dbrun
/
youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[audiomack] Simplify

This commit is contained in:
Philipp Hagemeister 2014-10-25 08:58:03 +02:00
parent 7fc54e5262
commit d3c72db894
1 changed files with 21 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
youtube_dl/extractor/audiomack.py
View File

@ -38,30 +38,32 @@ class AudiomackIE(InfoExtractor):
] ]
def _real_extract(self, url): def _real_extract(self, url):
#id is what follows /song/ in url, usually the uploader name + title video_id = self._match_id(url)
id = self._match_id(url)
#Call the api, which gives us a json doc with the real url inside api_response = self._download_json(
rightnow = int(time.time()) "http://www.audiomack.com/api/music/url/song/%s?_=%d" % (
apiresponse = self._download_json("http://www.audiomack.com/api/music/url/song/"+id+"?_="+str(rightnow), id) video_id, time.time()),
video_id)
if "url" not in apiresponse: if "url" not in api_response:
raise ExtractorError("Unable to deduce api url of song") raise ExtractorError("Unable to deduce api url of song")
realurl = apiresponse["url"] realurl = api_response["url"]
#Audiomack wraps a lot of soundcloud tracks in their branded wrapper #Audiomack wraps a lot of soundcloud tracks in their branded wrapper
# - if so, pass the work off to the soundcloud extractor # - if so, pass the work off to the soundcloud extractor
if SoundcloudIE.suitable(realurl): if SoundcloudIE.suitable(realurl):
return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'} return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'}
else:
#Pull out metadata webpage = self._download_webpage(url, video_id)
page = self._download_webpage(url, id) artist = self._html_search_regex(
artist = self._html_search_regex(r'<span class="artist">(.*)</span>', page, "artist") r'<span class="artist">(.*?)</span>', webpage, "artist")
songtitle = self._html_search_regex(r'<h1 class="profile-title song-title"><span class="artist">.*</span>(.*)</h1>', page, "title") songtitle = self._html_search_regex(
title = artist+" - "+songtitle r'<h1 class="profile-title song-title"><span class="artist">.*?</span>(.*?)</h1>',
return { webpage, "title")
'id': id, # ignore id, which is not useful in song name title = artist + " - " + songtitle
'title': title,
'url': realurl, return {
'ext': 'mp3' 'id': video_id,
} 'title': title,
'url': realurl,
}