diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2013-06-23 22:25:46 +0200 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2013-06-23 22:25:46 +0200 |
commit | 01c10ca26ed5e5df0b975a3421f1186e5b94d925 (patch) | |
tree | ef1ddf805330c2c28ab6a4d0064d15f2224e29c2 /youtube_dl/extractor | |
parent | 45aef472817b33194a4b59f345dbaf08701f65d3 (diff) |
[VBox7] move into own file
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/vbox7.py | 46 |
1 files changed, 46 insertions, 0 deletions
diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py new file mode 100644 index 000000000..2f3ce46e8 --- /dev/null +++ b/youtube_dl/extractor/vbox7.py @@ -0,0 +1,46 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, + + ExtractorError, +) + + +class Vbox7IE(InfoExtractor): + """Information Extractor for Vbox7""" + _VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)' + + def _real_extract(self,url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + video_id = mobj.group(1) + + redirect_page, urlh = self._download_webpage_handle(url, video_id) + new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location') + redirect_url = urlh.geturl() + new_location + webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page') + + title = self._html_search_regex(r'<title>(.*)</title>', + webpage, u'title').split('/')[0].strip() + + ext = "flv" + info_url = "http://vbox7.com/play/magare.do" + data = compat_urllib_parse.urlencode({'as3':'1','vid':video_id}) + info_request = compat_urllib_request.Request(info_url, data) + info_request.add_header('Content-Type', 'application/x-www-form-urlencoded') + info_response = self._download_webpage(info_request, video_id, u'Downloading info webpage') + if info_response is None: + raise ExtractorError(u'Unable to extract the media url') + (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&')) + + return [{ + 'id': video_id, + 'url': final_url, + 'ext': ext, + 'title': title, + 'thumbnail': thumbnail_url, + }] |