paradizelost/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[yourporn] Fix extraction (closes #21645, closes #22255, closes #23459)

Browse Source
This commit is contained in:
Moritz Patelscheck 2019-12-20 00:02:39 +01:00 committed by Sergey M․
parent 14bb191634
commit bfdc8340c9
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 14 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
youtube_dl/extractor/yourporn.py
View File

@ -1,6 +1,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str
from ..utils import ( from ..utils import (
parse_duration, parse_duration,
urljoin, urljoin,
@ -8,9 +9,9 @@ from ..utils import (
class YourPornIE(InfoExtractor): class YourPornIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:yourporn\.sexy|sxyprn\.com)/post/(?P<id>[^/?#&.]+)' _VALID_URL = r'https?://(?:www\.)?sxyprn\.com/post/(?P<id>[^/?#&.]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html', 'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
'md5': '6f8682b6464033d87acaa7a8ff0c092e', 'md5': '6f8682b6464033d87acaa7a8ff0c092e',
'info_dict': { 'info_dict': {
'id': '57ffcb2e1179b', 'id': '57ffcb2e1179b',
@ -33,11 +34,19 @@ class YourPornIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_url = urljoin(url, self._parse_json( parts = self._parse_json(
self._search_regex( self._search_regex(
r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info', r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
group='data'), group='data'),
video_id)[video_id]).replace('/cdn/', '/cdn5/') video_id)[video_id].split('/')
num = 0
for c in parts[6] + parts[7]:
if c.isnumeric():
num += int(c)
parts[5] = compat_str(int(parts[5]) - num)
parts[1] += '8'
video_url = urljoin(url, '/'.join(parts))
title = (self._search_regex( title = (self._search_regex(
r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
@ -54,4 +63,5 @@ class YourPornIE(InfoExtractor):
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'duration': duration, 'duration': duration,
'age_limit': 18, 'age_limit': 18,
'ext': 'mp4',
} }