python网络爬虫采集联想词示例

#coding:utf-8
import urllib2
import urllib
import re
import time
from random import choice
#特别提示，下面这个list中的代理ip可能失效，请换上有效的代理ip
iplist  = [‘27.24.158.153:81′,’46.209.70.74:8080′,’60.29.255.88:8888’]

list1 = [“集团”,”科技”]
for item in list1:
    ip= choice(iplist)
    gjc = urllib.quote(item)
    url = “http://sug.so.360.cn/suggest/word?callback=suggest_so&encodein=utf-8&encodeout=utf-8&word=”+gjc
    headers = {
                “GET”:url,
                “Host”:”sug.so.360.cn”,
                “Referer”:”http://www.so.com/”,
                “User-Agent”:”sMozilla/5.0 (Macintosh; Intel Mac OS X 10_8_4) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.56 Safari/537.17″,
                }

    proxy_support = urllib2.ProxyHandler({‘http’:’http://’+ip})

    opener = urllib2.build_opener(proxy_support)
    urllib2.install_opener( opener )
    req = urllib2.Request(url)

    for key in headers:
        req.add_header(key,headers[key])

    html = urllib2.urlope来源gaodaimacom搞#^代%!码&网n(req).read()

    ss = re.findall(“\”(.*?)\””,html)
    for item in ss:
        print item
    time.sleep(2)