youtube-dl/youtube_dl/extractor/audiomack.py

70 lines
2.4 KiB
Python
Raw Normal View History

2014-10-24 06:55:39 +09:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
2014-10-24 13:54:59 +09:00
from .soundcloud import SoundcloudIE
2014-10-25 11:07:01 +09:00
from ..utils import ExtractorError
2014-10-27 07:13:42 +09:00
2014-10-24 06:55:39 +09:00
import time
class AudiomackIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/song/(?P<id>[\w/-]+)'
2014-10-24 13:54:59 +09:00
IE_NAME = 'audiomack'
_TESTS = [
#hosted on audiomack
{
'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary',
'info_dict':
{
2014-10-25 11:07:01 +09:00
'id' : 'roosh-williams/extraordinary',
2014-10-24 13:54:59 +09:00
'ext': 'mp3',
'title': 'Roosh Williams - Extraordinary'
}
},
#hosted on soundcloud via audiomack
{
'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare',
'file': '172419696.mp3',
'info_dict':
{
'ext': 'mp3',
'title': 'Young Thug ft Lil Wayne - Take Kare',
"upload_date": "20141016",
"description": "New track produced by London On Da Track called “Take Kare\"\n\nhttp://instagram.com/theyoungthugworld\nhttps://www.facebook.com/ThuggerThuggerCashMoney\n",
"uploader": "Young Thug World"
}
2014-10-24 06:55:39 +09:00
}
2014-10-24 13:54:59 +09:00
]
2014-10-24 06:55:39 +09:00
def _real_extract(self, url):
2014-10-25 15:58:03 +09:00
video_id = self._match_id(url)
2014-10-24 06:55:39 +09:00
2014-10-25 15:58:03 +09:00
api_response = self._download_json(
"http://www.audiomack.com/api/music/url/song/%s?_=%d" % (
video_id, time.time()),
video_id)
2014-10-25 11:07:01 +09:00
2014-10-25 15:58:03 +09:00
if "url" not in api_response:
2014-10-25 11:07:01 +09:00
raise ExtractorError("Unable to deduce api url of song")
2014-10-25 15:58:03 +09:00
realurl = api_response["url"]
2014-10-24 13:54:59 +09:00
#Audiomack wraps a lot of soundcloud tracks in their branded wrapper
# - if so, pass the work off to the soundcloud extractor
if SoundcloudIE.suitable(realurl):
return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'}
2014-10-25 15:58:03 +09:00
webpage = self._download_webpage(url, video_id)
artist = self._html_search_regex(
r'<span class="artist">(.*?)</span>', webpage, "artist")
songtitle = self._html_search_regex(
r'<h1 class="profile-title song-title"><span class="artist">.*?</span>(.*?)</h1>',
webpage, "title")
title = artist + " - " + songtitle
return {
'id': video_id,
'title': title,
'url': realurl,
}