1. import requests
    2. from bs4 import BeautifulSoup
    3. import os
    4. from hashlib import md5
    5. class meizi(object):
    6.     def init(self):
    7.     self.baseURL = 'https://www.mzitu.com/tag/youhuo/page/{}/'
    8.     self.headers = {'If-None-Match': 'W/"5cc2cd8f-2c58"',
    9.     "Referer": "http://www.mzitu.com/all/",
    10.     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 UBrowser/6.1.2107.204 SafarMozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'
    11.     }
    12.     self.page = '2'
    13.     def getPage(self):
    14.         url = self.baseURL.format(self.page)
    15.         data = self.getRequest(url)
    16.         soup = BeautifulSoup(data, 'lxml')
    17.         self.page = soup.select('.page-numbers')[-2].get_text()
    18.         print(self.page)
    20.     def getRequest(self, url):
    21.         data = requests.get(url, headers=self.headers).content.decode()
    22.         return data
    24.     def getURL(self):
    25.         urlList = []
    26.         for i in range(1, (int(self.page) + 1)):
    27.             urlList.append(self.baseURL.format(str(i)))
    28.         return urlList
    30.     def xpath(self, data):
    31.         soup = BeautifulSoup(data, 'lxml')
    32.         list = soup.select('#pins li')
    33.         for item in list:
    34.             dataoriginal = item.select_one('img').get('data-original')
    35.             self.saveImage(dataoriginal)
    37.     def saveImage(self, imageURL, filePath='img'):
    38.         respose = requests.get(imageURL, headers=self.headers)
    39.         if respose.status_code == 200:
    40.             data = respose.content
    41.             try:
    42.                 if not os.path.exists(filePath):
    43.                     print('文件夹', filePath, '不存在，重新建立')
    44.                     os.makedirs(filePath)
    45.                 # 获得图片后缀
    46.                 file_suffix = os.path.splitext(imageURL)[1]
    47.                 # 拼接图片名（包含路径）
    48.                 filename = '{}/{}{}'.format(filePath, md5(data).hexdigest(),
    49.                                             file_suffix)
    50.                 with open(filename, 'wb')as f:
    51.                     f.write(data)
    53.             except IOError as e:
    54.                 print('文件操作失败:' + e)
    55.             except Exception as e:
    56.                 print('错误:' + e)
    58.     def startRun(self):
    59.         # self.getPage()
    60.         urlList = self.getURL()
    61.         for url in urlList:
    62.             print(url)
    63.             data = self.getRequest(url)
    64.             self.xpath(data)
    66. if name == 'main':
    67.     meizi().startRun()