_ 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': 're:^https?://.*\.jpg$',
  22             'view_count': int,
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         webpage = self._download_webpage(url, video_id)
  29
  30         video_url = self._html_search_regex(
  31             r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL')
  32         title = self._html_search_regex(
  33             r'<title>(.*?) - Golden Moustache</title>', webpage, 'title')
  34         thumbnail = self._og_search_thumbnail(webpage)
  35         description = self._og_search_description(webpage)
  36         view_count = int_or_none(self._html_search_regex(
  37             r'<strong>([0-9]+)</strong>\s*VUES</span>',
  38             webpage, 'view count', fatal=False))
  39
  40         return {
  41             'id': video_id,
  42             'url': video_url,
  43             'ext': 'mp4',
  44             'title': title,
  45             'description': description,
  46             'thumbnail': thumbnail,
  47             'view_count': view_count,
  48         }