add filters

download.py

@@ -1,12 +1,16 @@
-import os
 import sys
 from time import sleep
 
+import os
 import pexpect
+import shutil
+from glob import glob
 from pexpect.exceptions import ExceptionPexpect
 
 PERSISTENCE_FILENAME = 'persistence.txt'
 
+KEYWORDS_TO_FILTER_OUT = ['album complet', 'compil', 'full album', 'compilation', 'full ep', 'full']
+
 
 def get_music(name='Linkin Park papercut'):
     child = pexpect.spawn('instantmusic')
@@ -42,7 +46,15 @@ def run(song_filename, output_folder):
                 printable_music = music.strip()
                 print('Downloading {0}'.format(printable_music))
                 get_music(printable_music)
-                os.system('mv *.mp3 {}'.format(output_folder))
+
+                # print(glob('*.mp3'))
+                for mp3_music in glob('*.mp3'):
+                    for keyword_to_filter in KEYWORDS_TO_FILTER_OUT:
+                        if keyword_to_filter.lower() in mp3_music.lower():
+                            print('Music filtered {}.'.format(mp3_music))
+                            os.remove(mp3_music)
+                            continue
+                    shutil.move(mp3_music, output_folder + '/')
                 break
             except ExceptionPexpect:  # also check pexpect.exceptions.TIMEOUT: Timeout exceeded.
                 num_attempts += 1

list_songs/music_names_from_billboard.py

@@ -1,19 +1,20 @@
 # http://billboardtop100of.com/1989-2/
-import string
-
 import requests
+import string
 from bs4 import BeautifulSoup
 
 printable = set(string.printable)
 
-music_names = open('music.txt', 'w')
+output_filename = 'music.txt'
+print('Writing to {}.'.format(output_filename))
+music_names = open(output_filename, 'w')
 
 for year in range(1995, 2017):
 
     if year == 2013:
         continue
 
-    print(year)
+    print('Downloading for {}.'.format(year))
     response = requests.get('http://billboardtop100of.com/{0}-2/'.format(year))
     assert response.status_code == 200
     soup = BeautifulSoup(response.content, 'lxml')