1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-25 19:25:50 +01:00
youtube-dl/youtube_dl/extractor/porn91.py
Sergey M․ 15707c7e02 [compat] Add compat_urllib_parse_urlencode and eliminate encode_dict
encode_dict functionality has been improved and moved directly into compat_urllib_parse_urlencode
All occurrences of compat_urllib_parse.urlencode throughout the codebase have been replaced by compat_urllib_parse_urlencode

Closes #8974
2016-03-26 01:46:57 +06:00

79 lines
2.6 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# encoding: utf-8
from __future__ import unicode_literals
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_urlencode,
)
from .common import InfoExtractor
from ..utils import (
parse_duration,
int_or_none,
ExtractorError,
)
class Porn91IE(InfoExtractor):
IE_NAME = '91porn'
_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',
'duration': 431,
'age_limit': 18,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
self._set_cookie('91porn.com', 'language', 'cn_CN')
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">([^<]+)</div>', webpage, 'title')
title = title.replace('\n', '')
# get real url
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({
'VID': file_id,
'mp4': '1',
'seccode': sec_code,
'max_vid': max_vid,
})
info_cn = self._download_webpage(
'http://91porn.com/getfile.php?' + url_params, video_id,
'Downloading real video url')
video_url = compat_urllib_parse_unquote(self._search_regex(
r'file=([^&]+)&', info_cn, 'url'))
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))
return {
'id': video_id,
'title': title,
'url': video_url,
'duration': duration,
'comment_count': comment_count,
'age_limit': self._rta_search(webpage),
}