1. import requests, os
    3. base_url = 'https://tieba.baidu.com/f?'
    4. headers = {
    5.     'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36',
    6. }
    7. # 保存文件地址
    8. dirname = './tieba/woman/'
    9. if not os.path.exists(dirname):
    10.     os.makedirs(dirname)
    11. # len(对象)表示某个字符串或者数组的长度
    12. # range函数表示 返回的是列表
    13. # pn中表示的是页码，i为range定义的页码,从0-10,使用抓包，寻找规律
    14. # key自定义关键词
    15. key = 'JavaScript'
    16. for i in range(0, 10):
    17.     params = {
    18.         'ie': 'utf-8',
    19.         'kw': key,
    20.         'pn': str(i * 50)
    21.     }
    22.     response = requests.get(base_url, headers=headers, params=params)
    23.     with open(dirname + '美女第%s页.html' % (i+1), 'w', encoding='utf-8') as file:
    24.         file.write(response.content.decode('utf-8'))