百度贴吧赵丽颖吧图片爬取代码

import requests
from lxml import etree
import random
import time

class BaiduImageSpider(object):
    def __init__(self):
        self.headers={"User-Agent":'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; InfoPath.3)'}

    def get_parse_page(self,url,xpath):
        html=requests.get(url=url,headers=self.headers).content.decode('utf-8')
        parse_html=etree.HTML(html)
        r_list=parse_html.xpath(xpath)
        return r_list
    #获取帖子链接
    def get_tlink(self,url):
        html=requests.get(url,headers=self.headers).content.decode('utf-8')
        #提取帖子链接
        parse_html=etree.HTML(html)
        t_list=parse_html.xpath('//*[@id="thread_list"]/li[@class=" j_thread_listclearfix"]/div/div[2]/div[1]/div[1]/a/@href')
        for t in t_list:
            t_link='http://tieba.baidu.com' + t
            #把这1个帖子中所有图片保存到本地
            self.write_image(t_link)
    #把1个帖子中所有图片保存到本地
    def write_image(self,t_link):
        html=requests.get(t_link,headers=self.headers).content.decode('utf-8')
        parse_html=etree.HTML(html)
        img_list=parse_html.xpath('')
        for img_link in img_list:
            html=requests.get(
                url=img_link,
                headers=self.headers
            ).content
            filename= img_link[-10:]
            with open(filename,'wb') as f:
                f.write(html)
                print('%s下载成功' % filename)
                time.sleep(random.randint(1,3))
if __name__=="__main__":
    spider=BaiduImageSpider()
    spider.get_tlink('https://tieba.baidu.com/f?ie=utf-8&kw=%E8%B5%B5%E4%B8%BD%E9%A2%96')