使用pyhon脚本从一系列xml文件中提取图片的url

getImagefile.sh

#!/bin/env sh

#获取文件名
ls -lht *xml* > file_list_tmp
awk -F" " '{print $9}' file_list_tmp > file_list ;

----------------------------------------------------

getImageURL.py

import sys
import os
import re

cmd = "sh getimgurl.sh"
list_file=os.popen(cmd)
file_names = open("file_list",'r').readlines()
for file_name in file_names:
        file_name = file_name.replace('\n','')
        print "step 2"
        url_file=open("url_file","w")
        fp = open(file_name,"rx")
        lines=fp.readlines()
        fp.close()
        for line in lines:
                bt = '([a-zA-z]+://[^\s]*(jpg))' #url的正则表达式
                m= re.search(bt,line)
                if m is not None:
                        res = m.group()
                        print res
                        url_file.write(res+'\n')