yt_dlp/extractor/rumble.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     determine_ext,
  10     int_or_none,
  11     parse_iso8601,
  12     try_get,
  13 )
  14
  15
  16 class RumbleEmbedIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?rumble\.com/embed/(?:[0-9a-z]+\.)?(?P<id>[0-9a-z]+)'
  18     _TESTS = [{
  19         'url': 'https://rumble.com/embed/v5pv5f',
  20         'md5': '36a18a049856720189f30977ccbb2c34',
  21         'info_dict': {
  22             'id': 'v5pv5f',
  23             'ext': 'mp4',
  24             'title': 'WMAR 2 News Latest Headlines | October 20, 6pm',
  25             'timestamp': 1571611968,
  26             'upload_date': '20191020',
  27         }
  28     }, {
  29         'url': 'https://rumble.com/embed/ufe9n.v5pv5f',
  30         'only_matching': True,
  31     }]
  32
  33     @staticmethod
  34     def _extract_urls(webpage):
  35         return [
  36             mobj.group('url')
  37             for mobj in re.finditer(
  38                 r'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>%s)' % RumbleEmbedIE._VALID_URL,
  39                 webpage)]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43         video = self._download_json(
  44             'https://rumble.com/embedJS/', video_id,
  45             query={'request': 'video', 'v': video_id})
  46         title = video['title']
  47
  48         formats = []
  49         for height, ua in (video.get('ua') or {}).items():
  50             for i in range(2):
  51                 f_url = try_get(ua, lambda x: x[i], compat_str)
  52                 if f_url:
  53                     ext = determine_ext(f_url)
  54                     f = {
  55                         'ext': ext,
  56                         'format_id': '%s-%sp' % (ext, height),
  57                         'height': int_or_none(height),
  58                         'url': f_url,
  59                     }
  60                     bitrate = try_get(ua, lambda x: x[i + 2]['bitrate'])
  61                     if bitrate:
  62                         f['tbr'] = int_or_none(bitrate)
  63                     formats.append(f)
  64         self._sort_formats(formats)
  65
  66         author = video.get('author') or {}
  67
  68         return {
  69             'id': video_id,
  70             'title': title,
  71             'formats': formats,
  72             'thumbnail': video.get('i'),
  73             'timestamp': parse_iso8601(video.get('pubDate')),
  74             'channel': author.get('name'),
  75             'channel_url': author.get('url'),
  76             'duration': int_or_none(video.get('duration')),
  77         }