苹果表主题图片爬取！

imgurls = tree.xpath('//a[@class="thumb epcl-loader"]/span/@data-src')

spans = tree.xpath('//a[@class="thumb epcl-loader"]/span/@style')

    def get_response(self, url):
        i = 0
        while i < 4:
            try:
                response = requests.get(url, headers=self.headers, timeout=8)
                return response
            except requests.exceptions.RequestException:
                i += 1
                print(f">> 获取网页出错，8S后将重试获取第：{i} 次")
                time.sleep(6)

#buddywatch 表盘
#微信：huguo00289
# -*- coding: utf-8 -*-

from fake_useragent import UserAgent
from lxml import etree
import requests,time,re


class Bu(object):
    def __init__(self):
        self.url = "https://buddywatch.app/page/"
        self.ua = UserAgent()
        self.headers = {"User-Agent": self.ua.random}



    def get_list(self,page):
        url = f'{self.url}{page}/'
        response=self.get_response(url)
        html=response.content.decode('utf-8')
        tree=etree.HTML(html)
        imgurls = tree.xpath('//a[@class="thumb epcl-loader"]/span/@data-src')
        spans = tree.xpath('//a[@class="thumb epcl-loader"]/span/@style')
        print(spans)
        for span in spans:
            imgurl=self.get_imgurl(span)
            #imgurls.append(imgurl)
            imgurls.insert(0,imgurl)

        print(len(imgurls))
        print(imgurls)

        for imgurl in imgurls:
            self.down(imgurl)


    def get_imgurl(self,span):
        imgurl = re.findall(r'background-image: url(.+?);', span, re.S)[0]
        imgurl=imgurl[1:-1]
        print(imgurl)
        return imgurl



    def down(self,imgurl):
        imgname=imgurl.split('/')[-1]
        r=self.get_response(imgurl)
        with open(f'buddywatch/{imgname}', 'wb') as f:
            f.write(r.content)
        print(f'{imgname} 图片下载成功了！')


    # 4次重试
    def get_response(self, url):
        i = 0
        while i < 4:
            try:
                response = requests.get(url, headers=self.headers, timeout=8)
                return response
            except requests.exceptions.RequestException:
                i += 1
                print(f">> 获取网页出错，8S后将重试获取第：{i} 次")
                time.sleep(6)



def main(pagenum):
    spider = Bu()
    for page in range(pagenum+1):
        spider.get_list(page)


if __name__=='__main__':
    pagenum = 57
    main(pagenum)