youtube_dl/extractor/drtuber.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class DrTuberIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<title_dash>[\w-]+)'
  10     _TEST = {
  11         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
  12         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
  13         'info_dict': {
  14             'id': '1740434',
  15             'ext': 'mp4',
  16             'title': 'Hot Perky Blonde Naked Golf',
  17             'categories': list,  # NSFW
  18             'thumbnail': 're:https?://.*\.jpg$',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group('id')
  25
  26         webpage = self._download_webpage(url, video_id)
  27
  28         video_url = self._html_search_regex(
  29             r'<source src="([^"]+)"', webpage, 'video URL')
  30
  31         title = self._html_search_regex(
  32             r'<title>([^<]+)\s*-\s*Free', webpage, 'title')
  33
  34         thumbnail = self._html_search_regex(
  35             r'poster="([^"]+)"',
  36             webpage, 'thumbnail', fatal=False)
  37
  38         categories_str = self._html_search_regex(
  39             r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
  40         categories = categories_str.split(' ')
  41
  42         return {
  43             'id': video_id,
  44             'url': video_url,
  45             'title': title,
  46             'thumbnail': thumbnail,
  47             'categories': categories,
  48         }