# -*-coding:utf-8-*- from lxml import etree import requests import sys, os, re class Meizitu(object):     def __init__(self):         # 设置序号为图片名         self.i = 1         # 构建url         self.url = 'http://www.meizitu.com/a/more_{}.html'         # 构建header         self.headers = {
              "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36"         }         self.pattern = re.compile('http://www.meizitu.com/a/\d+.html', re.S)  # 使用正则匹配url         self.img_url = []     def get_page(self, url):         response = requests.get(url, headers=self.headers)         # print(response.encoding)  # 返回内容编码编码格式         return response.content     def parse_data(self, detail_data):         # 取得图片页url         str_data1 = self.pattern.findall(detail_data.decode('utf-8', 'ignore'))         return str_data1     def pic_info(self, image_list):         # 详细页面         img_url = []         for url in image_list:             img_page = self.get_page(url)             html = etree.HTML(img_page)             if html is not None:                 img_detial_list = html.xpath('//img/@src')                 if img_detial_list:                     for i in img_detial_list:                         if i not in self.img_url:                             self.img_url.append(i)  # 去重存到self.img_url                             img_url.append(i)     def download(self):         # print(image_list)         if not os.path.exists('images'):             os.makedirs('images')         for url in self.img_url:             print(url)             data = self.get_page(url)             with open('images' + os.sep + str(self.i) + '.jpg', 'wb+') as f:                 f.write(data)             self.i = self.i + 1     def run(self):         page = input('输入页码')         self.url = 'http://www.meizitu.com/a/more_{}.html'.format(page)

print(self.url)         detail_data = self.get_page(self.url)         # 抽取图片url         image_list = self.parse_data(detail_data)         self.pic_info(image_list)         self.download() if __name__ == '__main__':     meizi = Meizitu()     meizi.run()