爬虫小程序

# coding=utf-8
import urllib
import urllib2
import random


def tieba(url):


    ua_list = [
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
        "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
        "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6"
    ]


    request = urllib2.Request(url)
    user_agent = random.choice(ua_list)


    request.add_header("User-Agent", user_agent)


    response = urllib2.urlopen(request)


    html = response.read()


    filename = '我是文件夹啊'


    with open(filename, 'w') as f:
        f.write(html)


if __name__ == "__main__":
    name = raw_input('请输入要爬的吧：')
    url1 = "http://tieba.baidu.com/?f"


    keyword = {'kw':name}

    kw = urllib.urlencode(keyword)

    url = url1 + kw

    tieba(url)