1. """
    2. 目标网站：
    3.     https://pic.netbian.com/4kmeishi/
    4. 需求：
    5.     抓取当前页面美食图片
    6. 模块：
    7.     requests, lxml, os
    8. """
    10. import requests, os
    11. from lxml import etree
    13. url = 'https://pic.netbian.com/4kmeishi/'
    14. headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36'}
    15. if not os.path.exists('美食图片'):
    16.     os.mkdir('美食图片')
    17. # 如果不清楚网页的编码可以在console中输入 document.charset查看
    18. response = requests.get(url, headers=headers).content.decode('GBK')
    20. el_list = etree.HTML(response).xpath('//ul[@class="clearfix"]/li/a')
    21. for el in el_list:
    22.     pic_url = 'https://pic.netbian.com/' + el.xpath('./img/@src')[0]
    23.     img_name = el.xpath('./b/text()')[0]
    24.     img_path = f"美食图片/{img_name}.jpg"
    25.     pic = requests.get(pic_url, headers=headers).content
    26.     with open(img_path, 'wb')as f:
    27.         f.write(pic)
    28.         print(f'{img_name}下载成功')
    29. print(f'一共获取到{len(el_list)}个图片')
    32. """
    33. 总结：
    34.     01.在开发者工具中的console中输入 document.charset可以查看网页的编码，如果结果为"UTF-8"那么获取响应直接用response.text否则用response.content.decode()   
    35. """