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

youtube_dl/extractor/bellmedia.py

@@ -24,7 +24,7 @@ class BellMediaIE(InfoExtractor):
                 space
             )\.ca|
             much\.com
-        )/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6})'''
+        )/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
     _TESTS = [{
         'url': 'http://www.ctv.ca/video/player?vid=706966',
         'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0',
@@ -55,6 +55,9 @@ class BellMediaIE(InfoExtractor):
     }, {
         'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6',
         'only_matching': True,
+    }, {
+        'url': 'http://www.ctv.ca/DCs-Legends-of-Tomorrow/Video/S2E11-Turncoat-vid1051430',
+        'only_matching': True,
     }]
     _DOMAINS = {
         'thecomedynetwork': 'comedy',

youtube_dl/extractor/disney.py

@@ -9,13 +9,15 @@ from ..utils import (
     unified_strdate,
     compat_str,
     determine_ext,
+    ExtractorError,
 )
 
 
 class DisneyIE(InfoExtractor):
     _VALID_URL = r'''(?x)
-        https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|starwars\.com))/(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})'''
+        https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|(?:starwars|marvelkids)\.com))/(?:(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})|(?:[^/]+/)?(?P<display_id>[^/?#]+))'''
     _TESTS = [{
+        # Disney.EmbedVideo
         'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
         'info_dict': {
             'id': '545ed1857afee5a0ec239977',
@@ -28,6 +30,20 @@ class DisneyIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         }
+    }, {
+        # Grill.burger
+        'url': 'http://www.starwars.com/video/rogue-one-a-star-wars-story-intro-featurette',
+        'info_dict': {
+            'id': '5454e9f4e9804a552e3524c8',
+            'ext': 'mp4',
+            'title': '"Intro" Featurette: Rogue One: A Star Wars Story',
+            'upload_date': '20170104',
+            'description': 'Go behind-the-scenes of Rogue One: A Star Wars Story in this featurette with Director Gareth Edwards and the cast of the film.',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
     }, {
         'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
         'only_matching': True,
@@ -43,31 +59,55 @@ class DisneyIE(InfoExtractor):
     }, {
         'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
         'only_matching': True,
+    }, {
+        'url': 'http://spiderman.marvelkids.com/embed/522900d2ced3c565e4cc0677',
+        'only_matching': True,
+    }, {
+        'url': 'http://spiderman.marvelkids.com/videos/contest-of-champions-part-four-clip-1',
+        'only_matching': True,
+    }, {
+        'url': 'http://disneyjunior.en.disneyme.com/dj/watch-my-friends-tigger-and-pooh-promo',
+        'only_matching': True,
+    }, {
+        'url': 'http://disneyjunior.disney.com/galactech-the-galactech-grab-galactech-an-admiral-rescue',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        domain, video_id = re.match(self._VALID_URL, url).groups()
+        domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
+        if not video_id:
+            webpage = self._download_webpage(url, display_id)
+            grill = re.sub(r'"\s*\+\s*"', '', self._search_regex(
+                r'Grill\.burger\s*=\s*({.+})\s*:',
+                webpage, 'grill data'))
+            page_data = next(s for s in self._parse_json(grill, display_id)['stack'] if s.get('type') == 'video')
+            video_data = page_data['data'][0]
+        else:
             webpage = self._download_webpage(
                 'http://%s/embed/%s' % (domain, video_id), video_id)
-        video_data = self._parse_json(self._search_regex(
-            r'Disney\.EmbedVideo=({.+});', webpage, 'embed data'), video_id)['video']
+            page_data = self._parse_json(self._search_regex(
+                r'Disney\.EmbedVideo\s*=\s*({.+});',
+                webpage, 'embed data'), video_id)
+            video_data = page_data['video']
 
         for external in video_data.get('externals', []):
             if external.get('source') == 'vevo':
                 return self.url_result('vevo:' + external['data_id'], 'Vevo')
 
+        video_id = video_data['id']
         title = video_data['title']
 
         formats = []
         for flavor in video_data.get('flavors', []):
             flavor_format = flavor.get('format')
             flavor_url = flavor.get('url')
-            if not flavor_url or not re.match(r'https?://', flavor_url):
+            if not flavor_url or not re.match(r'https?://', flavor_url) or flavor_format == 'mp4_access':
                 continue
             tbr = int_or_none(flavor.get('bitrate'))
             if tbr == 99999:
                 formats.extend(self._extract_m3u8_formats(
-                    flavor_url, video_id, 'mp4', m3u8_id=flavor_format, fatal=False))
+                    flavor_url, video_id, 'mp4',
+                    m3u8_id=flavor_format, fatal=False))
                 continue
             format_id = []
             if flavor_format:
@@ -88,6 +128,10 @@ class DisneyIE(InfoExtractor):
                 'ext': ext,
                 'vcodec': 'none' if (width == 0 and height == 0) else None,
             })
+        if not formats and video_data.get('expired'):
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, page_data['translations']['video_expired']),
+                expected=True)
         self._sort_formats(formats)
 
         subtitles = {}

youtube_dl/extractor/generic.py

@@ -991,19 +991,6 @@ class GenericIE(InfoExtractor):
                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
             },
         },
-        # Kaltura embed protected with referrer
-        {
-            'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
-            'info_dict': {
-                'id': '1_g4fbemnq',
-                'ext': 'mp4',
-                'title': 'Violetta - Achter De Schermen - Ruggero',
-                'description': 'Achter de schermen met Ruggero',
-                'timestamp': 1435133761,
-                'upload_date': '20150624',
-                'uploader_id': 'echojecka',
-            },
-        },
         # Kaltura embed with single quotes
         {
             'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
@@ -2350,8 +2337,9 @@ class GenericIE(InfoExtractor):
                 'Channel': 'channel',
                 'ChannelList': 'channel_list',
             }
-            return self.url_result('limelight:%s:%s' % (
-                lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
+            return self.url_result(smuggle_url('limelight:%s:%s' % (
+                lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
+                'Limelight%s' % mobj.group(1), mobj.group(2))
 
         mobj = re.search(
             r'''(?sx)
@@ -2361,7 +2349,9 @@ class GenericIE(InfoExtractor):
                         value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
             ''', webpage)
         if mobj:
-            return self.url_result('limelight:media:%s' % mobj.group('id'))
+            return self.url_result(smuggle_url(
+                'limelight:media:%s' % mobj.group('id'),
+                {'source_url': url}), 'LimelightMedia', mobj.group('id'))
 
         # Look for AdobeTVVideo embeds
         mobj = re.search(

youtube_dl/extractor/limelight.py

@@ -8,6 +8,7 @@ from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
+    unsmuggle_url,
 )
 
 
@@ -15,20 +16,23 @@ class LimelightBaseIE(InfoExtractor):
     _PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s'
     _API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json'
 
-    def _call_playlist_service(self, item_id, method, fatal=True):
+    def _call_playlist_service(self, item_id, method, fatal=True, referer=None):
+        headers = {}
+        if referer:
+            headers['Referer'] = referer
         return self._download_json(
             self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
-            item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal)
+            item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers)
 
     def _call_api(self, organization_id, item_id, method):
         return self._download_json(
             self._API_URL % (organization_id, self._API_PATH, item_id, method),
             item_id, 'Downloading API %s JSON' % method)
 
-    def _extract(self, item_id, pc_method, mobile_method, meta_method):
-        pc = self._call_playlist_service(item_id, pc_method)
+    def _extract(self, item_id, pc_method, mobile_method, meta_method, referer=None):
+        pc = self._call_playlist_service(item_id, pc_method, referer=referer)
         metadata = self._call_api(pc['orgId'], item_id, meta_method)
-        mobile = self._call_playlist_service(item_id, mobile_method, fatal=False)
+        mobile = self._call_playlist_service(item_id, mobile_method, fatal=False, referer=referer)
         return pc, mobile, metadata
 
     def _extract_info(self, streams, mobile_urls, properties):
@@ -207,10 +211,13 @@ class LimelightMediaIE(LimelightBaseIE):
     _API_PATH = 'media'
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
         video_id = self._match_id(url)
 
         pc, mobile, metadata = self._extract(
-            video_id, 'getPlaylistByMediaId', 'getMobilePlaylistByMediaId', 'properties')
+            video_id, 'getPlaylistByMediaId',
+            'getMobilePlaylistByMediaId', 'properties',
+            smuggled_data.get('source_url'))
 
         return self._extract_info(
             pc['playlistItems'][0].get('streams', []),
@@ -247,11 +254,13 @@ class LimelightChannelIE(LimelightBaseIE):
     _API_PATH = 'channels'
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
         channel_id = self._match_id(url)
 
         pc, mobile, medias = self._extract(
             channel_id, 'getPlaylistByChannelId',
-            'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', 'media')
+            'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1',
+            'media', smuggled_data.get('source_url'))
 
         entries = [
             self._extract_info(