Script to delete files not requested for a long time

#!/usr/bin/env python
# videocache cleaner
 
import re
import time
import os
import sys
 
__version__ = 0.01
log_dir = '/var/log/videocache/'
log_dir_files = os.listdir(log_dir)
cache_dir = '/var/spool/videocache/'
hit_pattern = '(\d{4})-(\d{2})-(\d{2}) (\d{2}):(\d{2}):(\d{2}),\d{3} \w+ \d+\.\d+\.\d+\.\d+ ([a-zA-Z0-9\._-]+) CACHE_HIT (\w+)'
download_pattern = '(\d{4})-(\d{2})-(\d{2}) (\d{2}):(\d{2}):(\d{2}),\d{3} \w+ \d+\.\d+\.\d+\.\d+ ([a-zA-Z0-9\._-]+) DOWNLOAD (\w+)'
 
class TouchNotCompleteError(Exception):
  pass
 
class GetHitsNotCompleteError(Exception):
  pass
 
class CacheCleaner(object):
 
  def __init__(self, delete_age=90):
    self.all_logs = ''
    self.touch_complete = False
    self.get_hits_complete = False
    self.delete_age = delete_age
    self.now = time.mktime(time.localtime())
    self.last_hits = {}
    self.last_downloads = {}
 
  def _get_downloads(self):
    self._check_get_hits()
    download_list = re.findall(download_pattern, self.all_logs)
    for download in download_list:
      t = tuple([int(i) for i in download[:6]]) + (2, 35, 1)
      date = '%s%s%s%s%s.%s' %(str(download[0])[-2:], download[1], 
				   download[2], download[3], download[4], 
				   download[5])
      if download[6] not in self.last_hits:
	if self.last_downloads.has_key(download[6]):
	  delta = self.now - time.mktime(t)
	  if self.last_downloads[download[6]]['last_download'] > delta:
	    self.last_downloads[download[6]]['last_download'] = delta
	    self.last_downloads[download[6]]['last_download_date'] = date
	else:
	    self.last_downloads[download[6]] = {
	    'site':download[7].lower(),
	    'last_download':self.now - time.mktime(t),
	    'last_download_date':date
	    }
 
  def _get_hits(self):
    hit_list = re.findall(hit_pattern, self.all_logs)
    for hit in hit_list:
      t = tuple([int(i) for i in hit[:6]]) + (2, 35, 1)
      date = '%s%s%s%s%s.%s' %(str(hit[0])[-2:], hit[1], 
				   hit[2],hit[3], hit[4], hit[5])
      if self.last_hits.has_key(hit[6]):
	delta = self.now - time.mktime(t)
	if self.last_hits[hit[6]]['last_hit'] > delta:
	  self.last_hits[hit[6]]['last_hit'] = delta
	  self.last_hits[hit[6]]['last_hit_date'] = date
      else:
	  self.last_hits[hit[6]] = {
	  'site':hit[7].lower(),
	  'last_hit':self.now - time.mktime(t),
	  'last_hit_date':date
	  }
    self.get_hits_complete = True
 
  def _touch_files(self):
    for download in self.last_downloads:
      if self.last_downloads[download]['site'] == 'youtube':
	cmd = 'touch %s%s/%s -t %s' %(cache_dir, self.last_downloads[download]['site'],
				     download, self.last_downloads[download]['last_download_date'])
      else:
	cmd = 'touch %s%s/%s.flv -t %s' %(cache_dir, self.last_downloads[download]['site'],
				      download, self.last_downloads[download]['last_download_date'])
      os.system(cmd)
    for hit in self.last_hits:
      if self.last_hits[hit]['site'] == 'youtube':
	cmd = 'touch %s%s/%s -t %s' %(cache_dir, self.last_hits[hit]['site'],
				     hit, self.last_hits[hit]['last_hit_date'])
      else:
	cmd = 'touch %s%s/%s.flv -t %s' %(cache_dir, self.last_hits[hit]['site'],
				     hit, self.last_hits[hit]['last_hit_date'])
      os.system(cmd)
    self.touch_complete = True
 
 
  def run(self):
    self._get_logs()
    self._get_hits()
    self._get_downloads()
    self._touch_files()
    self._clear()
 
  def _check_get_hits(self):
    if not self.get_hits_complete:
      raise GetHitsNotCompleteError
 
  def _check_touch(self):
    if not self.touch_complete:
      raise TouchNotCompleteError
 
  def _clear(self):
    self._check_touch()
    cmd = "find %s -mtime +%s -exec rm -rf {} ';'" %(cache_dir, self.delete_age)
    os.system(cmd)
 
  def _clear_logs(self):
    """
    TODO
    """
    pass
 
  def _get_logs(self):
    self.all_logs = ''
    for log in log_dir_files:
      self.all_logs += open(log_dir+log).read()
 
def main():
  if len(sys.argv) > 1:
    c = CacheCleaner(delete_age=sys.argv[1])
  else:
    c = CacheCleaner()
  c.run()
 
if __name__ == '__main__':
  main()

diff --git a/scripts/vccleaner b/scripts/vccleaner
index 8bae0be..2512b70 100644
--- a/scripts/vccleaner
+++ b/scripts/vccleaner
@@ -115,7 +115,7 @@ def main(root, etc_dir):
         return (None, None, None, None)
     else:
         video_lifetime = int(mainconf.video_lifetime)
-    base_dir = [apply_install_root(root, dir.strip()) for dir in mainconf.base_dir.split('|')]
+    base_dir = [apply_install_root(root, dir_tup.split(':')[0].strip()) for dir_tup in mainconf.base_dir.strip().split('|')]
     logdir = apply_install_root(root, mainconf.logdir)
 
     # Youtube specific options