1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/youtube_dl/extractor/hotnewhiphop.py

70 lines
2.3 KiB
Python
Raw Normal View History

2014-01-22 00:55:50 +00:00
from __future__ import unicode_literals
2013-06-27 01:38:48 +00:00
import base64
from .common import InfoExtractor
2014-11-26 11:45:40 +00:00
from ..compat import (
2014-01-22 00:55:50 +00:00
compat_urllib_parse,
compat_urllib_request,
2014-11-26 11:45:40 +00:00
)
from ..utils import (
2014-01-22 00:55:50 +00:00
ExtractorError,
HEADRequest,
)
2013-06-27 01:38:48 +00:00
class HotNewHipHopIE(InfoExtractor):
_VALID_URL = r'http://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
2013-06-27 18:46:46 +00:00
_TEST = {
2014-01-22 00:55:50 +00:00
'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',
'info_dict': {
2014-11-26 11:45:40 +00:00
'id': '1435540',
'ext': 'mp3',
2014-01-22 00:55:50 +00:00
'title': 'Freddie Gibbs - Lay It Down'
2013-06-27 18:46:46 +00:00
}
}
2013-06-27 01:38:48 +00:00
def _real_extract(self, url):
2014-11-26 11:45:40 +00:00
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2013-06-27 01:38:48 +00:00
2014-01-22 00:55:50 +00:00
video_url_base64 = self._search_regex(
2014-11-26 11:45:40 +00:00
r'data-path="(.*?)"', webpage, 'video URL', default=None)
2014-01-22 00:55:50 +00:00
if video_url_base64 is None:
video_url = self._search_regex(
2014-11-26 11:45:40 +00:00
r'"contentUrl" content="(.*?)"', webpage, 'content URL')
return self.url_result(video_url, ie='Youtube')
2013-06-27 01:38:48 +00:00
2014-01-22 00:55:50 +00:00
reqdata = compat_urllib_parse.urlencode([
('mediaType', 's'),
('mediaId', video_id),
])
r = compat_urllib_request.Request(
'http://www.hotnewhiphop.com/ajax/media/getActions/', data=reqdata)
r.add_header('Content-Type', 'application/x-www-form-urlencoded')
mkd = self._download_json(
r, video_id, note='Requesting media key',
errnote='Could not download media key')
if 'mediaKey' not in mkd:
raise ExtractorError('Did not get a media key')
redirect_url = base64.b64decode(video_url_base64).decode('utf-8')
redirect_req = HEADRequest(redirect_url)
req = self._request_webpage(
redirect_req, video_id,
note='Resolving final URL', errnote='Could not resolve final URL')
video_url = req.geturl()
if video_url.endswith('.html'):
raise ExtractorError('Redirect failed')
2013-06-27 01:38:48 +00:00
2014-11-26 11:45:40 +00:00
video_title = self._og_search_title(webpage).strip()
2013-06-27 01:38:48 +00:00
2014-01-22 00:55:50 +00:00
return {
'id': video_id,
'url': video_url,
'title': video_title,
2014-11-26 11:45:40 +00:00
'thumbnail': self._og_search_thumbnail(webpage),
2014-01-22 00:55:50 +00:00
}