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     int_or_none,
   8     NO_DEFAULT,
   9     parse_duration,
  10     str_to_int,
  11 )
  12
  13
  14 class DrTuberIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:(?:www|m)\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
  16     _TESTS = [{
  17         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
  18         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
  19         'info_dict': {
  20             'id': '1740434',
  21             'display_id': 'hot-perky-blonde-naked-golf',
  22             'ext': 'mp4',
  23             'title': 'hot perky blonde naked golf',
  24             'like_count': int,
  25             'comment_count': int,
  26             'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
  27             'thumbnail': r're:https?://.*\.jpg$',
  28             'age_limit': 18,
  29         }
  30     }, {
  31         'url': 'http://www.drtuber.com/embed/489939',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://m.drtuber.com/video/3893529/lingerie-blowjob-from-beautiful-teen',
  35         'only_matching': True,
  36     }]
  37
  38     @staticmethod
  39     def _extract_urls(webpage):
  40         return re.findall(
  41             r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)',
  42             webpage)
  43
  44     def _real_extract(self, url):
  45         mobj = re.match(self._VALID_URL, url)
  46         video_id = mobj.group('id')
  47         display_id = mobj.group('display_id') or video_id
  48
  49         webpage = self._download_webpage(
  50             'http://www.drtuber.com/video/%s' % video_id, display_id)
  51
  52         video_data = self._download_json(
  53             'http://www.drtuber.com/player_config_json/', video_id, query={
  54                 'vid': video_id,
  55                 'embed': 0,
  56                 'aid': 0,
  57                 'domain_id': 0,
  58             })
  59
  60         formats = []
  61         for format_id, video_url in video_data['files'].items():
  62             if video_url:
  63                 formats.append({
  64                     'format_id': format_id,
  65                     'quality': 2 if format_id == 'hq' else 1,
  66                     'url': video_url
  67                 })
  68         self._sort_formats(formats)
  69
  70         duration = int_or_none(video_data.get('duration')) or parse_duration(
  71             video_data.get('duration_format'))
  72
  73         title = self._html_search_regex(
  74             (r'<h1[^>]+class=["\']title[^>]+>([^<]+)',
  75              r'<title>([^<]+)\s*@\s+DrTuber',
  76              r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
  77              r'<p[^>]+class="title_substrate">([^<]+)</p>',
  78              r'<title>([^<]+) - \d+'),
  79             webpage, 'title')
  80
  81         thumbnail = self._html_search_regex(
  82             r'poster="([^"]+)"',
  83             webpage, 'thumbnail', fatal=False)
  84
  85         def extract_count(id_, name, default=NO_DEFAULT):
  86             return str_to_int(self._html_search_regex(
  87                 r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
  88                 webpage, '%s count' % name, default=default, fatal=False))
  89
  90         like_count = extract_count('rate_likes', 'like')
  91         dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
  92         comment_count = extract_count('comments_count', 'comment')
  93
  94         cats_str = self._search_regex(
  95             r'<div[^>]+class="categories_list">(.+?)</div>',
  96             webpage, 'categories', fatal=False)
  97         categories = [] if not cats_str else re.findall(
  98             r'<a title="([^"]+)"', cats_str)
  99
 100         return {
 101             'id': video_id,
 102             'display_id': display_id,
 103             'formats': formats,
 104             'title': title,
 105             'thumbnail': thumbnail,
 106             'like_count': like_count,
 107             'dislike_count': dislike_count,
 108             'comment_count': comment_count,
 109             'categories': categories,
 110             'age_limit': self._rta_search(webpage),
 111             'duration': duration,
 112         }