yt_dlp/extractor/rule34video.py

   1 import re
   2
   3 from ..utils import parse_duration, unescapeHTML
   4 from .common import InfoExtractor
   5
   6
   7 class Rule34VideoIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?rule34video\.com/videos/(?P<id>\d+)'
   9     _TESTS = [
  10         {
  11             'url': 'https://rule34video.com/videos/3065157/shot-it-mmd-hmv/',
  12             'md5': 'ffccac2c23799dabbd192621ae4d04f3',
  13             'info_dict': {
  14                 'id': '3065157',
  15                 'ext': 'mp4',
  16                 'title': 'Shot It-(mmd hmv)',
  17                 'thumbnail': 'https://rule34video.com/contents/videos_screenshots/3065000/3065157/preview.jpg',
  18                 'duration': 347.0,
  19                 'age_limit': 18,
  20                 'tags': 'count:14'
  21             }
  22         },
  23         {
  24             'url': 'https://rule34video.com/videos/3065296/lara-in-trouble-ep-7-wildeerstudio/',
  25             'md5': '6bb5169f9f6b38cd70882bf2e64f6b86',
  26             'info_dict': {
  27                 'id': '3065296',
  28                 'ext': 'mp4',
  29                 'title': 'Lara in Trouble Ep. 7 [WildeerStudio]',
  30                 'thumbnail': 'https://rule34video.com/contents/videos_screenshots/3065000/3065296/preview.jpg',
  31                 'duration': 938.0,
  32                 'age_limit': 18,
  33                 'tags': 'count:50'
  34             }
  35         },
  36     ]
  37
  38     def _real_extract(self, url):
  39         video_id = self._match_id(url)
  40         webpage = self._download_webpage(url, video_id)
  41
  42         formats = []
  43
  44         for mobj in re.finditer(r'<a[^>]+href="(?P<video_url>[^"]+download=true[^"]+)".*>(?P<ext>[^\s]+) (?P<quality>[^<]+)p</a>', webpage):
  45             url, ext, quality = mobj.groups()
  46             formats.append({
  47                 'url': url,
  48                 'ext': ext.lower(),
  49                 'quality': quality,
  50             })
  51
  52         title = self._html_extract_title(webpage)
  53         thumbnail = self._html_search_regex(r'preview_url:\s+\'([^\']+)\'', webpage, 'thumbnail', default=None)
  54         duration = self._html_search_regex(r'"icon-clock"></i>\s+<span>((?:\d+:?)+)', webpage, 'duration', default=None)
  55
  56         return {
  57             'id': video_id,
  58             'formats': formats,
  59             'title': title,
  60             'thumbnail': thumbnail,
  61             'duration': parse_duration(duration),
  62             'age_limit': 18,
  63             'tags': list(map(unescapeHTML, re.findall(
  64                 r'<a class="tag_item"[^>]+\bhref="https://rule34video\.com/tags/\d+/"[^>]*>(?P<tag>[^>]*)</a>', webpage))),
  65         }