yt_dlp/extractor/porn91.py

   1 import urllib.parse
   2 from .common import InfoExtractor
   3 from ..utils import (
   4     determine_ext,
   5     int_or_none,
   6     parse_duration,
   7     remove_end,
   8     unified_strdate,
   9     ExtractorError,
  10 )
  11
  12
  13 class Porn91IE(InfoExtractor):
  14     IE_NAME = '91porn'
  15     _VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/view_video.php\?([^#]+&)?viewkey=(?P<id>\w+)'
  16
  17     _TESTS = [{
  18         'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
  19         'md5': 'd869db281402e0ef4ddef3c38b866f86',
  20         'info_dict': {
  21             'id': '7e42283b4f5ab36da134',
  22             'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！',
  23             'description': 'md5:1ff241f579b07ae936a54e810ad2e891',
  24             'ext': 'mp4',
  25             'duration': 431,
  26             'upload_date': '20150520',
  27             'comment_count': int,
  28             'view_count': int,
  29             'age_limit': 18,
  30         }
  31     }, {
  32         'url': 'https://91porn.com/view_video.php?viewkey=7ef0cf3d362c699ab91c',
  33         'md5': 'f8fd50540468a6d795378cd778b40226',
  34         'info_dict': {
  35             'id': '7ef0cf3d362c699ab91c',
  36             'title': '真实空乘，冲上云霄第二部',
  37             'description': 'md5:618bf9652cafcc66cd277bd96789baea',
  38             'ext': 'mp4',
  39             'duration': 248,
  40             'upload_date': '20221119',
  41             'comment_count': int,
  42             'view_count': int,
  43             'age_limit': 18,
  44         }
  45     }]
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49         self._set_cookie('91porn.com', 'language', 'cn_CN')
  50
  51         webpage = self._download_webpage(
  52             'http://91porn.com/view_video.php?viewkey=%s' % video_id, video_id)
  53
  54         if '视频不存在,可能已经被删除或者被举报为不良内容!' in webpage:
  55             raise ExtractorError('91 Porn says: Video does not exist', expected=True)
  56
  57         daily_limit = self._search_regex(
  58             r'作为游客，你每天只可观看([\d]+)个视频', webpage, 'exceeded daily limit', default=None, fatal=False)
  59         if daily_limit:
  60             raise ExtractorError(f'91 Porn says: Daily limit {daily_limit} videos exceeded', expected=True)
  61
  62         video_link_url = self._search_regex(
  63             r'document\.write\(\s*strencode2\s*\(\s*((?:"[^"]+")|(?:\'[^\']+\'))', webpage, 'video link')
  64         video_link_url = self._search_regex(
  65             r'src=["\']([^"\']+)["\']', urllib.parse.unquote(video_link_url), 'unquoted video link')
  66
  67         formats, subtitles = self._get_formats_and_subtitle(video_link_url, video_id)
  68
  69         return {
  70             'id': video_id,
  71             'title': remove_end(self._html_extract_title(webpage).replace('\n', ''), 'Chinese homemade video').strip(),
  72             'formats': formats,
  73             'subtitles': subtitles,
  74             'upload_date': unified_strdate(self._search_regex(
  75                 r'<span\s+class=["\']title-yakov["\']>(\d{4}-\d{2}-\d{2})</span>', webpage, 'upload_date', fatal=False)),
  76             'description': self._html_search_regex(
  77                 r'<span\s+class=["\']more title["\']>\s*([^<]+)', webpage, 'description', fatal=False),
  78             'duration': parse_duration(self._search_regex(
  79                 r'时长:\s*<span[^>]*>\s*(\d+(?::\d+){1,2})', webpage, 'duration', fatal=False)),
  80             'comment_count': int_or_none(self._search_regex(
  81                 r'留言:\s*<span[^>]*>\s*(\d+)\s*</span>', webpage, 'comment count', fatal=False)),
  82             'view_count': int_or_none(self._search_regex(
  83                 r'热度:\s*<span[^>]*>\s*(\d+)\s*</span>', webpage, 'view count', fatal=False)),
  84             'age_limit': 18,
  85         }
  86
  87     def _get_formats_and_subtitle(self, video_link_url, video_id):
  88         ext = determine_ext(video_link_url)
  89         if ext == 'm3u8':
  90             formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_link_url, video_id, ext='mp4')
  91         else:
  92             formats = [{'url': video_link_url, 'ext': ext}]
  93             subtitles = {}
  94
  95         return formats, subtitles