[hotnewhiphop] Retrieve media key

This commit is contained in:
Philipp Hagemeister 2014-01-22 01:55:50 +01:00
parent 00122de6a9
commit 99f770caa8

View File

@ -1,17 +1,25 @@
from __future__ import unicode_literals
import re import re
import base64 import base64
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
compat_urllib_request,
ExtractorError,
HEADRequest,
)
class HotNewHipHopIE(InfoExtractor): class HotNewHipHopIE(InfoExtractor):
_VALID_URL = r'http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html' _VALID_URL = r'http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html'
_TEST = { _TEST = {
u'url': u"http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html", 'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
u'file': u'1435540.mp3', 'file': '1435540.mp3',
u'md5': u'2c2cd2f76ef11a9b3b581e8b232f3d96', 'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',
u'info_dict': { 'info_dict': {
u"title": u'Freddie Gibbs "Lay It Down"' 'title': 'Freddie Gibbs - Lay It Down'
} }
} }
@ -21,24 +29,41 @@ class HotNewHipHopIE(InfoExtractor):
webpage_src = self._download_webpage(url, video_id) webpage_src = self._download_webpage(url, video_id)
video_url_base64 = self._search_regex(r'data-path="(.*?)"', video_url_base64 = self._search_regex(
webpage_src, u'video URL', fatal=False) r'data-path="(.*?)"', webpage_src, u'video URL', fatal=False)
if video_url_base64 == None: if video_url_base64 is None:
video_url = self._search_regex(r'"contentUrl" content="(.*?)"', webpage_src, video_url = self._search_regex(
u'video URL') r'"contentUrl" content="(.*?)"', webpage_src, u'video URL')
return self.url_result(video_url, ie='Youtube') return self.url_result(video_url, ie='Youtube')
video_url = base64.b64decode(video_url_base64).decode('utf-8') 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')
video_title = self._html_search_regex(r"<title>(.*)</title>", redirect_url = base64.b64decode(video_url_base64).decode('utf-8')
webpage_src, u'title') 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')
results = [{ video_title = self._og_search_title(webpage_src).strip()
return {
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'title': video_title, 'title': video_title,
'thumbnail': self._og_search_thumbnail(webpage_src), 'thumbnail': self._og_search_thumbnail(webpage_src),
'ext' : 'mp3', }
}]
return results