# -*- coding: utf-8 -*-
import urllib2
from urllib2 import HTTPError
url = "http://www.xicidaili.com/"
req_header = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
'Accept':'text/html;q=0.9,*/*;q=0.8',
'Accept-Charset':'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
'Accept-Encoding':'gzip',
'Connection':'close',
'Referer':None #注意如果依然不能抓取的话,这里可以设置抓取网站的host
}
req_timeout =5
req = urllib2.Request(url, None, req_header)
try:
response = urllib2.urlopen(req,None,req_timeout)
content = response.read()
except HTTPError, e:
if e.getcode() == 500:
content = e.read()
else:
raise
print content
|