[SoundcloudCom] Fix https://github.com/pyload/pyload/issues/1196

1 files changed, 43 insertions, 45 deletions

diff --git a/module/plugins/hoster/SoundcloudCom.py b/module/plugins/hoster/SoundcloudCom.py
index c7c9c3880..c559b392b 100644
--- a/module/plugins/hoster/SoundcloudCom.py
+++ b/module/plugins/hoster/SoundcloudCom.py
@@ -1,57 +1,55 @@
 # -*- coding: utf-8 -*-
 
-import pycurl
 import re
 
-from module.plugins.Hoster import Hoster
+from module.plugins.internal.SimpleHoster import SimpleHoster, create_getInfo
+from module.common.json_layer import json_loads
 
 
-class SoundcloudCom(Hoster):
+class SoundcloudCom(SimpleHoster):
     __name__    = "SoundcloudCom"
     __type__    = "hoster"
-    __version__ = "0.10"
+    __version__ = "0.11"
 
-    __pattern__ = r'https?://(?:www\.)?soundcloud\.com/(?P<UID>.+?)/(?P<SID>.+)'
+    __pattern__ = r'https?://(?:www\.)?soundcloud\.com/[\w-]+/[\w-]+'
+    __config__  = [("quality", "Lower;Higher", "Quality", "Higher")]
 
     __description__ = """SoundCloud.com hoster plugin"""
     __license__     = "GPLv3"
-    __authors__     = [("Peekayy", "peekayy.dev@gmail.com")]
-
-
-    def process(self, pyfile):
-        # default UserAgent of HTTPRequest fails for this hoster so we use this one
-        self.req.http.c.setopt(pycurl.USERAGENT, 'Mozilla/5.0')
-        self.html = self.load(pyfile.url)
-        m = re.search(r'<div class="haudio.*?large.*?" data-sc-track="(?P<ID>\d*)"', self.html)
-        songId = clientId = ""
-        if m:
-            songId = m.group('ID')
-        if len(songId) <= 0:
-            self.logError(_("Could not find song id"))
-            self.offline()
-        else:
-            m = re.search(r'"clientID":"(?P<CID>.*?)"', self.html)
-            if m:
-                clientId = m.group('CID')
-
-            if len(clientId) <= 0:
-                clientId = "b45b1aa10f1ac2941910a7f0d10f8e28"
-
-            m = re.search(r'<em itemprop="name">\s(?P<TITLE>.*?)\s</em>', self.html)
-            if m:
-                pyfile.name = m.group('TITLE') + ".mp3"
-            else:
-                pyfile.name = re.match(self.__pattern__, pyfile.url).group('SID') + ".mp3"
-
-            # url to retrieve the actual song url
-            self.html = self.load("https://api.sndcdn.com/i1/tracks/%s/streams" % songId, get={"client_id": clientId})
-            # getting streams
-            # for now we choose the first stream found in all cases
-            # it could be improved if relevant for this hoster
-            streams = [
-                (result.group('QUALITY'), result.group('URL'))
-                for result in re.finditer(r'"(?P<QUALITY>.*?)":"(?P<URL>.*?)"', self.html)
-            ]
-            self.logDebug("Found Streams", streams)
-            self.logDebug("Downloading", streams[0][0], streams[0][1])
-            self.download(streams[0][1])
+    __authors__     = [("Walter Purcaro", "vuolter@gmail.com")]
+
+
+    NAME_PATTERN    = r'title" content="(?P<N>.+?)"'
+    OFFLINE_PATTERN = r'<title>"SoundCloud - Hear the world’s sounds"</title>'
+
+
+    def handleFree(self, pyfile):
+        try:
+            song_id = re.search(r'sounds:(\d+)"', self.html).group(1)
+
+        except Exception:
+            self.error(_("Could not find song id"))
+
+        try:
+            client_id = re.search(r'"clientID":"(.+?)"', self.html).group(1)
+
+        except Exception:
+            client_id = "b45b1aa10f1ac2941910a7f0d10f8e28"
+
+        # url to retrieve the actual song url
+        streams = json_loads(self.load("https://api.soundcloud.com/tracks/%s/streams" % song_id,
+                             get={'client_id': client_id}))
+
+        regex = re.compile(r'[^\d]')
+        http_streams = sorted([(key, value) for key, value in streams.iteritems() if key.startswith('http_')],
+                              key=lambda t: regex.sub(t[0], ''),
+                              reverse=True)
+
+        self.logDebug("Streams found: %s" % (http_streams or "None"))
+
+        if http_streams:
+            stream_name, self.link = http_streams[0 if self.getConfig('quality') == "Higher" else -1]
+            pyfile.name += '.' + stream_name.split('_')[1].lower()
+
+
+getInfo = create_getInfo(SoundcloudCom)