[wistia] Add support for multiple generic embeds (closes #8347, closes #11385)

This commit is contained in:
Sergey M․ 2020-02-23 06:47:11 +07:00
parent 5d9f6cbc5a
commit fda6d237a5
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
2 changed files with 25 additions and 23 deletions

View File

@ -2537,14 +2537,15 @@ class GenericIE(InfoExtractor):
dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key()) dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
# Look for embedded Wistia player # Look for embedded Wistia player
wistia_url = WistiaIE._extract_url(webpage) wistia_urls = WistiaIE._extract_urls(webpage)
if wistia_url: if wistia_urls:
return { playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
for entry in playlist['entries']:
entry.update({
'_type': 'url_transparent', '_type': 'url_transparent',
'url': self._proto_relative_url(wistia_url),
'ie_key': WistiaIE.ie_key(),
'uploader': video_uploader, 'uploader': video_uploader,
} })
return playlist
# Look for SVT player # Look for SVT player
svt_url = SVTIE._extract_url(webpage) svt_url = SVTIE._extract_url(webpage)

View File

@ -45,22 +45,23 @@ class WistiaIE(InfoExtractor):
# https://wistia.com/support/embed-and-share/video-on-your-website # https://wistia.com/support/embed-and-share/video-on-your-website
@staticmethod @staticmethod
def _extract_url(webpage): def _extract_url(webpage):
match = re.search( urls = WistiaIE._extract_urls(webpage)
r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage) return urls[0] if urls else None
if match:
return unescapeHTML(match.group('url'))
match = re.search( @staticmethod
def _extract_urls(webpage):
urls = []
for match in re.finditer(
r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage):
urls.append(unescapeHTML(match.group('url')))
for match in re.finditer(
r'''(?sx) r'''(?sx)
<script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
<div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
''', webpage) ''', webpage):
if match: urls.append('wistia:%s' % match.group('id'))
return 'wistia:%s' % match.group('id') for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage):
urls.append('wistia:%s' % match.group('id'))
match = re.search(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage) return urls
if match:
return 'wistia:%s' % match.group('id')
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)