[soundcloud] Add an extractor for users (closes #1426)

diff --git a/test/test_playlists.py b/test/test_playlists.py
index 4a2e00b01a5a368a8ef2b14ecae231e53491935c..d079a4f23217d3a9216048a37e62f83b999e7763 100644 (file)
--- a/test/test_playlists.py
+++ b/test/test_playlists.py
@@ -8,7 +8,7 @@ import json
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 

-from youtube_dl.extractor import DailymotionPlaylistIE, VimeoChannelIE, UstreamChannelIE
+from youtube_dl.extractor import DailymotionPlaylistIE, VimeoChannelIE, UstreamChannelIE, SoundcloudUserIE

 from youtube_dl.utils import *
 
 from helper import FakeYDL
 from youtube_dl.utils import *
 
 from helper import FakeYDL


@@ -42,5 +42,13 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['id'], u'5124905')
         self.assertTrue(len(result['entries']) >= 11)
 
         self.assertEqual(result['id'], u'5124905')
         self.assertTrue(len(result['entries']) >= 11)
 

+    def test_soundcloud_user(self):
+        dl = FakeYDL()
+        ie = SoundcloudUserIE(dl)
+        result = ie.extract('https://soundcloud.com/the-concept-band')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], u'9615865')
+        self.assertTrue(len(result['entries']) >= 12)
+

 if __name__ == '__main__':
     unittest.main()
 if __name__ == '__main__':
     unittest.main()

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 06f9542d2389d8f2455b98e7532c4b4c6fea3944..19d57c2e9f77bcbb02381acf965f6855139b1504 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -82,7 +82,7 @@ from .sina import SinaIE
 from .slashdot import SlashdotIE
 from .slideshare import SlideshareIE
 from .sohu import SohuIE
 from .slashdot import SlashdotIE
 from .slideshare import SlideshareIE
 from .sohu import SohuIE

-from .soundcloud import SoundcloudIE, SoundcloudSetIE
+from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE

 from .spiegel import SpiegelIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .statigram import StatigramIE
 from .spiegel import SpiegelIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .statigram import StatigramIE

diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py
index 5f3a5540d2775ae1952d31ab86447ed5151e952f..29cd5617c7d1919fa95e0b48e7ff35585106b800 100644 (file)
--- a/youtube_dl/extractor/soundcloud.py
+++ b/youtube_dl/extractor/soundcloud.py
@@ -1,10 +1,12 @@
 import json
 import re
 import json
 import re

+import itertools

 
 from .common import InfoExtractor
 from ..utils import (
     compat_str,
     compat_urlparse,
 
 from .common import InfoExtractor
 from ..utils import (
     compat_str,
     compat_urlparse,

+    compat_urllib_parse,

 
     ExtractorError,
     unified_strdate,
 
     ExtractorError,
     unified_strdate,


@@ -53,10 +55,11 @@ class SoundcloudIE(InfoExtractor):
     def _resolv_url(cls, url):
         return 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID
 
     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):
+    def _extract_info_dict(self, info, full_title=None, quiet=False):

         video_id = info['id']
         name = full_title or video_id
         video_id = info['id']
         name = full_title or video_id

-        self.report_extraction(name)
+        if quiet == False:
+            self.report_extraction(name)

 
         thumbnail = info['artwork_url']
         if thumbnail is not None:
 
         thumbnail = info['artwork_url']
         if thumbnail is not None:


@@ -198,3 +201,41 @@ class SoundcloudSetIE(SoundcloudIE):
                 'id': info['id'],
                 'title': info['title'],
                 }
                 'id': info['id'],
                 'title': info['title'],
                 }

+
+
+class SoundcloudUserIE(SoundcloudIE):
+    _VALID_URL = r'https?://(www\.)?soundcloud.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
+    IE_NAME = u'soundcloud:user'
+
+    # it's in tests/test_playlists.py
+    _TEST = None
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        uploader = mobj.group('user')
+
+        url = 'http://soundcloud.com/%s/' % uploader
+        resolv_url = self._resolv_url(url)
+        user_json = self._download_webpage(resolv_url, uploader,
+            u'Downloading user info')
+        user = json.loads(user_json)
+
+        tracks = []
+        for i in itertools.count():
+            data = compat_urllib_parse.urlencode({'offset': i*50,
+                                                  'client_id': self._CLIENT_ID,
+                                                  })
+            tracks_url = 'http://api.soundcloud.com/users/%s/tracks.json?' % user['id'] + data
+            response = self._download_webpage(tracks_url, uploader, 
+                u'Downloading tracks page %s' % (i+1))
+            new_tracks = json.loads(response)
+            tracks.extend(self._extract_info_dict(track, quiet=True) for track in new_tracks)
+            if len(new_tracks) < 50:
+                break
+
+        return {
+            '_type': 'playlist',
+            'id': compat_str(user['id']),
+            'title': user['username'],
+            'entries': tracks,
+        }