]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/comedycentral.py
Merge tag 'upstream/2013.12.23'
[youtubedl] / youtube_dl / extractor / comedycentral.py
index 1bb359046b958b5554371ca4aa602696efe8fe8f..a54ce3ee7c44727a9e56b1ab8359bd099b48bb35 100644 (file)
@@ -1,7 +1,7 @@
 import re
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 
 from .common import InfoExtractor
+from .mtv import MTVServicesInfoExtractor
 from ..utils import (
     compat_str,
     compat_urllib_parse,
 from ..utils import (
     compat_str,
     compat_urllib_parse,
@@ -11,9 +11,32 @@ from ..utils import (
 )
 
 
 )
 
 
-class ComedyCentralIE(InfoExtractor):
-    """Information extractor for The Daily Show and Colbert Report """
+class ComedyCentralIE(MTVServicesInfoExtractor):
+    _VALID_URL = r'https?://(?:www.)?comedycentral.com/(video-clips|episodes|cc-studios)/(?P<title>.*)'
+    _FEED_URL = u'http://comedycentral.com/feeds/mrss/'
 
 
+    _TEST = {
+        u'url': u'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
+        u'md5': u'4167875aae411f903b751a21f357f1ee',
+        u'info_dict': {
+            u'id': u'cef0cbb3-e776-4bc9-b62e-8016deccb354',
+            u'ext': u'mp4',
+            u'title': u'Uncensored - Greg Fitzsimmons - Too Good of a Mother',
+            u'description': u'After a certain point, breastfeeding becomes c**kblocking.',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        title = mobj.group('title')
+        webpage = self._download_webpage(url, title)
+        mgid = self._search_regex(r'data-mgid="(?P<mgid>mgid:.*?)"',
+                                  webpage, u'mgid')
+        return self._get_videos_info(mgid)
+
+
+class ComedyCentralShowsIE(InfoExtractor):
+    IE_DESC = u'The Daily Show / Colbert Report'
     # urls can be abbreviations like :thedailyshow or :colbert
     # urls for episodes like:
     # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
     # urls can be abbreviations like :thedailyshow or :colbert
     # urls for episodes like:
     # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
@@ -25,8 +48,21 @@ class ComedyCentralIE(InfoExtractor):
                          (full-episodes/(?P<episode>.*)|
                           (?P<clip>
                               (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
                          (full-episodes/(?P<episode>.*)|
                           (?P<clip>
                               (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
-                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))))
+                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))|
+                          (?P<interview>
+                              extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?)))
                      $"""
                      $"""
+    _TEST = {
+        u'url': u'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
+        u'file': u'422212.mp4',
+        u'md5': u'4e2f5cb088a83cd8cdb7756132f9739d',
+        u'info_dict': {
+            u"upload_date": u"20121214", 
+            u"description": u"Kristen Stewart", 
+            u"uploader": u"thedailyshow", 
+            u"title": u"thedailyshow-kristen-stewart part 1"
+        }
+    }
 
     _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
 
 
     _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
 
@@ -39,12 +75,12 @@ class ComedyCentralIE(InfoExtractor):
         '400': 'mp4',
     }
     _video_dimensions = {
         '400': 'mp4',
     }
     _video_dimensions = {
-        '3500': '1280x720',
-        '2200': '960x540',
-        '1700': '768x432',
-        '1200': '640x360',
-        '750': '512x288',
-        '400': '384x216',
+        '3500': (1280, 720),
+        '2200': (960, 540),
+        '1700': (768, 432),
+        '1200': (640, 360),
+        '750': (512, 288),
+        '400': (384, 216),
     }
 
     @classmethod
     }
 
     @classmethod
@@ -52,11 +88,13 @@ class ComedyCentralIE(InfoExtractor):
         """Receives a URL and returns True if suitable for this IE."""
         return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
 
         """Receives a URL and returns True if suitable for this IE."""
         return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
 
-    def _print_formats(self, formats):
-        print('Available formats:')
-        for x in formats:
-            print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???')))
-
+    @staticmethod
+    def _transform_rtmp_url(rtmp_video_url):
+        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
+        if not m:
+            raise ExtractorError(u'Cannot transform RTMP url')
+        base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
+        return base + m.group('finalid')
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url, re.VERBOSE)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url, re.VERBOSE)
@@ -77,6 +115,9 @@ class ComedyCentralIE(InfoExtractor):
             else:
                 epTitle = mobj.group('cntitle')
             dlNewest = False
             else:
                 epTitle = mobj.group('cntitle')
             dlNewest = False
+        elif mobj.group('interview'):
+            epTitle = mobj.group('interview_title')
+            dlNewest = False
         else:
             dlNewest = not mobj.group('episode')
             if dlNewest:
         else:
             dlNewest = not mobj.group('episode')
             if dlNewest:
@@ -110,13 +151,12 @@ class ComedyCentralIE(InfoExtractor):
 
         uri = mMovieParams[0][1]
         indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
 
         uri = mMovieParams[0][1]
         indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
-        indexXml = self._download_webpage(indexUrl, epTitle,
+        idoc = self._download_xml(indexUrl, epTitle,
                                           u'Downloading show index',
                                           u'unable to download episode index')
 
         results = []
 
                                           u'Downloading show index',
                                           u'unable to download episode index')
 
         results = []
 
-        idoc = xml.etree.ElementTree.fromstring(indexXml)
         itemEls = idoc.findall('.//item')
         for partNum,itemEl in enumerate(itemEls):
             mediaId = itemEl.findall('./guid')[0].text
         itemEls = idoc.findall('.//item')
         for partNum,itemEl in enumerate(itemEls):
             mediaId = itemEl.findall('./guid')[0].text
@@ -127,10 +167,9 @@ class ComedyCentralIE(InfoExtractor):
 
             configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
                         compat_urllib_parse.urlencode({'uri': mediaId}))
 
             configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
                         compat_urllib_parse.urlencode({'uri': mediaId}))
-            configXml = self._download_webpage(configUrl, epTitle,
+            cdoc = self._download_xml(configUrl, epTitle,
                                                u'Downloading configuration for %s' % shortMediaId)
 
                                                u'Downloading configuration for %s' % shortMediaId)
 
-            cdoc = xml.etree.ElementTree.fromstring(configXml)
             turls = []
             for rendition in cdoc.findall('.//rendition'):
                 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
             turls = []
             for rendition in cdoc.findall('.//rendition'):
                 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
@@ -140,40 +179,26 @@ class ComedyCentralIE(InfoExtractor):
                 self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found')
                 continue
 
                 self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found')
                 continue
 
-            if self._downloader.params.get('listformats', None):
-                self._print_formats([i[0] for i in turls])
-                return
-
-            # For now, just pick the highest bitrate
-            format,rtmp_video_url = turls[-1]
-
-            # Get the format arg from the arg stream
-            req_format = self._downloader.params.get('format', None)
-
-            # Select format if we can find one
-            for f,v in turls:
-                if f == req_format:
-                    format, rtmp_video_url = f, v
-                    break
-
-            m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
-            if not m:
-                raise ExtractorError(u'Cannot transform RTMP url')
-            base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
-            video_url = base + m.group('finalid')
+            formats = []
+            for format, rtmp_video_url in turls:
+                w, h = self._video_dimensions.get(format, (None, None))
+                formats.append({
+                    'url': self._transform_rtmp_url(rtmp_video_url),
+                    'ext': self._video_extensions.get(format, 'mp4'),
+                    'format_id': format,
+                    'height': h,
+                    'width': w,
+                })
 
             effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
 
             effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
-            info = {
+            results.append({
                 'id': shortMediaId,
                 'id': shortMediaId,
-                'url': video_url,
+                'formats': formats,
                 'uploader': showId,
                 'upload_date': officialDate,
                 'title': effTitle,
                 'uploader': showId,
                 'upload_date': officialDate,
                 'title': effTitle,
-                'ext': 'mp4',
-                'format': format,
                 'thumbnail': None,
                 'thumbnail': None,
-                'description': officialTitle,
-            }
-            results.append(info)
+                'description': compat_str(officialTitle),
+            })
 
         return results
 
         return results