269 lines
12 KiB
Python
269 lines
12 KiB
Python
import openpyxl
|
||
import json
|
||
import os
|
||
import traceback
|
||
from openpyxl.utils import column_index_from_string
|
||
|
||
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, 'ZaiXiaoShengCount.json') # 在校生数JSON路径
|
||
|
||
# 教育阶段配置 - 在校生数(2015-2024年)
|
||
education_stages = [
|
||
{
|
||
'name': 'preschool',
|
||
'chinese_name': '学前教育',
|
||
'columns': [
|
||
{'year': 2015, 'urban': 'D', 'town': 'E', 'rural': 'F', 'total': 'G'},
|
||
{'year': 2016, 'urban': 'H', 'town': 'I', 'rural': 'J', 'total': 'K'},
|
||
{'year': 2017, 'urban': 'L', 'town': 'M', 'rural': 'N', 'total': 'O'},
|
||
{'year': 2018, 'urban': 'P', 'town': 'Q', 'rural': 'R', 'total': 'S'},
|
||
{'year': 2019, 'urban': 'T', 'town': 'U', 'rural': 'V', 'total': 'W'},
|
||
{'year': 2020, 'urban': 'X', 'town': 'Y', 'rural': 'Z', 'total': 'AA'},
|
||
{'year': 2021, 'urban': 'AB', 'town': 'AC', 'rural': 'AD', 'total': 'AE'},
|
||
{'year': 2022, 'urban': 'AF', 'town': 'AG', 'rural': 'AH', 'total': 'AI'},
|
||
{'year': 2023, 'urban': 'AJ', 'town': 'AK', 'rural': 'AL', 'total': 'AM'},
|
||
{'year': 2024, 'urban': 'AN', 'town': 'AO', 'rural': 'AP', 'total': 'AQ'}
|
||
]
|
||
},
|
||
{
|
||
'name': 'primary',
|
||
'chinese_name': '小学教育',
|
||
'columns': [
|
||
{'year': 2015, 'urban': 'AR', 'town': 'AS', 'rural': 'AT', 'total': 'AU'},
|
||
{'year': 2016, 'urban': 'AV', 'town': 'AW', 'rural': 'AX', 'total': 'AY'},
|
||
{'year': 2017, 'urban': 'AZ', 'town': 'BA', 'rural': 'BB', 'total': 'BC'},
|
||
{'year': 2018, 'urban': 'BD', 'town': 'BE', 'rural': 'BF', 'total': 'BG'},
|
||
{'year': 2019, 'urban': 'BH', 'town': 'BI', 'rural': 'BJ', 'total': 'BK'},
|
||
{'year': 2020, 'urban': 'BL', 'town': 'BM', 'rural': 'BN', 'total': 'BO'},
|
||
{'year': 2021, 'urban': 'BP', 'town': 'BQ', 'rural': 'BR', 'total': 'BS'},
|
||
{'year': 2022, 'urban': 'BT', 'town': 'BU', 'rural': 'BV', 'total': 'BW'},
|
||
{'year': 2023, 'urban': 'BX', 'town': 'BY', 'rural': 'BZ', 'total': 'CA'},
|
||
{'year': 2024, 'urban': 'CB', 'town': 'CC', 'rural': 'CD', 'total': 'CE'}
|
||
]
|
||
},
|
||
{
|
||
'name': 'junior',
|
||
'chinese_name': '初中教育',
|
||
'columns': [
|
||
{'year': 2015, 'urban': 'CF', 'town': 'CG', 'rural': 'CH', 'total': 'CI'},
|
||
{'year': 2016, 'urban': 'CJ', 'town': 'CK', 'rural': 'CL', 'total': 'CM'},
|
||
{'year': 2017, 'urban': 'CN', 'town': 'CO', 'rural': 'CP', 'total': 'CQ'},
|
||
{'year': 2018, 'urban': 'CR', 'town': 'CS', 'rural': 'CT', 'total': 'CU'},
|
||
{'year': 2019, 'urban': 'CV', 'town': 'CW', 'rural': 'CX', 'total': 'CY'},
|
||
{'year': 2020, 'urban': 'CZ', 'town': 'DA', 'rural': 'DB', 'total': 'DC'},
|
||
{'year': 2021, 'urban': 'DD', 'town': 'DE', 'rural': 'DF', 'total': 'DG'},
|
||
{'year': 2022, 'urban': 'DH', 'town': 'DI', 'rural': 'DJ', 'total': 'DK'},
|
||
{'year': 2023, 'urban': 'DL', 'town': 'DM', 'rural': 'DN', 'total': 'DO'},
|
||
{'year': 2024, 'urban': 'DP', 'town': 'DQ', 'rural': 'DR', 'total': 'DS'}
|
||
]
|
||
},
|
||
{
|
||
'name': 'senior',
|
||
'chinese_name': '高中教育',
|
||
'columns': [
|
||
{'year': 2015, 'urban': 'DT', 'town': 'DU', 'rural': 'DV', 'total': 'DW'},
|
||
{'year': 2016, 'urban': 'DX', 'town': 'DY', 'rural': 'DZ', 'total': 'EA'},
|
||
{'year': 2017, 'urban': 'EB', 'town': 'EC', 'rural': 'ED', 'total': 'EE'},
|
||
{'year': 2018, 'urban': 'EF', 'town': 'EG', 'rural': 'EH', 'total': 'EI'},
|
||
{'year': 2019, 'urban': 'EJ', 'town': 'EK', 'rural': 'EL', 'total': 'EM'},
|
||
{'year': 2020, 'urban': 'EN', 'town': 'EO', 'rural': 'EP', 'total': 'EQ'},
|
||
{'year': 2021, 'urban': 'ER', 'town': 'ES', 'rural': 'ET', 'total': 'EU'},
|
||
{'year': 2022, 'urban': 'EV', 'town': 'EW', 'rural': 'EX', 'total': 'EY'},
|
||
{'year': 2023, 'urban': 'EZ', 'town': 'FA', 'rural': 'FB', 'total': 'FC'},
|
||
{'year': 2024, 'urban': 'FD', 'town': 'FE', 'rural': 'FF', 'total': 'FG'}
|
||
]
|
||
},
|
||
{
|
||
'name': 'vocational',
|
||
'chinese_name': '中职教育',
|
||
'columns': [
|
||
{'year': 2015, 'total': 'FH'},
|
||
{'year': 2016, 'total': 'FI'},
|
||
{'year': 2017, 'total': 'FJ'},
|
||
{'year': 2018, 'total': 'FK'},
|
||
{'year': 2019, 'total': 'FL'},
|
||
{'year': 2020, 'total': 'FM'},
|
||
{'year': 2021, 'total': 'FN'},
|
||
{'year': 2022, 'total': 'FO'},
|
||
{'year': 2023, 'total': 'FP'},
|
||
{'year': 2024, 'total': 'FQ'}
|
||
]
|
||
}
|
||
]
|
||
|
||
def process_value(value):
|
||
"""处理单元格值，转换为适当类型"""
|
||
if value is None:
|
||
return 0
|
||
|
||
# 转换为字符串处理
|
||
str_value = str(value).strip()
|
||
|
||
# 处理空字符串
|
||
if not str_value:
|
||
return 0
|
||
|
||
# 处理特殊标记
|
||
if str_value in ['####', 'NA', 'N/A', '—', ' ']:
|
||
return 0
|
||
|
||
# 处理数字
|
||
try:
|
||
# 移除千分位逗号
|
||
if ',' in str_value:
|
||
str_value = str_value.replace(',', '')
|
||
return int(float(str_value))
|
||
except ValueError:
|
||
return 0
|
||
|
||
def main():
|
||
file_name = EXCEL_PATH
|
||
student_data = []
|
||
name_conversion_errors = []
|
||
conversion_records = []
|
||
processed_count = 0
|
||
|
||
try:
|
||
# 加载工作簿并选择在校生数Sheet
|
||
workbook = openpyxl.load_workbook(file_name, data_only=True)
|
||
if '在校生数' not in workbook.sheetnames:
|
||
print("❌ 错误：未找到'在校生数'Sheet")
|
||
return
|
||
sheet = workbook['在校生数']
|
||
|
||
print(f"✅ 成功加载Excel文件：{file_name}")
|
||
print(f"✅ 开始处理在校生数数据，共{sheet.max_row}行数据")
|
||
|
||
# 遍历行数据
|
||
for row_idx, row in enumerate(sheet.iter_rows(values_only=True), start=1):
|
||
# 跳过前4行表头
|
||
if row_idx < 5:
|
||
continue
|
||
|
||
# 从B列获取区域名称（索引1）
|
||
try:
|
||
# 检查行是否有足够的列
|
||
if len(row) < 2:
|
||
print(f"⚠️ 第{row_idx}行数据不足，跳过")
|
||
continue
|
||
|
||
raw_name = row[1]
|
||
if raw_name is None:
|
||
print(f"⚠️ 第{row_idx}行B列区域名称为空，跳过该行")
|
||
continue
|
||
|
||
raw_name = str(raw_name).strip()
|
||
if not raw_name:
|
||
print(f"⚠️ 第{row_idx}行B列区域名称为空字符串，跳过该行")
|
||
continue
|
||
|
||
# 查询区域信息
|
||
area_info = query_area_info(raw_name)
|
||
area_name = raw_name
|
||
area_code = 'unknown'
|
||
|
||
# 验证区域信息
|
||
if isinstance(area_info, dict):
|
||
if 'full_name' in area_info and 'area_code' in area_info:
|
||
area_name = area_info['full_name']
|
||
area_code = area_info['area_code']
|
||
conversion_records.append(f"✅ 第{row_idx}行: {raw_name} → {area_name}")
|
||
processed_count += 1
|
||
else:
|
||
name_conversion_errors.append(f"第{row_idx}行: {raw_name} (缺少必要字段)")
|
||
conversion_records.append(f"❌ 第{row_idx}行: {raw_name} (格式错误)")
|
||
else:
|
||
name_conversion_errors.append(f"第{row_idx}行: {raw_name}")
|
||
conversion_records.append(f"❌ 第{row_idx}行: {raw_name} (未找到匹配)")
|
||
|
||
# 创建区域数据对象
|
||
area_data = {
|
||
'area_name': area_name,
|
||
'area_code': area_code,
|
||
'raw_name': raw_name,
|
||
'student_data': {}
|
||
}
|
||
|
||
# 提取各教育阶段在校生数据
|
||
for stage in education_stages:
|
||
stage_name = stage['name']
|
||
stage_data = {}
|
||
|
||
for year_config in stage['columns']:
|
||
year = year_config['year']
|
||
year_data = {}
|
||
|
||
# 处理多类别教育阶段（学前到高中）
|
||
if 'urban' in year_config:
|
||
# 城区
|
||
urban_col = column_index_from_string(year_config['urban']) - 1
|
||
urban_val = row[urban_col] if len(row) > urban_col else None
|
||
year_data['urban'] = process_value(urban_val)
|
||
|
||
# 镇区
|
||
town_col = column_index_from_string(year_config['town']) - 1
|
||
town_val = row[town_col] if len(row) > town_col else None
|
||
year_data['town'] = process_value(town_val)
|
||
|
||
# 乡村
|
||
rural_col = column_index_from_string(year_config['rural']) - 1
|
||
rural_val = row[rural_col] if len(row) > rural_col else None
|
||
year_data['rural'] = process_value(rural_val)
|
||
|
||
# 总计
|
||
total_col = column_index_from_string(year_config['total']) - 1
|
||
total_val = row[total_col] if len(row) > total_col else None
|
||
year_data['total'] = process_value(total_val)
|
||
# 处理中职教育（单值）
|
||
else:
|
||
total_col = column_index_from_string(year_config['total']) - 1
|
||
total_val = row[total_col] if len(row) > total_col else None
|
||
year_data['total'] = process_value(total_val)
|
||
|
||
stage_data[str(year)] = year_data
|
||
|
||
area_data['student_data'][stage_name] = stage_data
|
||
|
||
student_data.append(area_data)
|
||
|
||
# 进度提示
|
||
if processed_count % 10 == 0 and processed_count > 0:
|
||
print(f"🔄 已处理{processed_count}条数据...")
|
||
|
||
except Exception as e:
|
||
print(f"🔴 处理第{row_idx}行时发生错误：{str(e)}")
|
||
continue
|
||
|
||
# 保存数据到JSON文件
|
||
with open(JSON_PATH, 'w', encoding='utf-8') as f:
|
||
json.dump(student_data, f, ensure_ascii=False, indent=2)
|
||
|
||
print("\n=== 数据处理完成 ===")
|
||
print(f"📊 共处理 {processed_count} 条地区数据")
|
||
print(f"✅ 区域名称转换成功: {processed_count - len(name_conversion_errors)}")
|
||
if name_conversion_errors:
|
||
print(f"❌ 区域名称转换失败: {len(name_conversion_errors)}个")
|
||
for error in name_conversion_errors[:5]:
|
||
print(f" - {error}")
|
||
if len(name_conversion_errors) > 5:
|
||
print(f" - ... 等{len(name_conversion_errors)-5}个错误")
|
||
|
||
print(f"💾 数据已保存至 {JSON_PATH}")
|
||
|
||
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:
|
||
if 'workbook' in locals():
|
||
workbook.close()
|
||
|
||
if __name__ == "__main__":
|
||
main()
|
||
|