import openpyxl # 添加缺少的导入 import json import os import traceback from Config.Config import EXCEL_PATH from Util.AreaUtil import query_area_info # 创建数据保存目录 DATA_DIR = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'Data') os.makedirs(DATA_DIR, exist_ok=True) JSON_PATH = os.path.join(DATA_DIR, 'TeacherCount.json') # 修改为教师数的JSON路径 file_name = EXCEL_PATH teacher_data = [] name_conversion_errors = [] # 记录转换失败的名称 conversion_records = [] # 定义转换记录变量 try: # 加载工作簿并选择教职工数、专任教师数Sheet workbook = openpyxl.load_workbook(file_name, data_only=True) if '教职工数、专任教师数' not in workbook.sheetnames: print("❌ 错误：未找到'教职工数、专任教师数'Sheet") exit(1) sheet = workbook['教职工数、专任教师数'] # 定义数据列范围与英文属性映射 data_columns = { # 学前教育（每年份8列：教职工总数/城区/镇区/乡村，专任教师总数/城区/镇区/乡村） 'preschool_teachers': { 'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024], 'columns': [ {'year': 2015, 'total_staff': 'D', 'urban_staff': 'E', 'town_staff': 'F', 'rural_staff': 'G', 'total_teacher': 'H', 'urban_teacher': 'I', 'town_teacher': 'J', 'rural_teacher': 'K'}, {'year': 2016, 'total_staff': 'L', 'urban_staff': 'M', 'town_staff': 'N', 'rural_staff': 'O', 'total_teacher': 'P', 'urban_teacher': 'Q', 'town_teacher': 'R', 'rural_teacher': 'S'}, {'year': 2017, 'total_staff': 'T', 'urban_staff': 'U', 'town_staff': 'V', 'rural_staff': 'W', 'total_teacher': 'X', 'urban_teacher': 'Y', 'town_teacher': 'Z', 'rural_teacher': 'AA'}, {'year': 2018, 'total_staff': 'AB', 'urban_staff': 'AC', 'town_staff': 'AD', 'rural_staff': 'AE', 'total_teacher': 'AF', 'urban_teacher': 'AG', 'town_teacher': 'AH', 'rural_teacher': 'AI'}, {'year': 2019, 'total_staff': 'AJ', 'urban_staff': 'AK', 'town_staff': 'AL', 'rural_staff': 'AM', 'total_teacher': 'AN', 'urban_teacher': 'AO', 'town_teacher': 'AP', 'rural_teacher': 'AQ'}, {'year': 2020, 'total_staff': 'AR', 'urban_staff': 'AS', 'town_staff': 'AT', 'rural_staff': 'AU', 'total_teacher': 'AV', 'urban_teacher': 'AW', 'town_teacher': 'AX', 'rural_teacher': 'AY'}, {'year': 2021, 'total_staff': 'AZ', 'urban_staff': 'BA', 'town_staff': 'BB', 'rural_staff': 'BC', 'total_teacher': 'BD', 'urban_teacher': 'BE', 'town_teacher': 'BF', 'rural_teacher': 'BG'}, {'year': 2022, 'total_staff': 'BH', 'urban_staff': 'BI', 'town_staff': 'BJ', 'rural_staff': 'BK', 'total_teacher': 'BL', 'urban_teacher': 'BM', 'town_teacher': 'BN', 'rural_teacher': 'BO'}, {'year': 2023, 'total_staff': 'BP', 'urban_staff': 'BQ', 'town_staff': 'BR', 'rural_staff': 'BS', 'total_teacher': 'BT', 'urban_teacher': 'BU', 'town_teacher': 'BV', 'rural_teacher': 'BW'}, {'year': 2024, 'total_staff': 'BX', 'urban_staff': 'BY', 'town_staff': 'BZ', 'rural_staff': 'CA', 'total_teacher': 'CB', 'urban_teacher': 'CC', 'town_teacher': 'CD', 'rural_teacher': 'CE'} ] }, # 小学教育 'primary_teachers': { 'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024], 'columns': [ {'year': 2015, 'total_staff': 'CF', 'urban_staff': 'CG', 'town_staff': 'CH', 'rural_staff': 'CI', 'total_teacher': 'CJ', 'urban_teacher': 'CK', 'town_teacher': 'CL', 'rural_teacher': 'CM'}, {'year': 2016, 'total_staff': 'CN', 'urban_staff': 'CO', 'town_staff': 'CP', 'rural_staff': 'CQ', 'total_teacher': 'CR', 'urban_teacher': 'CS', 'town_teacher': 'CT', 'rural_teacher': 'CU'}, {'year': 2017, 'total_staff': 'CV', 'urban_staff': 'CW', 'town_staff': 'CX', 'rural_staff': 'CY', 'total_teacher': 'CZ', 'urban_teacher': 'DA', 'town_teacher': 'DB', 'rural_teacher': 'DC'}, {'year': 2018, 'total_staff': 'DD', 'urban_staff': 'DE', 'town_staff': 'DF', 'rural_staff': 'DG', 'total_teacher': 'DH', 'urban_teacher': 'DI', 'town_teacher': 'DJ', 'rural_teacher': 'DK'}, {'year': 2019, 'total_staff': 'DL', 'urban_staff': 'DM', 'town_staff': 'DN', 'rural_staff': 'DO', 'total_teacher': 'DP', 'urban_teacher': 'DQ', 'town_teacher': 'DR', 'rural_teacher': 'DS'}, {'year': 2020, 'total_staff': 'DT', 'urban_staff': 'DU', 'town_staff': 'DV', 'rural_staff': 'DW', 'total_teacher': 'DX', 'urban_teacher': 'DY', 'town_teacher': 'DZ', 'rural_teacher': 'EA'}, {'year': 2021, 'total_staff': 'EB', 'urban_staff': 'EC', 'town_staff': 'ED', 'rural_staff': 'EE', 'total_teacher': 'EF', 'urban_teacher': 'EG', 'town_teacher': 'EH', 'rural_teacher': 'EI'}, {'year': 2022, 'total_staff': 'EJ', 'urban_staff': 'EK', 'town_staff': 'EL', 'rural_staff': 'EM', 'total_teacher': 'EN', 'urban_teacher': 'EO', 'town_teacher': 'EP', 'rural_teacher': 'EQ'}, {'year': 2023, 'total_staff': 'ER', 'urban_staff': 'ES', 'town_staff': 'ET', 'rural_staff': 'EU', 'total_teacher': 'EV', 'urban_teacher': 'EW', 'town_teacher': 'EX', 'rural_teacher': 'EY'}, {'year': 2024, 'total_staff': 'EZ', 'urban_staff': 'FA', 'town_staff': 'FB', 'rural_staff': 'FC', 'total_teacher': 'FD', 'urban_teacher': 'FE', 'town_teacher': 'FF', 'rural_teacher': 'FG'} ] }, # 初中教育 'junior_high_teachers': { 'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024], 'columns': [ {'year': 2015, 'total_staff': 'FH', 'urban_staff': 'FI', 'town_staff': 'FJ', 'rural_staff': 'FK', 'total_teacher': 'FL', 'urban_teacher': 'FM', 'town_teacher': 'FN', 'rural_teacher': 'FO'}, {'year': 2016, 'total_staff': 'FP', 'urban_staff': 'FQ', 'town_staff': 'FR', 'rural_staff': 'FS', 'total_teacher': 'FT', 'urban_teacher': 'FU', 'town_teacher': 'FV', 'rural_teacher': 'FW'}, {'year': 2017, 'total_staff': 'FX', 'urban_staff': 'FY', 'town_staff': 'FZ', 'rural_staff': 'GA', 'total_teacher': 'GB', 'urban_teacher': 'GC', 'town_teacher': 'GD', 'rural_teacher': 'GE'}, {'year': 2018, 'total_staff': 'GF', 'urban_staff': 'GG', 'town_staff': 'GH', 'rural_staff': 'GI', 'total_teacher': 'GJ', 'urban_teacher': 'GK', 'town_teacher': 'GL', 'rural_teacher': 'GM'}, {'year': 2019, 'total_staff': 'GN', 'urban_staff': 'GO', 'town_staff': 'GP', 'rural_staff': 'GQ', 'total_teacher': 'GR', 'urban_teacher': 'GS', 'town_teacher': 'GT', 'rural_teacher': 'GU'}, {'year': 2020, 'total_staff': 'GV', 'urban_staff': 'GW', 'town_staff': 'GX', 'rural_staff': 'GY', 'total_teacher': 'GZ', 'urban_teacher': 'HA', 'town_teacher': 'HB', 'rural_teacher': 'HC'}, {'year': 2021, 'total_staff': 'HD', 'urban_staff': 'HE', 'town_staff': 'HF', 'rural_staff': 'HG', 'total_teacher': 'HH', 'urban_teacher': 'HI', 'town_teacher': 'HJ', 'rural_teacher': 'HK'}, {'year': 2022, 'total_staff': 'HL', 'urban_staff': 'HM', 'town_staff': 'HN', 'rural_staff': 'HO', 'total_teacher': 'HP', 'urban_teacher': 'HQ', 'town_teacher': 'HR', 'rural_teacher': 'HS'}, {'year': 2023, 'total_staff': 'HT', 'urban_staff': 'HU', 'town_staff': 'HV', 'rural_staff': 'HW', 'total_teacher': 'HX', 'urban_teacher': 'HY', 'town_teacher': 'HZ', 'rural_teacher': 'IA'}, {'year': 2024, 'total_staff': 'IB', 'urban_staff': 'IC', 'town_staff': 'ID', 'rural_staff': 'IE', 'total_teacher': 'IF', 'urban_teacher': 'IG', 'town_teacher': 'IH', 'rural_teacher': 'II'} ] }, # 高中教育 'senior_high_teachers': { 'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024], 'columns': [ {'year': 2015, 'total_staff': 'IJ', 'urban_staff': 'IK', 'town_staff': 'IL', 'rural_staff': 'IM', 'total_teacher': 'IN', 'urban_teacher': 'IO', 'town_teacher': 'IP', 'rural_teacher': 'IQ'}, {'year': 2016, 'total_staff': 'IR', 'urban_staff': 'IS', 'town_staff': 'IT', 'rural_staff': 'IU', 'total_teacher': 'IV', 'urban_teacher': 'IW', 'town_teacher': 'IX', 'rural_teacher': 'IY'}, {'year': 2017, 'total_staff': 'IZ', 'urban_staff': 'JA', 'town_staff': 'JB', 'rural_staff': 'JC', 'total_teacher': 'JD', 'urban_teacher': 'JE', 'town_teacher': 'JF', 'rural_teacher': 'JG'}, {'year': 2018, 'total_staff': 'JH', 'urban_staff': 'JI', 'town_staff': 'JJ', 'rural_staff': 'JK', 'total_teacher': 'JL', 'urban_teacher': 'JM', 'town_teacher': 'JN', 'rural_teacher': 'JO'}, {'year': 2019, 'total_staff': 'JP', 'urban_staff': 'JQ', 'town_staff': 'JR', 'rural_staff': 'JS', 'total_teacher': 'JT', 'urban_teacher': 'JU', 'town_teacher': 'JV', 'rural_teacher': 'JW'}, {'year': 2020, 'total_staff': 'JX', 'urban_staff': 'JY', 'town_staff': 'JZ', 'rural_staff': 'KA', 'total_teacher': 'KB', 'urban_teacher': 'KC', 'town_teacher': 'KD', 'rural_teacher': 'KE'}, {'year': 2021, 'total_staff': 'KF', 'urban_staff': 'KG', 'town_staff': 'KH', 'rural_staff': 'KI', 'total_teacher': 'KJ', 'urban_teacher': 'KK', 'town_teacher': 'KL', 'rural_teacher': 'KM'}, {'year': 2022, 'total_staff': 'KN', 'urban_staff': 'KO', 'town_staff': 'KP', 'rural_staff': 'KQ', 'total_teacher': 'KR', 'urban_teacher': 'KS', 'town_teacher': 'KT', 'rural_teacher': 'KU'}, {'year': 2023, 'total_staff': 'KV', 'urban_staff': 'KW', 'town_staff': 'KX', 'rural_staff': 'KY', 'total_teacher': 'KZ', 'urban_teacher': 'LA', 'town_teacher': 'LB', 'rural_teacher': 'LC'}, {'year': 2024, 'total_staff': 'LD', 'urban_staff': 'LE', 'town_staff': 'LF', 'rural_staff': 'LG', 'total_teacher': 'LH', 'urban_teacher': 'LI', 'town_teacher': 'LJ', 'rural_teacher': 'LK'} ] }, # 中职教育（特殊：每年2列） 'vocational_teachers': { 'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024], 'columns': [ {'year': 2015, 'total_staff': 'LL', 'total_teacher': 'LM'}, {'year': 2016, 'total_staff': 'LN', 'total_teacher': 'LO'}, {'year': 2017, 'total_staff': 'LP', 'total_teacher': 'LQ'}, {'year': 2018, 'total_staff': 'LR', 'total_teacher': 'LS'}, {'year': 2019, 'total_staff': 'LT', 'total_teacher': 'LU'}, {'year': 2020, 'total_staff': 'LV', 'total_teacher': 'LW'}, {'year': 2021, 'total_staff': 'LX', 'total_teacher': 'LY'}, {'year': 2022, 'total_staff': 'LZ', 'total_teacher': 'MA'}, {'year': 2023, 'total_staff': 'MB', 'total_teacher': 'MC'}, {'year': 2024, 'total_staff': 'MD', 'total_teacher': 'ME'} ] } } # 遍历数据行（跳过前4行表头，从第5行开始） for row_num, row in enumerate(sheet.iter_rows(min_row=5, values_only=True), start=5): # 区域名称从B列获取（索引1） raw_name = row[1] if (len(row) > 1 and row[1] is not None) else '未知地区' if not raw_name: # 跳过空行 continue # 区域名称转换 str_raw_name = str(raw_name).strip() if raw_name is not None else '未知地区' area_info = query_area_info(str_raw_name) if area_info and isinstance(area_info, dict) and 'full_name' in area_info and 'area_code' in area_info: area_name = area_info['full_name'] area_code = area_info['area_code'] if raw_name != area_name: conversion_records.append({ 'row': row_num, 'raw_name': raw_name, 'converted_name': area_name }) else: area_name = raw_name area_code = 'unknown' name_conversion_errors.append(f"行 {row_num}: '{raw_name}'") area_data = { 'area_name': area_name, 'area_code': area_code, 'raw_name': raw_name } # 提取各教育阶段教师数据 for stage, config in data_columns.items(): stage_data = {} for year_config in config['columns']: year = year_config['year'] year_data = {} # 处理教职工数据 staff_cols = ['total_staff', 'urban_staff', 'town_staff', 'rural_staff'] has_staff_categories = all(col in year_config for col in staff_cols) if has_staff_categories: # 处理分类教职工数据 for col in staff_cols: col_name = year_config[col] col_idx = openpyxl.utils.column_index_from_string(col_name) - 1 if col_idx < len(row): value = row[col_idx] # 数据清洗与转换 if value is None: year_data[col] = 0 else: str_value = str(value).strip() if str_value in ['', '####']: year_data[col] = 0 else: year_data[col] = int(str_value) if str_value.isdigit() else 0 else: # 处理中职教职工总数 col_name = year_config['total_staff'] col_idx = openpyxl.utils.column_index_from_string(col_name) - 1 if col_idx < len(row): value = row[col_idx] if value is None: year_data['total_staff'] = 0 else: str_value = str(value).strip() if str_value in ['', '####']: year_data['total_staff'] = 0 else: year_data['total_staff'] = int(str_value) if str_value.isdigit() else 0 # 处理专任教师数据 teacher_cols = ['total_teacher', 'urban_teacher', 'town_teacher', 'rural_teacher'] has_teacher_categories = all(col in year_config for col in teacher_cols) if has_teacher_categories: # 处理分类专任教师数据 for col in teacher_cols: col_name = year_config[col] col_idx = openpyxl.utils.column_index_from_string(col_name) - 1 if col_idx < len(row): value = row[col_idx] # 数据清洗与转换 if value is None: year_data[col] = 0 else: str_value = str(value).strip() if str_value in ['', '####']: year_data[col] = 0 else: year_data[col] = int(str_value) if str_value.isdigit() else 0 else: # 处理中职专任教师总数 col_name = year_config['total_teacher'] col_idx = openpyxl.utils.column_index_from_string(col_name) - 1 if col_idx < len(row): value = row[col_idx] if value is None: year_data['total_teacher'] = 0 else: str_value = str(value).strip() if str_value in ['', '####']: year_data['total_teacher'] = 0 else: year_data['total_teacher'] = int(str_value) if str_value.isdigit() else 0 stage_data[str(year)] = year_data area_data[stage] = stage_data teacher_data.append(area_data) workbook.close() # 保存JSON文件 with open(JSON_PATH, 'w', encoding='utf-8') as f: json.dump(teacher_data, f, ensure_ascii=False, indent=2) # 输出统计信息 print(f"✅ 教师数据提取完成，已保存至：{JSON_PATH}") print(f"📊 共处理 {len(teacher_data)} 条地区数据") print("\n=== 名称转换记录 ===") if conversion_records: for record in conversion_records: print(f"🔄 行 {record['row']}: {record['raw_name']} → {record['converted_name']}") print(f"📊 共检测到 {len(conversion_records)} 项名称转换") else: print("📝 不存在名称转换的情况") if name_conversion_errors: print(f"⚠️ 发现 {len(name_conversion_errors)} 个区域名称转换失败：") for error in name_conversion_errors: print(f" - {error}") except FileNotFoundError: print(f"🔴 错误：Excel文件 '{file_name}' 不存在") except Exception as e: print(f"🔴 处理数据时发生错误：{str(e)}{traceback.format_exc()}") finally: try: workbook.close() except: pass