Python脚本实现自动化处理Excel选择题

df = pd.read_excel('data.xlsx', header=None)
lines = df[0].dropna().astype(str).tolist()

questions = re.split(r'\n(?=\d+\.)', text.strip())

result_df.to_excel("整理后题库.xlsx", index=False)

pip install pandas openpyxl

python script.py

import pandas as pd
import re

# =========================
# 读取Excel
# =========================
df = pd.read_excel('data.xlsx', header=None)

# 第一列转列表
lines = df[0].dropna().astype(str).tolist()

# 合并成文本
text = "\n".join(lines)

# =========================
# 按题号切分
# =========================
questions = re.split(r'\n(?=\d+\.)', text.strip())

result = []

for q in questions:

    row = {
        "题目": "",
        "选项A": "",
        "选项B": "",
        "选项C": "",
        "选项D": "",
        "选项E": "",
        "选项F": "",
        "答案": ""
    }

    q_lines = q.strip().split("\n")

    # 题目
    row["题目"] = q_lines[0]

    # 答案
    answer_match = re.search(r'答[:：]\s*([A-F]+)', q)
    if answer_match:
        row["答案"] = answer_match.group(1)

    # 选项
    for line in q_lines[1:]:

        line = line.strip()

        match = re.match(r'^([A-F])[、\.．](.*)', line)

        if match:
            option = match.group(1)
            content = match.group(2).strip()

            row[f"选项{option}"] = f"{option}、{content}"

    result.append(row)

# =========================
# 输出结果
# =========================
result_df = pd.DataFrame(result)

# 保存Excel
result_df.to_excel("整理后题库.xlsx", index=False)

print(result_df)