Python爬虫学习笔记（四）

# 分页抓取网站上的图片 并保存到文件夹中
import requests
import re
import  os
if __name__=="__main__":
    if not os.path.exists('./qiutuLibs/'):
        os.mkdir('./qiutuLibs/')
    headers = {
    
    
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3947.100 Safari/537.36"}
        #https://www.qiushibaike.com/imgrank/page/2/
        #https://www.qiushibaike.com/imgrank/page/4/
        # <div class="thumb">
        #
        # <a href="/article/123595000" target="_blank">
        # <img src="//pic.qiushibaike.com/system/pictures/12359/123595000/medium/6IUHDYTJXLDN16DA.jpg" alt="糗事#123595000" class="illustration" width="100%" height="auto">
        # </a>
        # </div>
    base_url = 'https://www.qiushibaike.com/imgrank/page/%d/'#  %d占位
    ex='<div class="thumb">.*?<img src="(.*?)" alt.*?</div>' #构建正则

    for pageNum in range(1,6):#1-5页的图片
        url = format(base_url%pageNum)     #  用pageNum代替之前的占位符
        #print('每页url',url)
        page_text = requests.get(url=url,headers=headers).text
        img_src_list = re.findall(ex,page_text,re.S)
        print(img_src_list)

        for src in img_src_list:
            src_url = "https:"+src
            img_data = requests.get(url=src_url,headers=headers).content
            img_name = src_url.split('/')[-1]#-1表示最后一个
            img_path = './qiutuLibs/'+img_name
            with open(img_path,'wb') as fp:
                fp.write(img_data)
                print(img_name,"Downloaded!!")