xZero707/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-24 11:51:11 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1676 from rzhxeo/extremetube

Browse Source 
Add support for http://www.extremetube.com
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-11-03 03:25:46 -08:00
commit 9ac6a01aaf
2 changed files with 51 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

@ -40,6 +40,7 @@
from .eighttracks import EightTracksIE from .eighttracks import EightTracksIE
from .escapist import EscapistIE from .escapist import EscapistIE
from .exfm import ExfmIE from .exfm import ExfmIE
from .extremetube import ExtremeTubeIE
from .facebook import FacebookIE from .facebook import FacebookIE
from .faz import FazIE from .faz import FazIE
from .fktv import ( from .fktv import (

50
youtube_dl/extractor/extremetube.py Normal file
View File

@ -0,0 +1,50 @@
import os
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
)
class ExtremeTubeIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
_TEST = {
u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
u'file': u'652431.mp4',
u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0',
u'info_dict': {
u"title": u"Music Video 14 british euro brit european cumshots swallow",
u"uploader": u"unknown",
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'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, u'title')
uploader = self._html_search_regex(r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, u'uploader', fatal=False)
video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, u'video_url'))
path = compat_urllib_parse_urlparse( video_url ).path
extension = os.path.splitext( path )[1][1:]
format = path.split('/')[5].split('_')[:2]
format = "-".join( format )
return {
'id': video_id,
'title': video_title,
'uploader': uploader,
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
'age_limit': 18,
}