Merge pull request #75 from ytdl-org/master

[pull] master from ytdl-org:master

youtube_dl/extractor/generic.py

@@ -2075,6 +2075,22 @@ class GenericIE(InfoExtractor):
             },
             'playlist_count': 6,
         },
+        {
+            # Squarespace video embed, 2019-08-28
+            'url': 'http://ootboxford.com',
+            'info_dict': {
+                'id': 'Tc7b_JGdZfw',
+                'title': 'Out of the Blue, at Childish Things 10',
+                'ext': 'mp4',
+                'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
+                'uploader_id': 'helendouglashouse',
+                'uploader': 'Helen & Douglas House',
+                'upload_date': '20140328',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
         {
             # Zype embed
             'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
@@ -2395,6 +2411,12 @@ class GenericIE(InfoExtractor):
         # Unescaping the whole page allows to handle those cases in a generic way
         webpage = compat_urllib_parse_unquote(webpage)
 
+        # Unescape squarespace embeds to be detected by generic extractor,
+        # see https://github.com/ytdl-org/youtube-dl/issues/21294
+        webpage = re.sub(
+            r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
+            lambda x: unescapeHTML(x.group(0)), webpage)
+
         # it's tempting to parse this further, but you would
         # have to take into account all the variations like
         #   Video Title - Site Name

youtube_dl/extractor/openload.py

@@ -243,12 +243,13 @@ class PhantomJSwrapper(object):
 
 
 class OpenloadIE(InfoExtractor):
-    _DOMAINS = r'''(?x)
+    _DOMAINS = r'''
                     (?:
                         openload\.(?:co|io|link|pw)|
                         oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website|vip)|
-                        oladblock\.(?:services|xyz|me)|openloed\.co)
+                        oladblock\.(?:services|xyz|me)|openloed\.co
-                    '''
+                    )
+                '''
     _VALID_URL = r'''(?x)
                     https?://
                         (?P<host>
@@ -396,7 +397,7 @@ class OpenloadIE(InfoExtractor):
     @classmethod
     def _extract_urls(cls, webpage):
         return re.findall(
-            r'<iframe[^>]+src=["\']((?:https?://)?%s/%s/[a-zA-Z0-9-_]+)'
+            r'(?x)<iframe[^>]+src=["\']((?:https?://)?%s/%s/[a-zA-Z0-9-_]+)'
             % (cls._DOMAINS, cls._EMBED_WORD), webpage)
 
     def _extract_decrypted_page(self, page_url, webpage, video_id):