表情包分頁存儲

import os
import requests
from lxml import etree


class Spider(object):
    def __init__(self):
        # self.url = 'https://www.doutula.com/photo/list/?page=1'
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
        }
        self.offset = 1

    def get_data(self, url):
        print('正在爬取第{}頁.....................'.format(self.offset))
        folder = 'img/' + '第{}頁'.format(self.offset)

        if not os.path.exists(folder):
            os.mkdir(folder)

        response = requests.get(url, headers=self.headers).text
        page = etree.HTML(response)
        node_list = page.xpath('//div[@class="page-content text-center"]//a')
        for node in node_list:
            pic_url = node.xpath('.//img/@data-original')[0]
            title = node.xpath('.//p/text()')[0]

            response2 = requests.get(pic_url, headers=self.headers).content

            save_name = folder + '/'+ title + '.jpg'
            print(save_name)
            try:
                with open(save_name, 'wb') as f:
                    f.write(response2)
            except:
                pass

        self.offset += 1
        next_url = 'https://www.doutula.com/photo/list/?page={}'.format(self.offset)
        self.get_data(next_url)



if __name__ == '__main__':
    s = Spider()
    s.get_data('https://www.doutula.com/photo/list/?page=1')