Adding a no-overwrites option that avoids re-downloading a song if it already exists locally

spotify_dl/spotify_dl.py

@@ -35,6 +35,9 @@ def spotify_dl():
                         help='Don\'t convert downloaded songs to mp3')
     parser.add_argument('-s', '--scrape', action="store",
                         help="Use HTML Scraper for YouTube Search", default=True)
+    parser.add_argument('-w', '--no-overwrites', action='store_true',
+                        help="Whether we should avoid overwriting the target audio file if it already exists",
+                        default=False)
     parser.add_argument('-V', '--verbose', action='store_true',
                         help='Show more information on what''s happening.')
     parser.add_argument('-v', '--version', action='store_true',
@@ -88,7 +91,8 @@ def spotify_dl():
         if args.keep_playlist_order:
             file_name_f = playlist_num_filename
 
-        download_songs(songs, save_path, args.format_str, args.skip_mp3, args.keep_playlist_order, file_name_f)
+        download_songs(songs, save_path, args.format_str, args.skip_mp3, args.keep_playlist_order, args.no_overwrites,
+                       file_name_f)
 
 
 if __name__ == '__main__':

spotify_dl/youtube.py

@@ -20,16 +20,18 @@ def playlist_num_filename(song):
 
 
 def download_songs(songs, download_directory, format_string, skip_mp3,
-                   keep_playlist_order=False, file_name_f=default_filename):
+                   keep_playlist_order=False, no_overwrites=False, file_name_f=default_filename):
     """
     Downloads songs from the YouTube URL passed to either current directory or download_directory, is it is passed.
     :param songs: Dictionary of songs and associated artist
     :param download_directory: Location where to save
     :param format_string: format string for the file conversion
     :param skip_mp3: Whether to skip conversion to MP3
     :param keep_playlist_order: Whether to keep original playlist ordering. Also, prefixes songs files with playlist num
+    :param no_overwrites: Whether we should avoid overwriting the song if it already exists
     :param file_name_f: optional func(song) -> str that returns a filename for the download (without extension)
     """
+    overwrites = not no_overwrites
     log.debug(f"Downloading to {download_directory}")
     for song in songs:
         query = f"{song.get('artist')} - {song.get('name')} Lyrics".replace(":", "").replace("\"", "")
@@ -66,25 +68,36 @@ def download_songs(songs, download_directory, format_string, skip_mp3,
                 continue
 
         if not skip_mp3:
-            try:
-                song_file = MP3(path.join(f"{file_path}.mp3"), ID3=EasyID3)
-            except mutagen.MutagenError as e:
-                log.debug(e)
-                print('Failed to download: {}, please ensure YouTubeDL is up-to-date. '.format(query))
-                continue
-            song_file['date'] = song.get('year')
-            if keep_playlist_order:
-                song_file['tracknumber'] = str(song.get('playlist_num'))
+            mp3filename = f"{file_path}.mp3"
+            mp3file_path = path.join(mp3filename)
+            if overwrites or not path.exists(mp3file_path):
+                try:
+                    song_file = MP3(mp3file_path, ID3=EasyID3)
+                except mutagen.MutagenError as e:
+                    log.debug(e)
+                    print('Failed to download: {}, please ensure YouTubeDL is up-to-date. '.format(query))
+                    continue
+                song_file['date'] = song.get('year')
+                if keep_playlist_order:
+                    song_file['tracknumber'] = str(song.get('playlist_num'))
+                else:
+                    song_file['tracknumber'] = str(song.get('num')) + '/' + str(song.get('num_tracks'))
+                song_file['genre'] = song.get('genre')
+                song_file.save()
+                song_file = MP3(mp3filename, ID3=ID3)
+                cover = song.get('cover')
+                if cover is not None:
+                    if cover.lower().startswith('http'):
+                        req = urllib.request.Request(cover)
+                    else:
+                        raise ValueError from None
+                    with urllib.request.urlopen(req) as resp:  # nosec
+                        song_file.tags['APIC'] = APIC(
+                            encoding=3,
+                            mime='image/jpeg',
+                            type=3, desc=u'Cover',
+                            data=resp.read()
+                        )
+                song_file.save()
             else:
-                song_file['tracknumber'] = str(song.get('num')) + '/' + str(song.get('num_tracks'))
-            song_file['genre'] = song.get('genre')
-            song_file.save()
-            song_file = MP3(f"{file_path}.mp3", ID3=ID3)
-            if song.get('cover') is not None:
-                song_file.tags['APIC'] = APIC(
-                    encoding=3,
-                    mime='image/jpeg',
-                    type=3, desc=u'Cover',
-                    data=urllib.request.urlopen(song.get('cover')).read()
-                )
-            song_file.save()
+                print('File {} already exists, we do not overwrite it '.format(mp3filename))