yt-dlp/yt_dlp/extractor/porn91.py

61 lines
2.0 KiB
Python
Raw Normal View History

from .common import InfoExtractor
2015-05-30 18:20:37 +02:00
from ..utils import (
parse_duration,
int_or_none,
2015-05-30 18:26:12 +02:00
ExtractorError,
2015-05-30 18:20:37 +02:00
)
class Porn91IE(InfoExtractor):
IE_NAME = '91porn'
_VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)'
_TEST = {
2015-05-30 17:35:55 +02:00
'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
'md5': '7fcdb5349354f40d41689bd0fa8db05a',
2015-05-30 17:35:55 +02:00
'info_dict': {
'id': '7e42283b4f5ab36da134',
'title': '18岁大一漂亮学妹水嫩性感再爽一次',
2015-05-30 18:20:37 +02:00
'ext': 'mp4',
'duration': 431,
2015-08-08 17:30:57 +02:00
'age_limit': 18,
2015-05-30 17:35:55 +02:00
}
}
def _real_extract(self, url):
2015-05-30 18:03:19 +02:00
video_id = self._match_id(url)
self._set_cookie('91porn.com', 'language', 'cn_CN')
2016-03-19 21:35:48 +01:00
webpage = self._download_webpage(
'http://91porn.com/view_video.php?viewkey=%s' % video_id, video_id)
2015-05-30 18:26:12 +02:00
if '作为游客你每天只可观看10个视频' in webpage:
raise ExtractorError('91 Porn says: Daily limit 10 videos exceeded', expected=True)
2015-05-27 19:37:24 +02:00
title = self._search_regex(
2015-05-30 18:03:19 +02:00
r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
2015-05-27 19:37:24 +02:00
title = title.replace('\n', '')
2019-07-13 21:57:44 +02:00
video_link_url = self._search_regex(
r'<textarea[^>]+id=["\']fm-video_link[^>]+>([^<]+)</textarea>',
webpage, 'video link')
videopage = self._download_webpage(video_link_url, video_id)
info_dict = self._parse_html5_media_entries(url, videopage, video_id)[0]
2015-05-30 18:20:37 +02:00
duration = parse_duration(self._search_regex(
r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
comment_count = int_or_none(self._search_regex(
r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False))
info_dict.update({
'id': video_id,
'title': title,
2015-05-30 18:20:37 +02:00
'duration': duration,
'comment_count': comment_count,
2015-08-08 17:30:57 +02:00
'age_limit': self._rta_search(webpage),
})
return info_dict