网络爬虫urllib2 tornado

 1 import tornado.httpclient
 2 
 3 def fetch(url):
 4 http_header={‘User-Agent‘:‘Chrome‘}
 5 http_request=tornado.httpclient.HTTPRequest(url=url,method=‘GET‘,headers=http_header,connect_timeout=200, request_timeout=600)
 6 
 7 http_client=tornado.httpclient.HTTPClient()
 8 
 9 http_response=http_client.fetch(http_request)
10 
11 print http_response.code
12 
13 all_fields=http_response.headers.get_all()
14 for field in all_fields:
15    print field
16 print http_response.body

import urllib2

def fetch(url):
    http_header = {‘User-Agent‘:‘Chrome‘}
    http_request = urllib2.Request(url,None,http_header)
    
    http_reponse = urllib2.urlopen(http_request)
    
    #Status code
    #200 OK
    #404 Invalid url
    #500 Internal error
    
    print(http_reponse.code)
    print(http_reponse.info())
    
    print(http_reponse.read())
    
调用：
if __name__="__main__":
    fetch("http://www.meituan.com/api/v1/divisions")