release 2014.01.22.2

[space] Add support for mobile URLs

README.md

@@ -44,6 +44,10 @@ which means you can modify it, redistribute it or use it however you like.
     --bidi-workaround          Work around terminals that lack bidirectional
                                text support. Requires bidiv or fribidi
                                executable in PATH
+    --default-search PREFIX    Use this prefix for unqualified URLs. For example
+                               "gvsearch2:" downloads two videos from google
+                               videos for  youtube-dl "large apple". By default
+                               (with value "auto") youtube-dl guesses.
 
 ## Video Selection:
     --playlist-start NUMBER    playlist video to start at (default is 1)

youtube_dl/YoutubeDL.py

@@ -152,6 +152,8 @@ class YoutubeDL(object):
                        support, using fridibi
     debug_printtraffic:Print out sent and received HTTP traffic
     include_ads:       Download ads as well
+    default_search:    Prepend this string if an input url is not valid.
+                       'auto' for elaborate guessing
 
     The following parameters are not used by YoutubeDL itself, they are used by
     the FileDownloader:

youtube_dl/__init__.py

@@ -199,7 +199,9 @@ def parseOpts(overrideArguments=None):
     general.add_option(
         '--bidi-workaround', dest='bidi_workaround', action='store_true',
         help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH')
-
+    general.add_option('--default-search',
+            dest='default_search', metavar='PREFIX',
+            help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for  youtube-dl "large apple". By default (with value "auto") youtube-dl guesses.')
 
     selection.add_option(
         '--playlist-start',
@@ -619,6 +621,8 @@ def _real_main(argv=None):
         date = DateRange.day(opts.date)
     else:
         date = DateRange(opts.dateafter, opts.datebefore)
+    if opts.default_search not in ('auto', None) and ':' not in opts.default_search:
+        parser.error(u'--default-search invalid; did you forget a colon (:) at the end?')
 
     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
     # this was the old behaviour if only --all-sub was given.
@@ -720,6 +724,7 @@ def _real_main(argv=None):
         'debug_printtraffic': opts.debug_printtraffic,
         'prefer_ffmpeg': opts.prefer_ffmpeg,
         'include_ads': opts.include_ads,
+        'default_search': opts.default_search,
     }
 
     with YoutubeDL(ydl_opts) as ydl:

youtube_dl/extractor/comedycentral.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -15,30 +17,22 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:www.)?comedycentral.com/
         (video-clips|episodes|cc-studios|video-collections)
         /(?P<title>.*)'''
-    _FEED_URL = u'http://comedycentral.com/feeds/mrss/'
+    _FEED_URL = '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.',
+        'url': 'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
+        'md5': '4167875aae411f903b751a21f357f1ee',
+        'info_dict': {
+            'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
+            'ext': 'mp4',
+            'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
+            'description': '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'
+    IE_DESC = '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
@@ -55,14 +49,14 @@ class ComedyCentralShowsIE(InfoExtractor):
                               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"
+        'url': 'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
+        'file': '422212.mp4',
+        'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
+        'info_dict': {
+            "upload_date": "20121214",
+            "description": "Kristen Stewart",
+            "uploader": "thedailyshow",
+            "title": "thedailyshow-kristen-stewart part 1"
         }
     }
 
@@ -94,20 +88,20 @@ class ComedyCentralShowsIE(InfoExtractor):
     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')
+            raise ExtractorError('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)
         if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
+            raise ExtractorError('Invalid URL: %s' % url)
 
         if mobj.group('shortname'):
             if mobj.group('shortname') in ('tds', 'thedailyshow'):
-                url = u'http://www.thedailyshow.com/full-episodes/'
+                url = 'http://www.thedailyshow.com/full-episodes/'
             else:
-                url = u'http://www.colbertnation.com/full-episodes/'
+                url = 'http://www.colbertnation.com/full-episodes/'
             mobj = re.match(self._VALID_URL, url, re.VERBOSE)
             assert mobj is not None
 
@@ -133,9 +127,9 @@ class ComedyCentralShowsIE(InfoExtractor):
             url = htmlHandle.geturl()
             mobj = re.match(self._VALID_URL, url, re.VERBOSE)
             if mobj is None:
-                raise ExtractorError(u'Invalid redirected URL: ' + url)
+                raise ExtractorError('Invalid redirected URL: ' + url)
             if mobj.group('episode') == '':
-                raise ExtractorError(u'Redirected URL is still not specific: ' + url)
+                raise ExtractorError('Redirected URL is still not specific: ' + url)
             epTitle = mobj.group('episode')
 
         mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
@@ -147,15 +141,15 @@ class ComedyCentralShowsIE(InfoExtractor):
 
             altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
             if len(altMovieParams) == 0:
-                raise ExtractorError(u'unable to find Flash URL in webpage ' + url)
+                raise ExtractorError('unable to find Flash URL in webpage ' + url)
             else:
                 mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
 
         uri = mMovieParams[0][1]
         indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
         idoc = self._download_xml(indexUrl, epTitle,
-                                          u'Downloading show index',
-                                          u'unable to download episode index')
+                                          'Downloading show index',
+                                          'unable to download episode index')
 
         results = []
 
@@ -170,7 +164,7 @@ class ComedyCentralShowsIE(InfoExtractor):
             configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
                         compat_urllib_parse.urlencode({'uri': mediaId}))
             cdoc = self._download_xml(configUrl, epTitle,
-                                               u'Downloading configuration for %s' % shortMediaId)
+                                               'Downloading configuration for %s' % shortMediaId)
 
             turls = []
             for rendition in cdoc.findall('.//rendition'):
@@ -178,7 +172,7 @@ class ComedyCentralShowsIE(InfoExtractor):
                 turls.append(finfo)
 
             if len(turls) == 0:
-                self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found')
+                self._downloader.report_error('unable to download ' + mediaId + ': No videos found')
                 continue
 
             formats = []
@@ -192,7 +186,7 @@ class ComedyCentralShowsIE(InfoExtractor):
                     'width': w,
                 })
 
-            effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
+            effTitle = showId + '-' + epTitle + ' part ' + compat_str(partNum+1)
             results.append({
                 'id': shortMediaId,
                 'formats': formats,

youtube_dl/extractor/cspan.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class CSpanIE(InfoExtractor):
-    _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)'
+    _VALID_URL = r'http://(?:www\.)?c-spanvideo\.org/program/(?P<name>.*)'
     IE_DESC = 'C-SPAN'
     _TEST = {
         'url': 'http://www.c-spanvideo.org/program/HolderonV',
@@ -24,9 +24,9 @@ class CSpanIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        prog_name = mobj.group(1)
+        prog_name = mobj.group('name')
         webpage = self._download_webpage(url, prog_name)
-        video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
+        video_id = self._search_regex(r'prog(?:ram)?id=(.*?)&', webpage, 'video id')
 
         title = self._html_search_regex(
             r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title')

youtube_dl/extractor/d8.py

@@ -1,22 +1,25 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 from .canalplus import CanalplusIE
 
 
 class D8IE(CanalplusIE):
     _VALID_URL = r'https?://www\.d8\.tv/.*?/(?P<path>.*)'
     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/d8/%s'
-    IE_NAME = u'd8.tv'
+    IE_NAME = 'd8.tv'
 
     _TEST = {
-        u'url': u'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
-        u'file': u'966289.flv',
-        u'info_dict': {
-            u'title': u'Campagne intime - Documentaire exceptionnel',
-            u'description': u'md5:d2643b799fb190846ae09c61e59a859f',
-            u'upload_date': u'20131108',
+        'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
+        'file': '966289.flv',
+        'info_dict': {
+            'title': 'Campagne intime - Documentaire exceptionnel',
+            'description': 'md5:d2643b799fb190846ae09c61e59a859f',
+            'upload_date': '20131108',
         },
-        u'params': {
+        'params': {
             # rtmp
-            u'skip_download': True,
+            'skip_download': True,
         },
+        'skip': 'videos get deleted after a while',
     }

youtube_dl/extractor/gametrailers.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .mtv import MTVServicesInfoExtractor
 
 
@@ -18,12 +16,3 @@ class GametrailersIE(MTVServicesInfoExtractor):
     }
 
     _FEED_URL = 'http://www.gametrailers.com/feeds/mrss'
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
-        mgid = self._search_regex([r'data-video="(?P<mgid>mgid:.*?)"',
-                                   r'data-contentId=\'(?P<mgid>mgid:.*?)\''],
-                                  webpage, 'mgid')
-        return self._get_videos_info(mgid)

youtube_dl/extractor/generic.py

@@ -162,8 +162,19 @@ class GenericIE(InfoExtractor):
     def _real_extract(self, url):
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:
-            self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
-            return self.url_result('http://' + url)
+            default_search = self._downloader.params.get('default_search')
+            if default_search is None:
+                default_search = 'auto'
+
+            if default_search == 'auto':
+                if '/' in url:
+                    self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
+                    return self.url_result('http://' + url)
+                else:
+                    return self.url_result('ytsearch:' + url)
+            else:
+                assert ':' in default_search
+                return self.url_result(default_search + url)
         video_id = os.path.splitext(url.split('/')[-1])[0]
 
         self.to_screen('%s: Requesting header' % video_id)

youtube_dl/extractor/imdb.py

@@ -67,23 +67,16 @@ class ImdbListIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         list_id = mobj.group('id')
-        
-        # RSS XML is sometimes malformed
-        rss = self._download_webpage('http://rss.imdb.com/list/%s' % list_id, list_id, 'Downloading list RSS')
-        list_title = self._html_search_regex(r'<title>(.*?)</title>', rss, 'list title')
-        
-        # Export is independent of actual author_id, but returns 404 if no author_id is provided.
-        # However, passing dummy author_id seems to be enough.
-        csv = self._download_webpage('http://www.imdb.com/list/export?list_id=%s&author_id=ur00000000' % list_id,
-                                     list_id, 'Downloading list CSV')
-        
-        entries = []
-        for item in csv.split('\n')[1:]:
-            cols = item.split(',')
-            if len(cols) < 2:
-                continue
-            item_id = cols[1][1:-1]
-            if item_id.startswith('vi'):
-                entries.append(self.url_result('http://www.imdb.com/video/imdb/%s' % item_id, 'Imdb'))
-        
+
+        webpage = self._download_webpage(url, list_id)
+        list_code = self._search_regex(
+            r'(?s)<div\s+class="list\sdetail">(.*?)class="see-more"',
+            webpage, 'list code')
+        entries = [
+            self.url_result('http://www.imdb.com' + m, 'Imdb')
+            for m in re.findall(r'href="(/video/imdb/vi[^"]+)"', webpage)]
+
+        list_title = self._html_search_regex(
+            r'<h1 class="header">(.*?)</h1>', webpage, 'list title')
+
         return self.playlist_result(entries, list_id, list_title)

youtube_dl/extractor/mtv.py

@@ -89,6 +89,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
         title = title_el.text
         if title is None:
             raise ExtractorError('Could not find video title')
+        title = title.strip()
 
         return {
             'title': title,
@@ -111,9 +112,12 @@ class MTVServicesInfoExtractor(InfoExtractor):
         title = url_basename(url)
         webpage = self._download_webpage(url, title)
         try:
-            # the url is in the format http://media.mtvnservices.com/fb/{mgid}.swf
-            fb_url = self._og_search_video_url(webpage)
-            mgid = url_basename(fb_url).rpartition('.')[0]
+            # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
+            # or http://media.mtvnservices.com/{mgid}
+            og_url = self._og_search_video_url(webpage)
+            mgid = url_basename(og_url)
+            if mgid.endswith('.swf'):
+                mgid = mgid[:-4]
         except RegexNotFoundError:
             mgid = self._search_regex(r'data-mgid="(.*?)"', webpage, u'mgid')
         return self._get_videos_info(mgid)

youtube_dl/extractor/novamov.py

@@ -19,7 +19,8 @@ class NovamovIE(InfoExtractor):
         'info_dict': {
             'title': 'search engine optimization',
             'description': 'search engine optimization is used to rank the web page in the google search engine'
-        }
+        },
+        'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/southparkstudios.py

@@ -18,14 +18,6 @@ class SouthParkStudiosIE(MTVServicesInfoExtractor):
         },
     }]
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        url = u'http://www.' + mobj.group(u'url')
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
-        mgid = self._search_regex(r'swfobject.embedSWF\(".*?(mgid:.*?)"',
-                                  webpage, u'mgid')
-        return self._get_videos_info(mgid)
 
 class SouthparkDeIE(SouthParkStudiosIE):
     IE_NAME = u'southpark.de'

youtube_dl/extractor/space.py

@@ -6,7 +6,7 @@ from ..utils import RegexNotFoundError, ExtractorError
 
 
 class SpaceIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html'
     _TEST = {
         u'add_ie': ['Brightcove'],
         u'url': u'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html',

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.01.22.1'
+__version__ = '2014.01.22.2'