youtube-dl/youtube_dl/extractor/porn91.py

79 lines
2.6 KiB
Python
Raw Normal View History

# encoding: utf-8
from __future__ import unicode_literals
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_urlencode,
)
from .common import InfoExtractor
2015-05-31 01:20:37 +09:00
from ..utils import (
parse_duration,
int_or_none,
2015-05-31 01:26:12 +09:00
ExtractorError,
2015-05-31 01:20:37 +09:00
)
class Porn91IE(InfoExtractor):
IE_NAME = '91porn'
_VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)'
_TEST = {
2015-05-31 00:35:55 +09:00
'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
'md5': '6df8f6d028bc8b14f5dbd73af742fb20',
'info_dict': {
'id': '7e42283b4f5ab36da134',
'title': '18岁大一漂亮学妹水嫩性感再爽一次',
2015-05-31 01:20:37 +09:00
'ext': 'mp4',
'duration': 431,
2015-08-09 00:30:57 +09:00
'age_limit': 18,
2015-05-31 00:35:55 +09:00
}
}
def _real_extract(self, url):
2015-05-31 01:03:19 +09:00
video_id = self._match_id(url)
self._set_cookie('91porn.com', 'language', 'cn_CN')
2016-03-20 05:35:48 +09:00
webpage = self._download_webpage(
'http://91porn.com/view_video.php?viewkey=%s' % video_id, video_id)
2015-05-31 01:26:12 +09:00
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)
2015-05-28 02:37:24 +09:00
title = self._search_regex(
2015-05-31 01:03:19 +09:00
r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
2015-05-28 02:37:24 +09:00
title = title.replace('\n', '')
# get real url
2015-05-31 01:03:19 +09:00
file_id = self._search_regex(
r'so.addVariable\(\'file\',\'(\d+)\'', webpage, 'file id')
sec_code = self._search_regex(
r'so.addVariable\(\'seccode\',\'([^\']+)\'', webpage, 'sec code')
max_vid = self._search_regex(
r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage, 'max vid')
url_params = compat_urllib_parse_urlencode({
2015-05-31 01:03:19 +09:00
'VID': file_id,
'mp4': '1',
2015-05-31 01:03:19 +09:00
'seccode': sec_code,
'max_vid': max_vid,
})
2015-05-31 01:03:19 +09:00
info_cn = self._download_webpage(
'http://91porn.com/getfile.php?' + url_params, video_id,
2016-03-20 05:35:48 +09:00
'Downloading real video url')
video_url = compat_urllib_parse_unquote(self._search_regex(
r'file=([^&]+)&', info_cn, 'url'))
2015-05-31 01:20:37 +09:00
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))
2015-05-31 01:03:19 +09:00
return {
'id': video_id,
'title': title,
'url': video_url,
2015-05-31 01:20:37 +09:00
'duration': duration,
'comment_count': comment_count,
2015-08-09 00:30:57 +09:00
'age_limit': self._rta_search(webpage),
}