一、原理

1.什么是爬虫

爬虫从初始网页的URL开始,获取初始网页上的URL
在抓取网页的过程中，不断从当前页面上抽取新的URL放X队列
直到满足系统给定的停止条件;

二、代码

1.安装必要的包

pip install requests
pip install BeautifulSoup4
pip install tqdm
pip install html5lib

2.代码

import requests
from bs4 import BeautifulSoup
import csv
from tqdm import tqdm

# 模拟浏览器访问
Headers = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3741.400 QQBrowser/10.5.3863.400'

# 表头
csvHeaders = ['题号', '难度', '标题', '通过率', '通过数/总提交数']

# 题目数据
subjects = []

# 爬取题目
print('题目信息爬取中：\n')
for pages in tqdm(range(1, 1 + 1)):

    # 网址
    r = requests.get(f'http://www.51mxd.cn/problemset.php-page={pages}.htm', Headers)
    # 获取网页内容
    r.raise_for_status()
    # 编码
    r.encoding = 'utf-8'
    # 创建 BeautifulSoup对象
    soup = BeautifulSoup(r.text, 'html5lib')
    # 找到所有td标签
    td = soup.find_all('td')

    subject = []

    for t in td:
        # 一列一列的获取值组成一行
        if t.string is not None:
            subject.append(t.string)
            if len(subject) == 5:
                subjects.append(subject)
                subject = []

#存放题目
with open('NYOJ_Subjects.csv', 'w', newline='') as file:
    fileWriter = csv.writer(file)
    fileWriter.writerow(csvHeaders)
    fileWriter.writerows(subjects)

print('\n题目信息爬取完成！！！')