mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-17 21:59:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add support for http://www.xtube.com

Browse source
This commit is contained in:
rzhxeo 2013-10-28 19:23:48 +01:00
parent 79b3f61228
commit dcc2a706ef
2 changed files with 55 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
youtube_dl/extractor/__init__.py
View file

@ -149,6 +149,7 @@
from .xhamster import XHamsterIE from .xhamster import XHamsterIE
from .xnxx import XNXXIE from .xnxx import XNXXIE
from .xvideos import XVideosIE from .xvideos import XVideosIE
from .xtube import XTubeIE
from .yahoo import YahooIE, YahooSearchIE from .yahoo import YahooIE, YahooSearchIE
from .youjizz import YouJizzIE from .youjizz import YouJizzIE
from .youku import YoukuIE from .youku import YoukuIE

54
youtube_dl/extractor/xtube.py Normal file
View file

@ -0,0 +1,54 @@
import os
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
)
class XTubeIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))'
_TEST = {
u'url': u'http://www.xtube.com/watch.php?v=kVTUy_G222_',
u'file': u'kVTUy_G222_.mp4',
u'md5': u'092fbdd3cbe292c920ef6fc6a8a9cdab',
u'info_dict': {
u"title": u"strange erotica",
u"uploader": u"greenshowers",
u"age_limit": 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(r'<div class="p_5px[^>]*>([^<]+)', webpage, u'title')
video_uploader = self._html_search_regex(r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, u'uploader', fatal=False)
video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, u'description', default=None)
video_url= self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, u'video_url').replace('\\/', '/')
path = compat_urllib_parse_urlparse( video_url ).path
extension = os.path.splitext( path )[1][1:]
format = path.split('/')[5].split('_')[:2]
format[0] += 'p'
format[1] += 'k'
format = "-".join( format )
return {
'id': video_id,
'title': video_title,
'uploader': video_uploader,
'description': video_description,
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
'age_limit': 18,
}