python爬虫chinaplay网页的前十个游戏 游戏名字、原价、现价、折扣、爬下来输出到excel文件

#!/usr/bin/env python
# -*- coding: utf-8 -*-

# chinaplay的前十个游戏 游戏名字 原价 现价 折扣 爬下来输出到excel文件
import csv
import re
import ssl
from urllib import request as req

ssl._create_default_https_context = ssl._create_unverified_context

class CrawlChinaplay(object):
    def fetch_html(self):
        url = "https://chinaplay.store/?countBuy=1&genre2=actions&utm_expid=.D1txQMWbRSepiu4sNydAgA.1&utm_referrer="
        html_contents = req.urlopen(url).read().decode("utf-8")
        return html_contents

    def analysis(self,html_contents):
        root_regex = '<div class="product"[\s\S]*?熊猫点\s*</div>\s*</div>\s*</div>\s*</div>'
        content_list = re.findall(root_regex, html_contents)
        sub_regex = r'<div class="product"[\s\S]*?<div class="action-badge">(.*?)<[\s\S]*?<div class="game-title">[\t|\n]*(.*?)[\t|\n]*?</[\s\S]*?old_price">(.*?)<[\s\S]*?">(.*?)</span>'
        result_list = []  # 初始化一个空列表
        for content in content_list:
            t_list = []  # 清空列表
            result = re.match(sub_regex, content)
            if result:
                t_list.append(result.group(2))
                t_list.append(result.group(3))
                t_list.append(result.group(4))
                t_list.append(result.group(1))
            result_list.append(t_list)
        return result_list

    def sava_csv(self,result_list):
        out = open("chinaplay.csv", "a+", newline="", encoding="utf-8")
        csv_writer = csv.writer(out, dialect="excel")
        csv_writer.writerow(['game_name', 'ori_price', 'sale_price', 'discount'])
        i = 0
        if len(result_list) > 9:
            while i < 10:
                csv_writer.writerow(result_list[i])
                i += 1
        else:
            while i < len(result_list):
                csv_writer.writerow(result_list[i])
                i += 1
        out.close()

    def crawl(self):
        html_content = self.fetch_html()
        result_list = self.analysis(html_content)
        self.sava_csv(result_list)

if __name__ == "__main__":
    crawl_chinaplay = CrawlChinaplay()
    crawl_chinaplay.crawl()

 因为这个网站加载比较慢些，故爬取会慢一些

结果：