[generic] Try parsing JWPlayer embedded videos (closes #12030)

[youtube-dl] / youtube_dl / extractor / generic.py

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index a23486620b8d8d9a9c81714b56777ebe3587c581..3db31debea88aee29718a56cdc38109487dd9c8e 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -20,6 +20,7 @@ from ..utils import (
     float_or_none,
     HEADRequest,
     is_html,
+    js_to_json,
     orderedSet,
     sanitized_Request,
     smuggle_url,
@@ -29,6 +30,7 @@ from ..utils import (
     UnsupportedError,
     xpath_text,
 )
+from .commonprotocols import RtmpIE
 from .brightcove import (
     BrightcoveLegacyIE,
     BrightcoveNewIE,
@@ -81,6 +83,7 @@ from .videa import VideaIE
 from .twentymin import TwentyMinutenIE
 from .ustream import UstreamIE
 from .openload import OpenloadIE
+from .videopress import VideoPressIE
 
 
 class GenericIE(InfoExtractor):
@@ -946,6 +949,29 @@ class GenericIE(InfoExtractor):
                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
             },
         },
+        # jwplayer rtmp
+        {
+            'url': 'http://www.suffolk.edu/sjc/',
+            'info_dict': {
+                'id': 'sjclive',
+                'ext': 'flv',
+                'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
+                'uploader': 'www.suffolk.edu',
+            },
+            'params': {
+                'skip_download': True,
+            }
+        },
+        # Complex jwplayer
+        {
+            'url': 'http://www.indiedb.com/games/king-machine/videos',
+            'info_dict': {
+                'id': 'videos',
+                'ext': 'mp4',
+                'title': 'king machine trailer 1',
+                'thumbnail': r're:^https?://.*\.jpg$',
+            },
+        },
         # rtl.nl embed
         {
             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
@@ -976,19 +1002,6 @@ 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',
@@ -1473,6 +1486,21 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
             'add_ie': [TwentyMinutenIE.ie_key()],
+        },
+        {
+            # VideoPress embed
+            'url': 'https://en.support.wordpress.com/videopress/',
+            'info_dict': {
+                'id': 'OcobLTqC',
+                'ext': 'm4v',
+                'title': 'IMG_5786',
+                'timestamp': 1435711927,
+                'upload_date': '20150701',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'add_ie': [VideoPressIE.ie_key()],
         }
         # {
         #     # TODO: find another test
@@ -2320,8 +2348,9 @@ 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)
@@ -2331,7 +2360,9 @@ 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(
@@ -2438,6 +2469,12 @@ class GenericIE(InfoExtractor):
             return _playlist_from_matches(
                 openload_urls, ie=OpenloadIE.ie_key())
 
+        # Look for VideoPress embeds
+        videopress_urls = VideoPressIE._extract_urls(webpage)
+        if videopress_urls:
+            return _playlist_from_matches(
+                videopress_urls, ie=VideoPressIE.ie_key())
+
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')
@@ -2462,9 +2499,20 @@ class GenericIE(InfoExtractor):
                 self._sort_formats(entry['formats'])
             return self.playlist_result(entries)
 
+        jwplayer_data_str = self._find_jwplayer_data(webpage)
+        if jwplayer_data_str:
+            try:
+                jwplayer_data = self._parse_json(
+                    jwplayer_data_str, video_id, transform_source=js_to_json)
+                return self._parse_jwplayer_data(jwplayer_data, video_id)
+            except ExtractorError:
+                pass
+
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True
+            if RtmpIE.suitable(vurl):
+                return True
             vpath = compat_urlparse.urlparse(vurl).path
             vext = determine_ext(vpath)
             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
@@ -2572,6 +2620,15 @@ class GenericIE(InfoExtractor):
                 'age_limit': age_limit,
             }
 
+            if RtmpIE.suitable(video_url):
+                entry_info_dict.update({
+                    '_type': 'url_transparent',
+                    'ie_key': RtmpIE.ie_key(),
+                    'url': video_url,
+                })
+                entries.append(entry_info_dict)
+                continue
+
             ext = determine_ext(video_url)
             if ext == 'smil':
                 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)