mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-09-03 00:25:08 +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

23
yt_dlp/extractor/dailymotion.py
View File

@ -99,6 +99,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
[/=](?P<id>[^/?_&]+)(?:.+?\bplaylist=(?P<playlist_id>x[0-9a-z]+))?
'''
IE_NAME = 'dailymotion'
_EMBED_REGEX = [r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1']
_TESTS = [{
'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
'md5': '074b95bdee76b9e3654137aee9c79dfe',
@ -208,18 +209,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
}
xid'''
@staticmethod
def _extract_urls(webpage):
urls = []
# Look for embedded Dailymotion player
@classmethod
def _extract_embed_urls(cls, url, webpage):
# https://developer.dailymotion.com/player#player-parameters
for mobj in re.finditer(
r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage):
urls.append(unescapeHTML(mobj.group('url')))
yield from super()._extract_embed_urls(url, webpage)
for mobj in re.finditer(
r'(?s)DM\.player\([^,]+,\s*{.*?video[\'"]?\s*:\s*["\']?(?P<id>[0-9a-zA-Z]+).+?}\s*\);', webpage):
urls.append('https://www.dailymotion.com/embed/video/' + mobj.group('id'))
return urls
yield from 'https://www.dailymotion.com/embed/video/' + mobj.group('id')
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url)
@ -378,6 +374,15 @@ class DailymotionPlaylistIE(DailymotionPlaylistBaseIE):
}]
_OBJECT_TYPE = 'collection'
@classmethod
def _extract_embed_urls(cls, url, webpage):
# Look for embedded Dailymotion playlist player (#3822)
for mobj in re.finditer(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1',
webpage):
for p in re.findall(r'list\[\]=/playlist/([^/]+)/', unescapeHTML(mobj.group('url'))):
yield '//dailymotion.com/playlist/%s' % p
class DailymotionUserIE(DailymotionPlaylistBaseIE):
IE_NAME = 'dailymotion:user'