yt-dlp/youtube_dl/extractor/hotnewhiphop.py

45 lines
1.4 KiB
Python
Raw Normal View History

2013-06-27 03:38:48 +02:00
import re
import base64
from .common import InfoExtractor
class HotNewHipHopIE(InfoExtractor):
2013-06-27 17:56:48 +02:00
_VALID_URL = r'http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html'
2013-06-27 20:46:46 +02:00
_TEST = {
2013-09-17 21:10:57 +02:00
u'url': u"http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html",
2013-06-27 20:46:46 +02:00
u'file': u'1435540.mp3',
u'md5': u'2c2cd2f76ef11a9b3b581e8b232f3d96',
u'info_dict': {
2013-09-17 21:10:57 +02:00
u"title": u"Freddie Gibbs - Lay It Down"
2013-06-27 20:46:46 +02:00
}
}
2013-06-27 03:38:48 +02:00
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
webpage_src = self._download_webpage(url, video_id)
video_url_base64 = self._search_regex(r'data-path="(.*?)"',
webpage_src, u'video URL', fatal=False)
if video_url_base64 == None:
video_url = self._search_regex(r'"contentUrl" content="(.*?)"', webpage_src,
u'video URL')
return self.url_result(video_url, ie='Youtube')
2013-06-27 03:38:48 +02:00
2013-06-27 17:56:48 +02:00
video_url = base64.b64decode(video_url_base64).decode('utf-8')
2013-06-27 03:38:48 +02:00
video_title = self._html_search_regex(r"<title>(.*)</title>",
webpage_src, u'title')
results = [{
'id': video_id,
'url' : video_url,
'title' : video_title,
'thumbnail' : self._og_search_thumbnail(webpage_src),
2013-06-27 03:38:48 +02:00
'ext' : 'mp3',
}]
return results