CCF题目列表

python处理源代码

import bs4
from bs4 import BeautifulSoup
# 先将网页源代码保存到文件中，可直接爬取

def main():
    html = ""
    with open(file="../file/1.html", encoding='utf-8') as f:
        html = f.read()
    # print(len(html))
    bs = bs4.BeautifulSoup(markup=html, features='lxml')
    problem = bs.find_all("td", "idn")
    # print(len(problem))
    # print(problem[0].parent)
    file = open(file='../file/out.txt', encoding='utf-8', mode='w')
    for i in problem:
        j = i.next_sibling
        text = i.string + " " + j.string+"\n"
        file.write(text)
    file.close()


if __name__ == "__main__":
    main()