Merge branch 'master' of https://github.com/rg3/youtube-dl

youtube_dl/extractor/bbc.py

@@ -1012,10 +1012,10 @@ class BBCCoUkPlaylistBaseIE(InfoExtractor):
 
 class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
     IE_NAME = 'bbc.co.uk:iplayer:playlist'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/episodes/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/(?:episodes|group)/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
     _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s'
     _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v',
         'info_dict': {
             'id': 'b05rcz9v',
@@ -1023,7 +1023,17 @@ class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
             'description': 'French thriller serial about a missing teenager.',
         },
         'playlist_mincount': 6,
-    }
+        'skip': 'This programme is not currently available on BBC iPlayer',
+    }, {
+        # Available for over a year unlike 30 days for most other programmes
+        'url': 'http://www.bbc.co.uk/iplayer/group/p02tcc32',
+        'info_dict': {
+            'id': 'p02tcc32',
+            'title': 'Bohemian Icons',
+            'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7',
+        },
+        'playlist_mincount': 10,
+    }]
 
     def _extract_title_and_description(self, webpage):
         title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)

youtube_dl/extractor/extractors.py

@@ -587,6 +587,7 @@ from .nytimes import (
     NYTimesArticleIE,
 )
 from .nuvid import NuvidIE
+from .odatv import OdaTVIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
 from .onet import (

youtube_dl/extractor/odatv.py

@@ -0,0 +1,50 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    NO_DEFAULT,
+    remove_start
+)
+
+
+class OdaTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?odatv\.com/(?:mob|vid)_video\.php\?.*\bid=(?P<id>[^&]+)'
+    _TESTS = [{
+        'url': 'http://odatv.com/vid_video.php?id=8E388',
+        'md5': 'dc61d052f205c9bf2da3545691485154',
+        'info_dict': {
+            'id': '8E388',
+            'ext': 'mp4',
+            'title': 'Artık Davutoğlu ile devam edemeyiz'
+        }
+    }, {
+        # mobile URL
+        'url': 'http://odatv.com/mob_video.php?id=8E388',
+        'only_matching': True,
+    }, {
+        # no video
+        'url': 'http://odatv.com/mob_video.php?id=8E900',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        no_video = 'NO VIDEO!' in webpage
+
+        video_url = self._search_regex(
+            r'mp4\s*:\s*(["\'])(?P<url>http.+?)\1', webpage, 'video url',
+            default=None if no_video else NO_DEFAULT, group='url')
+
+        if no_video:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': remove_start(self._og_search_title(webpage), 'Video: '),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/youjizz.py

@@ -9,8 +9,8 @@ from ..utils import (
 
 
 class YouJizzIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/[^/#?]+-(?P<id>[0-9]+)\.html(?:$|[?#])'
-    _TEST = {
+    _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/(?:[^/#?]+)?-(?P<id>[0-9]+)\.html(?:$|[?#])'
+    _TESTS = [{
         'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
         'md5': '07e15fa469ba384c7693fd246905547c',
         'info_dict': {
@@ -19,7 +19,10 @@ class YouJizzIE(InfoExtractor):
             'title': 'Zeichentrick 1',
             'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://www.youjizz.com/videos/-2189178.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/youtube.py

@@ -1736,7 +1736,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
 
 class YoutubeSharedVideoIE(InfoExtractor):
-    _VALID_URL = r'(?:https?:)?//(?:www\.)?youtube\.com/shared\?ci=(?P<id>[0-9A-Za-z_-]{11})'
+    _VALID_URL = r'(?:https?:)?//(?:www\.)?youtube\.com/shared\?.*\bci=(?P<id>[0-9A-Za-z_-]{11})'
     IE_NAME = 'youtube:shared'
 
     _TEST = {