aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/soundcloud.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/soundcloud.py')
-rw-r--r--youtube_dl/extractor/soundcloud.py237
1 files changed, 143 insertions, 94 deletions
diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py
index 29cd5617c..e22ff9c38 100644
--- a/youtube_dl/extractor/soundcloud.py
+++ b/youtube_dl/extractor/soundcloud.py
@@ -1,3 +1,4 @@
+# encoding: utf-8
import json
import re
import itertools
@@ -23,25 +24,72 @@ class SoundcloudIE(InfoExtractor):
"""
_VALID_URL = r'''^(?:https?://)?
- (?:(?:(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)/?(?:[?].*)?$)
+ (?:(?:(?:www\.|m\.)?soundcloud\.com/
+ (?P<uploader>[\w\d-]+)/
+ (?!sets/)(?P<title>[\w\d-]+)/?
+ (?P<token>[^?]+?)?(?:[?].*)?$)
|(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
- |(?P<widget>w.soundcloud.com/player/?.*?url=.*)
+ |(?P<widget>w\.soundcloud\.com/player/?.*?url=.*)
)
'''
IE_NAME = u'soundcloud'
- _TEST = {
- u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
- u'file': u'62986583.mp3',
- u'md5': u'ebef0a451b909710ed1d7787dddbf0d7',
- u'info_dict': {
- u"upload_date": u"20121011",
- u"description": u"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",
- u"uploader": u"E.T. ExTerrestrial Music",
- u"title": u"Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
- }
- }
+ _TESTS = [
+ {
+ u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
+ u'file': u'62986583.mp3',
+ u'md5': u'ebef0a451b909710ed1d7787dddbf0d7',
+ u'info_dict': {
+ u"upload_date": u"20121011",
+ u"description": u"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",
+ u"uploader": u"E.T. ExTerrestrial Music",
+ u"title": u"Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
+ }
+ },
+ # not streamable song
+ {
+ u'url': u'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep',
+ u'info_dict': {
+ u'id': u'47127627',
+ u'ext': u'mp3',
+ u'title': u'Goldrushed',
+ u'uploader': u'The Royal Concept',
+ u'upload_date': u'20120521',
+ },
+ u'params': {
+ # rtmp
+ u'skip_download': True,
+ },
+ },
+ # private link
+ {
+ u'url': u'https://soundcloud.com/jaimemf/youtube-dl-test-video-a-y-baw/s-8Pjrp',
+ u'md5': u'aa0dd32bfea9b0c5ef4f02aacd080604',
+ u'info_dict': {
+ u'id': u'123998367',
+ u'ext': u'mp3',
+ u'title': u'Youtube - Dl Test Video \'\' Ä↭',
+ u'uploader': u'jaimeMF',
+ u'description': u'test chars: \"\'/\\ä↭',
+ u'upload_date': u'20131209',
+ },
+ },
+ # downloadable song
+ {
+ u'url': u'https://soundcloud.com/simgretina/just-your-problem-baby-1',
+ u'md5': u'56a8b69568acaa967b4c49f9d1d52d19',
+ u'info_dict': {
+ u'id': u'105614606',
+ u'ext': u'wav',
+ u'title': u'Just Your Problem Baby (Acapella)',
+ u'description': u'Vocals',
+ u'uploader': u'Sim Gretina',
+ u'upload_date': u'20130815',
+ },
+ },
+ ]
_CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28'
+ _IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
@classmethod
def suitable(cls, url):
@@ -55,25 +103,85 @@ class SoundcloudIE(InfoExtractor):
def _resolv_url(cls, url):
return 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID
- def _extract_info_dict(self, info, full_title=None, quiet=False):
- video_id = info['id']
- name = full_title or video_id
- if quiet == False:
+ def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None):
+ track_id = compat_str(info['id'])
+ name = full_title or track_id
+ if quiet:
self.report_extraction(name)
thumbnail = info['artwork_url']
if thumbnail is not None:
thumbnail = thumbnail.replace('-large', '-t500x500')
- return {
- 'id': info['id'],
- 'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
+ ext = u'mp3'
+ result = {
+ 'id': track_id,
'uploader': info['user']['username'],
'upload_date': unified_strdate(info['created_at']),
- 'title': info['title'],
- 'ext': u'mp3',
+ 'title': info['title'],
'description': info['description'],
'thumbnail': thumbnail,
}
+ if info.get('downloadable', False):
+ # We can build a direct link to the song
+ format_url = (
+ u'https://api.soundcloud.com/tracks/{0}/download?client_id={1}'.format(
+ track_id, self._CLIENT_ID))
+ result['formats'] = [{
+ 'format_id': 'download',
+ 'ext': info.get('original_format', u'mp3'),
+ 'url': format_url,
+ 'vcodec': 'none',
+ }]
+ else:
+ # We have to retrieve the url
+ streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?'
+ 'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token))
+ stream_json = self._download_webpage(
+ streams_url,
+ track_id, u'Downloading track url')
+
+ formats = []
+ format_dict = json.loads(stream_json)
+ for key, stream_url in format_dict.items():
+ if key.startswith(u'http'):
+ formats.append({
+ 'format_id': key,
+ 'ext': ext,
+ 'url': stream_url,
+ 'vcodec': 'none',
+ })
+ elif key.startswith(u'rtmp'):
+ # The url doesn't have an rtmp app, we have to extract the playpath
+ url, path = stream_url.split('mp3:', 1)
+ formats.append({
+ 'format_id': key,
+ 'url': url,
+ 'play_path': 'mp3:' + path,
+ 'ext': ext,
+ 'vcodec': 'none',
+ })
+
+ 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': u'fallback',
+ 'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
+ 'ext': ext,
+ 'vcodec': 'none',
+ })
+
+ def format_pref(f):
+ if f['format_id'].startswith('http'):
+ return 2
+ if f['format_id'].startswith('rtmp'):
+ return 1
+ return 0
+
+ formats.sort(key=format_pref)
+ result['formats'] = formats
+
+ return result
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
@@ -81,6 +189,7 @@ class SoundcloudIE(InfoExtractor):
raise ExtractorError(u'Invalid URL: %s' % url)
track_id = mobj.group('track_id')
+ token = None
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
@@ -89,87 +198,28 @@ class SoundcloudIE(InfoExtractor):
return self.url_result(query['url'][0], ie='Soundcloud')
else:
# extract uploader (which is in the url)
- uploader = mobj.group(1)
+ uploader = mobj.group('uploader')
# extract simple title (uploader + slug of song title)
- slug_title = mobj.group(2)
- full_title = '%s/%s' % (uploader, slug_title)
+ slug_title = mobj.group('title')
+ token = mobj.group('token')
+ full_title = resolve_title = '%s/%s' % (uploader, slug_title)
+ if token:
+ resolve_title += '/%s' % token
self.report_resolve(full_title)
- url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
+ url = 'http://soundcloud.com/%s' % resolve_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)
+ return self._extract_info_dict(info, full_title, secret_token=token)
class SoundcloudSetIE(SoundcloudIE):
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)(?:[?].*)?$'
IE_NAME = u'soundcloud:set'
- _TEST = {
- u"url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
- u"playlist": [
- {
- u"file":"30510138.mp3",
- u"md5":"f9136bf103901728f29e419d2c70f55d",
- u"info_dict": {
- u"upload_date": u"20111213",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"D-D-Dance"
- }
- },
- {
- u"file":"47127625.mp3",
- u"md5":"09b6758a018470570f8fd423c9453dd8",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"The Royal Concept - Gimme Twice"
- }
- },
- {
- u"file":"47127627.mp3",
- u"md5":"154abd4e418cea19c3b901f1e1306d9c",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"uploader": u"The Royal Concept",
- u"title": u"Goldrushed"
- }
- },
- {
- u"file":"47127629.mp3",
- u"md5":"2f5471edc79ad3f33a683153e96a79c1",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"In the End"
- }
- },
- {
- u"file":"47127631.mp3",
- u"md5":"f9ba87aa940af7213f98949254f1c6e2",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / David / Povel / Magnus\r\nwww.theroyalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"Knocked Up"
- }
- },
- {
- u"file":"75206121.mp3",
- u"md5":"f9d1fe9406717e302980c30de4af9353",
- u"info_dict": {
- u"upload_date": u"20130116",
- 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! ",
- u"uploader": u"The Royal Concept",
- u"title": u"World On Fire"
- }
- }
- ]
- }
+ # it's in tests/test_playlists.py
+ _TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@@ -188,7 +238,6 @@ class SoundcloudSetIE(SoundcloudIE):
resolv_url = self._resolv_url(url)
info_json = self._download_webpage(resolv_url, full_title)
- videos = []
info = json.loads(info_json)
if 'errors' in info:
for err in info['errors']:
@@ -204,11 +253,11 @@ class SoundcloudSetIE(SoundcloudIE):
class SoundcloudUserIE(SoundcloudIE):
- _VALID_URL = r'https?://(www\.)?soundcloud.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
+ _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
IE_NAME = u'soundcloud:user'
# it's in tests/test_playlists.py
- _TEST = None
+ _TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
generated by cgit v1.2.3 (git 2.26.2) at 2025-10-31 05:50:04 +0000