From dcc2a706ef7df65839aa40ce5fda61f8cea36645 Mon Sep 17 00:00:00 2001 From: rzhxeo Date: Mon, 28 Oct 2013 19:23:48 +0100 Subject: [PATCH] Add support for http://www.xtube.com --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/xtube.py | 54 ++++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+) create mode 100644 youtube_dl/extractor/xtube.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 0d933986f..7efd097e4 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -149,6 +149,7 @@ from .worldstarhiphop import WorldStarHipHopIE from .xhamster import XHamsterIE from .xnxx import XNXXIE from .xvideos import XVideosIE +from .xtube import XTubeIE from .yahoo import YahooIE, YahooSearchIE from .youjizz import YouJizzIE from .youku import YoukuIE diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py new file mode 100644 index 000000000..7d06a7021 --- /dev/null +++ b/youtube_dl/extractor/xtube.py @@ -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\.)?(?Pxtube\.com/watch\.php\?v=(?P[^/?&]+))' + _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'
([^<]+)', 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, + }