Python读取网页内容的方法

import urllib2
#encoding = utf-8
class Crawler:
  def main(self):
    #req = urllib2.Request(‘http://www.baidu.com/‘)
    #req.add_header(‘User-Agent‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:5.0)‘)
    #urllib2.socket.setdefaulttimeout(10) # 超时10秒
    #page = urllib2.urlopen(req)
    page = urllib2.urlopen(‘http://www.google.com‘, timeout=10)
    data = page.read()
    print data
    print len(data) #计算字节长度
if __name__ == ‘__main__‘:
  me=Crawler()
  me.main()