Python_爬虫_爬取任意百度贴吧任意页数帖子中包含的图片

简单实现，还有很多不完善的地方

"""
输入任意贴吧名，爬取贴吧内任意页数中的图片
"""

import requests  # 请求网页
from lxml import etree  # 解析网页

tieba_name = input("请输入想爬取的贴吧名: ")
url = 'https://tieba.baidu.com/f?'

startPage = int(input("请输入爬取开始页: "))
endPage = int(input("请输入爬取结束页: "))

for page in range(startPage,endPage+1):
    pn_name = (page-1)*50

    response = requests.get(url,params={'kw':tieba_name,'pn':pn_name}).text
    element = etree.HTML(response)
    link_list = element.xpath('//a[@class="j_th_tit "]/@href')

    for link in link_list:
        full_link = 'https://tieba.baidu.com'+link
        tiezi_html = requests.get(full_link).text

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

        for my_img in img_list:
            img = requests.get(my_img).content
            img_name = my_img[-10:]
            with open ('img/'+img_name,'wb') as f:
                f.write(img)

            print(img_name)