python读取网页内容_Python根据url获取网页内容详解

#! /usr/bin/python

# -*- coding:utf-8 -*-

'''''

Created on 2013-11-5

@author: Java

'''

import urllib2

import time

import socket

from sgmllib import SGMLParser

class WebUtil():

def __init__(self):

self.trytims = 3

pass

#读取Url 内容

# timeout=10

# socket.setdefaulttimeout(timeout)#这里对整个socket层设置超时时间。后续文件中如果再使用到socket，不必再设置

# sleep_download_tine=10

# time.sleep(sleep_download_tine)

def readUrl(self,url):

try:

request = urllib2.Request(url,headers = {'User-Agent':'Magic Browser'})

webpage = urllib2.urlopen(url)

content = webpage.read()

return content

request.close()

except Exception,errmg:

print '读取失败：%s'%errmg

return None

if __name__=='__main__':

web = WebUtil()

content = web.readUrl('http://www.open-open.com')

print content