[brightcove] Recognize another player ID
[youtube-dl] / youtube_dl / extractor / generic.py
index 87daf83f88694cecb11c7bec1ebfe82ed38d34ac..a3ac7d26bd79d4719edfbd3f273d3297d7d6d2a5 100644 (file)
@@ -73,9 +73,11 @@ from .kaltura import KalturaIE
 from .eagleplatform import EaglePlatformIE
 from .facebook import FacebookIE
 from .soundcloud import SoundcloudIE
+from .tunein import TuneInBaseIE
 from .vbox7 import Vbox7IE
 from .dbtv import DBTVIE
 from .piksel import PikselIE
+from .videa import VideaIE
 
 
 class GenericIE(InfoExtractor):
@@ -237,7 +239,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Tikibad ontruimd wegens brand',
                 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
                 'duration': 33,
             },
             'params': {
@@ -298,7 +300,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'upload_date': '20130224',
                 'uploader_id': 'TheVerge',
-                'description': 're:^Chris Ziegler takes a look at the\.*',
+                'description': r're:^Chris Ziegler takes a look at the\.*',
                 'uploader': 'The Verge',
                 'title': 'First Firefox OS phones side-by-side',
             },
@@ -344,10 +346,10 @@ class GenericIE(InfoExtractor):
             },
             'skip': 'There is a limit of 200 free downloads / month for the test song',
         },
-        # embedded brightcove video
-        # it also tests brightcove videos that need to set the 'Referer' in the
-        # http requests
         {
+            # embedded brightcove video
+            # it also tests brightcove videos that need to set the 'Referer'
+            # in the http requests
             'add_ie': ['BrightcoveLegacy'],
             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
             'info_dict': {
@@ -361,6 +363,24 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            # embedded with itemprop embedURL and video id spelled as `idVideo`
+            'add_id': ['BrightcoveLegacy'],
+            'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
+            'info_dict': {
+                'id': '5255628253001',
+                'ext': 'mp4',
+                'title': 'md5:37c519b1128915607601e75a87995fc0',
+                'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
+                'uploader': 'BFM BUSINESS',
+                'uploader_id': '876450612001',
+                'timestamp': 1482255315,
+                'upload_date': '20161220',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
         {
             # https://github.com/rg3/youtube-dl/issues/2253
             'url': 'http://bcove.me/i6nfkrc3',
@@ -402,6 +422,26 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,  # m3u8 download
             },
         },
+        {
+            # Brightcove with alternative playerID key
+            'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
+            'info_dict': {
+                'id': 'nmeth.2062_SV1',
+                'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
+            },
+            'playlist': [{
+                'info_dict': {
+                    'id': '2228375078001',
+                    'ext': 'mp4',
+                    'title': 'nmeth.2062-sv1',
+                    'description': 'nmeth.2062-sv1',
+                    'timestamp': 1363357591,
+                    'upload_date': '20130315',
+                    'uploader': 'Nature Publishing Group',
+                    'uploader_id': '1964492299001',
+                },
+            }],
+        },
         # ooyala video
         {
             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
@@ -519,7 +559,7 @@ class GenericIE(InfoExtractor):
                 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
                 'ext': 'mp4',
                 'title': 'Ужастики, русский трейлер (2015)',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
                 'duration': 153,
             }
         },
@@ -739,7 +779,7 @@ class GenericIE(InfoExtractor):
                 'duration': 48,
                 'timestamp': 1401537900,
                 'upload_date': '20140531',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
             },
         },
         # Wistia embed
@@ -809,6 +849,21 @@ class GenericIE(InfoExtractor):
             },
             'playlist_mincount': 7,
         },
+        # TuneIn station embed
+        {
+            'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
+            'info_dict': {
+                'id': '204146',
+                'ext': 'mp3',
+                'title': 'CNRV',
+                'location': 'Paris, France',
+                'is_live': True,
+            },
+            'params': {
+                # Live stream
+                'skip_download': True,
+            },
+        },
         # Livestream embed
         {
             'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
@@ -996,7 +1051,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Навальный вышел на свободу',
                 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
                 'duration': 87,
                 'view_count': int,
                 'age_limit': 0,
@@ -1010,7 +1065,7 @@ class GenericIE(InfoExtractor):
                 'id': '12820',
                 'ext': 'mp4',
                 'title': "'O Sole Mio",
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
                 'duration': 216,
                 'view_count': int,
             },
@@ -1023,7 +1078,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
                 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
                 'duration': 694,
                 'age_limit': 0,
             },
@@ -1035,7 +1090,7 @@ class GenericIE(InfoExtractor):
                 'id': '3519514',
                 'ext': 'mp4',
                 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
-                'thumbnail': 're:^https?://.*\.png$',
+                'thumbnail': r're:^https?://.*\.png$',
                 'duration': 45.115,
             },
         },
@@ -1118,7 +1173,7 @@ class GenericIE(InfoExtractor):
                 'id': '300346',
                 'ext': 'mp4',
                 'title': '中一中男師變性 全校師生力挺',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
             },
             'params': {
                 # m3u8 download
@@ -1164,7 +1219,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Sauvons les abeilles ! - Le débat',
                 'description': 'md5:d9082128b1c5277987825d684939ca26',
-                'thumbnail': 're:^https?://.*\.jpe?g$',
+                'thumbnail': r're:^https?://.*\.jpe?g$',
                 'timestamp': 1434970506,
                 'upload_date': '20150622',
                 'uploader': 'Public Sénat',
@@ -1178,7 +1233,7 @@ class GenericIE(InfoExtractor):
                 'id': '2855',
                 'ext': 'mp4',
                 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
-                'thumbnail': 're:^https?://.*\.jpe?g$',
+                'thumbnail': r're:^https?://.*\.jpe?g$',
                 'uploader': 'ClickHole',
                 'uploader_id': 'clickhole',
             }
@@ -1404,6 +1459,15 @@ class GenericIE(InfoExtractor):
             },
             'playlist_mincount': 3,
         },
+        {
+            # Videa embeds
+            'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
+            'info_dict': {
+                'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
+                'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
+            },
+            'playlist_mincount': 2,
+        },
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject
@@ -1895,7 +1959,14 @@ class GenericIE(InfoExtractor):
                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
         if mobj is not None:
-            return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
+            embed_token = self._search_regex(
+                r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
+                webpage, 'ooyala embed token', default=None)
+            return OoyalaIE._build_url_result(smuggle_url(
+                mobj.group('ec'), {
+                    'domain': url,
+                    'embed_token': embed_token,
+                }))
 
         # Look for multiple Ooyala embeds on SBN network websites
         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
@@ -2060,6 +2131,11 @@ class GenericIE(InfoExtractor):
         if soundcloud_urls:
             return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
 
+        # Look for tunein player
+        tunein_urls = TuneInBaseIE._extract_urls(webpage)
+        if tunein_urls:
+            return _playlist_from_matches(tunein_urls)
+
         # Look for embedded mtvservices player
         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
         if mtvservices_url:
@@ -2340,6 +2416,11 @@ class GenericIE(InfoExtractor):
         if dbtv_urls:
             return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
 
+        # Look for Videa embeds
+        videa_urls = VideaIE._extract_urls(webpage)
+        if videa_urls:
+            return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
+
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')