2016-10-02 06:39:18 -05:00
# coding: utf-8
2014-01-16 20:29:41 -06:00
from __future__ import unicode_literals
2013-09-14 14:41:49 -05:00
import itertools
2017-09-01 03:08:24 -05:00
import re
2013-06-23 13:57:44 -05:00
2015-10-17 11:23:46 -05:00
from . common import (
InfoExtractor ,
SearchInfoExtractor
)
2014-12-13 05:24:42 -06:00
from . . compat import (
2013-06-23 13:57:44 -05:00
compat_str ,
2013-08-21 10:06:37 -05:00
compat_urlparse ,
2016-03-25 14:46:57 -05:00
compat_urllib_parse_urlencode ,
2014-12-13 05:24:42 -06:00
)
from . . utils import (
2013-06-23 13:57:44 -05:00
ExtractorError ,
2019-04-22 12:39:16 -05:00
float_or_none ,
2014-06-07 08:51:01 -05:00
int_or_none ,
2019-04-22 12:39:16 -05:00
KNOWN_EXTENSIONS ,
merge_dicts ,
mimetype2ext ,
str_or_none ,
2019-02-10 10:44:08 -06:00
try_get ,
unified_timestamp ,
2017-09-03 04:18:24 -05:00
update_url_query ,
2019-02-02 10:40:06 -06:00
url_or_none ,
2017-09-03 04:18:24 -05:00
)
2013-06-23 13:57:44 -05:00
class SoundcloudIE ( InfoExtractor ) :
""" Information extractor for soundcloud.com
To access the media , the uid of the song and a stream token
must be extracted from the page source and the script must make
a request to media . soundcloud . com / crossdomain . xml . Then
the media can be grabbed by requesting from an url composed
of the stream token and uid
"""
2014-05-04 20:12:41 -05:00
_VALID_URL = r ''' (?x)^(?:https?://)?
2013-12-19 09:39:01 -06:00
( ? : ( ? : ( ? : www \. | m \. ) ? soundcloud \. com /
2017-07-29 06:41:42 -05:00
( ? ! stations / track )
2013-12-09 12:57:00 -06:00
( ? P < uploader > [ \w \d - ] + ) /
2019-02-01 15:00:29 -06:00
( ? ! ( ? : tracks | albums | sets ( ? : / . + ? ) ? | reposts | likes | spotlight ) / ? ( ? : $ | [ ? #]))
2014-08-27 17:58:24 -05:00
( ? P < title > [ \w \d - ] + ) / ?
2013-12-09 10:08:58 -06:00
( ? P < token > [ ^ ? ] + ? ) ? ( ? : [ ? ] . * ) ? $ )
2014-09-18 01:02:03 -05:00
| ( ? : api \. soundcloud \. com / tracks / ( ? P < track_id > \d + )
2014-12-03 04:49:53 -06:00
( ? : / ? \? secret_token = ( ? P < secret_token > [ ^ & ] + ) ) ? )
2014-01-02 09:18:51 -06:00
| ( ? P < player > ( ? : w | player | p . ) \. soundcloud \. com / player / ? . * ? url = . * )
2013-07-24 07:39:21 -05:00
)
'''
2014-01-16 20:29:41 -06:00
IE_NAME = ' soundcloud '
2013-11-09 11:06:09 -06:00
_TESTS = [
{
2014-01-16 20:29:41 -06:00
' url ' : ' http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy ' ,
' md5 ' : ' ebef0a451b909710ed1d7787dddbf0d7 ' ,
' info_dict ' : {
2014-10-25 15:32:01 -05:00
' id ' : ' 62986583 ' ,
' ext ' : ' mp3 ' ,
2019-02-10 10:44:08 -06:00
' title ' : ' Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1 ' ,
2014-10-25 15:32:01 -05:00
' description ' : ' No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o \' d ' ,
' uploader ' : ' E.T. ExTerrestrial Music ' ,
2019-02-10 10:44:08 -06:00
' timestamp ' : 1349920598 ,
' upload_date ' : ' 20121011 ' ,
2019-04-22 12:39:16 -05:00
' duration ' : 143.216 ,
2016-09-18 04:53:05 -05:00
' license ' : ' all-rights-reserved ' ,
2019-02-10 10:44:08 -06:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2013-11-09 11:06:09 -06:00
}
} ,
# not streamable song
{
2014-01-16 20:29:41 -06:00
' url ' : ' https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep ' ,
' info_dict ' : {
' id ' : ' 47127627 ' ,
' ext ' : ' mp3 ' ,
' title ' : ' Goldrushed ' ,
2014-03-09 06:20:34 -05:00
' description ' : ' From Stockholm Sweden \r \n Povel / Magnus / Filip / David \r \n www.theroyalconcept.com ' ,
2014-01-16 20:29:41 -06:00
' uploader ' : ' The Royal Concept ' ,
2019-02-10 10:44:08 -06:00
' timestamp ' : 1337635207 ,
2014-01-16 20:29:41 -06:00
' upload_date ' : ' 20120521 ' ,
2019-02-10 10:44:08 -06:00
' duration ' : 30 ,
2016-09-18 04:53:05 -05:00
' license ' : ' all-rights-reserved ' ,
2019-02-10 10:44:08 -06:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2013-11-09 11:06:09 -06:00
} ,
2014-01-16 20:29:41 -06:00
' params ' : {
2013-11-09 11:06:09 -06:00
# rtmp
2014-01-16 20:29:41 -06:00
' skip_download ' : True ,
2013-11-09 11:06:09 -06:00
} ,
} ,
2013-12-09 10:08:58 -06:00
# private link
{
2014-01-16 20:29:41 -06:00
' url ' : ' https://soundcloud.com/jaimemf/youtube-dl-test-video-a-y-baw/s-8Pjrp ' ,
' md5 ' : ' aa0dd32bfea9b0c5ef4f02aacd080604 ' ,
' info_dict ' : {
' id ' : ' 123998367 ' ,
' ext ' : ' mp3 ' ,
' title ' : ' Youtube - Dl Test Video \' \' Ä↭ ' ,
' description ' : ' test chars: \" \' / \\ ä↭ ' ,
2019-02-10 10:44:08 -06:00
' uploader ' : ' jaimeMF ' ,
' timestamp ' : 1386604920 ,
2014-01-16 20:29:41 -06:00
' upload_date ' : ' 20131209 ' ,
2019-04-22 12:39:16 -05:00
' duration ' : 9.927 ,
2016-09-18 04:53:05 -05:00
' license ' : ' all-rights-reserved ' ,
2019-02-10 10:44:08 -06:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2013-12-09 10:08:58 -06:00
} ,
} ,
2014-09-18 01:02:03 -05:00
# private link (alt format)
{
' url ' : ' https://api.soundcloud.com/tracks/123998367?secret_token=s-8Pjrp ' ,
' md5 ' : ' aa0dd32bfea9b0c5ef4f02aacd080604 ' ,
' info_dict ' : {
' id ' : ' 123998367 ' ,
' ext ' : ' mp3 ' ,
' title ' : ' Youtube - Dl Test Video \' \' Ä↭ ' ,
' description ' : ' test chars: \" \' / \\ ä↭ ' ,
2019-02-10 10:44:08 -06:00
' uploader ' : ' jaimeMF ' ,
' timestamp ' : 1386604920 ,
2014-09-18 01:02:03 -05:00
' upload_date ' : ' 20131209 ' ,
2019-04-22 12:39:16 -05:00
' duration ' : 9.927 ,
2016-09-18 04:53:05 -05:00
' license ' : ' all-rights-reserved ' ,
2019-02-10 10:44:08 -06:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2014-09-18 01:02:03 -05:00
} ,
} ,
2013-12-10 06:04:21 -06:00
# downloadable song
{
2014-07-15 07:18:06 -05:00
' url ' : ' https://soundcloud.com/oddsamples/bus-brakes ' ,
2014-07-22 18:41:44 -05:00
' md5 ' : ' 7624f2351f8a3b2e7cd51522496e7631 ' ,
2014-01-16 20:29:41 -06:00
' info_dict ' : {
2014-07-15 07:18:06 -05:00
' id ' : ' 128590877 ' ,
2014-07-22 18:41:44 -05:00
' ext ' : ' mp3 ' ,
2014-07-15 07:18:06 -05:00
' title ' : ' Bus Brakes ' ,
2014-10-25 15:32:01 -05:00
' description ' : ' md5:0053ca6396e8d2fd7b7e1595ef12ab66 ' ,
2014-07-15 07:18:06 -05:00
' uploader ' : ' oddsamples ' ,
2019-02-10 10:44:08 -06:00
' timestamp ' : 1389232924 ,
2014-07-15 07:18:06 -05:00
' upload_date ' : ' 20140109 ' ,
2019-04-22 12:39:16 -05:00
' duration ' : 17.346 ,
2016-09-18 04:53:05 -05:00
' license ' : ' cc-by-sa ' ,
2019-02-10 10:44:08 -06:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2013-12-10 06:04:21 -06:00
} ,
} ,
2017-09-03 04:18:24 -05:00
# private link, downloadable format
{
' url ' : ' https://soundcloud.com/oriuplift/uponly-238-no-talking-wav/s-AyZUd ' ,
' md5 ' : ' 64a60b16e617d41d0bef032b7f55441e ' ,
' info_dict ' : {
' id ' : ' 340344461 ' ,
' ext ' : ' wav ' ,
' title ' : ' Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav] ' ,
' description ' : ' md5:fa20ee0fca76a3d6df8c7e57f3715366 ' ,
' uploader ' : ' Ori Uplift Music ' ,
2019-02-10 10:44:08 -06:00
' timestamp ' : 1504206263 ,
2017-09-03 04:18:24 -05:00
' upload_date ' : ' 20170831 ' ,
2019-04-22 12:39:16 -05:00
' duration ' : 7449.096 ,
2017-09-03 04:18:24 -05:00
' license ' : ' all-rights-reserved ' ,
2019-02-10 10:44:08 -06:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2017-09-03 04:18:24 -05:00
} ,
} ,
2018-01-04 19:25:42 -06:00
# no album art, use avatar pic for thumbnail
{
' url ' : ' https://soundcloud.com/garyvee/sideways-prod-mad-real ' ,
' md5 ' : ' 59c7872bc44e5d99b7211891664760c2 ' ,
' info_dict ' : {
' id ' : ' 309699954 ' ,
' ext ' : ' mp3 ' ,
' title ' : ' Sideways (Prod. Mad Real) ' ,
' description ' : ' md5:d41d8cd98f00b204e9800998ecf8427e ' ,
' uploader ' : ' garyvee ' ,
2019-02-10 10:44:08 -06:00
' timestamp ' : 1488152409 ,
2018-01-04 19:25:42 -06:00
' upload_date ' : ' 20170226 ' ,
2019-04-22 12:39:16 -05:00
' duration ' : 207.012 ,
2018-01-04 19:25:42 -06:00
' thumbnail ' : r ' re:https?://.* \ .jpg ' ,
' license ' : ' all-rights-reserved ' ,
2019-02-10 10:44:08 -06:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2018-01-04 19:25:42 -06:00
} ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2019-04-22 12:39:16 -05:00
# not avaialble via api.soundcloud.com/i1/tracks/id/streams
{
' url ' : ' https://soundcloud.com/giovannisarani/mezzo-valzer ' ,
' md5 ' : ' e22aecd2bc88e0e4e432d7dcc0a1abf7 ' ,
' info_dict ' : {
' id ' : ' 583011102 ' ,
' ext ' : ' mp3 ' ,
' title ' : ' Mezzo Valzer ' ,
' description ' : ' md5:4138d582f81866a530317bae316e8b61 ' ,
' uploader ' : ' Giovanni Sarani ' ,
' timestamp ' : 1551394171 ,
' upload_date ' : ' 20190228 ' ,
' duration ' : 180.157 ,
' thumbnail ' : r ' re:https?://.* \ .jpg ' ,
' license ' : ' all-rights-reserved ' ,
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
} ,
' expected_warnings ' : [ ' Unable to download JSON metadata ' ] ,
}
2013-11-09 11:06:09 -06:00
]
2013-06-23 13:57:44 -05:00
2019-06-28 12:33:35 -05:00
_CLIENT_ID = ' BeGVhOrGmfboy1LtiHTQF6Ejpt9ULJCI '
2013-07-24 07:05:14 -05:00
2016-07-28 10:16:05 -05:00
@staticmethod
def _extract_urls ( webpage ) :
return [ m . group ( ' url ' ) for m in re . finditer (
r ' <iframe[^>]+src=([ " \' ])(?P<url>(?:https?://)?(?:w \ .)?soundcloud \ .com/player.+?) \ 1 ' ,
webpage ) ]
2013-07-24 07:05:14 -05:00
@classmethod
def _resolv_url ( cls , url ) :
2017-06-27 09:20:18 -05:00
return ' https://api.soundcloud.com/resolve.json?url= ' + url + ' &client_id= ' + cls . _CLIENT_ID
2013-07-24 07:05:14 -05:00
2013-12-09 10:08:58 -06:00
def _extract_info_dict ( self , info , full_title = None , quiet = False , secret_token = None ) :
2013-11-09 11:06:09 -06:00
track_id = compat_str ( info [ ' id ' ] )
2019-02-10 10:44:08 -06:00
title = info [ ' title ' ]
2013-11-09 11:06:09 -06:00
name = full_title or track_id
2013-11-25 13:30:41 -06:00
if quiet :
2013-09-14 14:41:49 -05:00
self . report_extraction ( name )
2018-01-04 19:25:42 -06:00
thumbnail = info . get ( ' artwork_url ' ) or info . get ( ' user ' , { } ) . get ( ' avatar_url ' )
2016-09-20 09:55:57 -05:00
if isinstance ( thumbnail , compat_str ) :
2013-07-24 07:05:14 -05:00
thumbnail = thumbnail . replace ( ' -large ' , ' -t500x500 ' )
2019-02-10 10:44:08 -06:00
username = try_get ( info , lambda x : x [ ' user ' ] [ ' username ' ] , compat_str )
def extract_count ( key ) :
return int_or_none ( info . get ( ' %s _count ' % key ) )
2019-04-22 12:39:16 -05:00
like_count = extract_count ( ' favoritings ' )
if like_count is None :
like_count = extract_count ( ' likes ' )
2013-11-09 11:06:09 -06:00
result = {
2013-11-25 13:30:41 -06:00
' id ' : track_id ,
2019-02-10 10:44:08 -06:00
' uploader ' : username ,
' timestamp ' : unified_timestamp ( info . get ( ' created_at ' ) ) ,
' title ' : title ,
2016-09-20 09:55:57 -05:00
' description ' : info . get ( ' description ' ) ,
2013-07-24 07:05:14 -05:00
' thumbnail ' : thumbnail ,
2019-04-22 12:39:16 -05:00
' duration ' : float_or_none ( info . get ( ' duration ' ) , 1000 ) ,
2014-10-26 13:08:36 -05:00
' webpage_url ' : info . get ( ' permalink_url ' ) ,
2016-09-20 09:55:57 -05:00
' license ' : info . get ( ' license ' ) ,
2019-02-10 10:44:08 -06:00
' view_count ' : extract_count ( ' playback ' ) ,
2019-04-22 12:39:16 -05:00
' like_count ' : like_count ,
2019-02-10 10:44:08 -06:00
' comment_count ' : extract_count ( ' comment ' ) ,
' repost_count ' : extract_count ( ' reposts ' ) ,
' genre ' : info . get ( ' genre ' ) ,
2013-07-24 07:05:14 -05:00
}
2019-04-22 12:39:16 -05:00
format_urls = set ( )
2014-03-23 20:21:17 -05:00
formats = [ ]
2017-09-01 03:08:24 -05:00
query = { ' client_id ' : self . _CLIENT_ID }
if secret_token is not None :
query [ ' secret_token ' ] = secret_token
2013-11-09 11:06:09 -06:00
if info . get ( ' downloadable ' , False ) :
2013-11-21 06:16:19 -06:00
# We can build a direct link to the song
2017-09-01 03:08:24 -05:00
format_url = update_url_query (
2017-09-03 04:18:24 -05:00
' https://api.soundcloud.com/tracks/ %s /download ' % track_id , query )
2019-04-22 12:39:16 -05:00
format_urls . add ( format_url )
2014-03-23 20:21:17 -05:00
formats . append ( {
2013-11-25 13:30:41 -06:00
' format_id ' : ' download ' ,
2014-01-16 20:29:41 -06:00
' ext ' : info . get ( ' original_format ' , ' mp3 ' ) ,
2013-11-25 13:30:41 -06:00
' url ' : format_url ,
2013-11-25 15:34:56 -06:00
' vcodec ' : ' none ' ,
2014-03-23 20:21:17 -05:00
' preference ' : 10 ,
} )
2019-04-22 12:39:16 -05:00
# Old API, does not work for some tracks (e.g.
# https://soundcloud.com/giovannisarani/mezzo-valzer)
2014-05-04 20:12:41 -05:00
format_dict = self . _download_json (
2017-06-27 09:20:18 -05:00
' https://api.soundcloud.com/i1/tracks/ %s /streams ' % track_id ,
2019-04-22 12:39:16 -05:00
track_id , ' Downloading track url ' , query = query , fatal = False )
if format_dict :
for key , stream_url in format_dict . items ( ) :
if stream_url in format_urls :
continue
format_urls . add ( stream_url )
ext , abr = ' mp3 ' , None
mobj = re . search ( r ' _([^_]+)_( \ d+)_url ' , key )
if mobj :
ext , abr = mobj . groups ( )
abr = int ( abr )
if key . startswith ( ' http ' ) :
stream_formats = [ {
' format_id ' : key ,
' ext ' : ext ,
' url ' : stream_url ,
} ]
elif key . startswith ( ' rtmp ' ) :
# The url doesn't have an rtmp app, we have to extract the playpath
url , path = stream_url . split ( ' mp3: ' , 1 )
stream_formats = [ {
' format_id ' : key ,
' url ' : url ,
' play_path ' : ' mp3: ' + path ,
' ext ' : ' flv ' ,
} ]
elif key . startswith ( ' hls ' ) :
stream_formats = self . _extract_m3u8_formats (
stream_url , track_id , ext , entry_protocol = ' m3u8_native ' ,
m3u8_id = key , fatal = False )
else :
continue
if abr :
for f in stream_formats :
f [ ' abr ' ] = abr
formats . extend ( stream_formats )
# New API
transcodings = try_get (
info , lambda x : x [ ' media ' ] [ ' transcodings ' ] , list ) or [ ]
for t in transcodings :
if not isinstance ( t , dict ) :
2017-01-27 10:16:30 -06:00
continue
2019-04-22 12:39:16 -05:00
format_url = url_or_none ( t . get ( ' url ' ) )
if not format_url :
continue
stream = self . _download_json (
update_url_query ( format_url , query ) , track_id , fatal = False )
if not isinstance ( stream , dict ) :
continue
stream_url = url_or_none ( stream . get ( ' url ' ) )
if not stream_url :
continue
if stream_url in format_urls :
continue
format_urls . add ( stream_url )
protocol = try_get ( t , lambda x : x [ ' format ' ] [ ' protocol ' ] , compat_str )
if protocol != ' hls ' and ' /hls ' in format_url :
protocol = ' hls '
ext = None
preset = str_or_none ( t . get ( ' preset ' ) )
if preset :
ext = preset . split ( ' _ ' ) [ 0 ]
if ext not in KNOWN_EXTENSIONS :
mimetype = try_get (
t , lambda x : x [ ' format ' ] [ ' mime_type ' ] , compat_str )
ext = mimetype2ext ( mimetype ) or ' mp3 '
format_id_list = [ ]
if protocol :
format_id_list . append ( protocol )
format_id_list . append ( ext )
format_id = ' _ ' . join ( format_id_list )
formats . append ( {
' url ' : stream_url ,
' format_id ' : format_id ,
' ext ' : ext ,
' protocol ' : ' m3u8_native ' if protocol == ' hls ' else ' http ' ,
} )
2017-01-27 10:16:30 -06:00
if not formats :
# We fallback to the stream_url in the original info, this
# cannot be always used, sometimes it can give an HTTP 404 error
formats . append ( {
' format_id ' : ' fallback ' ,
2017-09-01 03:08:24 -05:00
' url ' : update_url_query ( info [ ' stream_url ' ] , query ) ,
2018-05-26 08:34:13 -05:00
' ext ' : ' mp3 ' ,
2017-01-27 10:16:30 -06:00
} )
2019-04-22 12:39:16 -05:00
self . _check_formats ( formats , track_id )
2017-01-27 10:16:30 -06:00
for f in formats :
f [ ' vcodec ' ] = ' none '
2013-11-25 13:30:41 -06:00
2015-03-02 10:39:32 -06:00
self . _sort_formats ( formats )
result [ ' formats ' ] = formats
2013-11-21 06:16:19 -06:00
2013-11-09 11:06:09 -06:00
return result
2013-07-24 07:05:14 -05:00
2013-06-23 13:57:44 -05:00
def _real_extract ( self , url ) :
2013-07-24 07:39:21 -05:00
mobj = re . match ( self . _VALID_URL , url , flags = re . VERBOSE )
2013-06-23 13:57:44 -05:00
if mobj is None :
2014-03-23 20:15:31 -05:00
raise ExtractorError ( ' Invalid URL: %s ' % url )
2013-06-23 13:57:44 -05:00
2013-07-24 07:39:21 -05:00
track_id = mobj . group ( ' track_id ' )
2019-04-22 12:39:16 -05:00
new_info = { }
2016-09-18 04:53:05 -05:00
2013-07-24 07:39:21 -05:00
if track_id is not None :
2017-06-27 09:20:18 -05:00
info_json_url = ' https://api.soundcloud.com/tracks/ ' + track_id + ' .json?client_id= ' + self . _CLIENT_ID
2013-07-24 07:39:21 -05:00
full_title = track_id
2014-09-18 01:02:03 -05:00
token = mobj . group ( ' secret_token ' )
if token :
2016-02-14 03:37:17 -06:00
info_json_url + = ' &secret_token= ' + token
2014-01-02 09:18:51 -06:00
elif mobj . group ( ' player ' ) :
2013-08-21 10:06:37 -05:00
query = compat_urlparse . parse_qs ( compat_urlparse . urlparse ( url ) . query )
2015-04-17 03:46:25 -05:00
real_url = query [ ' url ' ] [ 0 ]
# If the token is in the query of the original url we have to
# manually add it
if ' secret_token ' in query :
real_url + = ' ?secret_token= ' + query [ ' secret_token ' ] [ 0 ]
return self . url_result ( real_url )
2013-07-24 07:39:21 -05:00
else :
# extract uploader (which is in the url)
2013-12-09 10:08:58 -06:00
uploader = mobj . group ( ' uploader ' )
2013-07-24 07:39:21 -05:00
# extract simple title (uploader + slug of song title)
2014-11-23 14:20:46 -06:00
slug_title = mobj . group ( ' title ' )
2013-12-09 10:08:58 -06:00
token = mobj . group ( ' token ' )
full_title = resolve_title = ' %s / %s ' % ( uploader , slug_title )
if token :
resolve_title + = ' / %s ' % token
2014-11-23 13:41:03 -06:00
2019-04-22 12:39:16 -05:00
webpage = self . _download_webpage ( url , full_title , fatal = False )
if webpage :
entries = self . _parse_json (
self . _search_regex (
r ' var \ s+c \ s*= \ s*( \ [.+? \ ]) \ s*, \ s*o \ s*=Date \ b ' , webpage ,
' data ' , default = ' [] ' ) , full_title , fatal = False )
if entries :
for e in entries :
if not isinstance ( e , dict ) :
continue
if e . get ( ' id ' ) != 67 :
continue
data = try_get ( e , lambda x : x [ ' data ' ] [ 0 ] , dict )
if data :
new_info = data
break
info_json_url = self . _resolv_url (
' https://soundcloud.com/ %s ' % resolve_title )
# Contains some additional info missing from new_info
info = self . _download_json (
info_json_url , full_title , ' Downloading info JSON ' )
return self . _extract_info_dict (
merge_dicts ( info , new_info ) , full_title , secret_token = token )
2013-06-23 13:57:44 -05:00
2014-05-04 20:12:41 -05:00
2016-09-24 07:29:49 -05:00
class SoundcloudPlaylistBaseIE ( SoundcloudIE ) :
2016-09-24 07:18:01 -05:00
@staticmethod
def _extract_id ( e ) :
return compat_str ( e [ ' id ' ] ) if e . get ( ' id ' ) else None
def _extract_track_entries ( self , tracks ) :
return [
self . url_result (
track [ ' permalink_url ' ] , SoundcloudIE . ie_key ( ) ,
video_id = self . _extract_id ( track ) )
for track in tracks if track . get ( ' permalink_url ' ) ]
2016-09-24 07:29:49 -05:00
class SoundcloudSetIE ( SoundcloudPlaylistBaseIE ) :
2015-03-30 10:03:38 -05:00
_VALID_URL = r ' https?://(?:(?:www|m) \ .)?soundcloud \ .com/(?P<uploader>[ \ w \ d-]+)/sets/(?P<slug_title>[ \ w \ d-]+)(?:/(?P<token>[^?/]+))? '
2014-01-16 20:29:41 -06:00
IE_NAME = ' soundcloud:set '
2014-08-27 17:58:24 -05:00
_TESTS = [ {
' url ' : ' https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep ' ,
' info_dict ' : {
2015-02-01 08:24:38 -06:00
' id ' : ' 2284613 ' ,
2014-08-27 17:58:24 -05:00
' title ' : ' The Royal Concept EP ' ,
} ,
2017-06-27 09:26:46 -05:00
' playlist_mincount ' : 5 ,
2016-08-30 13:56:15 -05:00
} , {
' url ' : ' https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep/token ' ,
' only_matching ' : True ,
2014-08-27 17:58:24 -05:00
} ]
2013-06-23 13:57:44 -05:00
def _real_extract ( self , url ) :
mobj = re . match ( self . _VALID_URL , url )
# extract uploader (which is in the url)
2014-09-18 04:35:11 -05:00
uploader = mobj . group ( ' uploader ' )
2013-06-23 13:57:44 -05:00
# extract simple title (uploader + slug of song title)
2014-09-18 04:35:11 -05:00
slug_title = mobj . group ( ' slug_title ' )
2013-06-23 13:57:44 -05:00
full_title = ' %s /sets/ %s ' % ( uploader , slug_title )
2017-06-27 09:20:18 -05:00
url = ' https://soundcloud.com/ %s /sets/ %s ' % ( uploader , slug_title )
2014-09-18 04:35:11 -05:00
token = mobj . group ( ' token ' )
if token :
full_title + = ' / ' + token
url + = ' / ' + token
2013-06-23 13:57:44 -05:00
2013-07-24 07:05:14 -05:00
resolv_url = self . _resolv_url ( url )
2014-05-04 20:12:41 -05:00
info = self . _download_json ( resolv_url , full_title )
2013-06-23 13:57:44 -05:00
if ' errors ' in info :
2015-04-17 12:24:30 -05:00
msgs = ( compat_str ( err [ ' error_message ' ] ) for err in info [ ' errors ' ] )
raise ExtractorError ( ' unable to download video webpage: %s ' % ' , ' . join ( msgs ) )
2013-06-23 13:57:44 -05:00
2016-09-24 07:18:01 -05:00
entries = self . _extract_track_entries ( info [ ' tracks ' ] )
2015-07-25 04:47:53 -05:00
2014-08-27 17:58:24 -05:00
return {
' _type ' : ' playlist ' ,
2015-07-25 04:47:53 -05:00
' entries ' : entries ,
2015-02-01 08:24:38 -06:00
' id ' : ' %s ' % info [ ' id ' ] ,
2014-08-27 17:58:24 -05:00
' title ' : info [ ' title ' ] ,
}
2013-09-14 14:41:49 -05:00
2017-07-29 06:41:42 -05:00
class SoundcloudPagedPlaylistBaseIE ( SoundcloudPlaylistBaseIE ) :
_API_V2_BASE = ' https://api-v2.soundcloud.com '
def _extract_playlist ( self , base_url , playlist_id , playlist_title ) :
COMMON_QUERY = {
' limit ' : 50 ,
' client_id ' : self . _CLIENT_ID ,
' linked_partitioning ' : ' 1 ' ,
}
query = COMMON_QUERY . copy ( )
query [ ' offset ' ] = 0
next_href = base_url + ' ? ' + compat_urllib_parse_urlencode ( query )
entries = [ ]
for i in itertools . count ( ) :
response = self . _download_json (
next_href , playlist_id , ' Downloading track page %s ' % ( i + 1 ) )
collection = response [ ' collection ' ]
2019-02-01 15:00:29 -06:00
if not isinstance ( collection , list ) :
collection = [ ]
# Empty collection may be returned, in this case we proceed
# straight to next_href
2017-07-29 06:41:42 -05:00
2019-02-02 10:40:06 -06:00
def resolve_entry ( candidates ) :
for cand in candidates :
if not isinstance ( cand , dict ) :
continue
permalink_url = url_or_none ( cand . get ( ' permalink_url ' ) )
if not permalink_url :
continue
return self . url_result (
permalink_url ,
ie = SoundcloudIE . ie_key ( ) if SoundcloudIE . suitable ( permalink_url ) else None ,
video_id = self . _extract_id ( cand ) ,
video_title = cand . get ( ' title ' ) )
2017-07-29 06:41:42 -05:00
for e in collection :
2019-02-02 10:40:06 -06:00
entry = resolve_entry ( ( e , e . get ( ' track ' ) , e . get ( ' playlist ' ) ) )
if entry :
entries . append ( entry )
2017-07-29 06:41:42 -05:00
next_href = response . get ( ' next_href ' )
if not next_href :
break
parsed_next_href = compat_urlparse . urlparse ( response [ ' next_href ' ] )
qs = compat_urlparse . parse_qs ( parsed_next_href . query )
qs . update ( COMMON_QUERY )
next_href = compat_urlparse . urlunparse (
parsed_next_href . _replace ( query = compat_urllib_parse_urlencode ( qs , True ) ) )
return {
' _type ' : ' playlist ' ,
' id ' : playlist_id ,
' title ' : playlist_title ,
' entries ' : entries ,
}
class SoundcloudUserIE ( SoundcloudPagedPlaylistBaseIE ) :
2015-07-31 16:50:03 -05:00
_VALID_URL = r ''' (?x)
https ? : / /
( ? : ( ? : www | m ) \. ) ? soundcloud \. com /
( ? P < user > [ ^ / ] + )
( ? : /
2019-02-01 15:00:29 -06:00
( ? P < rsrc > tracks | albums | sets | reposts | likes | spotlight )
2015-07-31 16:50:03 -05:00
) ?
/ ? ( ? : [ ? #].*)?$
'''
2014-01-16 20:29:41 -06:00
IE_NAME = ' soundcloud:user '
2014-08-27 17:58:24 -05:00
_TESTS = [ {
2019-02-01 15:11:32 -06:00
' url ' : ' https://soundcloud.com/soft-cell-official ' ,
2014-08-27 17:58:24 -05:00
' info_dict ' : {
2019-02-01 15:11:32 -06:00
' id ' : ' 207965082 ' ,
' title ' : ' Soft Cell (All) ' ,
2014-08-27 17:58:24 -05:00
} ,
2019-02-01 15:11:32 -06:00
' playlist_mincount ' : 28 ,
2014-08-27 17:58:24 -05:00
} , {
2019-02-01 15:11:32 -06:00
' url ' : ' https://soundcloud.com/soft-cell-official/tracks ' ,
2014-08-27 17:58:24 -05:00
' info_dict ' : {
2019-02-01 15:11:32 -06:00
' id ' : ' 207965082 ' ,
' title ' : ' Soft Cell (Tracks) ' ,
2014-08-27 17:58:24 -05:00
} ,
2019-02-01 15:11:32 -06:00
' playlist_mincount ' : 27 ,
2015-06-24 09:49:22 -05:00
} , {
2019-02-01 15:11:32 -06:00
' url ' : ' https://soundcloud.com/soft-cell-official/albums ' ,
' info_dict ' : {
' id ' : ' 207965082 ' ,
' title ' : ' Soft Cell (Albums) ' ,
} ,
' playlist_mincount ' : 1 ,
} , {
' url ' : ' https://soundcloud.com/jcv246/sets ' ,
2015-07-30 13:54:26 -05:00
' info_dict ' : {
2019-02-01 15:11:32 -06:00
' id ' : ' 12982173 ' ,
' title ' : ' Jordi / cv (Playlists) ' ,
2015-07-30 13:54:26 -05:00
} ,
2016-09-24 07:18:01 -05:00
' playlist_mincount ' : 2 ,
2015-07-30 13:54:26 -05:00
} , {
2019-02-01 15:11:32 -06:00
' url ' : ' https://soundcloud.com/jcv246/reposts ' ,
2015-07-30 13:54:26 -05:00
' info_dict ' : {
2019-02-01 15:11:32 -06:00
' id ' : ' 12982173 ' ,
' title ' : ' Jordi / cv (Reposts) ' ,
2015-07-30 13:54:26 -05:00
} ,
2019-02-01 15:11:32 -06:00
' playlist_mincount ' : 6 ,
2015-07-30 13:54:26 -05:00
} , {
2019-02-01 15:11:32 -06:00
' url ' : ' https://soundcloud.com/clalberg/likes ' ,
2015-07-30 13:54:26 -05:00
' info_dict ' : {
2019-02-01 15:11:32 -06:00
' id ' : ' 11817582 ' ,
' title ' : ' clalberg (Likes) ' ,
2015-07-30 13:54:26 -05:00
} ,
2019-02-01 15:11:32 -06:00
' playlist_mincount ' : 5 ,
2015-07-30 13:54:26 -05:00
} , {
' url ' : ' https://soundcloud.com/grynpyret/spotlight ' ,
' info_dict ' : {
' id ' : ' 7098329 ' ,
2017-06-27 09:26:46 -05:00
' title ' : ' Grynpyret (Spotlight) ' ,
2015-07-30 13:54:26 -05:00
} ,
' playlist_mincount ' : 1 ,
2014-08-27 17:58:24 -05:00
} ]
2013-09-14 14:41:49 -05:00
2015-07-30 13:54:26 -05:00
_BASE_URL_MAP = {
2019-02-01 15:00:29 -06:00
' all ' : ' %s /stream/users/ %% s ' % SoundcloudPagedPlaylistBaseIE . _API_V2_BASE ,
' tracks ' : ' %s /users/ %% s/tracks ' % SoundcloudPagedPlaylistBaseIE . _API_V2_BASE ,
' albums ' : ' %s /users/ %% s/albums ' % SoundcloudPagedPlaylistBaseIE . _API_V2_BASE ,
2017-07-29 06:41:42 -05:00
' sets ' : ' %s /users/ %% s/playlists ' % SoundcloudPagedPlaylistBaseIE . _API_V2_BASE ,
2019-02-01 15:00:29 -06:00
' reposts ' : ' %s /stream/users/ %% s/reposts ' % SoundcloudPagedPlaylistBaseIE . _API_V2_BASE ,
2017-07-29 06:41:42 -05:00
' likes ' : ' %s /users/ %% s/likes ' % SoundcloudPagedPlaylistBaseIE . _API_V2_BASE ,
' spotlight ' : ' %s /users/ %% s/spotlight ' % SoundcloudPagedPlaylistBaseIE . _API_V2_BASE ,
2015-07-30 13:54:26 -05:00
}
_TITLE_MAP = {
' all ' : ' All ' ,
' tracks ' : ' Tracks ' ,
2019-02-01 15:00:29 -06:00
' albums ' : ' Albums ' ,
2015-07-30 13:54:26 -05:00
' sets ' : ' Playlists ' ,
' reposts ' : ' Reposts ' ,
' likes ' : ' Likes ' ,
' spotlight ' : ' Spotlight ' ,
}
2013-09-14 14:41:49 -05:00
def _real_extract ( self , url ) :
mobj = re . match ( self . _VALID_URL , url )
uploader = mobj . group ( ' user ' )
2017-06-27 09:20:18 -05:00
url = ' https://soundcloud.com/ %s / ' % uploader
2013-09-14 14:41:49 -05:00
resolv_url = self . _resolv_url ( url )
2014-05-04 20:12:41 -05:00
user = self . _download_json (
resolv_url , uploader , ' Downloading user info ' )
2015-07-30 13:54:26 -05:00
resource = mobj . group ( ' rsrc ' ) or ' all '
2017-07-29 06:41:42 -05:00
return self . _extract_playlist (
self . _BASE_URL_MAP [ resource ] % user [ ' id ' ] , compat_str ( user [ ' id ' ] ) ,
' %s ( %s ) ' % ( user [ ' username ' ] , self . _TITLE_MAP [ resource ] ) )
2016-01-07 13:54:31 -06:00
2013-09-14 14:41:49 -05:00
2017-07-29 06:41:42 -05:00
class SoundcloudTrackStationIE ( SoundcloudPagedPlaylistBaseIE ) :
_VALID_URL = r ' https?://(?:(?:www|m) \ .)?soundcloud \ .com/stations/track/[^/]+/(?P<id>[^/?#&]+) '
IE_NAME = ' soundcloud:trackstation '
_TESTS = [ {
' url ' : ' https://soundcloud.com/stations/track/officialsundial/your-text ' ,
' info_dict ' : {
' id ' : ' 286017854 ' ,
' title ' : ' Track station: your-text ' ,
} ,
' playlist_mincount ' : 47 ,
} ]
2015-07-30 13:54:26 -05:00
2017-07-29 06:41:42 -05:00
def _real_extract ( self , url ) :
track_name = self . _match_id ( url )
2015-07-30 13:54:26 -05:00
2017-07-29 06:41:42 -05:00
webpage = self . _download_webpage ( url , track_name )
2016-01-07 13:54:31 -06:00
2017-07-29 06:41:42 -05:00
track_id = self . _search_regex (
r ' soundcloud:track-stations:( \ d+) ' , webpage , ' track id ' )
2013-09-14 14:41:49 -05:00
2017-07-29 06:41:42 -05:00
return self . _extract_playlist (
' %s /stations/soundcloud:track-stations: %s /tracks '
% ( self . _API_V2_BASE , track_id ) ,
track_id , ' Track station: %s ' % track_name )
2014-05-04 20:12:41 -05:00
2016-09-24 07:29:49 -05:00
class SoundcloudPlaylistIE ( SoundcloudPlaylistBaseIE ) :
2014-09-18 11:57:04 -05:00
_VALID_URL = r ' https?://api \ .soundcloud \ .com/playlists/(?P<id>[0-9]+)(?:/? \ ?secret_token=(?P<token>[^&]+?))?$ '
2014-05-04 20:12:41 -05:00
IE_NAME = ' soundcloud:playlist '
2014-09-18 11:57:04 -05:00
_TESTS = [ {
2017-06-27 09:20:18 -05:00
' url ' : ' https://api.soundcloud.com/playlists/4110309 ' ,
2014-09-18 11:57:04 -05:00
' info_dict ' : {
' id ' : ' 4110309 ' ,
' title ' : ' TILT Brass - Bowery Poetry Club, August \' 03 [Non-Site SCR 02] ' ,
' description ' : ' re:.*?TILT Brass - Bowery Poetry Club ' ,
} ,
' playlist_count ' : 6 ,
} ]
2014-05-04 20:12:41 -05:00
def _real_extract ( self , url ) :
mobj = re . match ( self . _VALID_URL , url )
playlist_id = mobj . group ( ' id ' )
base_url = ' %s //api.soundcloud.com/playlists/ %s .json? ' % ( self . http_scheme ( ) , playlist_id )
2014-09-18 04:35:11 -05:00
data_dict = {
2014-05-04 20:12:41 -05:00
' client_id ' : self . _CLIENT_ID ,
2014-09-18 04:35:11 -05:00
}
token = mobj . group ( ' token ' )
if token :
data_dict [ ' secret_token ' ] = token
2016-03-25 14:46:57 -05:00
data = compat_urllib_parse_urlencode ( data_dict )
2014-05-04 20:12:41 -05:00
data = self . _download_json (
base_url + data , playlist_id , ' Downloading playlist ' )
2016-09-24 07:18:01 -05:00
entries = self . _extract_track_entries ( data [ ' tracks ' ] )
2014-05-04 20:12:41 -05:00
return {
' _type ' : ' playlist ' ,
' id ' : playlist_id ,
' title ' : data . get ( ' title ' ) ,
' description ' : data . get ( ' description ' ) ,
' entries ' : entries ,
2013-09-14 14:41:49 -05:00
}
2015-10-17 11:23:46 -05:00
class SoundcloudSearchIE ( SearchInfoExtractor , SoundcloudIE ) :
IE_NAME = ' soundcloud:search '
IE_DESC = ' Soundcloud search '
2015-10-30 17:56:07 -05:00
_MAX_RESULTS = float ( ' inf ' )
2015-10-17 11:23:46 -05:00
_TESTS = [ {
' url ' : ' scsearch15:post-avant jazzcore ' ,
' info_dict ' : {
' title ' : ' post-avant jazzcore ' ,
} ,
' playlist_count ' : 15 ,
} ]
_SEARCH_KEY = ' scsearch '
2015-10-30 17:56:07 -05:00
_MAX_RESULTS_PER_PAGE = 200
_DEFAULT_RESULTS_PER_PAGE = 50
2015-10-17 14:18:42 -05:00
_API_V2_BASE = ' https://api-v2.soundcloud.com '
2015-10-17 11:23:46 -05:00
def _get_collection ( self , endpoint , collection_id , * * query ) :
2015-11-21 12:49:58 -06:00
limit = min (
2015-10-30 17:56:07 -05:00
query . get ( ' limit ' , self . _DEFAULT_RESULTS_PER_PAGE ) ,
self . _MAX_RESULTS_PER_PAGE )
2015-11-21 09:21:21 -06:00
query [ ' limit ' ] = limit
2015-10-17 11:23:46 -05:00
query [ ' client_id ' ] = self . _CLIENT_ID
query [ ' linked_partitioning ' ] = ' 1 '
2015-11-21 09:21:21 -06:00
query [ ' offset ' ] = 0
2016-03-25 14:46:57 -05:00
data = compat_urllib_parse_urlencode ( query )
2015-11-21 09:21:21 -06:00
next_url = ' {0} {1} ? {2} ' . format ( self . _API_V2_BASE , endpoint , data )
2015-10-17 11:23:46 -05:00
collected_results = 0
2015-11-21 09:21:21 -06:00
for i in itertools . count ( 1 ) :
2015-11-21 08:04:35 -06:00
response = self . _download_json (
2015-11-21 09:21:21 -06:00
next_url , collection_id , ' Downloading page {0} ' . format ( i ) ,
2015-11-21 08:04:35 -06:00
' Unable to download API page ' )
2015-10-17 11:23:46 -05:00
2015-11-21 09:21:21 -06:00
collection = response . get ( ' collection ' , [ ] )
if not collection :
break
2015-10-17 11:23:46 -05:00
2015-11-21 09:21:21 -06:00
collection = list ( filter ( bool , collection ) )
2015-10-17 11:23:46 -05:00
collected_results + = len ( collection )
2015-11-21 09:21:21 -06:00
for item in collection :
yield self . url_result ( item [ ' uri ' ] , SoundcloudIE . ie_key ( ) )
2015-10-17 11:23:46 -05:00
2015-11-21 09:21:21 -06:00
if not collection or collected_results > = limit :
2015-10-17 11:23:46 -05:00
break
2015-11-21 08:04:35 -06:00
next_url = response . get ( ' next_href ' )
2015-11-21 09:21:21 -06:00
if not next_url :
break
2015-10-17 11:23:46 -05:00
def _get_n_results ( self , query , n ) :
2015-11-21 09:21:21 -06:00
tracks = self . _get_collection ( ' /search/tracks ' , query , limit = n , q = query )
return self . playlist_result ( tracks , playlist_title = query )