-# encoding: utf-8
+# coding: utf-8
from __future__ import unicode_literals
-import re
-
-from ..compat import compat_urllib_parse
from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+ parse_duration,
+ int_or_none,
+ ExtractorError,
+)
class Porn91IE(InfoExtractor):
_VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)'
_TEST = {
- '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!',
- 'ext': 'mp4'
- }
+ 'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
+ 'md5': '7fcdb5349354f40d41689bd0fa8db05a',
+ 'info_dict': {
+ 'id': '7e42283b4f5ab36da134',
+ 'title': '18岁大一漂亮学妹,水嫩性感,再爽一次!',
+ 'ext': 'mp4',
+ 'duration': 431,
+ 'age_limit': 18,
+ }
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id
+ video_id = self._match_id(url)
self._set_cookie('91porn.com', 'language', 'cn_CN')
- webpage = self._download_webpage(url, video_id, "get HTML content")
+
+ webpage = self._download_webpage(
+ 'http://91porn.com/view_video.php?viewkey=%s' % video_id, video_id)
+
+ 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)
+
title = self._search_regex(
- r'<div id="viewvideo-title">(?P<title>.+?)</div>',
- webpage, 'title', flags=re.DOTALL)
+ r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
title = title.replace('\n', '')
- # get real url
- n1 = self._search_regex(
- r'so.addVariable\(\'file\',\'(?P<n1>\d+)\'', webpage, 'n1')
- n2 = self._search_regex(
- r'so.addVariable\(\'seccode\',\'(?P<n2>.+?)\'', webpage, 'n2')
- n3 = self._search_regex(
- r'so.addVariable\(\'max_vid\',\'(?P<n3>\d+)\'', webpage, 'n3')
- url_params = compat_urllib_parse.urlencode({
- 'VID': n1,
- 'mp4': '1',
- 'seccode': n2,
- 'max_vid': n3,
- })
- t_url = 'http://91porn.com/getfile.php?' + url_params
- info_cn = self._download_webpage(t_url, video_id, "get real video_url")
- video_url = self._search_regex(r'file=(?P<url>http.+?)&', info_cn, 'url')
+ info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
+
+ 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))
- # construct info
- info = {
+ info_dict.update({
'id': video_id,
'title': title,
- 'url': video_url,
- }
+ 'duration': duration,
+ 'comment_count': comment_count,
+ 'age_limit': self._rta_search(webpage),
+ })
- return info
+ return info_dict