yt_dlp/extractor/drtuber.py

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