github/yt-dlp
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-29 14:26:24 +01:00
Code Releases Activity

[youporn] Add support form generic embeds

Browse Source
This commit is contained in:
Sergey M․ 2020-04-05 20:56:14 +07:00
parent 8fae1a04eb
commit 52c4c51556
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
2 changed files with 23 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
youtube_dl/extractor/generic.py
View File

@ -61,6 +61,7 @@ from .drtuber import DrTuberIE
from .redtube import RedTubeIE from .redtube import RedTubeIE
from .tube8 import Tube8IE from .tube8 import Tube8IE
from .spankwire import SpankwireIE from .spankwire import SpankwireIE
from .youporn import YouPornIE
from .vimeo import VimeoIE from .vimeo import VimeoIE
from .dailymotion import DailymotionIE from .dailymotion import DailymotionIE
from .dailymail import DailyMailIE from .dailymail import DailyMailIE
@ -2721,6 +2722,11 @@ class GenericIE(InfoExtractor):
if spankwire_urls: if spankwire_urls:
return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key()) return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
# Look for embedded YouPorn player
youporn_urls = YouPornIE._extract_urls(webpage)
if youporn_urls:
return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
# Look for embedded Tvigle player # Look for embedded Tvigle player
mobj = re.search( mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage) r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)

23
youtube_dl/extractor/youporn.py
View File

@ -5,7 +5,6 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
sanitized_Request,
str_to_int, str_to_int,
unescapeHTML, unescapeHTML,
unified_strdate, unified_strdate,
@ -15,7 +14,7 @@ from ..aes import aes_decrypt_text
class YouPornIE(InfoExtractor): class YouPornIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
_TESTS = [{ _TESTS = [{
'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
'md5': '3744d24c50438cf5b6f6d59feb5055c2', 'md5': '3744d24c50438cf5b6f6d59feb5055c2',
@ -57,16 +56,28 @@ class YouPornIE(InfoExtractor):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
}, {
'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/',
'only_matching': True,
}, {
'url': 'http://www.youporn.com/watch/505835',
'only_matching': True,
}] }]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)',
webpage)
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
display_id = mobj.group('display_id') display_id = mobj.group('display_id') or video_id
request = sanitized_Request(url) webpage = self._download_webpage(
request.add_header('Cookie', 'age_verified=1') 'http://www.youporn.com/watch/%s' % video_id, display_id,
webpage = self._download_webpage(request, display_id) headers={'Cookie': 'age_verified=1'})
title = self._html_search_regex( title = self._html_search_regex(
r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>', r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',