1. from bs4 import BeautifulSoup as bs
    2. import requests
    3. from fake_useragent import UserAgent
    4. import os
    5. class Tupian:
    7.     def __init__(self,cate,page):
    8.         self.page = page
    9.         self.cate = cate
    10.         self.base_url = 'https://www.umeitu.com/'
    11.         if int(page) == 1:
    12.             self.url = self.base_url + self.cate
    13.         else:
    14.             self.url = f'{self.base_url}{self.cate}index_{page}.htm'
    15.         if not os.path.exists('./' + self.cate):
    16.             os.makedirs('./' + self.cate)
    18.     def get_data(self):
    19.         headers = {
    20.             'User-Agent':UserAgent().random,
    21.             'Referer':self.base_url
    22.         }
    23.         try:
    24.             print(f'获取第{self.page}页图片')
    25.             response = requests.get(self.url, headers=headers)
    26.             if response.status_code == 200:
    27.                 response.encoding = 'utf-8'
    28.                 html = response.text
    29.                 soup = bs(html,'lxml')
    30.                 a_list = soup.find_all('a',class_='TypeBigPics')
    31.                 for a in a_list:
    32.                     img_src = a.find('img')['src']
    33.                     img_name = a.find('span').string
    34.                     self.downImg(img_name,img_src)
    35.                 print(f'第{self.page}页数据爬取完成')
    36.             else:
    37.                 print(response.reason)
    38.         except Exception as error:
    39.             print(error)
    41.     # 下载图片
    42.     def downImg(self,img_name,img_src):
    43.         response = requests.get(img_src)
    44.         print(f'下载图片【{img_name}】...')
    45.         if response.status_code == 200:
    46.             with open(f'./{self.cate}{img_name}.jpg','wb') as file:
    47.                 file.write(response.content)
    49. cates = [  # 分类
    50.     'meinvtupian/siwameinv/',
    51.     'meinvtupian/meinvxiezhen/',
    52.     'meinvtupian/nayimeinv/',
    53.     'meinvtupian/jiepaimeinv/',
    54.     'meinvtupian/rentiyishu/'
    55. ]
    56. page = 0
    57. for cate in cates:
    58.     page += 1
    59.     tupian = Tupian(cate,page)
    60.     tupian.get_data()