{article Dive into Python}{title} {text} {/article}
for Loop in MP3FileInfo
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 (
__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("/music/_singles/", [".mp3"]):
print ("\n".join(["%s=%s" % (k, v) for k, v in info.items()]))
print
tagDataMap is a class attribute that defines the tags you're looking for in an MP3 file. Tags are stored in fixed−length fields. Once you read the last 128 bytes of the file, bytes 3 through 32 of those are always the song title, 33 through 62 are always the artist name, 63 through 92 are the album name, and so forth. Note that tagDataMap is a dictionary of tuples, and each tuple contains two integers and a function reference.
This looks complicated, but it's not. The structure of the for variables matches the structure of the elements of the list returned by items. Remember that items returns a list of tuples of the form (key, value). The first element of that list is ("title", (3, 33, <function stripnulls>)), so the first time around the loop, tag gets "title", start gets 3, end gets 33, and parseFunc gets the function stripnulls
Now that you've extracted all the parameters for a single MP3 tag, saving the tag data is easy. You slice tagdata from start to end to get the actual data for this tag, call parseFunc to post−process the data, and assign this as the value for the key tag in the pseudo−dictionary self. After iterating through all the elements in tagDataMap, self has the values for all the tags, and you know what that looks like.
fileinfo.py
{source}
<!-- You can place html anywhere within the source tags -->
<pre class="brush: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 fileinfoinfo = 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 (
__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:passdef __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 FileInforeturn [getFileInfoClass(f)(f) for f in fileList]
if __name__ == "__main__":for info in listDirectory("/music/_singles/", [".mp3"]):print ("\n".join(["%s=%s" % (k, v) for k, v in info.items()]))print
</pre>
<script language="javascript" type="text/javascript">// You can place JavaScript like this
</script>
<?php// You can place PHP like this
?>
{/source}