爬取任意百度贴吧图片

luoyunjian

import requests
from lxml import etree

l
tieba_name = input('请输入你要爬取的贴吧:')

startPage = int(input('开始页:'))
endPage = int(input('结束页:'))

url = 'https://tieba.baidu.com/f?'

for page in range(startPage,endPage+1):
    yema = (page - 1) * 50
    response = requests.get(url,params={'kw':tieba_name,'pn':yema})
    html = response.text # 网页源代码
    # print(html)


    # 第二步 找到每条链接
    element = etree.HTML(html)
    link_list = element.xpath('//a[@class="j_th_tit "]/@href')
    for link in link_list:

        fulllink = 'https://tieba.baidu.com/'+link

        # 请求链接地址
        tiezi_resp = requests.get(fulllink)
        tiezi_html = tiezi_resp.text

        img_link = etree.HTML(tiezi_html)
        img_list = img_link.xpath('//img[@class="BDE_Image"]/@src')

        for my_img in img_list:

            # 请求图片的链接地址
            img_response = requests.get(my_img)

            img = img_response.content

            # 获取图片的名字
            img_name = my_img[-10:]
            # print(img_name)
            f = open('img/'+img_name,'wb')
            f.write(img)
            f.close()