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             'age_limit': 18,
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26
  27         webpage = self._download_webpage(url, video_id)
  28
  29         video_url = self._html_search_regex(
  30             r'<source src="([^"]+)"', webpage, 'video URL')
  31
  32         title = self._html_search_regex(
  33             r'<title>([^<]+)\s*-\s*Free', webpage, 'title')
  34
  35         thumbnail = self._html_search_regex(
  36             r'poster="([^"]+)"',
  37             webpage, 'thumbnail', fatal=False)
  38
  39         cats_str = self._html_search_regex(
  40             r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
  41         categories = None if cats_str is None else cats_str.split(' ')
  42
  43         return {
  44             'id': video_id,
  45             'url': video_url,
  46             'title': title,
  47             'thumbnail': thumbnail,
  48             'categories': categories,
  49             'age_limit': self._rta_search(webpage),
  50         }