[pornhub:playlist] Improve extraction (closes #11594)
[youtube-dl] / youtube_dl / extractor / generic.py
index 87daf83f88694cecb11c7bec1ebfe82ed38d34ac..d71d0dc46516db928ccc121b70c2da15c93dfcc4 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):
@@ -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',
@@ -809,6 +829,21 @@ 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',
@@ -1404,6 +1439,15 @@ 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
@@ -2060,6 +2104,11 @@ 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 +2389,11 @@ 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')