youtube_dl/extractor/oktoberfesttv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class OktoberfestTVIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?oktoberfest-tv\.de/[^/]+/[^/]+/video/(?P<id>[^/?#]+)'
   9
  10     _TEST = {
  11         'url': 'http://www.oktoberfest-tv.de/de/kameras/video/hb-zelt',
  12         'info_dict': {
  13             'id': 'hb-zelt',
  14             'ext': 'mp4',
  15             'title': 're:^Live-Kamera: Hofbräuzelt [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  16             'thumbnail': r're:^https?://.*\.jpg$',
  17             'is_live': True,
  18         },
  19         'params': {
  20             'skip_download': True,
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(url, video_id)
  27
  28         title = self._live_title(self._html_search_regex(
  29             r'<h1><strong>.*?</strong>(.*?)</h1>', webpage, 'title'))
  30
  31         clip = self._search_regex(
  32             r"clip:\s*\{\s*url:\s*'([^']+)'", webpage, 'clip')
  33         ncurl = self._search_regex(
  34             r"netConnectionUrl:\s*'([^']+)'", webpage, 'rtmp base')
  35         video_url = ncurl + clip
  36         thumbnail = self._search_regex(
  37             r"canvas:\s*\{\s*backgroundImage:\s*'url\(([^)]+)\)'", webpage,
  38             'thumbnail', fatal=False)
  39
  40         return {
  41             'id': video_id,
  42             'title': title,
  43             'url': video_url,
  44             'ext': 'mp4',
  45             'is_live': True,
  46             'thumbnail': thumbnail,
  47         }