镀金的天空-GlidedSky(解题笔记)

 第一关：爬虫基础

import requests
from bs4 import BeautifulSoup
import re
def w1():
    url="http://www.glidedsky.com/level/web/crawler-basic-1"
    header={
        "Upgrade-Insecure-Requests": "1",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
        "Referer": "http://www.glidedsky.com/level/crawler-basic-1",
        #将cookie换成自己的就ok了
        "Cookie": "----------"
    }
    rs1=requests.get(url=url,headers=header)
    print(rs1.text)
    soup = BeautifulSoup(rs1.text, 'html.parser')

    pattern = re.compile(r'\b\d{3}\b')

    # 找到所有符合条件的div标签
    div_tags = soup.find_all('div', class_='col-md-1')

    # 提取匹配的数字并求和
    total_sum = sum([int(pattern.search(tag.text).group()) for tag in div_tags if pattern.search(tag.text)])

    print(f"总和：{total_sum}")

if __name__ =="__main__":
    w1()