[extractor/rumble] Detect JS embed

Closes #4064
This commit is contained in:
pukkandan 2022-06-13 19:07:56 +05:30
parent 21a73e9f39
commit 79e591b59b
No known key found for this signature in database
GPG key ID: 7EEE9E1E817D0A39
2 changed files with 43 additions and 7 deletions

View file

@ -2563,6 +2563,41 @@ class GenericIE(InfoExtractor):
}
}]
},
{
'note': 'Rumble embed',
'url': 'https://rumble.com/vdmum1-moose-the-dog-helps-girls-dig-a-snow-fort.html',
'md5': '53af34098a7f92c4e51cf0bd1c33f009',
'info_dict': {
'id': 'vb0ofn',
'ext': 'mp4',
'timestamp': 1612662578,
'uploader': 'LovingMontana',
'channel': 'LovingMontana',
'upload_date': '20210207',
'title': 'Winter-loving dog helps girls dig a snow fort ',
'channel_url': 'https://rumble.com/c/c-546523',
'thumbnail': 'https://sp.rmbl.ws/s8/1/5/f/x/x/5fxxb.OvCc.1-small-Moose-The-Dog-Helps-Girls-D.jpg',
'duration': 103,
}
},
{
'note': 'Rumble JS embed',
'url': 'https://therightscoop.com/what-does-9-plus-1-plus-1-equal-listen-to-this-audio-of-attempted-kavanaugh-assassins-call-and-youll-get-it',
'md5': '4701209ac99095592e73dbba21889690',
'info_dict': {
'id': 'v15eqxl',
'ext': 'mp4',
'channel': 'Mr Producer Media',
'duration': 92,
'title': '911 Audio From The Man Who Wanted To Kill Supreme Court Justice Kavanaugh',
'channel_url': 'https://rumble.com/c/RichSementa',
'thumbnail': 'https://sp.rmbl.ws/s8/1/P/j/f/A/PjfAe.OvCc-small-911-Audio-From-The-Man-Who-.jpg',
'timestamp': 1654892716,
'uploader': 'Mr Producer Media',
'upload_date': '20220610',
}
}
]
def report_following_redirect(self, new_url):

View file

@ -50,13 +50,14 @@ class RumbleEmbedIE(InfoExtractor):
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [
mobj.group('url')
for mobj in re.finditer(
r'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>%s)' % RumbleEmbedIE._VALID_URL,
webpage)]
@classmethod
def _extract_urls(cls, webpage):
embeds = tuple(re.finditer(
fr'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>{cls._VALID_URL})', webpage))
if embeds:
return [mobj.group('url') for mobj in 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)]
def _real_extract(self, url):
video_id = self._match_id(url)