ExfmIE: extract Soundcloud songs using SoundcloudIE

Now SouncloudIE accepts api urls.
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-07-24 14:39:21 +02:00
parent 7d2392691c
commit eb6a41ba0f
2 changed files with 54 additions and 29 deletions

View file

@ -8,17 +8,30 @@ class ExfmIE(InfoExtractor):
IE_NAME = u'exfm'
IE_DESC = u'ex.fm'
_VALID_URL = r'(?:http://)?(?:www\.)?ex\.fm/song/([^/]+)'
_SOUNDCLOUD_URL_ = r'(?:http://)?(?:www\.)?api\.soundcloud.com/tracks/([^/]+)/stream'
_TEST = {
u'url': u'http://ex.fm/song/1bgtzg',
u'file': u'1bgtzg.mp3',
u'md5': u'8a7967a3fef10e59a1d6f86240fd41cf',
u'info_dict': {
u"title": u"We Can't Stop",
u"uploader": u"Miley Cyrus",
u'thumbnail': u'http://i1.sndcdn.com/artworks-000049666230-w9i7ef-t500x500.jpg?9d68d37'
}
}
_SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud.com/tracks/([^/]+)/stream'
_TESTS = [
{
u'url': u'http://ex.fm/song/1bgtzg',
u'file': u'95223130.mp3',
u'md5': u'8a7967a3fef10e59a1d6f86240fd41cf',
u'info_dict': {
u"title": u"We Can't Stop - Miley Cyrus",
u"uploader": u"Miley Cyrus",
u'upload_date': u'20130603',
u'description': u'Download "We Can\'t Stop" \r\niTunes: http://smarturl.it/WeCantStop?IQid=SC\r\nAmazon: http://smarturl.it/WeCantStopAMZ?IQid=SC',
},
u'note': u'Soundcloud song',
},
{
u'url': u'http://ex.fm/song/wddt8',
u'file': u'wddt8.mp3',
u'md5': u'966bd70741ac5b8570d8e45bfaed3643',
u'info_dict': {
u'title': u'Safe and Sound',
u'uploader': u'Capital Cities',
},
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@ -26,11 +39,10 @@ class ExfmIE(InfoExtractor):
info_url = "http://ex.fm/api/v3/song/%s" %(song_id)
webpage = self._download_webpage(info_url, song_id)
info = json.loads(webpage)
song_url = re.match(self._SOUNDCLOUD_URL_,info['song']['url'])
if song_url is not None:
song_url = song_url.group() + "?client_id=b45b1aa10f1ac2941910a7f0d10f8e28"
else:
song_url = info['song']['url']
song_url = info['song']['url']
if re.match(self._SOUNDCLOUD_URL, song_url) is not None:
self.to_screen('Soundcloud song detected')
return self.url_result(song_url.replace('/stream',''), 'Soundcloud')
return [{
'id': song_id,
'url': song_url,

View file

@ -19,7 +19,11 @@ class SoundcloudIE(InfoExtractor):
of the stream token and uid
"""
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)/?(?:[?].*)?$'
_VALID_URL = r'''^(?:https?://)?
(?:(?:(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)/?(?:[?].*)?$)
|(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
)
'''
IE_NAME = u'soundcloud'
_TEST = {
u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
@ -35,6 +39,10 @@ class SoundcloudIE(InfoExtractor):
_CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28'
@classmethod
def suitable(cls, url):
return re.match(cls._VALID_URL, url, flags=re.VERBOSE) is not None
def report_resolve(self, video_id):
"""Report information extraction."""
self.to_screen(u'%s: Resolving id' % video_id)
@ -63,21 +71,26 @@ class SoundcloudIE(InfoExtractor):
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
# extract uploader (which is in the url)
uploader = mobj.group(1)
# extract simple title (uploader + slug of song title)
slug_title = mobj.group(2)
full_title = '%s/%s' % (uploader, slug_title)
track_id = mobj.group('track_id')
if track_id is not None:
info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
full_title = track_id
else:
# extract uploader (which is in the url)
uploader = mobj.group(1)
# extract simple title (uploader + slug of song title)
slug_title = mobj.group(2)
full_title = '%s/%s' % (uploader, slug_title)
self.report_resolve(full_title)
self.report_resolve(full_title)
url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
resolv_url = self._resolv_url(url)
info_json = self._download_webpage(resolv_url, full_title, u'Downloading info JSON')
url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
info_json_url = self._resolv_url(url)
info_json = self._download_webpage(info_json_url, full_title, u'Downloading info JSON')
info = json.loads(info_json)
return self._extract_info_dict(info, full_title)