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

12
yt_dlp/extractor/glomex.py
View File

@ -174,7 +174,7 @@ class GlomexEmbedIE(GlomexBaseIE):
return cls._smuggle_origin_url(f'https:{cls._BASE_PLAYER_URL}?{query_string}', origin_url)
@classmethod
def _extract_urls(cls, webpage, origin_url):
def _extract_embed_urls(cls, url, webpage):
# https://docs.glomex.com/publisher/video-player-integration/javascript-api/
quot_re = r'["\']'
@ -183,9 +183,9 @@ class GlomexEmbedIE(GlomexBaseIE):
(?:https?:)?{cls._BASE_PLAYER_URL_RE}\?(?:(?!(?P=q)).)+
)(?P=q)'''
for mobj in re.finditer(regex, webpage):
url = unescapeHTML(mobj.group('url'))
if cls.suitable(url):
yield cls._smuggle_origin_url(url, origin_url)
embed_url = unescapeHTML(mobj.group('url'))
if cls.suitable(embed_url):
yield cls._smuggle_origin_url(embed_url, url)
regex = fr'''(?x)
<glomex-player [^>]+?>|
@ -193,7 +193,7 @@ class GlomexEmbedIE(GlomexBaseIE):
for mobj in re.finditer(regex, webpage):
attrs = extract_attributes(mobj.group(0))
if attrs.get('data-integration-id') and attrs.get('data-playlist-id'):
yield cls.build_player_url(attrs['data-playlist-id'], attrs['data-integration-id'], origin_url)
yield cls.build_player_url(attrs['data-playlist-id'], attrs['data-integration-id'], url)
# naive parsing of inline scripts for hard-coded integration parameters
regex = fr'''(?x)
@ -206,7 +206,7 @@ class GlomexEmbedIE(GlomexBaseIE):
continue
playlist_id = re.search(regex % 'playlistId', script)
if playlist_id:
yield cls.build_player_url(playlist_id, integration_id, origin_url)
yield cls.build_player_url(playlist_id, integration_id, url)
def _real_extract(self, url):
url, origin_url = self._unsmuggle_origin_url(url)