import pandas as pd

# 文件路径
final_lib_file = "/root/.openclaw/media/inbound/â_¼ï_LV1-å_ç_å_è_åº_-ç¼_å_é_è_ç_è_é---1de9de11-1a6b-45c7-856a-4d69f9b26aa9.xlsx" # 定稿单词库
difficulty_file = "/root/.openclaw/media/inbound/é_¾åº_æ_æ_å_è_ç³_æ_1.0---a5011ea1-5bef-47af-be44-633db83f822e.xlsx" # 难度表
output_file = "/root/.openclaw/workspace-xiaoban/极简版单词上下册分类结果.xlsx"

# 读取表格
df_final = pd.read_excel(final_lib_file)
df_diff = pd.read_excel(difficulty_file)

# 完全按原始顺序拆分：前250行上册，后250行下册，无视内容
final_words_all = df_final['单词'].tolist()
upper_words = final_words_all[:250]
lower_words = final_words_all[250:]

# 直接匹配，无视重复
upper_df = df_diff[df_diff['单词'].isin(upper_words)]
lower_df = df_diff[df_diff['单词'].isin(lower_words)]

# 写入结果
with pd.ExcelWriter(output_file, engine='openpyxl') as writer:
    upper_df.to_excel(writer, sheet_name='上册单词', index=False)
    lower_df.to_excel(writer, sheet_name='下册单词', index=False)

print(f"处理完成！结果已保存到：{output_file}")
print(f"上册单词数量：{len(upper_df)}")
print(f"下册单词数量：{len(lower_df)}")