python 网络爬虫初级实现代码

import re
import urllib

def getHtml(url):
 page = urllib.urlopen(url)
 html = page.read()
 return html

def getImg(html):
 reg = r'src="(.*?\.gif)"'
 imgre = re.compile(reg)
 imgList = re.findall(imgre,html)
 print imgList
 cnt = 1
 for imgurl in imgList:
  urllib.urlretrieve(imgurl,'%s.jpg' %cnt)
  cnt += 1

if __name__ == '__main__':
 html = getHtml('http://www.baidu.com')
 getImg(html)

import tornado.httpclient

def Fetch(url):
 http_header = {'User-Agent' : 'Chrome'}
 http_request = tornado.httpclient.HTTPRequest(url=url,method='GET',headers=http_header,connect_timeout=200,request_timeout=600)
 print 'Hello'
 http_client = tornado.httpclient.HTTPClient()
 print 'Hello World'

 print 'Start downloading data...'
 http_response = http_client.fetch(http_request)
 print 'Finish downloading data...'

 print http_response.code

 all_fields = http_response.headers.get_all()
 for field in all_fields:
  print field

 print http_response.body

if __name__ == '__main__':
 Fetch('http://www.baidu.com')