1. import requests
    2. from bs4 import BeautifulSoup
    3. from hashlib import md5
    4. import os
    5. class JXAriUniversity(object):
    6.     def init(self):
    7.         self.baseURL = 'http://www.jxau.edu.cn/10/list.htm'
    8.         self.edu = 'http://www.jxau.edu.cn'
    9.         self.headers = {
    10.         'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Mobile Safari/537.36'
    11.         }
    12.     def respose(self, url):
    13.         content = requests.get(url,
    14.                                headers=self.headers).content.decode()
    15.         return content
    17.     def getRequest(self):
    18.         content = self.respose(self.baseURL)
    19.         soup = BeautifulSoup(content, 'lxml')
    20.         list = soup.select('.news_list li')
    21.         edu_list = []
    22.         for item in list:
    23.             dict = {}
    24.             dict['href'] = self.edu + item.select_one('a').get('href')
    25.             dict['title'] = item.select_one('a').get('title')
    26.             edu_list.append(dict)
    28.         for item in edu_list:
    29.             edu_url = item['href']
    30.             edu_title = item['title']
    31.             edu_html = self.respose(edu_url)
    32.             soup_edu = BeautifulSoup(edu_html, 'lxml')
    33.             image_list = soup_edu.select('.wp_articlecontent img')
    34.             images = []
    35.             for item in image_list:
    36.                 image_url = self.edu + item.get('src')
    37.                 self.saveImage(image_url, 'edu/江西农业大学/{}'.format(edu_title))
    39.     def saveImage(self, image_url, file_path):
    40.         respose = requests.get(image_url)
    41.         if respose.status_code == 200:
    42.             data = respose.content
    43.             try:
    44.                 if not os.path.exists(file_path):
    45.                     print('文件夹', file_path, '不存在，重新建立')
    46.                     os.makedirs(file_path)
    47.                 # 获得图片后缀
    48.                 file_suffix = os.path.splitext(image_url)[1]
    49.                 # 拼接图片名（包含路径）
    50.                 filename = '{}/{}{}'.format(file_path, md5(data).hexdigest(),
    51.                                             file_suffix)
    52.                 with open(filename, 'wb')as f:
    53.                     f.write(data)
    55.             except IOError as e:
    56.                 print('文件操作失败:' + e)
    57.             except Exception as e:
    58.                 print('错误:' + e)
    60.     def run(self):
    61.         self.getRequest()
    63. if name == 'main':
    64.     JXAriUniversity().run()

    截屏2020-11-11 15.48.50.png