Raphaël G. Git Repositories - youtubedl/blob - 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<display_id>[\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             'display_id': 'hot-perky-blonde-naked-golf',
  17             'ext': 'mp4',
  18             'title': 'hot perky blonde naked golf',
  19             'like_count': int,
  20             'dislike_count': int,
  21             'comment_count': int,
  22             'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
  23             'thumbnail': 're:https?://.*\.jpg$',
  24             'age_limit': 18,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31         display_id = mobj.group('display_id')
  32
  33         webpage = self._download_webpage(url, display_id)
  34
  35         video_url = self._html_search_regex(
  36             r'<source src="([^"]+)"', webpage, 'video URL')
  37
  38         title = self._html_search_regex(
  39             [r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'],
  40             webpage, 'title')
  41
  42         thumbnail = self._html_search_regex(
  43             r'poster="([^"]+)"',
  44             webpage, 'thumbnail', fatal=False)
  45
  46         def extract_count(id_, name):
  47             return str_to_int(self._html_search_regex(
  48                 r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
  49                 webpage, '%s count' % name, fatal=False))
  50
  51         like_count = extract_count('rate_likes', 'like')
  52         dislike_count = extract_count('rate_dislikes', 'dislike')
  53         comment_count = extract_count('comments_count', 'comment')
  54
  55         cats_str = self._search_regex(
  56             r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False)
  57         categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
  58
  59         return {
  60             'id': video_id,
  61             'display_id': display_id,
  62             'url': video_url,
  63             'title': title,
  64             'thumbnail': thumbnail,
  65             'like_count': like_count,
  66             'dislike_count': dislike_count,
  67             'comment_count': comment_count,
  68             'categories': categories,
  69             'age_limit': self._rta_search(webpage),
  70         }