Subliminal update

libs/subliminal/infos.py

@@ -15,4 +15,4 @@
 #
 # You should have received a copy of the GNU Lesser General Public License
 # along with subliminal.  If not, see <http://www.gnu.org/licenses/>.
-__version__ = '0.6.1'
+__version__ = '0.6.2'

libs/subliminal/services/addic7ed.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # Copyright 2012 Olivier Leveau <olifozzy@gmail.com>
+# Copyright 2012 Antoine Bertin <diaoulael@gmail.com>
 #
 # This file is part of subliminal.
 #
@@ -20,7 +21,7 @@ from ..cache import cachedmethod
 from ..exceptions import DownloadFailedError
 from ..language import Language, language_set
 from ..subtitles import get_subtitle_path, ResultSubtitle
-from ..utils import get_keywords
+from ..utils import get_keywords, split_keyword
 from ..videos import Episode
 from bs4 import BeautifulSoup
 import logging
@@ -31,97 +32,32 @@ import re
 logger = logging.getLogger(__name__)
 
 
-def match(pattern, string):
-    try:
-        return re.search(pattern, string).group(1)
-    except AttributeError:
-        logger.debug(u'Could not match %r on %r' % (pattern, string))
-        return None
-
-
-def matches(pattern, string):
-    try:
-        return re.search(pattern, string).group(1, 2)
-    except AttributeError:
-        logger.debug(u'Could not match %r on %r' % (pattern, string))
-        return None
-
-
 class Addic7ed(ServiceBase):
     server_url = 'http://www.addic7ed.com'
     api_based = False
     #TODO: Complete this
-    languages = language_set(['ar', 'ca', 'de', 'el', 'en', 'es', 'eu', 'fr', 'ga', 'he', 'hr', 'hu', 'it',
-                              'pl', 'pt', 'ro', 'ru', 'se', 'pt-br'])
+    languages = language_set(['ar', 'ca', 'de', 'el', 'en', 'es', 'eu', 'fr', 'ga', 'gl', 'he', 'hr', 'hu',
+                              'it', 'pl', 'pt', 'ro', 'ru', 'se', 'pt-br'])
     language_map = {'Portuguese (Brazilian)': Language('por-BR'), 'Greek': Language('gre'),
-                    'Spanish (Latin America)': Language('spa'), }
+                    'Spanish (Latin America)': Language('spa'), 'Galego': Language('glg'),
+                    u'Català': Language('cat')}
     videos = [Episode]
     require_video = False
     required_features = ['permissive']
 
     @cachedmethod
-    def get_likely_series_id(self, name):
+    def get_series_id(self, name):
+        """Get the show page and cache every show found in it"""
         r = self.session.get('%s/shows.php' % self.server_url)
         soup = BeautifulSoup(r.content, self.required_features)
-        for elem in soup.find_all('h3'):
-            show_name = elem.a.text.lower()
-            show_id = int(match('show/([0-9]+)', elem.a['href']))
-            # we could just return the id of the queried show, but as we
-            # already downloaded the whole page we might as well fill in the
-            # information for all the shows
-            self.cache_for(self.get_likely_series_id, args=(show_name,), result=show_id)
-        return self.cached_value(self.get_likely_series_id, args=(name,))
-
-    @cachedmethod
-    def get_episode_url(self, series_id, season, number):
-        """Get the Addic7ed id for the given episode. Raises KeyError if none
-        could be found
-
-        """
-        # download the page of the show, contains ids for all episodes all seasons
-        r = self.session.get('%s/show/%d' % (self.server_url, series_id))
-        soup = BeautifulSoup(r.content, self.required_features)
-        form = soup.find('form', attrs={'name': 'multidl'})
-        for table in form.find_all('table'):
-            for row in table.find_all('tr'):
-                cell = row.find('td', 'MultiDldS')
-                if not cell:
-                    continue
-                m = matches('/serie/.+/([0-9]+)/([0-9]+)/', cell.a['href'])
-                if not m:
-                    continue
-                episode_url = cell.a['href']
-                season_number = int(m[0])
-                episode_number = int(m[1])
-                # we could just return the url of the queried episode, but as we
-                # already downloaded the whole page we might as well fill in the
-                # information for all the episodes of the show
-                self.cache_for(self.get_episode_url, args=(series_id, season_number, episode_number), result=episode_url)
-        # raises KeyError if not found
-        return self.cached_value(self.get_episode_url, args=(series_id, season, number))
-
-    # Do not cache this method in order to always check for the most recent
-    # subtitles
-    def get_sub_urls(self, episode_url):
-        suburls = []
-        r = self.session.get('%s/%s' % (self.server_url, episode_url))
-        epsoup = BeautifulSoup(r.content, self.required_features)
-        for releaseTable in epsoup.find_all('table', 'tabel95'):
-            releaseRow = releaseTable.find('td', 'NewsTitle')
-            if not releaseRow:
+        for html_series in soup.select('h3 > a'):
+            series_name = html_series.text.lower()
+            match = re.search('show/([0-9]+)', html_series['href'])
+            if match is None:
                 continue
-            release = releaseRow.text.strip()
-            for row in releaseTable.find_all('tr'):
-                link = row.find('a', 'buttonDownload')
-                if not link:
-                    continue
-                if 'href' not in link.attrs or not (link['href'].startswith('/original') or link['href'].startswith('/updated')):
-                    continue
-                suburl = link['href']
-                lang = self.get_language(row.find('td', 'language').text.strip())
-                result = {'suburl': suburl, 'language': lang, 'release': release}
-                suburls.append(result)
-        return suburls
+            series_id = int(match.group(1))
+            self.cache_for(self.get_series_id, args=(series_name,), result=series_id)
+        return self.cached_value(self.get_series_id, args=(name,))
 
     def list_checked(self, video, languages):
         return self.query(video.path or video.release, languages, get_keywords(video.guess), video.series, video.season, video.episode)
@@ -130,25 +66,36 @@ class Addic7ed(ServiceBase):
         logger.debug(u'Getting subtitles for %s season %d episode %d with languages %r' % (series, season, episode, languages))
         self.init_cache()
         try:
-            sid = self.get_likely_series_id(series.lower())
+            series_id = self.get_series_id(series.lower())
         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
+        r = self.session.get('%s/show/%d&season=%d' % (self.server_url, series_id, season))
+        soup = BeautifulSoup(r.content, self.required_features)
         subtitles = []
-        for suburl in suburls:
-            language = suburl['language']
-            if language not in languages:
+        for row in soup('tr', {'class': 'epeven completed'}):
+            cells = row('td')
+            if int(cells[0].text.strip()) != season or int(cells[1].text.strip()) != episode:
                 continue
-            path = get_subtitle_path(filepath, language, self.config.multi)
-            subtitle = ResultSubtitle(path, language, self.__class__.__name__.lower(), '%s/%s' % (self.server_url, suburl['suburl']),
-                                      keywords=[suburl['release']])
+            if cells[6].text.strip():
+                logger.debug(u'Skipping hearing impaired')
+                continue
+            sub_status = cells[5].text.strip()
+            if sub_status != 'Completed':
+                logger.debug(u'Wrong subtitle status %s' % sub_status)
+                continue
+            sub_language = self.get_language(cells[3].text.strip())
+            if sub_language not in languages:
+                logger.debug(u'Language %r not in wanted languages %r' % (sub_language, languages))
+                continue
+            sub_keywords = split_keyword(cells[4].text.strip().lower())
+            #TODO: Maybe allow empty keywords here? (same in Subtitulos)
+            if not keywords & sub_keywords:
+                logger.debug(u'None of subtitle keywords %r in %r' % (sub_keywords, keywords))
+                continue
+            sub_link = '%s/%s' % (self.server_url, cells[9].a['href'])
+            sub_path = get_subtitle_path(filepath, sub_language, self.config.multi)
+            subtitle = ResultSubtitle(sub_path, sub_language, self.__class__.__name__.lower(), sub_link, keywords=sub_keywords)
             subtitles.append(subtitle)
         return subtitles
 

libs/subliminal/services/bierdopje.py

@@ -36,6 +36,7 @@ logger = logging.getLogger(__name__)
 
 class BierDopje(ServiceBase):
     server_url = 'http://api.bierdopje.com/A2B638AC5D804C2E/'
+    user_agent = 'Subliminal/0.6'
     api_based = True
     languages = language_set(['eng', 'dut'])
     videos = [Episode]

libs/subliminal/services/subswiki.py

@@ -19,11 +19,10 @@ from . import ServiceBase
 from ..exceptions import ServiceError
 from ..language import language_set, Language
 from ..subtitles import get_subtitle_path, ResultSubtitle
+from ..utils import get_keywords, split_keyword
 from ..videos import Episode, Movie
 from bs4 import BeautifulSoup
-from subliminal.utils import get_keywords, split_keyword
 import logging
-import re
 import urllib
 
 
@@ -40,7 +39,6 @@ class SubsWiki(ServiceBase):
     language_code = 'name'
     videos = [Episode, Movie]
     require_video = False
-    release_pattern = re.compile('\nVersion (.+), ([0-9]+).([0-9])+ MBs')
     required_features = ['permissive']
 
     def list_checked(self, video, languages):
@@ -78,22 +76,22 @@ class SubsWiki(ServiceBase):
         soup = BeautifulSoup(r.content, self.required_features)
         subtitles = []
         for sub in soup('td', {'class': 'NewsTitle'}):
-            sub_keywords = split_keyword(self.release_pattern.search(sub.contents[1]).group(1).lower())
+            sub_keywords = split_keyword(sub.b.string.lower())
             if not keywords & sub_keywords:
                 logger.debug(u'None of subtitle keywords %r in %r' % (sub_keywords, keywords))
                 continue
-            for html_language in sub.parent.parent.findAll('td', {'class': 'language'}):
+            for html_language in sub.parent.parent.find_all('td', {'class': 'language'}):
                 language = self.get_language(html_language.string.strip())
                 if language not in languages:
                     logger.debug(u'Language %r not in wanted languages %r' % (language, languages))
                     continue
-                html_status = html_language.findNextSibling('td')
-                status = html_status.find('strong').string.strip()
-                if status != 'Completed':
+                html_status = html_language.find_next_sibling('td')
+                status = html_status.strong.string.strip()
+                if status != 'Completado':
                     logger.debug(u'Wrong subtitle status %s' % status)
                     continue
                 path = get_subtitle_path(filepath, language, self.config.multi)
-                subtitle = ResultSubtitle(path, language, self.__class__.__name__.lower(), '%s%s' % (self.server_url, html_status.findNext('td').find('a')['href']))
+                subtitle = ResultSubtitle(path, language, self.__class__.__name__.lower(), '%s%s' % (self.server_url, html_status.find_next('td').find('a')['href']))
                 subtitles.append(subtitle)
         return subtitles
 

libs/subliminal/services/subtitulos.py

@@ -18,9 +18,9 @@
 from . import ServiceBase
 from ..language import language_set, Language
 from ..subtitles import get_subtitle_path, ResultSubtitle
+from ..utils import get_keywords, split_keyword
 from ..videos import Episode
 from bs4 import BeautifulSoup
-from subliminal.utils import get_keywords, split_keyword
 import logging
 import re
 import unicodedata

libs/subliminal/subtitles.py

@@ -23,7 +23,7 @@ import os.path
 __all__ = ['Subtitle', 'EmbeddedSubtitle', 'ExternalSubtitle', 'ResultSubtitle', 'get_subtitle_path']
 
 #: Subtitles extensions
-EXTENSIONS = ['.srt', '.sub', '.txt']
+EXTENSIONS = ['.srt', '.sub', '.txt', '.ass']
 
 
 class Subtitle(object):

libs/subliminal/videos.py

@@ -18,7 +18,7 @@
 from . import subtitles
 from .language import Language
 from .utils import to_unicode
-import enzyme
+import enzyme.core
 import guessit
 import hashlib
 import logging
@@ -135,6 +135,8 @@ class Video(object):
         # brackets inside the filename, so we have to use basic string
         # startswith/endswith comparisons
         folder, basename = os.path.split(basepath)
+        if folder == '':
+            folder = '.'
         existing = [f for f in os.listdir(folder) if f.startswith(basename)]
         for path in existing:
             for ext in subtitles.EXTENSIONS: