Plex MP4 media file scanner

Mpeg4 Tag Scanner.py

import re, os, os.path
import tempfile
import pickle
import Media, VideoFiles, Stack
import dircache
import commands
import UnicodeHelper
import hashlib
from mp4file import mp4file, atomsearch

mp4Info='/opt/local/bin/mp4info'
nameRegex='^ Name: '
artistRegex='^ Artist: '
albumRegex='^ Album: '
trackRegex='^ Track: '
dumpfileName='Mpeg4TagScannerDump.dat'
indexfileName='Mpeg4TagScannerIndex.dat'
matcher = re.compile('^\.')
nameMatcher = re.compile(nameRegex)
artistMatcher = re.compile(artistRegex)
albumMatcher = re.compile(albumRegex)
trackMatcher = re.compile(trackRegex)

# get mp4 tags
def getTags(file):
  info = commands.getoutput(mp4Info + ' "' + file + '"')
  title = artist = album = track = None
  for line in info.splitlines():
    if nameMatcher.match(line):
      title = re.sub(nameRegex, '', line)
    elif artistMatcher.match(line):
      artist = re.sub(artistRegex, '', line)
    elif albumMatcher.match(line):
      album = re.sub(albumRegex, '', line)
    elif trackMatcher.match(line):
      track = re.search(r'(\d+) of \d+', re.sub(trackRegex, '', line)).group(1)
  
  if title == None or title == '':
      title = os.path.splitext(os.path.basename(file))[0]
  if artist == None or artist == '':
      artist = 'その他のアーチスト'
  if album == None or album == '':
      album = 'その他の作品'
  if track == None or track == '':
      track = 0
  
  return Media.Episode(UnicodeHelper.fixEncoding(album), 0, track, UnicodeHelper.fixEncoding(title), None)

# Look for episodes.
def Scan(path, files, mediaList, subdirs):
  # Scan for video files.
  VideoFiles.Scan(path, files, mediaList, subdirs)
  
  list = dict()
  dumpfile = tempfile.gettempdir() + '/' + dumpfileName
  if os.path.exists(dumpfile):
    fi = None
    try:
      fi = open(dumpfile)
      list = pickle.load(fi)
    finally:
      if (fi):
        fi.close()

  indexlist = dict()
  indexfile = tempfile.gettempdir() + '/' + indexfileName
  if os.path.exists(indexfile):
    fix = None
    try:
      fix = open(indexfile)
      indexlist = pickle.load(fix)
    finally:
      if (fix):
        fix.close()
  
  change = False
  for file in files:
    if not matcher.match(file):
      key = hashlib.md5(file).hexdigest()
      size = os.path.getsize(file)
      if list.has_key(key) and list[key][0] == size:
        media = list[key][1]
      else:
        change = True
        media = getTags(file)
        if media.episode == 0:
          index = 0
          if indexlist.has_key(media.show):
            index = indexlist[media.show] + 1
          else:
            index = 101
          media.episode = index
          indexlist[media.show] = index
        list[key] = [size, media]
      
      media.parts.append(file)
      mediaList.append(media)
  
  if (change):
    fo = None
    try:
      fo = open(dumpfile, 'w')
      pickle.dump(list, fo)
    finally:
      if (fo):
        fo.close()
    fox = None
    try:
      fox = open(indexfile, 'w')
      pickle.dump(indexlist, fox)
    finally:
      if (fox):
        fox.close()
 
  # Stack the results.
  Stack.Scan(path, files, mediaList, subdirs)

def find_data(atom, name):
  child = atomsearch.find_path(atom, name)
  data_atom = child.find('data')
  if data_atom and 'data' in data_atom.attrs:
    return data_atom.attrs['data']

import sys
    
if __name__ == '__main__':
  print "Hello, world!"
  path = sys.argv[1]
  files = [os.path.join(path, file) for file in os.listdir(path)]
  media = []
  Scan(path[1:], files, media, [])
  print "Media:", media