github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-25 15:12:49 +00:00
Code Issues Projects Releases Packages Wiki Activity

[wistia] reduce embed extraction false positives and support inline embeds(closes #22931)

Browse source
This commit is contained in:
Remita Amine 2019-11-01 17:44:34 +01:00
parent 20cc7c082b
commit 152f22920d
1 changed files with 8 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
youtube_dl/extractor/wistia.py
View file

@ -12,7 +12,7 @@
class WistiaIE(InfoExtractor): class WistiaIE(InfoExtractor):
_VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]+)' _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]{10})'
_API_URL = 'http://fast.wistia.com/embed/medias/%s.json' _API_URL = 'http://fast.wistia.com/embed/medias/%s.json'
_IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s' _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s'
@ -43,25 +43,26 @@ class WistiaIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
# https://wistia.com/support/embed-and-share/video-on-your-website
@staticmethod @staticmethod
def _extract_url(webpage): def _extract_url(webpage):
match = re.search( match = re.search(
r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/iframe/.+?)\1', webpage) r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage)
if match: if match:
return unescapeHTML(match.group('url')) return unescapeHTML(match.group('url'))
match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
if match:
return 'wistia:%s' % match.group('id')
match = re.search( match = re.search(
r'''(?sx) r'''(?sx)
<script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*? <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
<div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
''', webpage) ''', webpage)
if match: if match:
return 'wistia:%s' % match.group('id') return 'wistia:%s' % match.group('id')
match = re.search(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage)
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)