Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/eroprofile.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class EroProfileIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)'
   8     _TEST = {
   9         'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
  10         'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
  11         'info_dict': {
  12             'id': '3733775',
  13             'display_id': 'sexy-babe-softcore',
  14             'ext': 'm4v',
  15             'title': 'sexy babe softcore',
  16             'thumbnail': 're:https?://.*\.jpg',
  17             'age_limit': 18,
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         display_id = self._match_id(url)
  23
  24         webpage = self._download_webpage(url, display_id)
  25
  26         video_id = self._search_regex(
  27             [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
  28             webpage, 'video id', default=None)
  29
  30         video_url = self._search_regex(
  31             r'<source src="([^"]+)', webpage, 'video url')
  32         title = self._html_search_regex(
  33             r'Title:</th><td>([^<]+)</td>', webpage, 'title')
  34         thumbnail = self._search_regex(
  35             r'onclick="showVideoPlayer\(\)"><img src="([^"]+)',
  36             webpage, 'thumbnail', fatal=False)
  37
  38         return {
  39             'id': video_id,
  40             'display_id': display_id,
  41             'url': video_url,
  42             'title': title,
  43             'thumbnail': thumbnail,
  44             'age_limit': 18,
  45         }