2016-10-02 07:39:18 -04:00
# coding: utf-8
2014-01-16 21:29:41 -05:00
from __future__ import unicode_literals
2013-09-14 15:41:49 -04:00
import itertools
2017-09-01 04:08:24 -04:00
import re
2013-06-23 14:57:44 -04:00
2015-10-17 12:23:46 -04:00
from . common import (
InfoExtractor ,
SearchInfoExtractor
)
2014-12-13 06:24:42 -05:00
from . . compat import (
2019-12-31 03:49:29 -05:00
compat_HTTPError ,
compat_kwargs ,
2013-06-23 14:57:44 -04:00
compat_str ,
2013-08-21 11:06:37 -04:00
compat_urlparse ,
2014-12-13 06:24:42 -05:00
)
from . . utils import (
2019-12-31 15:31:22 -05:00
error_to_compat_str ,
2013-06-23 14:57:44 -04:00
ExtractorError ,
2019-04-22 13:39:16 -04:00
float_or_none ,
2019-10-27 12:52:46 -04:00
HEADRequest ,
2014-06-07 09:51:01 -04:00
int_or_none ,
2019-04-22 13:39:16 -04:00
KNOWN_EXTENSIONS ,
mimetype2ext ,
str_or_none ,
2019-02-10 11:44:08 -05:00
try_get ,
unified_timestamp ,
2017-09-03 05:18:24 -04:00
update_url_query ,
2019-02-02 11:40:06 -05:00
url_or_none ,
2017-09-03 05:18:24 -04:00
)
2013-06-23 14:57:44 -04:00
2019-10-27 12:52:46 -04:00
class SoundcloudEmbedIE ( InfoExtractor ) :
2019-12-09 08:38:12 -05:00
_VALID_URL = r ' https?://(?:w|player|p) \ .soundcloud \ .com/player/?.*? \ burl=(?P<id>.+) '
_TEST = {
# from https://www.soundi.fi/uutiset/ennakkokuuntelussa-timo-kaukolammen-station-to-station-to-station-julkaisua-juhlitaan-tanaan-g-livelabissa/
' url ' : ' https://w.soundcloud.com/player/?visual=true&url=https % 3A %2F %2F api.soundcloud.com %2F playlists %2F 922213810&show_artwork=true&maxwidth=640&maxheight=960&dnt=1&secret_token=s-ziYey ' ,
' only_matching ' : True ,
}
2019-10-27 12:52:46 -04:00
@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 ) ]
def _real_extract ( self , url ) :
2019-12-09 08:38:12 -05:00
query = compat_urlparse . parse_qs (
compat_urlparse . urlparse ( url ) . query )
api_url = query [ ' url ' ] [ 0 ]
secret_token = query . get ( ' secret_token ' )
if secret_token :
api_url = update_url_query ( api_url , { ' secret_token ' : secret_token [ 0 ] } )
return self . url_result ( api_url )
2019-10-27 12:52:46 -04:00
2013-06-23 14:57:44 -04:00
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 21:12:41 -04:00
_VALID_URL = r ''' (?x)^(?:https?://)?
2013-12-19 10:39:01 -05:00
( ? : ( ? : ( ? : www \. | m \. ) ? soundcloud \. com /
2017-07-29 07:41:42 -04:00
( ? ! stations / track )
2013-12-09 13:57:00 -05:00
( ? P < uploader > [ \w \d - ] + ) /
2019-02-01 16:00:29 -05:00
( ? ! ( ? : tracks | albums | sets ( ? : / . + ? ) ? | reposts | likes | spotlight ) / ? ( ? : $ | [ ? #]))
2014-08-27 18:58:24 -04:00
( ? P < title > [ \w \d - ] + ) / ?
2013-12-09 11:08:58 -05:00
( ? P < token > [ ^ ? ] + ? ) ? ( ? : [ ? ] . * ) ? $ )
2019-10-27 12:52:46 -04:00
| ( ? : api ( ? : - v2 ) ? \. soundcloud \. com / tracks / ( ? P < track_id > \d + )
2014-12-03 05:49:53 -05:00
( ? : / ? \? secret_token = ( ? P < secret_token > [ ^ & ] + ) ) ? )
2013-07-24 08:39:21 -04:00
)
'''
2014-01-16 21:29:41 -05:00
IE_NAME = ' soundcloud '
2013-11-09 12:06:09 -05:00
_TESTS = [
{
2014-01-16 21:29:41 -05:00
' url ' : ' http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy ' ,
' md5 ' : ' ebef0a451b909710ed1d7787dddbf0d7 ' ,
' info_dict ' : {
2014-10-25 16:32:01 -04:00
' id ' : ' 62986583 ' ,
' ext ' : ' mp3 ' ,
2019-02-10 11:44:08 -05:00
' title ' : ' Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1 ' ,
2014-10-25 16:32:01 -04:00
' 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 ' ,
2019-10-27 12:52:46 -04:00
' uploader_id ' : ' 1571244 ' ,
2019-02-10 11:44:08 -05:00
' timestamp ' : 1349920598 ,
' upload_date ' : ' 20121011 ' ,
2019-04-22 13:39:16 -04:00
' duration ' : 143.216 ,
2016-09-18 05:53:05 -04:00
' license ' : ' all-rights-reserved ' ,
2019-02-10 11:44:08 -05:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2013-11-09 12:06:09 -05:00
}
} ,
2020-01-14 16:13:10 -05:00
# not streamable song, preview
2013-11-09 12:06:09 -05:00
{
2014-01-16 21:29:41 -05:00
' 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 07:20:34 -04:00
' description ' : ' From Stockholm Sweden \r \n Povel / Magnus / Filip / David \r \n www.theroyalconcept.com ' ,
2014-01-16 21:29:41 -05:00
' uploader ' : ' The Royal Concept ' ,
2019-10-27 12:52:46 -04:00
' uploader_id ' : ' 9615865 ' ,
2019-02-10 11:44:08 -05:00
' timestamp ' : 1337635207 ,
2014-01-16 21:29:41 -05:00
' upload_date ' : ' 20120521 ' ,
2019-02-10 11:44:08 -05:00
' duration ' : 30 ,
2016-09-18 05:53:05 -04:00
' license ' : ' all-rights-reserved ' ,
2019-02-10 11:44:08 -05:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2013-11-09 12:06:09 -05:00
} ,
2014-01-16 21:29:41 -05:00
' params ' : {
2013-11-09 12:06:09 -05:00
# rtmp
2014-01-16 21:29:41 -05:00
' skip_download ' : True ,
2013-11-09 12:06:09 -05:00
} ,
} ,
2013-12-09 11:08:58 -05:00
# private link
{
2014-01-16 21:29:41 -05:00
' 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 11:44:08 -05:00
' uploader ' : ' jaimeMF ' ,
2019-10-27 12:52:46 -04:00
' uploader_id ' : ' 69767071 ' ,
2019-02-10 11:44:08 -05:00
' timestamp ' : 1386604920 ,
2014-01-16 21:29:41 -05:00
' upload_date ' : ' 20131209 ' ,
2019-04-22 13:39:16 -04:00
' duration ' : 9.927 ,
2016-09-18 05:53:05 -04:00
' license ' : ' all-rights-reserved ' ,
2019-02-10 11:44:08 -05:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2013-12-09 11:08:58 -05:00
} ,
} ,
2014-09-18 02:02:03 -04:00
# 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 11:44:08 -05:00
' uploader ' : ' jaimeMF ' ,
2019-10-27 12:52:46 -04:00
' uploader_id ' : ' 69767071 ' ,
2019-02-10 11:44:08 -05:00
' timestamp ' : 1386604920 ,
2014-09-18 02:02:03 -04:00
' upload_date ' : ' 20131209 ' ,
2019-04-22 13:39:16 -04:00
' duration ' : 9.927 ,
2016-09-18 05:53:05 -04:00
' license ' : ' all-rights-reserved ' ,
2019-02-10 11:44:08 -05:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2014-09-18 02:02:03 -04:00
} ,
} ,
2013-12-10 07:04:21 -05:00
# downloadable song
{
2014-07-15 08:18:06 -04:00
' url ' : ' https://soundcloud.com/oddsamples/bus-brakes ' ,
2014-07-22 19:41:44 -04:00
' md5 ' : ' 7624f2351f8a3b2e7cd51522496e7631 ' ,
2014-01-16 21:29:41 -05:00
' info_dict ' : {
2014-07-15 08:18:06 -04:00
' id ' : ' 128590877 ' ,
2014-07-22 19:41:44 -04:00
' ext ' : ' mp3 ' ,
2014-07-15 08:18:06 -04:00
' title ' : ' Bus Brakes ' ,
2014-10-25 16:32:01 -04:00
' description ' : ' md5:0053ca6396e8d2fd7b7e1595ef12ab66 ' ,
2014-07-15 08:18:06 -04:00
' uploader ' : ' oddsamples ' ,
2019-10-27 12:52:46 -04:00
' uploader_id ' : ' 73680509 ' ,
2019-02-10 11:44:08 -05:00
' timestamp ' : 1389232924 ,
2014-07-15 08:18:06 -04:00
' upload_date ' : ' 20140109 ' ,
2019-04-22 13:39:16 -04:00
' duration ' : 17.346 ,
2016-09-18 05:53:05 -04:00
' license ' : ' cc-by-sa ' ,
2019-02-10 11:44:08 -05:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2013-12-10 07:04:21 -05:00
} ,
} ,
2017-09-03 05:18:24 -04:00
# 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 ' ,
2019-10-27 12:52:46 -04:00
' uploader_id ' : ' 12563093 ' ,
2019-02-10 11:44:08 -05:00
' timestamp ' : 1504206263 ,
2017-09-03 05:18:24 -04:00
' upload_date ' : ' 20170831 ' ,
2019-04-22 13:39:16 -04:00
' duration ' : 7449.096 ,
2017-09-03 05:18:24 -04:00
' license ' : ' all-rights-reserved ' ,
2019-02-10 11:44:08 -05:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2017-09-03 05:18:24 -04:00
} ,
} ,
2018-01-04 20:25:42 -05:00
# 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 ' ,
2019-10-27 12:52:46 -04:00
' uploader_id ' : ' 2366352 ' ,
2019-02-10 11:44:08 -05:00
' timestamp ' : 1488152409 ,
2018-01-04 20:25:42 -05:00
' upload_date ' : ' 20170226 ' ,
2019-04-22 13:39:16 -04:00
' duration ' : 207.012 ,
2018-01-04 20:25:42 -05:00
' thumbnail ' : r ' re:https?://.* \ .jpg ' ,
' license ' : ' all-rights-reserved ' ,
2019-02-10 11:44:08 -05:00
' view_count ' : int ,
' like_count ' : int ,
' comment_count ' : int ,
' repost_count ' : int ,
2018-01-04 20:25:42 -05:00
} ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2019-07-26 11:30:18 -04:00
# not available via api.soundcloud.com/i1/tracks/id/streams
2019-04-22 13:39:16 -04:00
{
' url ' : ' https://soundcloud.com/giovannisarani/mezzo-valzer ' ,
' md5 ' : ' e22aecd2bc88e0e4e432d7dcc0a1abf7 ' ,
' info_dict ' : {
' id ' : ' 583011102 ' ,
' ext ' : ' mp3 ' ,
' title ' : ' Mezzo Valzer ' ,
' description ' : ' md5:4138d582f81866a530317bae316e8b61 ' ,
' uploader ' : ' Giovanni Sarani ' ,
2019-10-27 12:52:46 -04:00
' uploader_id ' : ' 3352531 ' ,
2019-04-22 13:39:16 -04:00
' 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 12:06:09 -05:00
]
2013-06-23 14:57:44 -04:00
2019-10-27 12:52:46 -04:00
_API_BASE = ' https://api.soundcloud.com/ '
_API_V2_BASE = ' https://api-v2.soundcloud.com/ '
_BASE_URL = ' https://soundcloud.com/ '
_IMAGE_REPL_RE = r ' -([0-9a-z]+) \ .jpg '
_ARTWORK_MAP = {
' mini ' : 16 ,
' tiny ' : 20 ,
' small ' : 32 ,
' badge ' : 47 ,
' t67x67 ' : 67 ,
' large ' : 100 ,
' t300x300 ' : 300 ,
' crop ' : 400 ,
' t500x500 ' : 500 ,
' original ' : 0 ,
}
2016-07-28 11:16:05 -04:00
2019-12-31 15:31:22 -05:00
def _store_client_id ( self , client_id ) :
self . _downloader . cache . store ( ' soundcloud ' , ' client_id ' , client_id )
2019-12-31 03:49:29 -05:00
def _update_client_id ( self ) :
webpage = self . _download_webpage ( ' https://soundcloud.com/ ' , None )
for src in reversed ( re . findall ( r ' <script[^>]+src= " ([^ " ]+) " ' , webpage ) ) :
script = self . _download_webpage ( src , None , fatal = False )
if script :
client_id = self . _search_regex (
r ' client_id \ s*: \ s* " ([0-9a-zA-Z] {32} ) " ' ,
script , ' client id ' , default = None )
if client_id :
self . _CLIENT_ID = client_id
2019-12-31 15:31:22 -05:00
self . _store_client_id ( client_id )
2019-12-31 03:49:29 -05:00
return
raise ExtractorError ( ' Unable to extract client id ' )
def _download_json ( self , * args , * * kwargs ) :
2019-12-31 15:31:22 -05:00
non_fatal = kwargs . get ( ' fatal ' ) is False
if non_fatal :
del kwargs [ ' fatal ' ]
2019-12-31 03:49:29 -05:00
query = kwargs . get ( ' query ' , { } ) . copy ( )
for _ in range ( 2 ) :
query [ ' client_id ' ] = self . _CLIENT_ID
kwargs [ ' query ' ] = query
try :
return super ( SoundcloudIE , self ) . _download_json ( * args , * * compat_kwargs ( kwargs ) )
except ExtractorError as e :
if isinstance ( e . cause , compat_HTTPError ) and e . cause . code == 401 :
2019-12-31 15:31:22 -05:00
self . _store_client_id ( None )
2019-12-31 03:49:29 -05:00
self . _update_client_id ( )
continue
2019-12-31 15:31:22 -05:00
elif non_fatal :
self . _downloader . report_warning ( error_to_compat_str ( e ) )
return False
2019-12-31 03:49:29 -05:00
raise
def _real_initialize ( self ) :
self . _CLIENT_ID = self . _downloader . cache . load ( ' soundcloud ' , ' client_id ' ) or ' YUKXoArFcqrlQn9tfNHvvyfnDISj04zk '
2013-07-24 08:05:14 -04:00
@classmethod
def _resolv_url ( cls , url ) :
2019-12-31 03:49:29 -05:00
return SoundcloudIE . _API_V2_BASE + ' resolve?url= ' + url
2013-07-24 08:05:14 -04:00
2019-10-27 12:52:46 -04:00
def _extract_info_dict ( self , info , full_title = None , secret_token = None , version = 2 ) :
2013-11-09 12:06:09 -05:00
track_id = compat_str ( info [ ' id ' ] )
2019-02-10 11:44:08 -05:00
title = info [ ' title ' ]
2019-10-27 12:52:46 -04:00
track_base_url = self . _API_BASE + ' tracks/ %s ' % track_id
2019-04-22 13:39:16 -04:00
format_urls = set ( )
2014-03-23 21:21:17 -04:00
formats = [ ]
2017-09-01 04:08:24 -04:00
query = { ' client_id ' : self . _CLIENT_ID }
2019-10-27 12:52:46 -04:00
if secret_token :
2017-09-01 04:08:24 -04:00
query [ ' secret_token ' ] = secret_token
2019-10-27 12:52:46 -04:00
2019-11-11 03:53:04 -05:00
if info . get ( ' downloadable ' ) and info . get ( ' has_downloads_left ' ) :
2017-09-01 04:08:24 -04:00
format_url = update_url_query (
2019-10-27 12:52:46 -04:00
info . get ( ' download_url ' ) or track_base_url + ' /download ' , query )
2019-04-22 13:39:16 -04:00
format_urls . add ( format_url )
2019-10-27 12:52:46 -04:00
if version == 2 :
v1_info = self . _download_json (
track_base_url , track_id , query = query , fatal = False ) or { }
else :
v1_info = info
2014-03-23 21:21:17 -04:00
formats . append ( {
2013-11-25 14:30:41 -05:00
' format_id ' : ' download ' ,
2019-10-27 12:52:46 -04:00
' ext ' : v1_info . get ( ' original_format ' ) or ' mp3 ' ,
' filesize ' : int_or_none ( v1_info . get ( ' original_content_size ' ) ) ,
2013-11-25 14:30:41 -05:00
' url ' : format_url ,
2014-03-23 21:21:17 -04:00
' preference ' : 10 ,
} )
2019-10-27 12:52:46 -04:00
def invalid_url ( url ) :
2020-01-14 16:13:10 -05:00
return not url or url in format_urls
2019-04-22 13:39:16 -04:00
2020-01-14 16:13:10 -05:00
def add_format ( f , protocol , is_preview = False ) :
2019-10-27 12:52:46 -04:00
mobj = re . search ( r ' \ .(?P<abr> \ d+) \ .(?P<ext>[0-9a-z] { 3,4})(?=[/?]) ' , stream_url )
if mobj :
for k , v in mobj . groupdict ( ) . items ( ) :
if not f . get ( k ) :
f [ k ] = v
format_id_list = [ ]
if protocol :
format_id_list . append ( protocol )
for k in ( ' ext ' , ' abr ' ) :
v = f . get ( k )
if v :
format_id_list . append ( v )
2020-01-14 16:13:10 -05:00
preview = is_preview or re . search ( r ' /(?:preview|playlist)/0/30/ ' , f [ ' url ' ] )
if preview :
format_id_list . append ( ' preview ' )
2019-10-27 12:52:46 -04:00
abr = f . get ( ' abr ' )
if abr :
f [ ' abr ' ] = int ( abr )
f . update ( {
' format_id ' : ' _ ' . join ( format_id_list ) ,
' protocol ' : ' m3u8_native ' if protocol == ' hls ' else ' http ' ,
2020-01-14 16:13:10 -05:00
' preference ' : - 10 if preview else None ,
2019-10-27 12:52:46 -04:00
} )
formats . append ( f )
2019-04-22 13:39:16 -04:00
# 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 11:16:30 -05:00
continue
2019-04-22 13:39:16 -04:00
format_url = url_or_none ( t . get ( ' url ' ) )
2020-01-14 16:13:10 -05:00
if not format_url :
2019-04-22 13:39:16 -04:00
continue
stream = self . _download_json (
2019-10-27 12:52:46 -04:00
format_url , track_id , query = query , fatal = False )
2019-04-22 13:39:16 -04:00
if not isinstance ( stream , dict ) :
continue
stream_url = url_or_none ( stream . get ( ' url ' ) )
2019-10-27 12:52:46 -04:00
if invalid_url ( stream_url ) :
2019-04-22 13:39:16 -04:00
continue
format_urls . add ( stream_url )
2019-10-27 12:52:46 -04:00
stream_format = t . get ( ' format ' ) or { }
protocol = stream_format . get ( ' protocol ' )
2019-04-22 13:39:16 -04:00
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 ]
2019-10-27 12:52:46 -04:00
if ext not in KNOWN_EXTENSIONS :
ext = mimetype2ext ( stream_format . get ( ' mime_type ' ) )
add_format ( {
2019-04-22 13:39:16 -04:00
' url ' : stream_url ,
' ext ' : ext ,
2020-01-14 16:13:10 -05:00
} , ' http ' if protocol == ' progressive ' else protocol ,
t . get ( ' snipped ' ) or ' /preview/ ' in format_url )
2019-10-27 12:52:46 -04:00
if not formats :
# Old API, does not work for some tracks (e.g.
# https://soundcloud.com/giovannisarani/mezzo-valzer)
# and might serve preview URLs (e.g.
# http://www.soundcloud.com/snbrn/ele)
format_dict = self . _download_json (
track_base_url + ' /streams ' , track_id ,
' Downloading track url ' , query = query , fatal = False ) or { }
for key , stream_url in format_dict . items ( ) :
if invalid_url ( stream_url ) :
continue
format_urls . add ( stream_url )
mobj = re . search ( r ' (http|hls)_([^_]+)_( \ d+)_url ' , key )
if mobj :
protocol , ext , abr = mobj . groups ( )
add_format ( {
' abr ' : abr ,
' ext ' : ext ,
' url ' : stream_url ,
} , protocol )
2017-01-27 11:16:30 -05:00
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
2019-10-27 12:52:46 -04:00
urlh = self . _request_webpage (
HEADRequest ( info . get ( ' stream_url ' ) or track_base_url + ' /stream ' ) ,
track_id , query = query , fatal = False )
if urlh :
stream_url = urlh . geturl ( )
if not invalid_url ( stream_url ) :
add_format ( { ' url ' : stream_url } , ' http ' )
2017-01-27 11:16:30 -05:00
for f in formats :
f [ ' vcodec ' ] = ' none '
2013-11-25 14:30:41 -05:00
2015-03-02 11:39:32 -05:00
self . _sort_formats ( formats )
2013-11-21 07:16:19 -05:00
2019-10-27 12:52:46 -04:00
user = info . get ( ' user ' ) or { }
thumbnails = [ ]
artwork_url = info . get ( ' artwork_url ' )
thumbnail = artwork_url or user . get ( ' avatar_url ' )
if isinstance ( thumbnail , compat_str ) :
if re . search ( self . _IMAGE_REPL_RE , thumbnail ) :
for image_id , size in self . _ARTWORK_MAP . items ( ) :
i = {
' id ' : image_id ,
' url ' : re . sub ( self . _IMAGE_REPL_RE , ' - %s .jpg ' % image_id , thumbnail ) ,
}
if image_id == ' tiny ' and not artwork_url :
size = 18
elif image_id == ' original ' :
i [ ' preference ' ] = 10
if size :
i . update ( {
' width ' : size ,
' height ' : size ,
} )
thumbnails . append ( i )
else :
thumbnails = [ { ' url ' : thumbnail } ]
def extract_count ( key ) :
return int_or_none ( info . get ( ' %s _count ' % key ) )
return {
' id ' : track_id ,
' uploader ' : user . get ( ' username ' ) ,
' uploader_id ' : str_or_none ( user . get ( ' id ' ) ) or user . get ( ' permalink ' ) ,
' uploader_url ' : user . get ( ' permalink_url ' ) ,
' timestamp ' : unified_timestamp ( info . get ( ' created_at ' ) ) ,
' title ' : title ,
' description ' : info . get ( ' description ' ) ,
' thumbnails ' : thumbnails ,
' duration ' : float_or_none ( info . get ( ' duration ' ) , 1000 ) ,
' webpage_url ' : info . get ( ' permalink_url ' ) ,
' license ' : info . get ( ' license ' ) ,
' view_count ' : extract_count ( ' playback ' ) ,
' like_count ' : extract_count ( ' favoritings ' ) or extract_count ( ' likes ' ) ,
' comment_count ' : extract_count ( ' comment ' ) ,
' repost_count ' : extract_count ( ' reposts ' ) ,
' genre ' : info . get ( ' genre ' ) ,
' formats ' : formats
}
2013-07-24 08:05:14 -04:00
2013-06-23 14:57:44 -04:00
def _real_extract ( self , url ) :
2019-10-27 12:52:46 -04:00
mobj = re . match ( self . _VALID_URL , url )
2013-06-23 14:57:44 -04:00
2013-07-24 08:39:21 -04:00
track_id = mobj . group ( ' track_id ' )
2016-09-18 05:53:05 -04:00
2019-12-31 03:49:29 -05:00
query = { }
2019-10-27 12:52:46 -04:00
if track_id :
info_json_url = self . _API_V2_BASE + ' tracks/ ' + track_id
2013-07-24 08:39:21 -04:00
full_title = track_id
2014-09-18 02:02:03 -04:00
token = mobj . group ( ' secret_token ' )
if token :
2019-10-27 12:52:46 -04:00
query [ ' secret_token ' ] = token
2013-07-24 08:39:21 -04:00
else :
2019-10-27 12:52:46 -04:00
full_title = resolve_title = ' %s / %s ' % mobj . group ( ' uploader ' , ' title ' )
2013-12-09 11:08:58 -05:00
token = mobj . group ( ' token ' )
if token :
resolve_title + = ' / %s ' % token
2019-10-27 12:52:46 -04:00
info_json_url = self . _resolv_url ( self . _BASE_URL + resolve_title )
2014-11-23 14:41:03 -05:00
2019-10-27 12:52:46 -04:00
version = 2
2019-04-22 13:39:16 -04:00
info = self . _download_json (
2019-10-27 12:52:46 -04:00
info_json_url , full_title , ' Downloading info JSON ' , query = query , fatal = False )
if not info :
info = self . _download_json (
info_json_url . replace ( self . _API_V2_BASE , self . _API_BASE ) ,
full_title , ' Downloading info JSON ' , query = query )
version = 1
2019-04-22 13:39:16 -04:00
2019-10-27 12:52:46 -04:00
return self . _extract_info_dict ( info , full_title , token , version )
2013-06-23 14:57:44 -04:00
2014-05-04 21:12:41 -04:00
2016-09-24 08:29:49 -04:00
class SoundcloudPlaylistBaseIE ( SoundcloudIE ) :
2019-10-27 12:52:46 -04:00
def _extract_track_entries ( self , tracks , token = None ) :
entries = [ ]
for track in tracks :
track_id = str_or_none ( track . get ( ' id ' ) )
url = track . get ( ' permalink_url ' )
if not url :
if not track_id :
continue
url = self . _API_V2_BASE + ' tracks/ ' + track_id
if token :
url + = ' ?secret_token= ' + token
entries . append ( self . url_result (
url , SoundcloudIE . ie_key ( ) , track_id ) )
return entries
2016-09-24 08:18:01 -04:00
2016-09-24 08:29:49 -04:00
class SoundcloudSetIE ( SoundcloudPlaylistBaseIE ) :
2015-03-30 11:03:38 -04:00
_VALID_URL = r ' https?://(?:(?:www|m) \ .)?soundcloud \ .com/(?P<uploader>[ \ w \ d-]+)/sets/(?P<slug_title>[ \ w \ d-]+)(?:/(?P<token>[^?/]+))? '
2014-01-16 21:29:41 -05:00
IE_NAME = ' soundcloud:set '
2014-08-27 18:58:24 -04:00
_TESTS = [ {
' url ' : ' https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep ' ,
' info_dict ' : {
2015-02-01 09:24:38 -05:00
' id ' : ' 2284613 ' ,
2014-08-27 18:58:24 -04:00
' title ' : ' The Royal Concept EP ' ,
} ,
2017-06-27 10:26:46 -04:00
' playlist_mincount ' : 5 ,
2016-08-30 14:56:15 -04:00
} , {
' url ' : ' https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep/token ' ,
' only_matching ' : True ,
2014-08-27 18:58:24 -04:00
} ]
2013-06-23 14:57:44 -04:00
def _real_extract ( self , url ) :
mobj = re . match ( self . _VALID_URL , url )
2019-10-27 12:52:46 -04:00
full_title = ' %s /sets/ %s ' % mobj . group ( ' uploader ' , ' slug_title ' )
2014-09-18 05:35:11 -04:00
token = mobj . group ( ' token ' )
if token :
full_title + = ' / ' + token
2013-06-23 14:57:44 -04:00
2019-10-27 12:52:46 -04:00
info = self . _download_json ( self . _resolv_url (
self . _BASE_URL + full_title ) , full_title )
2013-06-23 14:57:44 -04:00
if ' errors ' in info :
2015-04-17 13:24:30 -04:00
msgs = ( compat_str ( err [ ' error_message ' ] ) for err in info [ ' errors ' ] )
raise ExtractorError ( ' unable to download video webpage: %s ' % ' , ' . join ( msgs ) )
2013-06-23 14:57:44 -04:00
2019-10-27 12:52:46 -04:00
entries = self . _extract_track_entries ( info [ ' tracks ' ] , token )
2015-07-25 05:47:53 -04:00
2019-10-27 12:52:46 -04:00
return self . playlist_result (
entries , str_or_none ( info . get ( ' id ' ) ) , info . get ( ' title ' ) )
2013-09-14 15:41:49 -04:00
2017-07-29 07:41:42 -04:00
class SoundcloudPagedPlaylistBaseIE ( SoundcloudPlaylistBaseIE ) :
def _extract_playlist ( self , base_url , playlist_id , playlist_title ) :
COMMON_QUERY = {
2019-10-27 12:52:46 -04:00
' limit ' : 2000000000 ,
2017-07-29 07:41:42 -04:00
' linked_partitioning ' : ' 1 ' ,
}
query = COMMON_QUERY . copy ( )
query [ ' offset ' ] = 0
2019-10-27 12:52:46 -04:00
next_href = base_url
2017-07-29 07:41:42 -04:00
entries = [ ]
for i in itertools . count ( ) :
response = self . _download_json (
2019-10-27 12:52:46 -04:00
next_href , playlist_id ,
' Downloading track page %s ' % ( i + 1 ) , query = query )
2017-07-29 07:41:42 -04:00
collection = response [ ' collection ' ]
2019-02-01 16:00:29 -05:00
if not isinstance ( collection , list ) :
collection = [ ]
# Empty collection may be returned, in this case we proceed
# straight to next_href
2017-07-29 07:41:42 -04:00
2019-02-02 11:40:06 -05:00
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 ,
2019-10-27 12:52:46 -04:00
SoundcloudIE . ie_key ( ) if SoundcloudIE . suitable ( permalink_url ) else None ,
str_or_none ( cand . get ( ' id ' ) ) , cand . get ( ' title ' ) )
2017-07-29 07:41:42 -04:00
for e in collection :
2019-02-02 11:40:06 -05:00
entry = resolve_entry ( ( e , e . get ( ' track ' ) , e . get ( ' playlist ' ) ) )
if entry :
entries . append ( entry )
2017-07-29 07:41:42 -04:00
next_href = response . get ( ' next_href ' )
if not next_href :
break
2019-10-27 12:52:46 -04:00
next_href = response [ ' next_href ' ]
parsed_next_href = compat_urlparse . urlparse ( next_href )
query = compat_urlparse . parse_qs ( parsed_next_href . query )
query . update ( COMMON_QUERY )
2017-07-29 07:41:42 -04:00
return {
' _type ' : ' playlist ' ,
' id ' : playlist_id ,
' title ' : playlist_title ,
' entries ' : entries ,
}
class SoundcloudUserIE ( SoundcloudPagedPlaylistBaseIE ) :
2015-07-31 17:50:03 -04:00
_VALID_URL = r ''' (?x)
https ? : / /
( ? : ( ? : www | m ) \. ) ? soundcloud \. com /
( ? P < user > [ ^ / ] + )
( ? : /
2019-02-01 16:00:29 -05:00
( ? P < rsrc > tracks | albums | sets | reposts | likes | spotlight )
2015-07-31 17:50:03 -04:00
) ?
/ ? ( ? : [ ? #].*)?$
'''
2014-01-16 21:29:41 -05:00
IE_NAME = ' soundcloud:user '
2014-08-27 18:58:24 -04:00
_TESTS = [ {
2019-02-01 16:11:32 -05:00
' url ' : ' https://soundcloud.com/soft-cell-official ' ,
2014-08-27 18:58:24 -04:00
' info_dict ' : {
2019-02-01 16:11:32 -05:00
' id ' : ' 207965082 ' ,
' title ' : ' Soft Cell (All) ' ,
2014-08-27 18:58:24 -04:00
} ,
2019-02-01 16:11:32 -05:00
' playlist_mincount ' : 28 ,
2014-08-27 18:58:24 -04:00
} , {
2019-02-01 16:11:32 -05:00
' url ' : ' https://soundcloud.com/soft-cell-official/tracks ' ,
2014-08-27 18:58:24 -04:00
' info_dict ' : {
2019-02-01 16:11:32 -05:00
' id ' : ' 207965082 ' ,
' title ' : ' Soft Cell (Tracks) ' ,
2014-08-27 18:58:24 -04:00
} ,
2019-02-01 16:11:32 -05:00
' playlist_mincount ' : 27 ,
2015-06-24 10:49:22 -04:00
} , {
2019-02-01 16:11:32 -05:00
' 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 14:54:26 -04:00
' info_dict ' : {
2019-02-01 16:11:32 -05:00
' id ' : ' 12982173 ' ,
2019-10-27 12:52:46 -04:00
' title ' : ' Jordi / cv (Sets) ' ,
2015-07-30 14:54:26 -04:00
} ,
2016-09-24 08:18:01 -04:00
' playlist_mincount ' : 2 ,
2015-07-30 14:54:26 -04:00
} , {
2019-02-01 16:11:32 -05:00
' url ' : ' https://soundcloud.com/jcv246/reposts ' ,
2015-07-30 14:54:26 -04:00
' info_dict ' : {
2019-02-01 16:11:32 -05:00
' id ' : ' 12982173 ' ,
' title ' : ' Jordi / cv (Reposts) ' ,
2015-07-30 14:54:26 -04:00
} ,
2019-02-01 16:11:32 -05:00
' playlist_mincount ' : 6 ,
2015-07-30 14:54:26 -04:00
} , {
2019-02-01 16:11:32 -05:00
' url ' : ' https://soundcloud.com/clalberg/likes ' ,
2015-07-30 14:54:26 -04:00
' info_dict ' : {
2019-02-01 16:11:32 -05:00
' id ' : ' 11817582 ' ,
' title ' : ' clalberg (Likes) ' ,
2015-07-30 14:54:26 -04:00
} ,
2019-02-01 16:11:32 -05:00
' playlist_mincount ' : 5 ,
2015-07-30 14:54:26 -04:00
} , {
' url ' : ' https://soundcloud.com/grynpyret/spotlight ' ,
' info_dict ' : {
' id ' : ' 7098329 ' ,
2017-06-27 10:26:46 -04:00
' title ' : ' Grynpyret (Spotlight) ' ,
2015-07-30 14:54:26 -04:00
} ,
' playlist_mincount ' : 1 ,
2014-08-27 18:58:24 -04:00
} ]
2013-09-14 15:41:49 -04:00
2015-07-30 14:54:26 -04:00
_BASE_URL_MAP = {
2019-10-27 12:52:46 -04:00
' all ' : ' stream/users/ %s ' ,
' tracks ' : ' users/ %s /tracks ' ,
' albums ' : ' users/ %s /albums ' ,
' sets ' : ' users/ %s /playlists ' ,
' reposts ' : ' stream/users/ %s /reposts ' ,
' likes ' : ' users/ %s /likes ' ,
' spotlight ' : ' users/ %s /spotlight ' ,
2015-07-30 14:54:26 -04:00
}
2013-09-14 15:41:49 -04:00
def _real_extract ( self , url ) :
mobj = re . match ( self . _VALID_URL , url )
uploader = mobj . group ( ' user ' )
2014-05-04 21:12:41 -04:00
user = self . _download_json (
2019-10-27 12:52:46 -04:00
self . _resolv_url ( self . _BASE_URL + uploader ) ,
uploader , ' Downloading user info ' )
2015-07-30 14:54:26 -04:00
resource = mobj . group ( ' rsrc ' ) or ' all '
2017-07-29 07:41:42 -04:00
return self . _extract_playlist (
2019-10-27 12:52:46 -04:00
self . _API_V2_BASE + self . _BASE_URL_MAP [ resource ] % user [ ' id ' ] ,
str_or_none ( user . get ( ' id ' ) ) ,
' %s ( %s ) ' % ( user [ ' username ' ] , resource . capitalize ( ) ) )
2016-01-07 14:54:31 -05:00
2013-09-14 15:41:49 -04:00
2017-07-29 07:41:42 -04:00
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 ' ,
2019-10-27 12:52:46 -04:00
' title ' : ' Track station: your text ' ,
2017-07-29 07:41:42 -04:00
} ,
' playlist_mincount ' : 47 ,
} ]
2015-07-30 14:54:26 -04:00
2017-07-29 07:41:42 -04:00
def _real_extract ( self , url ) :
track_name = self . _match_id ( url )
2015-07-30 14:54:26 -04:00
2019-10-27 12:52:46 -04:00
track = self . _download_json ( self . _resolv_url ( url ) , track_name )
2017-07-29 07:41:42 -04:00
track_id = self . _search_regex (
2019-10-27 12:52:46 -04:00
r ' soundcloud:track-stations:( \ d+) ' , track [ ' id ' ] , ' track id ' )
2013-09-14 15:41:49 -04:00
2017-07-29 07:41:42 -04:00
return self . _extract_playlist (
2019-10-27 12:52:46 -04:00
self . _API_V2_BASE + ' stations/ %s /tracks ' % track [ ' id ' ] ,
track_id , ' Track station: %s ' % track [ ' title ' ] )
2014-05-04 21:12:41 -04:00
2016-09-24 08:29:49 -04:00
class SoundcloudPlaylistIE ( SoundcloudPlaylistBaseIE ) :
2019-10-27 12:52:46 -04:00
_VALID_URL = r ' https?://api(?:-v2)? \ .soundcloud \ .com/playlists/(?P<id>[0-9]+)(?:/? \ ?secret_token=(?P<token>[^&]+?))?$ '
2014-05-04 21:12:41 -04:00
IE_NAME = ' soundcloud:playlist '
2014-09-18 12:57:04 -04:00
_TESTS = [ {
2017-06-27 10:20:18 -04:00
' url ' : ' https://api.soundcloud.com/playlists/4110309 ' ,
2014-09-18 12:57:04 -04:00
' 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 21:12:41 -04:00
def _real_extract ( self , url ) :
mobj = re . match ( self . _VALID_URL , url )
playlist_id = mobj . group ( ' id ' )
2019-12-31 03:49:29 -05:00
query = { }
2014-09-18 05:35:11 -04:00
token = mobj . group ( ' token ' )
if token :
2019-10-27 12:52:46 -04:00
query [ ' secret_token ' ] = token
2014-09-18 05:35:11 -04:00
2014-05-04 21:12:41 -04:00
data = self . _download_json (
2019-10-27 12:52:46 -04:00
self . _API_V2_BASE + ' playlists/ ' + playlist_id ,
playlist_id , ' Downloading playlist ' , query = query )
2014-05-04 21:12:41 -04:00
2019-10-27 12:52:46 -04:00
entries = self . _extract_track_entries ( data [ ' tracks ' ] , token )
2014-05-04 21:12:41 -04:00
2019-10-27 12:52:46 -04:00
return self . playlist_result (
entries , playlist_id , data . get ( ' title ' ) , data . get ( ' description ' ) )
2015-10-17 12:23:46 -04:00
class SoundcloudSearchIE ( SearchInfoExtractor , SoundcloudIE ) :
IE_NAME = ' soundcloud:search '
IE_DESC = ' Soundcloud search '
2015-10-30 18:56:07 -04:00
_MAX_RESULTS = float ( ' inf ' )
2015-10-17 12:23:46 -04:00
_TESTS = [ {
' url ' : ' scsearch15:post-avant jazzcore ' ,
' info_dict ' : {
' title ' : ' post-avant jazzcore ' ,
} ,
' playlist_count ' : 15 ,
} ]
_SEARCH_KEY = ' scsearch '
2015-10-30 18:56:07 -04:00
_MAX_RESULTS_PER_PAGE = 200
_DEFAULT_RESULTS_PER_PAGE = 50
2015-10-17 12:23:46 -04:00
def _get_collection ( self , endpoint , collection_id , * * query ) :
2015-11-21 13:49:58 -05:00
limit = min (
2015-10-30 18:56:07 -04:00
query . get ( ' limit ' , self . _DEFAULT_RESULTS_PER_PAGE ) ,
self . _MAX_RESULTS_PER_PAGE )
2019-10-27 12:52:46 -04:00
query . update ( {
' limit ' : limit ,
' linked_partitioning ' : 1 ,
' offset ' : 0 ,
} )
next_url = update_url_query ( self . _API_V2_BASE + endpoint , query )
2015-10-17 12:23:46 -04:00
collected_results = 0
2015-11-21 10:21:21 -05:00
for i in itertools . count ( 1 ) :
2015-11-21 09:04:35 -05:00
response = self . _download_json (
2015-11-21 10:21:21 -05:00
next_url , collection_id , ' Downloading page {0} ' . format ( i ) ,
2015-11-21 09:04:35 -05:00
' Unable to download API page ' )
2015-10-17 12:23:46 -04:00
2015-11-21 10:21:21 -05:00
collection = response . get ( ' collection ' , [ ] )
if not collection :
break
2015-10-17 12:23:46 -04:00
2015-11-21 10:21:21 -05:00
collection = list ( filter ( bool , collection ) )
2015-10-17 12:23:46 -04:00
collected_results + = len ( collection )
2015-11-21 10:21:21 -05:00
for item in collection :
yield self . url_result ( item [ ' uri ' ] , SoundcloudIE . ie_key ( ) )
2015-10-17 12:23:46 -04:00
2015-11-21 10:21:21 -05:00
if not collection or collected_results > = limit :
2015-10-17 12:23:46 -04:00
break
2015-11-21 09:04:35 -05:00
next_url = response . get ( ' next_href ' )
2015-11-21 10:21:21 -05:00
if not next_url :
break
2015-10-17 12:23:46 -04:00
def _get_n_results ( self , query , n ) :
2019-10-27 12:52:46 -04:00
tracks = self . _get_collection ( ' search/tracks ' , query , limit = n , q = query )
2015-11-21 10:21:21 -05:00
return self . playlist_result ( tracks , playlist_title = query )