github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[facebook] Add support for plugin video embeds and multiple embeds (closes #13493)

Browse source
This commit is contained in:
Sergey M․ 2017-06-27 22:25:34 +07:00
parent bf2dc9cc6e
commit 0646e34c7d
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
3 changed files with 17 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
youtube_dl/extractor/buzzfeed.py
View file

@ -84,9 +84,10 @@ def _real_extract(self, url):
continue continue
entries.append(self.url_result(video['url'])) entries.append(self.url_result(video['url']))
facebook_url = FacebookIE._extract_url(webpage) facebook_urls = FacebookIE._extract_urls(webpage)
if facebook_url: entries.extend([
entries.append(self.url_result(facebook_url)) self.url_result(facebook_url)
for facebook_url in facebook_urls])
return { return {
'_type': 'playlist', '_type': 'playlist',

20
youtube_dl/extractor/facebook.py
View file

@ -203,19 +203,19 @@ class FacebookIE(InfoExtractor):
}] }]
@staticmethod @staticmethod
def _extract_url(webpage): def _extract_urls(webpage):
mobj = re.search( urls = []
r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage) for mobj in re.finditer(
if mobj is not None: r'<iframe[^>]+?src=(["\'])(?P<url>https?://www\.facebook\.com/(?:video/embed|plugins/video\.php).+?)\1',
return mobj.group('url') webpage):
urls.append(mobj.group('url'))
# Facebook API embed # Facebook API embed
# see https://developers.facebook.com/docs/plugins/embedded-video-player # see https://developers.facebook.com/docs/plugins/embedded-video-player
mobj = re.search(r'''(?x)<div[^>]+ for mobj in re.finditer(r'''(?x)<div[^>]+
class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+ class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+
data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''', webpage) data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''', webpage):
if mobj is not None: urls.append(mobj.group('url'))
return mobj.group('url') return urls
def _login(self): def _login(self):
(useremail, password) = self._get_login_info() (useremail, password) = self._get_login_info()

6
youtube_dl/extractor/generic.py
View file

@ -2222,9 +2222,9 @@ def _real_extract(self, url):
return self.url_result(mobj.group('url')) return self.url_result(mobj.group('url'))
# Look for embedded Facebook player # Look for embedded Facebook player
facebook_url = FacebookIE._extract_url(webpage) facebook_urls = FacebookIE._extract_urls(webpage)
if facebook_url is not None: if facebook_urls:
return self.url_result(facebook_url, 'Facebook') return self.playlist_from_matches(facebook_urls, video_id, video_title)
# Look for embedded VK player # Look for embedded VK player
mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage) mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)