yt_dlp/extractor/rule34video.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3 import re
   4
   5 from ..utils import parse_duration
   6 from .common import InfoExtractor
   7
   8
   9 class Rule34VideoIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?rule34video\.com/videos/(?P<id>\d+)'
  11     _TESTS = [
  12         {
  13             'url': 'https://rule34video.com/videos/3065157/shot-it-mmd-hmv/',
  14             'md5': 'ffccac2c23799dabbd192621ae4d04f3',
  15             'info_dict': {
  16                 'id': '3065157',
  17                 'ext': 'mp4',
  18                 'title': 'Shot It-(mmd hmv)',
  19                 'thumbnail': 'https://rule34video.com/contents/videos_screenshots/3065000/3065157/preview.jpg',
  20                 'duration': 347.0,
  21                 'age_limit': 18
  22             }
  23         },
  24         {
  25             'url': 'https://rule34video.com/videos/3065296/lara-in-trouble-ep-7-wildeerstudio/',
  26             'md5': '6bb5169f9f6b38cd70882bf2e64f6b86',
  27             'info_dict': {
  28                 'id': '3065296',
  29                 'ext': 'mp4',
  30                 'title': 'Lara in Trouble Ep. 7 [WildeerStudio]',
  31                 'thumbnail': 'https://rule34video.com/contents/videos_screenshots/3065000/3065296/preview.jpg',
  32                 'duration': 938.0,
  33                 'age_limit': 18
  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         self._sort_formats(formats)
  57
  58         return {
  59             'id': video_id,
  60             'formats': formats,
  61             'title': title,
  62             'thumbnail': thumbnail,
  63             'duration': parse_duration(duration),
  64             'age_limit': 18
  65         }