python爬糗图

import requests
import re
import os

if __name__ == '__main__':
    #创建图片文件夹
    if not os.path.exists('./qiutu'):
        os.mkdir('./qiutu')
        # 请求头
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36'
    }
    #爬取的通用地址
    url = 'https://xiaohua.zol.com.cn/qutu/qiushi/%d.html'
    #获取页码对应地址
    for page_num in range(1,3):
        new_url = format(url%page_num)
        #获取整页的源代码
        page_text = requests.get(url=new_url,headers=headers).text
        # print(page_text)
        #通过正则取出图片的地址
        ze = '<li class="article-summary">.*?<img .*?src="(.*?)" alt.*?</li>'
        # ze = '<li class="article-summary">.*?</li>'
        img_src = re.findall(ze,page_text,re.S)
        # print(img_src)
        #遍历请求图片地址
        for img in img_src:
            img_data = requests.get(url=img,headers=headers).content
            img_name = img.split('/')[-1]
            img_path = './qiutu/'+img_name
            with open(img_path,'wb') as f:
                f.write(img_data)
                print("%s下载成功" %img_name)