python3爬虫入门(正则+requests 糗事百科单页图片爬取)

Dear 丶 2022-11-25 11:51 154阅读 0赞

`入门基本都会学到的图片下载编写，希望自己的思路能给入门困惑的朋友一点启发`  
`代码如下`:

import requests
    import re
    import os
    
    def get_page():
        global header
        url = "https://www.qiushibaike.com/imgrank/"
        page_text = requests.get(url=url, headers=header).text
        rex = '<img.*?src="(.*?)" alt=.*? width.*?'
        list = re.findall(rex, page_text)
        # print(list)
        return list
    
    
    def For_list():
        global header
        global links_list
        for link in links_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")
        links_list = get_page()
        For_list()

`学无止境`

![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/20221124/1685ea598ee445108314890254bd3d74.png