X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fsoundcloud.py;h=c23c5ee0fb853f86e4662ad574b587610456159c;hb=363cf58645d021810b7fd579084de07471407ae3;hp=2bed3c35094dc6482420b5ea9c0b709729964270;hpb=2f834e938192a61fd4a32fa98bffb5e1b614bc29;p=youtube-dl.git
diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py
index 2bed3c350..c23c5ee0f 100644
--- a/youtube_dl/extractor/soundcloud.py
+++ b/youtube_dl/extractor/soundcloud.py
@@ -5,11 +5,12 @@ import re
import itertools
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_str,
compat_urlparse,
compat_urllib_parse,
-
+)
+from ..utils import (
ExtractorError,
int_or_none,
unified_strdate,
@@ -32,7 +33,7 @@ class SoundcloudIE(InfoExtractor):
(?P
[\w\d-]+)/?
(?P[^?]+?)?(?:[?].*)?$)
|(?:api\.soundcloud\.com/tracks/(?P\d+)
- (?:/?\?secret_token=(?P[^&]+?))?$)
+ (?:/?\?secret_token=(?P[^&]+))?)
|(?P(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*)
)
'''
@@ -40,14 +41,15 @@ class SoundcloudIE(InfoExtractor):
_TESTS = [
{
'url': 'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
- 'file': '62986583.mp3',
'md5': 'ebef0a451b909710ed1d7787dddbf0d7',
'info_dict': {
- "upload_date": "20121011",
- "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",
- "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1",
- "duration": 143,
+ 'id': '62986583',
+ 'ext': 'mp3',
+ 'upload_date': '20121011',
+ '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',
+ 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1',
+ 'duration': 143,
}
},
# not streamable song
@@ -103,7 +105,7 @@ class SoundcloudIE(InfoExtractor):
'id': '128590877',
'ext': 'mp3',
'title': 'Bus Brakes',
- 'description': 'md5:0170be75dd395c96025d210d261c784e',
+ 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66',
'uploader': 'oddsamples',
'upload_date': '20140109',
'duration': 17,
@@ -140,6 +142,7 @@ class SoundcloudIE(InfoExtractor):
'description': info['description'],
'thumbnail': thumbnail,
'duration': int_or_none(info.get('duration'), 1000),
+ 'webpage_url': info.get('permalink_url'),
}
formats = []
if info.get('downloadable', False):
@@ -157,7 +160,7 @@ class SoundcloudIE(InfoExtractor):
# 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))
+ 'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token))
format_dict = self._download_json(
streams_url,
track_id, 'Downloading track url')
@@ -177,7 +180,7 @@ class SoundcloudIE(InfoExtractor):
'format_id': key,
'url': url,
'play_path': 'mp3:' + path,
- 'ext': ext,
+ 'ext': 'flv',
'vcodec': 'none',
})
@@ -197,8 +200,9 @@ class SoundcloudIE(InfoExtractor):
if f['format_id'].startswith('rtmp'):
f['protocol'] = 'rtmp'
- self._sort_formats(formats)
- result['formats'] = formats
+ self._check_formats(formats, track_id)
+ self._sort_formats(formats)
+ result['formats'] = formats
return result
@@ -217,19 +221,24 @@ class SoundcloudIE(InfoExtractor):
info_json_url += "&secret_token=" + token
elif mobj.group('player'):
query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
- return self.url_result(query['url'][0])
+ 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)
else:
# extract uploader (which is in the url)
uploader = mobj.group('uploader')
# extract simple title (uploader + slug of song title)
- slug_title = mobj.group('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' % resolve_title
info_json_url = self._resolv_url(url)
info = self._download_json(info_json_url, full_title, 'Downloading info JSON')
@@ -238,11 +247,12 @@ class SoundcloudIE(InfoExtractor):
class SoundcloudSetIE(SoundcloudIE):
- _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/(?P[\w\d-]+)/sets/(?P[\w\d-]+)(?:/(?P[^?/]+))?'
+ _VALID_URL = r'https?://(?:(?:www|m)\.)?soundcloud\.com/(?P[\w\d-]+)/sets/(?P[\w\d-]+)(?:/(?P[^?/]+))?'
IE_NAME = 'soundcloud:set'
_TESTS = [{
'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep',
'info_dict': {
+ 'id': '2284613',
'title': 'The Royal Concept EP',
},
'playlist_mincount': 6,
@@ -269,20 +279,19 @@ class SoundcloudSetIE(SoundcloudIE):
info = self._download_json(resolv_url, full_title)
if 'errors' in info:
- for err in info['errors']:
- self._downloader.report_error('unable to download video webpage: %s' % compat_str(err['error_message']))
- return
+ msgs = (compat_str(err['error_message']) for err in info['errors'])
+ raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs))
return {
'_type': 'playlist',
'entries': [self._extract_info_dict(track, secret_token=token) for track in info['tracks']],
- 'id': info['id'],
+ 'id': '%s' % info['id'],
'title': info['title'],
}
class SoundcloudUserIE(SoundcloudIE):
- _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P[^/]+)/?((?Ptracks|likes)/?)?(\?.*)?$'
+ _VALID_URL = r'https?://(?:(?:www|m)\.)?soundcloud\.com/(?P[^/]+)/?((?Ptracks|likes)/?)?(\?.*)?$'
IE_NAME = 'soundcloud:user'
_TESTS = [{
'url': 'https://soundcloud.com/the-concept-band',
@@ -327,7 +336,7 @@ class SoundcloudUserIE(SoundcloudIE):
if len(new_entries) == 0:
self.to_screen('%s: End page received' % uploader)
break
- entries.extend(self._extract_info_dict(e, quiet=True) for e in new_entries)
+ entries.extend(self.url_result(e['permalink_url'], 'Soundcloud') for e in new_entries)
return {
'_type': 'playlist',
@@ -338,20 +347,17 @@ class SoundcloudUserIE(SoundcloudIE):
class SoundcloudPlaylistIE(SoundcloudIE):
- _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P[0-9]+)(?:/?\?secret_token=(?P[^&]+?))$'
+ _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P[0-9]+)(?:/?\?secret_token=(?P[^&]+?))?$'
IE_NAME = 'soundcloud:playlist'
- _TESTS = [
-
- {
- 'url': 'http://api.soundcloud.com/playlists/4110309',
- '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,
- }
- ]
+ _TESTS = [{
+ 'url': 'http://api.soundcloud.com/playlists/4110309',
+ '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,
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@@ -372,7 +378,7 @@ class SoundcloudPlaylistIE(SoundcloudIE):
entries = [
self._extract_info_dict(t, quiet=True, secret_token=token)
- for t in data['tracks']]
+ for t in data['tracks']]
return {
'_type': 'playlist',