李毅吧是一个比较大的百度贴吧了，里面的热门内容都是非常好的内容。所以，我就写了一个实现抓去里面热门帖子图片的脚步，现在分享出来给大家，希望大家一起进步学习：

import requests
from lxml import etree
from bs4 import BeautifulSoup
import threading
import time
import os
import re
import random
class tieba():
    def __init__(self,tiebaname):
        self.i=0
        UserAgentlist = ['Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko)',
                         'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101',
                         'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:81.0) Gecko/20100101']

        userage = random.choice(UserAgentlist)
        self.headers = {'User-Agent': userage}
        self.tiebaname=tiebaname

    def res(self,url):
        res = requests.get(url, headers=self.headers)
        soup = BeautifulSoup(res.text, 'lxml')
        return soup
    def shouye(self):
        for page in range(0, 2):
            url = "https://tieba.baidu.com/f?kw=" + self.tiebaname + "&ie=utf-8&pn=" + str(page)
            soup=self.res(url)
            tti=soup.find_all('div',class_='t_con cleafix')
            for title in tti:
                title=str(title)
                self.shuaixuan(title)
    def shuaixuan(self,title):

        zhiding=re.findall('<i alt=(.*?)</i>',title)
        huifushu=re.findall('title="回复">(.*?)</span>',title)
        url=re.findall('href="(.*?)"',title)

        url=url[0]
        zhiding=len(zhiding)
        huifushu=int(huifushu[0])

        if zhiding==0 and huifushu>100:
            url='https://tieba.baidu.com'+url
            print(url)
            self.ziye(url)

    def ziye(self,url):
        soup = self.res(url)
        title=soup.find('h3')
        print(title)
        if title is None:
            title=soup.find('h1')
        neirong=soup.find_all('div',class_='d_post_content j_d_post_content')
        title=str(title)
        title=re.findall('title="(.*?)"',title)
        title=title[0]
        title=title.strip('?')
        title = title.strip()
        print(title)
        os.makedirs('/tiebaimgs/' + title + '/', exist_ok=True)
        lujing = '/tiebaimgs/' + title+ '/'
        self.i=0
        for wen in neirong:
            wen=str(wen)
            imgs=re.findall('src="(.*?)"',wen)
            if len(imgs)>0:
                self.img_load(imgs,lujing)
    def img_load(self,imgs,lujing):

        for imgurl in imgs:
            print(imgurl)
            print(self.i)
            if 'gsp0' in imgurl:
                pass
            else:
                res=requests.get(url=imgurl,headers=self.headers)
                with open(lujing+str(self.i)+'.jpg', 'wb') as f:
                    f.write(res.content)
                time.sleep(1)
                self.i+=1

if __name__ == '__main__':
    liyi=tieba('李毅')
    liyi.shouye()