mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-09-03 08:35:32 +00:00
Code Issues Projects Releases Wiki Activity

[extractors] Use new framework for existing embeds (#4307)

Browse Source 
`Brightcove` is difficult to migrate because it's subclasses may depend
on the signature of the current functions. So it is left as-is for now

Note: Tests have not been migrated
This commit is contained in:
pukkandan
2022-08-01 06:53:25 +05:30
parent 1e8fe57e5c
commit bfd973ece3
138 changed files with 499 additions and 1909 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
yt_dlp/extractor/facebook.py
View File

@ -57,6 +57,13 @@ class FacebookIE(InfoExtractor):
)
(?P<id>[0-9]+)
'''
_EMBED_REGEX = [
r'<iframe[^>]+?src=(["\'])(?P<url>https?://www\.facebook\.com/(?:video/embed|plugins/video\.php).+?)\1',
# Facebook API embed https://developers.facebook.com/docs/plugins/embedded-video-player
r'''(?x)<div[^>]+
class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+
data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''',
]
_LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
_CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
_NETRC_MACHINE = 'facebook'
@ -311,21 +318,6 @@ class FacebookIE(InfoExtractor):
'graphURI': '/api/graphql/'
}
@staticmethod
def _extract_urls(webpage):
urls = []
for mobj in re.finditer(
r'<iframe[^>]+?src=(["\'])(?P<url>https?://www\.facebook\.com/(?:video/embed|plugins/video\.php).+?)\1',
webpage):
urls.append(mobj.group('url'))
# Facebook API embed
# see https://developers.facebook.com/docs/plugins/embedded-video-player
for mobj in re.finditer(r'''(?x)<div[^>]+
class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+
data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''', webpage):
urls.append(mobj.group('url'))
return urls
def _perform_login(self, username, password):
login_page_req = sanitized_Request(self._LOGIN_URL)
self._set_cookie('facebook.com', 'locale', 'en_US')