[webofstories] Tolerate malforder og:title (Closes #8417)

youtube_dl/extractor/webofstories.py

@@ -12,8 +12,7 @@ class WebOfStoriesIE(InfoExtractor):
     _VIDEO_DOMAIN = 'http://eu-mobile.webofstories.com/'
     _GREAT_LIFE_STREAMER = 'rtmp://eu-cdn1.webofstories.com/cfx/st/'
     _USER_STREAMER = 'rtmp://eu-users.webofstories.com/cfx/st/'
-    _TESTS = [
-        {
+    _TESTS = [{
         'url': 'http://www.webofstories.com/play/hans.bethe/71',
         'md5': '373e4dd915f60cfe3116322642ddf364',
         'info_dict': {
@@ -24,8 +23,7 @@ class WebOfStoriesIE(InfoExtractor):
             'description': 'Hans Bethe talks about calculating the temperature of the sun',
             'duration': 238,
         }
-        },
-        {
+    }, {
         'url': 'http://www.webofstories.com/play/55908',
         'md5': '2985a698e1fe3211022422c4b5ed962c',
         'info_dict': {
@@ -35,15 +33,31 @@ class WebOfStoriesIE(InfoExtractor):
             'thumbnail': 're:^https?://.*\.jpg$',
             'description': 'Planctomycete talks about The story of Gemmata obscuriglobus',
             'duration': 169,
-            }
         },
-    ]
+        'skip': 'notfound',
+    }, {
+        # malformed og:title meta
+        'url': 'http://www.webofstories.com/play/54215?o=MS',
+        'info_dict': {
+            'id': '54215',
+            'ext': 'mp4',
+            'title': '"A Leg to Stand On"',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'Oliver Sacks talks about the death and resurrection of a limb',
+            'duration': 97,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        title = self._og_search_title(webpage)
+        # Sometimes og:title meta is malformed
+        title = self._og_search_title(webpage, default=None) or self._html_search_regex(
+            r'(?s)<strong>Title:\s*</strong>(.+?)<', webpage, 'title')
         description = self._html_search_meta('description', webpage)
         thumbnail = self._og_search_thumbnail(webpage)