1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-05 02:32:44 +01:00
yt-dlp/yt_dlp/extractor/porn91.py
pukkandan 86e5f3ed2e
[cleanup] Upgrade syntax
Using https://github.com/asottile/pyupgrade

1. `__future__` imports and `coding: utf-8` were removed
2. Files were rewritten with `pyupgrade --py36-plus --keep-percent-format`
3. f-strings were cherry-picked from `pyupgrade --py36-plus`

Extractors are left untouched (except removing header) to avoid unnecessary merge conflicts
2022-04-12 05:32:51 +05:30

61 lines
2.0 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.

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': '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):
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', '')
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]
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,
'duration': duration,
'comment_count': comment_count,
'age_limit': self._rta_search(webpage),
})
return info_dict