import glob
import pandas as pd

name = False
header = False
headline = []
sheet_name_black_list = ['填表说明', '数据资源目录结构', '新增需求填报']

xlsx_files = glob.glob('./附件2*.xlsx')
for file in xlsx_files:
    print(f"正在处理文件: {file}")
    out_file_name = file.split('：')[1].split('_')[0]
    # 读取Excel文件
    xls = pd.ExcelFile(file)
    # 打开一个文件用于写入
    with open(out_file_name + '.txt', 'w', encoding='utf-8') as file:
        for sheet_name in xls.sheet_names:
            name = False
            header = False
            if sheet_name in sheet_name_black_list:
                continue
            print(f"正在处理工作表: {sheet_name}")
            # 读取当前工作表到DataFrame
            df = xls.parse(sheet_name)
            file.write(sheet_name + "\n")
            initialized_header = False
            for index, row in df.iterrows():
                # 检查当前行的B列是否为空
                if pd.isnull(row[1]):
                    file.write("\n\n")
                    name = False
                    header = False
                    continue
                if not name:
                    file.write(row[1] + "\n")
                    name = True
                    continue
                if not header:
                    if not initialized_header:
                        initialized_header = True
                        new_row = [row[1]]
                        new_row.extend(row[4:])
                        for cell in new_row:
                            headline.append(cell)
                    header = True
                    continue
                new_row = [row[1]]
                new_row.extend(row[4:])
                for head, cell in zip(headline, new_row):
                    file.write(head + ":" + str(cell).replace('\n', '') + "\n")
                file.write("\n")
    xls.close()
print("处理完成")