python/java处理文件遍历

1397535668

　　最近这几天，一直在学习python，发现python在脚本处理方面有很多的便捷性，这点要比java要好，但是文档找起来并不是那么方便，刚上手，有点生疏。
　　以下代码是python用来处理文件夹遍历的脚本(OS : ubuntu 11.04 python:2.7)

#coding:utf-8
#iterator folder use python
import os
CODING = 'gb2312'
def iteratorFolder(fall,fileName):
files = os.listdir(fileName)
sep = os.path.sep
for name in files:
fullname = fileName + sep + name
if os.path.isdir(fullname):
iteratorFolder(fall,fullname)
else    :
pass
#fall.append(unicode(fullname,CODING))
#fall.append(fullname)
fall.append(unicode(fullname,CODING))
#fall.append(fullname)
return fall
def main():
fall = []
fileName = '/home/gavin/projects/email/mail_project_doc'
file = open('log.log','w')  
fall = iteratorFolder(fall,fileName)

for f in fall:
print f
print f.encode(CODING)
file.writelines(f+'\n')
file.close()
#print file.name   
#print len(fall)
if __name__ == '__main__':
main()

　　相对比的java代码如下:

package com.sohu.test;
import java.io.*;
import java.util.*;

public class IteratorFolder {
public static List<String> iteratorFolder(List<String> list,String fileName) throws UnsupportedEncodingException{
File file = new File(fileName);
File[] files = file.listFiles();
String separator = File.separator;
for(int i = 0 ; i < files.length ; i ++){
File f = files;
String fname = f.getName();
String fullName = fileName + separator + fname;
if(f.isDirectory()){
iteratorFolder(list,fullName);
}
list.add(fullName);
}
return list;
}

public static void main(String[] args)throws Exception {
//check file
String name = "/home/gavin/projects/email/test";
List<String> list = new ArrayList<String>();
list = iteratorFolder(list,name);
File file = new File("log_java.log");
FileOutputStream fos = new FileOutputStream(file);
PrintWriter out = new PrintWriter(new OutputStreamWriter(fos));
for(String fullName : list){
out.write(fullName+"\n");
}
out.close();
fos.close();
System.out.println(file.getAbsolutePath());
System.out.println(list.size());
}
}

 　　感觉还是python在文件处理上比java要方便些！在跟同事看了之后，给了一个更简单的处理方式os.walk，这个可以直接遍历文件夹目录做处理，如:

#file = open(fileName,'r')
files = os.walk(fileName)
for f in files:
for ff in f:
print ff

 　　可参考os.walk用法:http://www.cnblogs.com/phonefans/archive/2008/10/15/1311707.html
　　后续再做python的脚本优化！(文件校验判断，文件的参数传入等)