dgr', 'din',
+                              'div', 'doi', 'dra', 'dua', 'dum', 'dut', 'dyu', 'dzo', 'efi', 'egy', 'eka', 'ell',
+                              'elx', 'eng', 'enm', 'epo', 'est', 'ewe', 'ewo', 'fan', 'fao', 'fat', 'fij', 'fil',
+                              'fin', 'fiu', 'fon', 'fre', 'frm', 'fro', 'fry', 'ful', 'fur', 'gaa', 'gay', 'gba',
+                              'gem', 'geo', 'ger', 'gez', 'gil', 'gla', 'gle', 'glg', 'glv', 'gmh', 'goh', 'gon',
+                              'gor', 'got', 'grb', 'grc', 'grn', 'guj', 'gwi', 'hai', 'hat', 'hau', 'haw', 'heb',
+                              'her', 'hil', 'him', 'hin', 'hit', 'hmn', 'hmo', 'hrv', 'hun', 'hup', 'iba', 'ibo',
+                              'ice', 'ido', 'iii', 'ijo', 'iku', 'ile', 'ilo', 'ina', 'inc', 'ind', 'ine', 'inh',
+                              'ipk', 'ira', 'iro', 'ita', 'jav', 'jpn', 'jpr', 'jrb', 'kaa', 'kab', 'kac', 'kal',
+                              'kam', 'kan', 'kar', 'kas', 'kau', 'kaw', 'kaz', 'kbd', 'kha', 'khi', 'khm', 'kho',
+                              'kik', 'kin', 'kir', 'kmb', 'kok', 'kom', 'kon', 'kor', 'kos', 'kpe', 'krc', 'kro',
+                              'kru', 'kua', 'kum', 'kur', 'kut', 'lad', 'lah', 'lam', 'lao', 'lat', 'lav', 'lez',
+                              'lim', 'lin', 'lit', 'lol', 'loz', 'ltz', 'lua', 'lub', 'lug', 'lui', 'lun', 'luo',
+                              'lus', 'mac', 'mad', 'mag', 'mah', 'mai', 'mak', 'mal', 'man', 'mao', 'map', 'mar',
+                              'mas', 'may', 'mdf', 'mdr', 'men', 'mga', 'mic', 'min', 'mkh', 'mlg', 'mlt', 'mnc',
+                              'mni', 'mno', 'moh', 'mon', 'mos', 'mun', 'mus', 'mwl', 'mwr', 'myn', 'myv', 'nah',
+                              'nai', 'nap', 'nau', 'nav', 'nbl', 'nde', 'ndo', 'nds', 'nep', 'new', 'nia', 'nic',
+                              'niu', 'nno', 'nob', 'nog', 'non', 'nor', 'nso', 'nub', 'nwc', 'nya', 'nym', 'nyn',
+                              'nyo', 'nzi', 'oci', 'oji', 'ori', 'orm', 'osa', 'oss', 'ota', 'oto', 'paa', 'pag',
+                              'pal', 'pam', 'pan', 'pap', 'pau', 'peo', 'per', 'phi', 'phn', 'pli', 'pol', 'pon',
+                              'por', 'pra', 'pro', 'pus', 'que', 'raj', 'rap', 'rar', 'roa', 'roh', 'rom', 'rum',
+                              'run', 'rup', 'rus', 'sad', 'sag', 'sah', 'sai', 'sal', 'sam', 'san', 'sas', 'sat',
+                              'scn', 'sco', 'sel', 'sem', 'sga', 'sgn', 'shn', 'sid', 'sin', 'sio', 'sit', 'sla',
+                              'slo', 'slv', 'sma', 'sme', 'smi', 'smj', 'smn', 'smo', 'sms', 'sna', 'snd', 'snk',
+                              'sog', 'som', 'son', 'sot', 'spa', 'srd', 'srp', 'srr', 'ssa', 'ssw', 'suk', 'sun',
+                              'sus', 'sux', 'swa', 'swe', 'syr', 'tah', 'tai', 'tam', 'tat', 'tel', 'tem', 'ter',
+                              'tet', 'tgk', 'tgl', 'tha', 'tib', 'tig', 'tir', 'tiv', 'tkl', 'tlh', 'tli', 'tmh',
+                              'tog', 'ton', 'tpi', 'tsi', 'tsn', 'tso', 'tuk', 'tum', 'tup', 'tur', 'tut', 'tvl',
+                              'twi', 'tyv', 'udm', 'uga', 'uig', 'ukr', 'umb', 'urd', 'uzb', 'vai', 'ven', 'vie',
+                              'vol', 'vot', 'wak', 'wal', 'war', 'was', 'wel', 'wen', 'wln', 'wol', 'xal', 'xho',
+                              'yao', 'yap', 'yid', 'yor', 'ypk', 'zap', 'zen', 'zha', 'znd', 'zul', 'zun',
+                              'por-BR', 'rum-MD'])
+    language_map = {'mol': Language('rum-MD'), 'scc': Language('srp'), 'pob': Language('por-BR'),
+                    Language('rum-MD'): 'mol', Language('srp'): 'scc', Language('por-BR'): 'pob'}
+    language_code = 'alpha3'
     videos = [Episode, Movie]
     require_video = False
     confidence_order = ['moviehash', 'imdbid', 'fulltext']
@@ -131,7 +109,7 @@ class OpenSubtitles(ServiceBase):
         if not searches:
             raise ServiceError('One or more parameter missing')
         for search in searches:
-            search['sublanguageid'] = ','.join(l.opensubtitles for l in languages)
+            search['sublanguageid'] = ','.join(self.get_code(l) for l in languages)
         logger.debug(u'Getting subtitles %r with token %s' % (searches, self.token))
         results = self.server.SearchSubtitles(self.token, searches)
         if not results['data']:
@@ -139,7 +117,7 @@ class OpenSubtitles(ServiceBase):
             return []
         subtitles = []
         for result in results['data']:
-            language = guessit.Language(result['SubLanguageID'])
+            language = self.get_language(result['SubLanguageID'])
             path = get_subtitle_path(filepath, language, self.config.multi)
             confidence = 1 - float(self.confidence_order.index(result['MatchedBy'])) / float(len(self.confidence_order))
             subtitle = ResultSubtitle(path, language, service=self.__class__.__name__.lower(), link=result['SubDownloadLink'],

libs/subliminal/services/podnapisi.py

@@ -17,12 +17,11 @@
 # along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
 from . import ServiceBase
 from ..exceptions import ServiceError, DownloadFailedError
+from ..language import language_set, Language
 from ..subtitles import get_subtitle_path, ResultSubtitle
 from ..utils import to_unicode
 from ..videos import Episode, Movie
-from guessit.language import lang_set
 from hashlib import md5, sha256
-import guessit
 import logging
 import xmlrpclib
 
@@ -33,11 +32,16 @@ logger = logging.getLogger(__name__)
 class Podnapisi(ServiceBase):
     server_url = 'http://ssp.podnapisi.net:8000'
     api_based = True
-    languages = lang_set(['sl', 'en', 'nn', 'ko', 'de', 'is', 'cs', 'fr', 'it', 'bs', 'jp', 'ar', 'ro',
-                          'hu', 'gr', 'zh', 'lt', 'et', 'lv', 'he', 'nl', 'da', 'sv', 'pl', 'ru', 'es',
-                          'sq', 'tr', 'fi', 'pt', 'bg', 'mk', 'sr', 'sk', 'hr', 'hi', 'th', 'ca', 'uk',
-                          'pb', 'ga', 'be', 'vi', 'fa', 'ca', 'id', 'ms'])
-    #FIXME: ag and cyr not recognized by guessit
+    languages = language_set(['ar', 'be', 'bg', 'bs', 'ca', 'ca', 'cs', 'da', 'de', 'el', 'en',
+                              'es', 'et', 'fa', 'fi', 'fr', 'ga', 'he', 'hi', 'hr', 'hu', 'id',
+                              'is', 'it', 'ja', 'ko', 'lt', 'lv', 'mk', 'ms', 'nl', 'nn', 'pl',
+                              'pt', 'ro', 'ru', 'sk', 'sl', 'sq', 'sr', 'sv', 'th', 'tr', 'uk',
+                              'vi', 'zh', 'es-ar', 'pt-br'])
+    language_map = {'jp': Language('jpn'), Language('jpn'): 'jp',
+                    'gr': Language('gre'), Language('gre'): 'gr',
+                    'pb': Language('por-BR'), Language('por-BR'): 'pb',
+                    'ag': Language('spa-AR'), Language('spa-AR'): 'ag',
+                    'cyr': Language('srp')}
     videos = [Episode, Movie]
     require_video = True
 
@@ -71,8 +75,8 @@ class Podnapisi(ServiceBase):
             return []
         subtitles = []
         for result in results['results'][moviehash]['subtitles']:
-            language = guessit.Language(result['lang'])
-            if language == guessit.language.UNDETERMINED or language not in languages:
+            language = self.get_language(result['lang'])
+            if language not in languages:
                 continue
             path = get_subtitle_path(filepath, language, self.config.multi)
             subtitle = ResultSubtitle(path, language, service=self.__class__.__name__.lower(), link=result['id'],

libs/subliminal/services/subswiki.py

@@ -17,12 +17,11 @@
 # along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
 from . import ServiceBase
 from ..exceptions import ServiceError
+from ..language import language_set, Language
 from ..subtitles import get_subtitle_path, ResultSubtitle
 from ..videos import Episode, Movie
 from bs4 import BeautifulSoup
-from guessit.language import lang_set
 from subliminal.utils import get_keywords, split_keyword
-import guessit
 import logging
 import re
 import urllib
@@ -34,9 +33,11 @@ logger = logging.getLogger(__name__)
 class SubsWiki(ServiceBase):
     server_url = 'http://www.subswiki.com'
     api_based = False
-    languages = lang_set([u'English (US)', u'English (UK)', u'English', u'French', u'Brazilian',
-                          u'Portuguese', u'Español (Latinoamérica)', u'Español (España)',
-                          u'Español', u'Italian', u'Català'], strict=True)
+    languages = language_set(['eng-US', 'eng-GB', 'eng', 'fre', 'por-BR', 'por', 'spa-ES', u'spa', u'ita', u'cat'])
+    language_map = {u'Español': Language('spa'), u'Español (España)': Language('spa'), u'Español (Latinoamérica)': Language('spa'),
+                    u'Català': Language('cat'), u'Brazilian': Language('por-BR'), u'English (US)': Language('eng-US'),
+                    u'English (UK)': Language('eng-GB')}
+    language_code = 'name'
     videos = [Episode, Movie]
     require_video = False
     release_pattern = re.compile('\nVersion (.+), ([0-9]+).([0-9])+ MBs')
@@ -82,7 +83,7 @@ class SubsWiki(ServiceBase):
                 logger.debug(u'None of subtitle keywords %r in %r' % (sub_keywords, keywords))
                 continue
             for html_language in sub.parent.parent.findAll('td', {'class': 'language'}):
-                language = guessit.Language(html_language.string.strip())
+                language = self.get_language(html_language.string.strip())
                 if language not in languages:
                     logger.debug(u'Language %r not in wanted languages %r' % (language, languages))
                     continue

libs/subliminal/services/subtitulos.py

@@ -16,12 +16,11 @@
 # You should have received a copy of the GNU Lesser General Public License
 # along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
 from . import ServiceBase
+from ..language import language_set, Language
 from ..subtitles import get_subtitle_path, ResultSubtitle
 from ..videos import Episode
 from bs4 import BeautifulSoup
-from guessit.language import lang_set
 from subliminal.utils import get_keywords, split_keyword
-import guessit
 import logging
 import re
 import unicodedata
@@ -34,9 +33,11 @@ logger = logging.getLogger(__name__)
 class Subtitulos(ServiceBase):
     server_url = 'http://www.subtitulos.es'
     api_based = False
-    languages = lang_set([u'English (US)', u'English (UK)', u'English', u'French', u'Brazilian',
-                          u'Portuguese', u'Español (Latinoamérica)', u'Español (España)', u'Español',
-                          u'Italian', u'Català'], strict=True)
+    languages = language_set(['eng-US', 'eng-GB', 'eng', 'fre', 'por-BR', 'por', 'spa-ES', u'spa', u'ita', u'cat'])
+    language_map = {u'Español': Language('spa'), u'Español (España)': Language('spa'), u'Español (Latinoamérica)': Language('spa'),
+                    u'Català': Language('cat'), u'Brazilian': Language('por-BR'), u'English (US)': Language('eng-US'),
+                    u'English (UK)': Language('eng-GB')}
+    language_code = 'name'
     videos = [Episode]
     require_video = False
     required_features = ['permissive']
@@ -68,7 +69,7 @@ class Subtitulos(ServiceBase):
                 logger.debug(u'None of subtitle keywords %r in %r' % (sub_keywords, keywords))
                 continue
             for html_language in sub.findAllNext('ul', {'class': 'sslist'}):
-                language = guessit.Language(html_language.findNext('li', {'class': 'li-idioma'}).find('strong').contents[0].string.strip())
+                language = self.get_language(html_language.findNext('li', {'class': 'li-idioma'}).find('strong').contents[0].string.strip())
                 if language not in languages:
                     logger.debug(u'Language %r not in wanted languages %r' % (language, languages))
                     continue

libs/subliminal/services/thesubdb.py

@@ -16,10 +16,9 @@
 # You should have received a copy of the GNU Lesser General Public License
 # along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
 from . import ServiceBase
+from ..language import language_set
 from ..subtitles import get_subtitle_path, ResultSubtitle
 from ..videos import Episode, Movie, UnknownVideo
-from guessit.language import lang_set
-import guessit
 import logging
 
 
@@ -27,13 +26,13 @@ logger = logging.getLogger(__name__)
 
 
 class TheSubDB(ServiceBase):
-    server_url = 'http://api.thesubdb.com/'  # for testing purpose, use http://sandbox.thesubdb.com/ instead
-    user_agent = 'SubDB/1.0 (subliminal/0.6; https://github.com/Diaoul/subliminal)'  # defined by the API
+    server_url = 'http://api.thesubdb.com'
+    user_agent = 'SubDB/1.0 (subliminal/0.6; https://github.com/Diaoul/subliminal)'
     api_based = True
-    languages = lang_set(['af', 'cs', 'da', 'de', 'en', 'es', 'fi',
-                          'fr', 'hu', 'id', 'it', 'la', 'nl', 'no',
-                          'oc', 'pl', 'pt', 'ro', 'ru', 'sl', 'sr',
-                          'sv', 'tr'], strict=True)  # list available with the API at http://sandbox.thesubdb.com/?action=languages
+    # Source: http://api.thesubdb.com/?action=languages
+    languages = language_set(['af', 'cs', 'da', 'de', 'en', 'es', 'fi', 'fr', 'hu', 'id', 'it',
+                              'la', 'nl', 'no', 'oc', 'pl', 'pt', 'ro', 'ru', 'sl', 'sr', 'sv',
+                              'tr'])
     videos = [Movie, Episode, UnknownVideo]
     require_video = True
 
@@ -48,7 +47,7 @@ class TheSubDB(ServiceBase):
         if r.status_code != 200:
             logger.error(u'Request %s returned status code %d' % (r.url, r.status_code))
             return []
-        available_languages = set(guessit.Language(l) for l in r.content.split(','))
+        available_languages = language_set(r.content.split(','))
         languages &= available_languages
         if not languages:
             logger.debug(u'Could not find subtitles for hash %s with languages %r (only %r available)' % (moviehash, languages, available_languages))

libs/subliminal/services/tvsubtitles.py

@@ -17,12 +17,11 @@
 # along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
 from . import ServiceBase
 from ..cache import cachedmethod
+from ..language import language_set, Language
 from ..subtitles import get_subtitle_path, ResultSubtitle
+from ..utils import get_keywords
 from ..videos import Episode
 from bs4 import BeautifulSoup
-from guessit.language import lang_set
-from subliminal.utils import get_keywords
-import guessit
 import logging
 import re
 
@@ -41,12 +40,11 @@ def match(pattern, string):
 class TvSubtitles(ServiceBase):
     server_url = 'http://www.tvsubtitles.net'
     api_based = False
-    languages = lang_set([u'English', u'Español', u'French', u'German',
-                          u'Brazilian', u'Russian', u'Ukrainian', u'Italian',
-                          u'Greek', u'Arabic', u'Hungarian', u'Polish',
-                          u'Turkish', u'Dutch', u'Portuguese', u'Swedish',
-                          u'Danish', u'Finnish', u'Korean', u'Chinese',
-                          u'Japanese', u'Bulgarian', u'Czech', u'Romanian'], strict=True)
+    languages = language_set(['ar', 'bg', 'cs', 'da', 'de', 'el', 'en', 'es', 'fi', 'fr', 'hu',
+                              'it', 'ja', 'ko', 'nl', 'pl', 'pt', 'ro', 'ru', 'sv', 'tr', 'uk',
+                              'zh', 'pt-br'])
+    #TODO: Find more exceptions
+    language_map = {'gr': Language('gre'), 'cz': Language('cze'), 'ua': Language('ukr')}
     videos = [Episode]
     require_video = False
     required_features = ['permissive']
@@ -78,11 +76,9 @@ class TvSubtitles(ServiceBase):
             cells = row.find_all('td')
             if not cells:
                 continue
-
             episode_number = match('x([0-9]+)', cells[0].text)
             if not episode_number:
                 continue
-
             episode_number = int(episode_number)
             episode_id = int(match('episode-([0-9]+)', cells[1].a['href']))
             # we could just return the id of the queried episode, but as we
@@ -102,14 +98,13 @@ class TvSubtitles(ServiceBase):
             if 'href' not in subdiv.attrs or not subdiv['href'].startswith('/subtitle'):
                 continue
             subid = int(match('([0-9]+)', subdiv['href']))
-            lang = guessit.Language(match('flags/(.*).gif', subdiv.img['src']))
+            lang = self.get_language(match('flags/(.*).gif', subdiv.img['src']))
             result = {'subid': subid, 'language': lang}
             for p in subdiv.find_all('p'):
                 if 'alt' in p.attrs and p['alt'] == 'rip':
                     result['rip'] = p.text.strip()
                 if 'alt' in p.attrs and p['alt'] == 'release':
                     result['release'] = p.text.strip()
-
             subids.append(result)
         return subids