import re

filename = r"D:\temp\g1ans.txt"


with open(filename,"r",encoding = "u8") as f:
    raw_data = f.read()
data = re.findall(r"\\begin\{document\}([\s\S]*?)\\end\{document\}",raw_data)[0]
#预处理
data = data.replace("\\newpage","").replace("\\item","<enditem><item>").replace("\\end{enumerate}","<enditem>").replace("\\section","<enditem>")
#读取题目
problems = re.findall(r"<item>([\s\S]*?)<enditem>",data)

IDandAnswer = {}
for p in problems:
    id = re.findall(r"\((\d{6})\)",p)[0]
    # print(id)
    pos = re.search(r"\\textcolor\{red\}",p)
    while pos != None:
        p = p[pos.span()[1]:]
        pos = re.search(r"\\textcolor\{red\}",p)
    answer = p.strip()[1:-2].strip()
    print(id,answer)
    if not "暂无答案" in answer:
        IDandAnswer[id] = answer

output = "ans\n\n"
for id in IDandAnswer:
    output += id + "\n" + IDandAnswer[id] + "\n\n\n"

with open("文本文件/metadata.txt","w",encoding="u8") as f:
    f.write(output)