youtube_dl/extractor/drtuber.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import str_to_int
   7
   8
   9 class DrTuberIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<title_dash>[\w-]+)'
  11     _TEST = {
  12         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
  13         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
  14         'info_dict': {
  15             'id': '1740434',
  16             'ext': 'mp4',
  17             'title': 'Hot Perky Blonde Naked Golf',
  18             'like_count': int,
  19             'dislike_count': int,
  20             'comment_count': int,
  21             'categories': list,  # NSFW
  22             'thumbnail': 're:https?://.*\.jpg$',
  23             'age_limit': 18,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         video_url = self._html_search_regex(
  34             r'<source src="([^"]+)"', webpage, 'video URL')
  35
  36         title = self._html_search_regex(
  37             r'<title>([^<]+)\s*-\s*Free', webpage, 'title')
  38
  39         thumbnail = self._html_search_regex(
  40             r'poster="([^"]+)"',
  41             webpage, 'thumbnail', fatal=False)
  42
  43         like_count = str_to_int(self._html_search_regex(
  44             r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
  45             webpage, 'like count', fatal=False))
  46         dislike_count = str_to_int(self._html_search_regex(
  47             r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
  48             webpage, 'like count', fatal=False))
  49         comment_count = str_to_int(self._html_search_regex(
  50             r'<span class="comments_count">([\d,\.]+)</span>',
  51             webpage, 'comment count', fatal=False))
  52
  53         cats_str = self._html_search_regex(
  54             r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
  55         categories = None if cats_str is None else cats_str.split(' ')
  56
  57         return {
  58             'id': video_id,
  59             'url': video_url,
  60             'title': title,
  61             'thumbnail': thumbnail,
  62             'like_count': like_count,
  63             'dislike_count': dislike_count,
  64             'comment_count': comment_count,
  65             'categories': categories,
  66             'age_limit': self._rta_search(webpage),
  67         }