1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-09-03 16:45:17 +00:00

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

`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

View File

@ -15,6 +15,7 @@ from ..utils import (
class RumbleEmbedIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rumble\.com/embed/(?:[0-9a-z]+\.)?(?P<id>[0-9a-z]+)'
_EMBED_REGEX = [fr'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://rumble.com/embed/v5pv5f',
'md5': '36a18a049856720189f30977ccbb2c34',
@ -51,11 +52,10 @@ class RumbleEmbedIE(InfoExtractor):
}]
@classmethod
def _extract_urls(cls, webpage):
embeds = tuple(re.finditer(
fr'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>{cls._VALID_URL})', webpage))
def _extract_embed_urls(cls, url, webpage):
embeds = tuple(super()._extract_embed_urls(url, webpage))
if embeds:
return [mobj.group('url') for mobj in embeds]
return embeds
return [f'https://rumble.com/embed/{mobj.group("id")}' for mobj in re.finditer(
r'<script>\s*Rumble\(\s*"play"\s*,\s*{\s*[\'"]video[\'"]\s*:\s*[\'"](?P<id>[0-9a-z]+)[\'"]', webpage)]