[extractor/generic] Add support for squarespace embeds (closes #21294)

This commit is contained in:
Barbara Miller 2019-07-22 14:09:21 -07:00 committed by Sergey M․
parent cc73d5ad15
commit d78657fd18
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -2075,6 +2075,17 @@ class GenericIE(InfoExtractor):
}, },
'playlist_count': 6, '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',
},
'params': {
'skip_download': True,
},
},
{ {
# Zype embed # Zype embed
'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites', 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
@ -2395,6 +2406,13 @@ def _real_extract(self, url):
# Unescaping the whole page allows to handle those cases in a generic way # Unescaping the whole page allows to handle those cases in a generic way
webpage = compat_urllib_parse_unquote(webpage) webpage = compat_urllib_parse_unquote(webpage)
# unescape re.sub replacement
def unescape_resub(m):
return unescapeHTML(m.group(0))
# unescape squarespace video embeds
webpage = re.sub(r'<div[^>]+class=[^>]*?sqs-video-wrapper[^>]*>', unescape_resub, webpage)
# it's tempting to parse this further, but you would # it's tempting to parse this further, but you would
# have to take into account all the variations like # have to take into account all the variations like
# Video Title - Site Name # Video Title - Site Name