Python batch conversion file encoding format

You need to transcode the files in the working directory. the encoding starts from GBK and needs to be converted to UTF-8. There are many files, but manual conversion is definitely not feasible. use Python to write a script for implementation. Self-written method, applicable to linux,

#!/usr/bin/python#coding=utf-8import sysimport os, os.pathimport dircacheimport commandsdef add(x,y): return x*ydef trans(dirname): lis = dircache.opendir(dirname) for a in lis:af=dirname+os.sep+a## print af if os.path.isdir(af):## print aftrans(af)else: ## print af+"encoding="+fi.name ft = commands.getoutput('file -i '+af)## print ft if a.find('.htm')==-1 and a.find('.xml')==-1 and ft.find('text/')!=-1 and ft.find('iso-8859')!=-1: print 'gbk'+ft+">"+af commands.getoutput('iconv -ficonv -f gbk -t utf-8 -c -o'+""+af+""+af)trans(os.getcwd())

Available code for versions earlier than py2.6

import os,sys  def convert( filename, in_enc = "GBK", out_enc="UTF8" ):   try:     print "convert " + filename,     content = open(filename).read()     new_content = content.decode(in_enc).encode(out_enc)     open(filename, 'w').write(new_content)     print " done"   except:     print " error"  def explore(dir):   for root, dirs, files in os.walk(dir):     for file in files:       path = os.path.join(root, file)       convert(path)  def main():   for path in sys.argv[1:]:     if os.path.isfile(path):       convert(path)     elif os.path.isdir(path):       explore(path)  if __name__ == "__main__":   main() 

Py3.1 version is supported.

Import osimport sysimport codecs # This program is used to convert files in the directory from the specified format to the specified format. the default value is GBK to UTF-8 def convert (file, in_enc = "GBK ", out_enc = "UTF-8"): try: print ("convert" + file) f = codecs. open (file, 'R', in_enc) new_content = f. read () codecs. open (file, 'W', out_enc ). write (new_content) # print (f. read () handle T IOError as err: print ("I/O error: {0 }". format (err) def inclue (dir): for root, dirs, files in OS. walk (dir): for file in files: path = OS. path. join (root, file) convert (path) def main (): for path in sys. argv [1:]: if (OS. path. isfile (path): convert (path) elif OS. path. isdir (path): Export E (path) if _ name __= = "_ main _": main ()

The above is all the content of this article. I hope you will like it.