Merge pull request #8876 from remitamine/html5_media

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

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 764697bd29577c8b59b716c233e1a42baddb9b0c..cddd1a817efb6dd5acb79b7198f1faa755686f7b 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -49,7 +49,10 @@ from .pornhub import PornHubIE
 from .xhamster import XHamsterEmbedIE
 from .tnaflix import TNAFlixNetworkEmbedIE
 from .vimeo import VimeoIE
-from .dailymotion import DailymotionCloudIE
+from .dailymotion import (
+    DailymotionIE,
+    DailymotionCloudIE,
+)
 from .onionstudios import OnionStudiosIE
 from .viewlift import ViewLiftEmbedIE
 from .screenwavemedia import ScreenwaveMediaIE
@@ -1310,6 +1313,38 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Kaltura'],
         },
+        {
+            # Non-standard Vimeo embed
+            'url': 'https://openclassrooms.com/courses/understanding-the-web',
+            'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
+            'info_dict': {
+                'id': '148867247',
+                'ext': 'mp4',
+                'title': 'Understanding the web - Teaser',
+                'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
+                'upload_date': '20151214',
+                'uploader': 'OpenClassrooms',
+                'uploader_id': 'openclassrooms',
+            },
+            'add_ie': ['Vimeo'],
+        },
+        # {
+        #     # TODO: find another test
+        #     # http://schema.org/VideoObject
+        #     'url': 'https://flipagram.com/f/nyvTSJMKId',
+        #     'md5': '888dcf08b7ea671381f00fab74692755',
+        #     'info_dict': {
+        #         'id': 'nyvTSJMKId',
+        #         'ext': 'mp4',
+        #         'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
+        #         'description': '#love for cats.',
+        #         'timestamp': 1461244995,
+        #         'upload_date': '20160421',
+        #     },
+        #     'params': {
+        #         'force_generic_extractor': True,
+        #     },
+        # }
     ]
 
     def report_following_redirect(self, new_url):
@@ -1673,12 +1708,9 @@ class GenericIE(InfoExtractor):
         if matches:
             return _playlist_from_matches(matches, lambda m: m[-1])
 
-        # Look for embedded Dailymotion player
-        matches = re.findall(
-            r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
+        matches = DailymotionIE._extract_urls(webpage)
         if matches:
-            return _playlist_from_matches(
-                matches, lambda m: unescapeHTML(m[1]))
+            return _playlist_from_matches(matches)
 
         # Look for embedded Dailymotion playlist player (#3822)
         m = re.search(
@@ -2157,6 +2189,19 @@ class GenericIE(InfoExtractor):
         if embed_url:
             return self.url_result(embed_url)
 
+        # Looking for http://schema.org/VideoObject
+        json_ld = self._search_json_ld(
+            webpage, video_id, default=None, expected_type='VideoObject')
+        if json_ld and json_ld.get('url'):
+            info_dict.update({
+                'title': video_title or info_dict['title'],
+                'description': video_description,
+                'thumbnail': video_thumbnail,
+                'age_limit': age_limit
+            })
+            info_dict.update(json_ld)
+            return info_dict
+
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True