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 (
   7     NO_DEFAULT,
   8     str_to_int,
   9 )
  10
  11
  12 class DrTuberIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
  14     _TESTS = [{
  15         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
  16         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
  17         'info_dict': {
  18             'id': '1740434',
  19             'display_id': 'hot-perky-blonde-naked-golf',
  20             'ext': 'mp4',
  21             'title': 'hot perky blonde naked golf',
  22             'like_count': int,
  23             'comment_count': int,
  24             'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
  25             'thumbnail': r're:https?://.*\.jpg$',
  26             'age_limit': 18,
  27         }
  28     }, {
  29         'url': 'http://www.drtuber.com/embed/489939',
  30         'only_matching': True,
  31     }]
  32
  33     @staticmethod
  34     def _extract_urls(webpage):
  35         return re.findall(
  36             r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)',
  37             webpage)
  38
  39     def _real_extract(self, url):
  40         mobj = re.match(self._VALID_URL, url)
  41         video_id = mobj.group('id')
  42         display_id = mobj.group('display_id') or video_id
  43
  44         webpage = self._download_webpage(
  45             'http://www.drtuber.com/video/%s' % video_id, display_id)
  46
  47         video_url = self._html_search_regex(
  48             r'<source src="([^"]+)"', webpage, 'video URL')
  49
  50         title = self._html_search_regex(
  51             (r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
  52              r'<p[^>]+class="title_substrate">([^<]+)</p>',
  53              r'<title>([^<]+) - \d+'),
  54             webpage, 'title')
  55
  56         thumbnail = self._html_search_regex(
  57             r'poster="([^"]+)"',
  58             webpage, 'thumbnail', fatal=False)
  59
  60         def extract_count(id_, name, default=NO_DEFAULT):
  61             return str_to_int(self._html_search_regex(
  62                 r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
  63                 webpage, '%s count' % name, default=default, fatal=False))
  64
  65         like_count = extract_count('rate_likes', 'like')
  66         dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
  67         comment_count = extract_count('comments_count', 'comment')
  68
  69         cats_str = self._search_regex(
  70             r'<div[^>]+class="categories_list">(.+?)</div>',
  71             webpage, 'categories', fatal=False)
  72         categories = [] if not cats_str else re.findall(
  73             r'<a title="([^"]+)"', cats_str)
  74
  75         return {
  76             'id': video_id,
  77             'display_id': display_id,
  78             'url': video_url,
  79             'title': title,
  80             'thumbnail': thumbnail,
  81             'like_count': like_count,
  82             'dislike_count': dislike_count,
  83             'comment_count': comment_count,
  84             'categories': categories,
  85             'age_limit': self._rta_search(webpage),
  86         }