python3爬虫入门(正则+requests 糗事百科多页图片爬取)

约定不等于承诺〃 2022-12-03 05:11 143阅读 0赞

import requests
    import re
    import os
    
    
    def get_data():
        global header
        url = "https://www.qiushibaike.com/imgrank/page/%d/"
        number = int(input("输入需要爬取的总页数："))
        for ye in range(1, number + 1):
            new_url = format(url % ye)
            page_text = requests.get(url=new_url, headers=header).text
            # print(page_text)
            rex = '<img.*?src="(.*?)" alt=.*? width.*?'
            list = re.findall(rex, page_text)
            for link in list:
                link = "https:" + link
                data = requests.get(url=link, headers=header).content
                filename = link.split("/")[-1]
                pathname = "./tu/" + filename
                with open(pathname, "wb") as f:
                    f.write(data)
                    print("图片下载成功", pathname)
                    print("图片下载地址为", link)
    
    
    if __name__ == "__main__":
        header = { 
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                          "Chrome/84.0.4147.105 Safari/537.36 "
        }
        if not os.path.exists("./tu") :
            os.mkdir("./tu")
        else:
            os.rmdir("./tu")
        get_data()

`笔记思路入门参考`

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2tpbmdvZmxvbmdldml0eQ_size_16_color_FFFFFF_t_70_pic_center]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2tpbmdvZmxvbmdldml0eQ_size_16_color_FFFFFF_t_70_pic_center]: /images/20221123/3ad902fa8fdd405597319ced4c0a9459.png