0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-29 01:51:06 +00:00
yt-dlp/yt_dlp/extractor/hotnewhiphop.py
Pccode66 7a5c1cfe93
Completely change project name to yt-dlp (#85)
* All modules and binary names are changed
* All documentation references changed
* yt-dlp no longer loads youtube-dlc config files
* All URLs changed to point to organization account

Co-authored-by: Pccode66
Co-authored-by: pukkandan
2021-02-25 00:15:56 +05:30

66 lines
2.2 KiB
Python

from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_b64decode
from ..utils import (
ExtractorError,
HEADRequest,
sanitized_Request,
urlencode_postdata,
)
class HotNewHipHopIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
_TEST = {
'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',
'info_dict': {
'id': '1435540',
'ext': 'mp3',
'title': 'Freddie Gibbs - Lay It Down'
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url_base64 = self._search_regex(
r'data-path="(.*?)"', webpage, 'video URL', default=None)
if video_url_base64 is None:
video_url = self._search_regex(
r'"contentUrl" content="(.*?)"', webpage, 'content URL')
return self.url_result(video_url, ie='Youtube')
reqdata = urlencode_postdata([
('mediaType', 's'),
('mediaId', video_id),
])
r = sanitized_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 = compat_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')
video_title = self._og_search_title(webpage).strip()
return {
'id': video_id,
'url': video_url,
'title': video_title,
'thumbnail': self._og_search_thumbnail(webpage),
}