mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-10-30 21:20:34 +00:00
78 lines
2.4 KiB
Python
78 lines
2.4 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import compat_str
|
|
from ..utils import (
|
|
determine_ext,
|
|
int_or_none,
|
|
parse_iso8601,
|
|
try_get,
|
|
)
|
|
|
|
|
|
class RumbleEmbedIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:www\.)?rumble\.com/embed/(?:[0-9a-z]+\.)?(?P<id>[0-9a-z]+)'
|
|
_TESTS = [{
|
|
'url': 'https://rumble.com/embed/v5pv5f',
|
|
'md5': '36a18a049856720189f30977ccbb2c34',
|
|
'info_dict': {
|
|
'id': 'v5pv5f',
|
|
'ext': 'mp4',
|
|
'title': 'WMAR 2 News Latest Headlines | October 20, 6pm',
|
|
'timestamp': 1571611968,
|
|
'upload_date': '20191020',
|
|
}
|
|
}, {
|
|
'url': 'https://rumble.com/embed/ufe9n.v5pv5f',
|
|
'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)]
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
video = self._download_json(
|
|
'https://rumble.com/embedJS/', video_id,
|
|
query={'request': 'video', 'v': video_id})
|
|
title = video['title']
|
|
|
|
formats = []
|
|
for height, ua in (video.get('ua') or {}).items():
|
|
for i in range(2):
|
|
f_url = try_get(ua, lambda x: x[i], compat_str)
|
|
if f_url:
|
|
ext = determine_ext(f_url)
|
|
f = {
|
|
'ext': ext,
|
|
'format_id': '%s-%sp' % (ext, height),
|
|
'height': int_or_none(height),
|
|
'url': f_url,
|
|
}
|
|
bitrate = try_get(ua, lambda x: x[i + 2]['bitrate'])
|
|
if bitrate:
|
|
f['tbr'] = int_or_none(bitrate)
|
|
formats.append(f)
|
|
self._sort_formats(formats)
|
|
|
|
author = video.get('author') or {}
|
|
|
|
return {
|
|
'id': video_id,
|
|
'title': title,
|
|
'formats': formats,
|
|
'thumbnail': video.get('i'),
|
|
'timestamp': parse_iso8601(video.get('pubDate')),
|
|
'channel': author.get('name'),
|
|
'channel_url': author.get('url'),
|
|
'duration': int_or_none(video.get('duration')),
|
|
}
|