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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class GoldenMoustacheIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?goldenmoustache\.com/(?P<display_id>[\w-]+)-(?P<id>\d+)'
   8     _TESTS = [{
   9         'url': 'http://www.goldenmoustache.com/suricate-le-poker-3700/',
  10         'md5': '0f904432fa07da5054d6c8beb5efb51a',
  11         'info_dict': {
  12             'id': '3700',
  13             'ext': 'mp4',
  14             'title': 'Suricate - Le Poker',
  15             'description': 'md5:3d1f242f44f8c8cb0a106f1fd08e5dc9',
  16             'thumbnail': 're:^https?://.*\.jpg$',
  17         }
  18     }, {
  19         'url': 'http://www.goldenmoustache.com/le-lab-tout-effacer-mc-fly-et-carlito-55249/',
  20         'md5': '27f0c50fb4dd5f01dc9082fc67cd5700',
  21         'info_dict': {
  22             'id': '55249',
  23             'ext': 'mp4',
  24             'title': 'Le LAB - Tout Effacer (Mc Fly et Carlito)',
  25             'description': 'md5:9b7fbf11023fb2250bd4b185e3de3b2a',
  26             'thumbnail': 're:^https?://.*\.(?:png|jpg)$',
  27         }
  28     }]
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32         webpage = self._download_webpage(url, video_id)
  33
  34         video_url = self._html_search_regex(
  35             r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL')
  36         title = self._html_search_regex(
  37             r'<title>(.*?)(?: - Golden Moustache)?</title>', webpage, 'title')
  38         thumbnail = self._og_search_thumbnail(webpage)
  39         description = self._og_search_description(webpage)
  40
  41         return {
  42             'id': video_id,
  43             'url': video_url,
  44             'ext': 'mp4',
  45             'title': title,
  46             'description': description,
  47             'thumbnail': thumbnail,
  48         }