python批量访问网页保存结果_Python检测批量URL状态，并将返回正常的URL保存文件...

-- coding: UTF-8 --

#author == huangyishan

import os

import sys

import urllib2

urls = sys.argv[1] #从程序外部调用参数，0即程序本身

result = list()

def check_url_status():

f = open(urls,‘r‘) #以读方式打开文件

for line in f.readlines(): #依次读取每行

line = line.strip() #去掉每行头尾空白

if len(line) !=0:

if line[0:7]==‘http://‘ or line[0:8]==‘https://‘:

pass

else:

line=‘http://‘+line

print line

try:

#response = urllib2.urlopen(line,timeout=4)

status = urllib2.urlopen(line,timeout=4).code

#print response

print status

result.append(line)

open(‘url_ok.txt‘, ‘w‘).write(‘%s‘ % ‘\n‘.join(result)) #保存入结果文件

except urllib2.HTTPError, e:

print e.code

with open(‘url_notok.txt‘, ‘w‘) as f: #保存入结果文件

f.write(line + ‘ : ‘ + str(e.code) + ‘\n‘)

except:

print "error"

with open(‘url_notok.txt‘, ‘a‘) as f: #保存入结果文件

f.write(line + ‘ : ‘ + ‘error‘ + ‘\n‘)

if name == ‘main‘:

check_url_status()

原文地址：http://blog.51cto.com/linuxpython/2105821