百度贴吧爬虫并保存至目录中

#!/usr/bin/env python
# encoding: utf-8

import urllib2
from lxml import etree
import urllib
import os
from shutil import copyfile

if __name__ == "__main__":
    #  首先请求爬取到所有页面中有图片的地方
    keyword = raw_input("请输入需要搜索的内容：")
    kw = {"kw": keyword}
    kw = urllib.urlencode(kw)
    url = "http://tieba.baidu.com/f?" + kw
    header = {"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"}
    request = urllib2.Request(url)
    html = urllib2.urlopen(request).read()
    # 使用etree的方法解析成xml文件，然后用xpath的方法来解析，直接拿到图片后几位数字，拼接成链接
    content = etree.HTML(html)
    link_list = content.xpath('//div[@class="t_con cleafix"]/div/div/div/a/@href')
    for link in link_list:
        fulllink = "http://tieba.baidu.com" + link
        # print fulllink