【用Python写爬虫】获取html的方法【一】：使用urllib

href="file:///C:/DOCUME~1/ADMINI~1/LOCALS~1/Temp/msohtml1/01/clip_filelist.xml" rel="File-List" /> # -*- coding: UTF-8 -*-

import urllib

 

' 获取web页面内容并返回'

def getWebPageContent(url):

    f = urllib.urlopen(url)

    data = f.read()

    f.close()

return data

 

url = 'http://blog.csdn.net'

content = getWebPageContent(url)

print content