_ Git - youtube-dl/blob - youtube_dl/extractor/twitcasting.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6 import re
   7
   8
   9 class TwitcastingIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:(?:www|ssl|en|pt|es|ja|ko)\.)?twitcasting\.tv/(?P<uploader_id>[^\/]+)/movie/(?P<video_id>[0-9]+)'
  11     _TEST = {
  12         'url': 'https://twitcasting.tv/ivetesangalo/movie/2357609',
  13         'md5': '745243cad58c4681dc752490f7540d7f',
  14         'info_dict': {
  15             'id': '2357609',
  16             'ext': 'mp4',
  17             'title': 'Recorded Live #2357609',
  18             'uploader_id': 'ivetesangalo',
  19             'description': "Moi! I'm live on TwitCasting from my iPhone.",
  20             'thumbnail': r're:^https?://.*\.jpg$',
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         video_id = mobj.group('video_id')
  27         uploader_id = mobj.group('uploader_id')
  28
  29         webpage = self._download_webpage(url, video_id)
  30
  31         playlist_url = self._html_search_regex(r'(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage, name='playlist url', group='url')
  32         formats = self._extract_m3u8_formats(playlist_url, video_id, ext='mp4')
  33         thumbnail = self._og_search_thumbnail(webpage)
  34         title = self._html_search_meta('twitter:title', webpage)
  35         description = self._og_search_description(webpage) or self._html_search_meta('twitter:description', webpage)
  36         return{
  37             'id': video_id,
  38             'url': url,
  39             'title': title,
  40             'description': description,
  41             'thumbnail': thumbnail,
  42             'uploader_id': uploader_id,
  43             'formats': formats,
  44         }