Audio albums sorting and README update

Rast1234 · Jul 4, 2013 · e8234e2 · e8234e2
1 parent 0559848
commit e8234e2
Show file tree

Hide file tree

Showing 2 changed files with 46 additions and 10 deletions.
diff --git a/PostParser.py b/PostParser.py
@@ -26,7 +26,34 @@ def escape(name):
     """Escape the filename"""
     result =  unicode(re.sub('[^+=\-()$!#%&,.\w\s]', '_', name, flags=re.UNICODE).strip())
     #print("\t{}\n\t{}".format(name, result))
-    return result[:100]
+    return result[:250]
+
+def get_album_name(*args):
+    """Try to find and cache album name"""
+    names = {}
+    def inner_function(owner, album, args):
+        """Wrapped get_album_name function"""
+        key = "{}_{}".format(str(owner), str(album))
+        try:
+            return names[key]
+        except KeyError:
+            #get all albums once
+            print("Building album index...")
+            (data, json_stuff) = call_api("audio.getAlbums", [("owner_id", owner), ("offset", 0), ("count", 1)], args)
+            count = data[0]
+            for x in xrange(count):
+                (data, json_stuff) = call_api("audio.getAlbums", [("owner_id", owner), ("offset", x), ("count", 1)], args)
+                oid = data[1][u'owner_id']
+                aid = data[1][u'album_id']
+                val = data[1]['title']
+                tmp_key = "{}_{}".format(oid, aid)
+                names[tmp_key] = val
+                logging.info(u"Found album: owner={}  id={}    name={}".format(oid, aid, val))
+            print("Album index OK, count: {}".format(count))
+            return names[key]
+    return inner_function
+get_album_name = get_album_name()  # boo!
+
 
 class PostParser(object):
     """Parses given post into data lists (text, music, photos, info, etc.)
@@ -233,19 +260,26 @@ def dl_photos_list(self, data):
             self.dl_photo(x)
 
     def dl_audio(self, data):
+        initial_data = data
         aid = data["aid"]
         owner = data["owner_id"]
         request = "{}_{}".format(owner, aid)
         (audio_data, json_stuff) = call_api("audio.getById", [("audios", request), ], self.args)
+        album = ''
         try:
             data = audio_data[0]
-            name = u"{artist} - {title}.mp3".format(**data)
-            self.save_url(data["url"], name)
+            artist = data['artist'][:100]
+            title= data['title'][:100]
+            name = u"{} - {}.mp3".format(artist, title)
+            album = data['album']
+            album = get_album_name(owner, album, self.args)
+            album = escape(album)
+            make_dir(self.post_directory, album)
+            self.save_url(data["url"], name, album)
         except IndexError: # deleted :(
-            logging.warning("Deleted track: {}".format(str(data)))
+            logging.warning("Deleted track: {}".format(str(initial_data)))
             return
 
-
         # store lyrics if any
         try:
             lid = data["lyrics_id"]
@@ -254,7 +288,8 @@ def dl_audio(self, data):
         (lyrics_data, json_stuff) = call_api("audio.getLyrics", [("lyrics_id", lid), ], self.args)
         text = lyrics_data["text"].encode('utf-8')
         name = escape(name)
-        f_name = path.join(self.post_directory, name+'.txt')
+        f_name = path.join(self.post_directory, album)
+        f_name = path.join(f_name, name+'.txt')
         # escape!
         out_file = open(f_name, 'a+')
         out_file.write(text)

diff --git a/README.md b/README.md
@@ -15,7 +15,7 @@ VK dumper - save stuff from your vk.com to local drive
 * Download audio tracks
     * Correct fime naming
     * Text stored also (if available)
-    * **TODO:** sort by playlists
+    * Sort by playlists (as subfolders)
 * Download docs
     * Auto-change filename if exists
     * Write correct extension
@@ -24,11 +24,10 @@ VK dumper - save stuff from your vk.com to local drive
 
 **Known limitations, bugs and other considerations:**
 
-* Unable to download videos (Someone need this?)
+* Unable to download videos (Anyone need this?)
 * Unable to download note comments (Maybe an unneeded feature?)
-* Tested on a particular user, not tested on a group
+* Tested on a particular user, audio tested on a group
 * Can't grant access by itself, so you need to enter auth token manually (see below)
-* Not tested on Windows
 * If wall, documents or audio list has been modified during work, it **will** cause unpredictable things.
 * Sometimes you need to solve CAPTCHA (interactively)
 
@@ -76,6 +75,8 @@ Everything will be stored in specified directory, say, `some_dir`:
             |     +---- Artist1 - Track.mp3
             |     +---- Artist2 - Track.mp3
             |     +---- Artist2 - Track.mp3.txt    (text for that song)
+			|     +---- Album1                     (audio album name)
+            |     |     +---- Artist - track.mp3   (tracks in that album)
             |     +---- ...
             +---- post_1234                        (wall post id)
             |     +---- text.html                  (post text)