yt_dlp/extractor/drtuber.py

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