2016-10-02 20:39:18 +09:00
|
|
|
|
# coding: utf-8
|
2015-05-28 01:37:00 +09:00
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
2022-04-10 22:19:35 +09:00
|
|
|
|
import re
|
|
|
|
|
|
2015-05-28 01:37:00 +09:00
|
|
|
|
from .common import InfoExtractor
|
2022-04-10 22:19:35 +09:00
|
|
|
|
from ..compat import (
|
|
|
|
|
compat_urllib_parse_unquote,
|
|
|
|
|
)
|
2015-05-31 01:20:37 +09:00
|
|
|
|
from ..utils import (
|
2022-04-10 22:19:35 +09:00
|
|
|
|
clean_html,
|
|
|
|
|
extract_attributes,
|
|
|
|
|
get_elements_by_class,
|
2015-05-31 01:20:37 +09:00
|
|
|
|
parse_duration,
|
2015-05-31 01:26:12 +09:00
|
|
|
|
ExtractorError,
|
2022-04-10 22:19:35 +09:00
|
|
|
|
str_to_int,
|
|
|
|
|
strip_or_none,
|
|
|
|
|
unified_strdate,
|
2015-05-31 01:20:37 +09:00
|
|
|
|
)
|
2015-05-28 01:37:00 +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',
|
2022-04-10 22:19:35 +09:00
|
|
|
|
'md5': 'd869db281402e0ef4ddef3c38b866f86',
|
2015-05-31 00:35:55 +09:00
|
|
|
|
'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,
|
2022-04-10 22:19:35 +09:00
|
|
|
|
'upload_date': '20150520',
|
|
|
|
|
'uploader': '千岁九王爷',
|
2015-05-31 00:35:55 +09:00
|
|
|
|
}
|
2015-05-28 01:37:00 +09:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2015-05-31 01:03:19 +09:00
|
|
|
|
video_id = self._match_id(url)
|
2022-04-19 12:05:23 +09:00
|
|
|
|
# set language for page to be extracted
|
2015-05-28 01:37:00 +09:00
|
|
|
|
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)
|
|
|
|
|
|
2022-04-10 22:19:35 +09:00
|
|
|
|
title = self._html_search_regex(
|
|
|
|
|
r'(?s)<title\b[^>]*>\s*(.+?)\s*(?:Chinese\s+homemade\s+video\s*)?</title', webpage, 'title')
|
2015-05-28 01:37:00 +09:00
|
|
|
|
|
2019-07-14 04:57:44 +09:00
|
|
|
|
video_link_url = self._search_regex(
|
2022-04-10 22:19:35 +09:00
|
|
|
|
r'''document\s*\.\s*write\s*\(\s*strencode2\s*\((?P<q>"|')(?P<enc_str>[%\da-fA-F]+)(?P=q)\s*\)''',
|
|
|
|
|
webpage, 'video link', group='enc_str')
|
|
|
|
|
video_link_url = compat_urllib_parse_unquote(video_link_url)
|
2019-07-14 04:57:44 +09:00
|
|
|
|
|
2022-04-10 22:19:35 +09:00
|
|
|
|
info_dict = self._parse_html5_media_entries(url, '<video>%s</video>' % (video_link_url, ), video_id)[0]
|
2015-05-28 01:37:00 +09:00
|
|
|
|
|
2022-04-19 12:05:23 +09:00
|
|
|
|
# extract various fields in <tag class=info>Name: value</tag>
|
2022-04-10 22:19:35 +09:00
|
|
|
|
FIELD_MAP = {
|
2022-04-19 12:05:23 +09:00
|
|
|
|
# cn_CN name: (yt-dl key, value parser, en name)
|
2022-04-10 22:19:35 +09:00
|
|
|
|
'时长': ('duration', parse_duration, 'Runtime', ),
|
|
|
|
|
'查看': ('view_count', str_to_int, 'Views', ),
|
|
|
|
|
'留言': ('comment_count', str_to_int, 'Comments', ),
|
|
|
|
|
'收藏': ('like_count', str_to_int, 'Favorites', ),
|
|
|
|
|
'添加时间': ('upload_date', unified_strdate, 'Added', ),
|
|
|
|
|
# same as title for en, not description for cn_CN
|
|
|
|
|
'__ignore__': ('description', strip_or_none, 'Description', ),
|
|
|
|
|
'作者': ('uploader', strip_or_none, 'From', ),
|
|
|
|
|
}
|
2022-04-19 12:05:23 +09:00
|
|
|
|
# yt-dl's original implementation of get_elements_by_class() uses regex
|
|
|
|
|
# yt-dlp uses an actual HTML parser, and can be confused by bad HTML fragments
|
|
|
|
|
for elt in get_elements_by_class(
|
|
|
|
|
'info',
|
|
|
|
|
# concatenate <span>s ...
|
|
|
|
|
re.sub(r'(?i)</span>\s*<span\b[^>]*?>', '',
|
|
|
|
|
# ... and strip out possibly unbalanced <font> for yt-dlp
|
|
|
|
|
re.sub(r'(?i)(?:<font\b[^>]*?>|</font\s*>)', '', webpage))) or []:
|
2022-04-10 22:19:35 +09:00
|
|
|
|
elt = re.split(r':\s*', clean_html(elt), 1)
|
|
|
|
|
if len(elt) != 2 or elt[1] == '':
|
|
|
|
|
continue
|
|
|
|
|
parm = FIELD_MAP.get(elt[0].strip())
|
|
|
|
|
if parm and elt[1] is not None:
|
|
|
|
|
info_dict[parm[0]] = parm[1](elt[1]) if parm[1] else elt[1]
|
2015-05-31 01:20:37 +09:00
|
|
|
|
|
2022-04-10 22:19:35 +09:00
|
|
|
|
thumbnail = extract_attributes(
|
|
|
|
|
self._search_regex(
|
|
|
|
|
r'''(<video\b[^>]*\bid\s*=\s*(?P<q>"|')player_one(?P=q)[^>]*>)''',
|
|
|
|
|
webpage, 'poster', default='')).get('poster')
|
2015-05-31 01:20:37 +09:00
|
|
|
|
|
2017-04-22 22:16:36 +09:00
|
|
|
|
info_dict.update({
|
2015-05-28 01:37:00 +09:00
|
|
|
|
'id': video_id,
|
|
|
|
|
'title': title,
|
2015-08-09 00:30:57 +09:00
|
|
|
|
'age_limit': self._rta_search(webpage),
|
2022-04-10 22:19:35 +09:00
|
|
|
|
'thumbnail': thumbnail,
|
2017-04-22 22:16:36 +09:00
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
return info_dict
|