MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 15:16:52 +01:00
Code Issues Projects Releases Wiki Activity

[porn91] Fix extraction (closes #12814)

Browse Source
This commit is contained in:
Yen Chi Hsuan 2017-04-22 21:16:36 +08:00
parent cb2520802d
commit 3110bb937d
No known key found for this signature in database
GPG Key ID: 7F902A182457CA23
2 changed files with 7 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ChangeLog
View File

@ -1,6 +1,7 @@
version <unreleased> version <unreleased>
Extractors Extractors
* [porn91] Fix extraction (#12814)
+ [generic] Support Brightcove videos in <iframe> (#12482) + [generic] Support Brightcove videos in <iframe> (#12482)
+ [brightcove] Support URLs with bcpid instead of playerID (#12482) + [brightcove] Support URLs with bcpid instead of playerID (#12482)

32
youtube_dl/extractor/porn91.py
View File

@ -1,10 +1,6 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_urlencode,
)
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
parse_duration, parse_duration,
@ -19,7 +15,7 @@ class Porn91IE(InfoExtractor):
_TEST = { _TEST = {
'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134', 'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
'md5': '6df8f6d028bc8b14f5dbd73af742fb20', 'md5': '7fcdb5349354f40d41689bd0fa8db05a',
'info_dict': { 'info_dict': {
'id': '7e42283b4f5ab36da134', 'id': '7e42283b4f5ab36da134',
'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！', 'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！',
@ -43,24 +39,7 @@ def _real_extract(self, url):
r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title') r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
title = title.replace('\n', '') title = title.replace('\n', '')
# get real url info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
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( duration = parse_duration(self._search_regex(
r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False)) r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
@ -68,11 +47,12 @@ def _real_extract(self, url):
comment_count = int_or_none(self._search_regex( comment_count = int_or_none(self._search_regex(
r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False)) r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False))
return { info_dict.update({
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': video_url,
'duration': duration, 'duration': duration,
'comment_count': comment_count, 'comment_count': comment_count,
'age_limit': self._rta_search(webpage), 'age_limit': self._rta_search(webpage),
} })
return info_dict