4 from .common import InfoExtractor
13 class SoundcloudIE(InfoExtractor):
14 """Information extractor for soundcloud.com
15 To access the media, the uid of the song and a stream token
16 must be extracted from the page source and the script must make
17 a request to media.soundcloud.com/crossdomain.xml. Then
18 the media can be grabbed by requesting from an url composed
19 of the stream token and uid
22 _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
23 IE_NAME = u'soundcloud'
25 def report_resolve(self, video_id):
26 """Report information extraction."""
27 self.to_screen(u'%s: Resolving id' % video_id)
29 def _real_extract(self, url):
30 mobj = re.match(self._VALID_URL, url)
32 raise ExtractorError(u'Invalid URL: %s' % url)
34 # extract uploader (which is in the url)
35 uploader = mobj.group(1)
36 # extract simple title (uploader + slug of song title)
37 slug_title = mobj.group(2)
38 full_title = '%s/%s' % (uploader, slug_title)
40 self.report_resolve(full_title)
42 url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
43 resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
44 info_json = self._download_webpage(resolv_url, full_title, u'Downloading info JSON')
46 info = json.loads(info_json)
48 self.report_extraction(full_title)
50 streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
51 stream_json = self._download_webpage(streams_url, full_title,
52 u'Downloading stream definitions',
53 u'unable to download stream definitions')
55 streams = json.loads(stream_json)
56 mediaURL = streams['http_mp3_128_url']
57 upload_date = unified_strdate(info['created_at'])
62 'uploader': info['user']['username'],
63 'upload_date': upload_date,
64 'title': info['title'],
66 'description': info['description'],
69 class SoundcloudSetIE(InfoExtractor):
70 """Information extractor for soundcloud.com sets
71 To access the media, the uid of the song and a stream token
72 must be extracted from the page source and the script must make
73 a request to media.soundcloud.com/crossdomain.xml. Then
74 the media can be grabbed by requesting from an url composed
75 of the stream token and uid
78 _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
79 IE_NAME = u'soundcloud:set'
81 u"url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
84 u"file":"30510138.mp3",
85 u"md5":"f9136bf103901728f29e419d2c70f55d",
87 u"upload_date": u"20111213",
88 u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
89 u"uploader": u"The Royal Concept",
90 u"title": u"D-D-Dance"
94 u"file":"47127625.mp3",
95 u"md5":"09b6758a018470570f8fd423c9453dd8",
97 u"upload_date": u"20120521",
98 u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
99 u"uploader": u"The Royal Concept",
100 u"title": u"The Royal Concept - Gimme Twice"
104 u"file":"47127627.mp3",
105 u"md5":"154abd4e418cea19c3b901f1e1306d9c",
107 u"upload_date": u"20120521",
108 u"uploader": u"The Royal Concept",
109 u"title": u"Goldrushed"
113 u"file":"47127629.mp3",
114 u"md5":"2f5471edc79ad3f33a683153e96a79c1",
116 u"upload_date": u"20120521",
117 u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
118 u"uploader": u"The Royal Concept",
119 u"title": u"In the End"
123 u"file":"47127631.mp3",
124 u"md5":"f9ba87aa940af7213f98949254f1c6e2",
126 u"upload_date": u"20120521",
127 u"description": u"The Royal Concept from Stockholm\r\nFilip / David / Povel / Magnus\r\nwww.theroyalconceptband.com",
128 u"uploader": u"The Royal Concept",
129 u"title": u"Knocked Up"
133 u"file":"75206121.mp3",
134 u"md5":"f9d1fe9406717e302980c30de4af9353",
136 u"upload_date": u"20130116",
137 u"description": u"The unreleased track World on Fire premiered on the CW's hit show Arrow (8pm/7pm central). \r\nAs a gift to our fans we would like to offer you a free download of the track! ",
138 u"uploader": u"The Royal Concept",
139 u"title": u"World On Fire"
145 def report_resolve(self, video_id):
146 """Report information extraction."""
147 self.to_screen(u'%s: Resolving id' % video_id)
149 def _real_extract(self, url):
150 mobj = re.match(self._VALID_URL, url)
152 raise ExtractorError(u'Invalid URL: %s' % url)
154 # extract uploader (which is in the url)
155 uploader = mobj.group(1)
156 # extract simple title (uploader + slug of song title)
157 slug_title = mobj.group(2)
158 full_title = '%s/sets/%s' % (uploader, slug_title)
160 self.report_resolve(full_title)
162 url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
163 resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
164 info_json = self._download_webpage(resolv_url, full_title)
167 info = json.loads(info_json)
169 for err in info['errors']:
170 self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err['error_message']))
173 self.report_extraction(full_title)
174 for track in info['tracks']:
175 video_id = track['id']
177 streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
178 stream_json = self._download_webpage(streams_url, video_id, u'Downloading track info JSON')
180 self.report_extraction(video_id)
181 streams = json.loads(stream_json)
182 mediaURL = streams['http_mp3_128_url']
187 'uploader': track['user']['username'],
188 'upload_date': unified_strdate(track['created_at']),
189 'title': track['title'],
191 'description': track['description'],