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

   1 from __future__ import unicode_literals
   2
   3 import re
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     parse_duration,
   7     int_or_none,
   8 )
   9
  10
  11 class GoldenMoustacheIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?goldenmoustache\.com/(?P<display_id>[\w-]+)-(?P<id>\d+)'
  13     _TEST = {
  14         'url': 'http://www.goldenmoustache.com/suricate-le-poker-3700/',
  15         'md5': '0f904432fa07da5054d6c8beb5efb51a',
  16         'info_dict': {
  17             'id': '3700',
  18             'ext': 'mp4',
  19             'title': 'Suricate - Le Poker',
  20             'description': 'md5:3d1f242f44f8c8cb0a106f1fd08e5dc9',
  21             'thumbnail': 'md5:fd41386bc1f932552622da4a7e9a7242',
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         mobj = re.match(self._VALID_URL, url)
  27         video_id = mobj.group('id')
  28
  29         webpage = self._download_webpage(url, video_id)
  30
  31         video_url = self._html_search_regex(r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL')
  32
  33         title = self._html_search_regex(r'<title>(.*?) - Golden Moustache</title>', webpage, 'title')
  34
  35         thumbnail = self._html_search_meta('og:image', webpage, 'thumbnail')
  36
  37         description = self._html_search_meta('og:description', webpage, 'description')
  38
  39         view_count = int_or_none(self._html_search_regex(
  40             r'<strong>(\d+)</strong>\s*VUES</span>', webpage, 'view count', fatal=False))
  41
  42         return {
  43             'id': video_id,
  44             'url': video_url,
  45             'ext': 'mp4',
  46             'title': title,
  47             'description': description,
  48             'thumbnail': thumbnail,
  49             'view_count': view_count,
  50         }