{article Dive into Python}{title} {text} {readmore}{/article}

Here is a complete, working Python program. Read the doc strings of the module, the classes, and the functions
to get an overview of what this program does and how it works. As usual, don't worry about the stuff you don't
understand; that's what the rest of the chapter is for.

fileinfo.py

"""Framework for getting filetype-specific metadata.

Instantiate appropriate class with filename. Returned object acts like a
dictionary, with key-value pairs for each piece of metadata.
import fileinfo
info = fileinfo.MP3FileInfo("/music/ap/mahadeva.mp3")
print "\\n".join(["%s=%s" % (k, v) for k, v in info.items()])

Or use listDirectory function to get info on all files in a directory.
for info in fileinfo.listDirectory("/music/ap/", [".mp3"]):
...

Framework can be extended by adding classes for particular file types, e.g.
HTMLFileInfo, MPGFileInfo, DOCFileInfo. Each class is completely responsible for
parsing its files appropriately; see MP3FileInfo for example.

This program is part of "Dive Into Python", a free Python book for
experienced programmers. Visit http://diveintopython.org/ for the
latest version.
"""

__author__ = "Mark Pilgrim (This email address is being protected from spambots. You need JavaScript enabled to view it.)"
__version__ = "$Revision: 1.3 $"
__date__ = "$Date: 2004/05/05 21:57:19 $"
__copyright__ = "Copyright (c) 2001 Mark Pilgrim"
__license__ = "Python"

import os
import sys
from UserDict import UserDict

def stripnulls(data):
"strip whitespace and nulls"
return data.replace("\00", " ").strip()

class FileInfo(UserDict):
"store file metadata"
def __init__(self, filename=None):
UserDict.__init__(self)
self["name"] = filename

class MP3FileInfo(FileInfo):
"store ID3v1.0 MP3 tags"
tagDataMap = {"title" : ( 3, 33, stripnulls),
"artist" : ( 33, 63, stripnulls),
"album" : ( 63, 93, stripnulls),
"year" : ( 93, 97, stripnulls),
"comment" : ( 97, 126, stripnulls),
"genre" : (127, 128, ord)}

def __parse(self, filename):
"parse ID3v1.0 tags from MP3 file"
self.clear()
try:
fsock = open(filename, "rb", 0)
try:
fsock.seek(-128, 2)
tagdata = fsock.read(128)
finally:
fsock.close()
if tagdata[:3] == 'TAG':
for tag, (start, end, parseFunc) in self.tagDataMap.items():
self[tag] = parseFunc(tagdata[start:end])
except IOError:
pass

def __setitem__(self, key, item):
if key == "name" and item:
self.__parse(item)
FileInfo.__setitem__(self, key, item)

def listDirectory(directory, fileExtList):
"get list of file info objects for files of particular extensions"
fileList = [os.path.normcase(f) for f in os.listdir(directory)]
fileList = [os.path.join(directory, f) for f in fileList \
if os.path.splitext(f)[1] in fileExtList]
def getFileInfoClass(filename, module=sys.modules[FileInfo.__module__]):
"get file info class from filename extension"
subclass = "%sFileInfo" % os.path.splitext(filename)[1].upper()[1:]
return hasattr(module, subclass) and getattr(module, subclass) or FileInfo
return [getFileInfoClass(f)(f) for f in fileList]

if __name__ == "__main__":
for info in listDirectory("/Users/Public/Music/Sample Music/", [".mp3"]):
print ("\n".join(["%s=%s" % (k, v) for k, v in info.items()]))
print

This program's output depends on the files on your hard drive. To get meaningful output, you'll need to change
the directory path to point to a directory of MP3 files on your own machine

>>>
name=/Users/Public/Music/Sample Music/kalimba.mp3
name=/Users/Public/Music/Sample Music/maid with the flaxen hair.mp3
name=/Users/Public/Music/Sample Music/sleep away.mp3
>>>