96 lines
3.8 KiB
Python
96 lines
3.8 KiB
Python
|
import openpyxl
|
|||
|
|
import json
|
|||
|
|
import os
|
|||
|
|
|
|||
|
|
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, 'RenKou.json')
|
|||
|
|
|
|||
|
|
file_name = EXCEL_PATH
|
|||
|
|
population_data = []
|
|||
|
|
name_conversion_errors = [] # 记录转换失败的名称
|
|||
|
|
|
|||
|
|
try:
|
|||
|
|
# 加载工作簿并选择人口Sheet
|
|||
|
|
workbook = openpyxl.load_workbook(file_name, read_only=True)
|
|||
|
|
if '人口' not in workbook.sheetnames:
|
|||
|
|
print("❌ 错误：未找到'人口'Sheet")
|
|||
|
|
exit(1)
|
|||
|
|
sheet = workbook['人口']
|
|||
|
|
|
|||
|
|
# 定义数据列范围与英文属性映射
|
|||
|
|
data_columns = {
|
|||
|
|
'total_population': {'start_col': 'B', 'end_col': 'K', 'year_start': 2015}, # 年末总人口
|
|||
|
|
'urban_population': {'start_col': 'L', 'end_col': 'U', 'year_start': 2015}, # 城镇人口
|
|||
|
|
'rural_population': {'start_col': 'V', 'end_col': 'AE', 'year_start': 2015}, # 乡村人口
|
|||
|
|
'urbanization_rate': {'start_col': 'AF', 'end_col': 'AO', 'year_start': 2015}, # 城镇化率
|
|||
|
|
'birth_population': {'start_col': 'AP', 'end_col': 'AY', 'year_start': 2015} # 出生人口
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
# 遍历数据行（跳过前2行表头）
|
|||
|
|
for row_num, row in enumerate(sheet.iter_rows(min_row=3, values_only=True), start=3):
|
|||
|
|
raw_name = row[0] if row[0] else '未知地区'
|
|||
|
|
if not raw_name: # 跳过空行
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
# 区域名称转换（核心修改）
|
|||
|
|
area_info = query_area_info(raw_name.strip())
|
|||
|
|
if area_info:
|
|||
|
|
area_name = area_info['full_name']
|
|||
|
|
area_code = area_info['area_code']
|
|||
|
|
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 # 保留原始名称用于调试
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
# 提取各指标年度数据
|
|||
|
|
for metric, config in data_columns.items():
|
|||
|
|
start_col = openpyxl.utils.column_index_from_string(config['start_col']) - 1
|
|||
|
|
end_col = openpyxl.utils.column_index_from_string(config['end_col']) - 1
|
|||
|
|
year_data = {}
|
|||
|
|
|
|||
|
|
for col_idx, year in zip(range(start_col, end_col + 1), range(config['year_start'], 2025)):
|
|||
|
|
value = row[col_idx]
|
|||
|
|
# 处理空值和非数值
|
|||
|
|
if value is None or str(value).strip() == '':
|
|||
|
|
year_data[str(year)] = 0
|
|||
|
|
else:
|
|||
|
|
try:
|
|||
|
|
year_data[str(year)] = float(value) if '.' in str(value) else int(value)
|
|||
|
|
except (ValueError, TypeError):
|
|||
|
|
year_data[str(year)] = 0
|
|||
|
|
|
|||
|
|
area_data[metric] = year_data
|
|||
|
|
|
|||
|
|
population_data.append(area_data)
|
|||
|
|
|
|||
|
|
workbook.close()
|
|||
|
|
|
|||
|
|
# 保存为JSON文件
|
|||
|
|
with open(JSON_PATH, 'w', encoding='utf-8') as f:
|
|||
|
|
json.dump(population_data, f, ensure_ascii=False, indent=2)
|
|||
|
|
|
|||
|
|
# 输出转换结果统计
|
|||
|
|
print(f"✅ 人口数据提取完成，已保存至：{JSON_PATH}")
|
|||
|
|
print(f"📊 共处理 {len(population_data)} 条地区数据")
|
|||
|
|
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}")
|
|||
|
|
else:
|
|||
|
|
print("✅ 所有区域名称均成功转换为全称")
|
|||
|
|
|
|||
|
|
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)}")
|