Add Excel analysis and conversion scripts for order data processing
This commit is contained in:
63
analyze_excel.py
Normal file
63
analyze_excel.py
Normal file
@@ -0,0 +1,63 @@
|
|||||||
|
"""
|
||||||
|
分析 Excel 文件的数据结构
|
||||||
|
"""
|
||||||
|
import pandas as pd
|
||||||
|
import openpyxl
|
||||||
|
import sys
|
||||||
|
|
||||||
|
# 设置输出编码
|
||||||
|
if sys.platform == 'win32':
|
||||||
|
import io
|
||||||
|
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
|
||||||
|
|
||||||
|
# 读取 Excel 文件
|
||||||
|
file_path = "data/导出文件.xlsx"
|
||||||
|
|
||||||
|
print("=" * 80)
|
||||||
|
print("1. 读取所有工作表名称")
|
||||||
|
print("=" * 80)
|
||||||
|
|
||||||
|
wb = openpyxl.load_workbook(file_path)
|
||||||
|
sheet_names = wb.sheetnames
|
||||||
|
print(f"工作表数量: {len(sheet_names)}")
|
||||||
|
print(f"工作表名称: {sheet_names}")
|
||||||
|
|
||||||
|
print("\n" + "=" * 80)
|
||||||
|
print("2. 逐行读取原始数据(使用 openpyxl)")
|
||||||
|
print("=" * 80)
|
||||||
|
|
||||||
|
for sheet_name in sheet_names:
|
||||||
|
print(f"\n--- 工作表: {sheet_name} ---")
|
||||||
|
ws = wb[sheet_name]
|
||||||
|
|
||||||
|
for idx, row in enumerate(ws.iter_rows(values_only=True), 1):
|
||||||
|
# 检查是否为空行
|
||||||
|
is_empty = all(cell is None or str(cell).strip() == "" for cell in row)
|
||||||
|
if is_empty:
|
||||||
|
print(f"行 {idx}: [空行]")
|
||||||
|
else:
|
||||||
|
# 过滤掉 None 和空字符串,只显示有效数据
|
||||||
|
valid_data = [str(cell) if cell is not None else "" for cell in row]
|
||||||
|
print(f"行 {idx}: {valid_data}")
|
||||||
|
|
||||||
|
print("\n" + "=" * 80)
|
||||||
|
print("3. 使用 pandas 读取数据(观察列结构)")
|
||||||
|
print("=" * 80)
|
||||||
|
|
||||||
|
for sheet_name in sheet_names:
|
||||||
|
print(f"\n--- 工作表: {sheet_name} ---")
|
||||||
|
df = pd.read_excel(file_path, sheet_name=sheet_name)
|
||||||
|
print(f"DataFrame 形状: {df.shape}")
|
||||||
|
print(f"\n列名:")
|
||||||
|
for i, col in enumerate(df.columns):
|
||||||
|
print(f" 列 {i}: {col}")
|
||||||
|
print(f"\n数据预览:")
|
||||||
|
pd.set_option('display.max_rows', 25)
|
||||||
|
pd.set_option('display.max_columns', 20)
|
||||||
|
pd.set_option('display.width', 200)
|
||||||
|
pd.set_option('display.max_colwidth', 30)
|
||||||
|
print(df)
|
||||||
|
pd.reset_option('display.max_rows')
|
||||||
|
pd.reset_option('display.max_columns')
|
||||||
|
pd.reset_option('display.width')
|
||||||
|
pd.reset_option('display.max_colwidth')
|
||||||
213
convert_excel.py
Normal file
213
convert_excel.py
Normal file
@@ -0,0 +1,213 @@
|
|||||||
|
"""
|
||||||
|
将 Excel 报表数据转换为数据库记录形式
|
||||||
|
"""
|
||||||
|
import pandas as pd
|
||||||
|
import openpyxl
|
||||||
|
from typing import List, Dict
|
||||||
|
import os
|
||||||
|
|
||||||
|
def parse_sheet(ws) -> List[Dict]:
|
||||||
|
"""
|
||||||
|
解析一个工作表,返回所有订单的数据
|
||||||
|
|
||||||
|
每个订单包含:
|
||||||
|
- order_info: 订单头信息
|
||||||
|
- materials: 物料数据列表
|
||||||
|
"""
|
||||||
|
orders = []
|
||||||
|
all_rows = list(ws.iter_rows(values_only=True))
|
||||||
|
|
||||||
|
# 查找所有空行,用于分割订单
|
||||||
|
empty_rows = [i for i, row in enumerate(all_rows) if all(cell is None or str(cell).strip() == "" for cell in row)]
|
||||||
|
|
||||||
|
print(f"检测到空行索引: {empty_rows}")
|
||||||
|
print(f"总行数: {len(all_rows)}")
|
||||||
|
|
||||||
|
# 逐行扫描,按订单结构解析
|
||||||
|
i = 0
|
||||||
|
while i < len(all_rows):
|
||||||
|
row = all_rows[i]
|
||||||
|
|
||||||
|
# 检查是否是订单标题行
|
||||||
|
if row and '离散备料计划' in str(row[0]):
|
||||||
|
print(f"\n在行 {i + 1} 发现订单标题")
|
||||||
|
|
||||||
|
# 解析订单头信息(接下来的4行)
|
||||||
|
order_info = {}
|
||||||
|
for j in range(1, 5):
|
||||||
|
if i + j < len(all_rows) and all_rows[i + j]:
|
||||||
|
parse_header_row(all_rows[i + j], order_info)
|
||||||
|
|
||||||
|
print(f"订单头信息: {order_info}")
|
||||||
|
|
||||||
|
# 跳过空行,找到表格标题行
|
||||||
|
table_row = i + 5
|
||||||
|
while table_row < len(all_rows) and (not all_rows[table_row] or not all_rows[table_row][0]):
|
||||||
|
table_row += 1
|
||||||
|
|
||||||
|
# 检查是否是表格标题行
|
||||||
|
if table_row < len(all_rows) and all_rows[table_row] and all_rows[table_row][0] == '序号':
|
||||||
|
print(f"在行 {table_row + 1} 发现表格标题")
|
||||||
|
|
||||||
|
# 解析物料数据
|
||||||
|
materials = []
|
||||||
|
footer_info = {} # 页脚信息
|
||||||
|
data_row = table_row + 1
|
||||||
|
while data_row < len(all_rows) and all_rows[data_row]:
|
||||||
|
# 检查是否是页脚信息(制单人、打印人)
|
||||||
|
if all_rows[data_row][0] and ('制单人' in str(all_rows[data_row][0]) or '打印人' in str(all_rows[data_row][0])):
|
||||||
|
print(f"在行 {data_row + 1} 发现页脚信息")
|
||||||
|
# 解析页脚信息
|
||||||
|
parse_header_row(all_rows[data_row], footer_info)
|
||||||
|
# 检查下一行是否也是页脚信息
|
||||||
|
if data_row + 1 < len(all_rows) and all_rows[data_row + 1]:
|
||||||
|
parse_header_row(all_rows[data_row + 1], footer_info)
|
||||||
|
print(f"页脚信息: {footer_info}")
|
||||||
|
break
|
||||||
|
|
||||||
|
# 检查是否是物料行(第一列是数字)
|
||||||
|
if all_rows[data_row][0] and str(all_rows[data_row][0]).strip().isdigit():
|
||||||
|
material_row = all_rows[data_row]
|
||||||
|
material = {
|
||||||
|
'序号': material_row[0],
|
||||||
|
'材料编码': material_row[1],
|
||||||
|
'材料名称': material_row[2],
|
||||||
|
'规格': material_row[3],
|
||||||
|
'型号': material_row[4],
|
||||||
|
'图号': material_row[5],
|
||||||
|
'物料材质': material_row[6],
|
||||||
|
'计划数量': material_row[7],
|
||||||
|
'单位': material_row[8],
|
||||||
|
'需用日期': material_row[9],
|
||||||
|
'发料仓库': material_row[10],
|
||||||
|
'单位用量': material_row[11],
|
||||||
|
'累计出库数量': material_row[12],
|
||||||
|
}
|
||||||
|
materials.append(material)
|
||||||
|
print(f" 添加物料: {material['材料编码']} - {material['材料名称']}")
|
||||||
|
|
||||||
|
data_row += 1
|
||||||
|
|
||||||
|
print(f"共解析到 {len(materials)} 条物料数据")
|
||||||
|
|
||||||
|
orders.append({
|
||||||
|
'order_info': {**order_info, **footer_info},
|
||||||
|
'materials': materials
|
||||||
|
})
|
||||||
|
|
||||||
|
i += 1
|
||||||
|
|
||||||
|
return orders
|
||||||
|
|
||||||
|
def parse_header_row(row: tuple, info: Dict):
|
||||||
|
"""
|
||||||
|
解析订单头信息的一行(字段名和值交错排列)
|
||||||
|
"""
|
||||||
|
i = 0
|
||||||
|
while i < len(row):
|
||||||
|
cell = row[i]
|
||||||
|
if cell and str(cell).strip() and ':' in str(cell):
|
||||||
|
# 找到字段名
|
||||||
|
field_name = str(cell).replace(':', '').strip()
|
||||||
|
|
||||||
|
# 重命名冲突字段
|
||||||
|
field_name_mapping = {
|
||||||
|
'计划数量': '产品计划数量',
|
||||||
|
'单位': '产品单位'
|
||||||
|
}
|
||||||
|
if field_name in field_name_mapping:
|
||||||
|
field_name = field_name_mapping[field_name]
|
||||||
|
|
||||||
|
# 跳过空单元格,找到第一个非字段名的值
|
||||||
|
j = i + 1
|
||||||
|
while j < len(row) and (not row[j] or not str(row[j]).strip() or ':' in str(row[j])):
|
||||||
|
j += 1
|
||||||
|
if j < len(row) and row[j] and not ':' in str(row[j]):
|
||||||
|
info[field_name] = str(row[j]).strip()
|
||||||
|
# 跳过已处理的值,继续找下一个字段名
|
||||||
|
i = j + 1
|
||||||
|
else:
|
||||||
|
i += 1
|
||||||
|
|
||||||
|
def convert_to_dataframe(orders: List[Dict]) -> pd.DataFrame:
|
||||||
|
"""
|
||||||
|
将订单数据转换为扁平化的 DataFrame
|
||||||
|
"""
|
||||||
|
all_records = []
|
||||||
|
|
||||||
|
for order in orders:
|
||||||
|
order_info = order['order_info']
|
||||||
|
materials = order['materials']
|
||||||
|
|
||||||
|
for material in materials:
|
||||||
|
record = {
|
||||||
|
**order_info,
|
||||||
|
**material
|
||||||
|
}
|
||||||
|
all_records.append(record)
|
||||||
|
|
||||||
|
return pd.DataFrame(all_records)
|
||||||
|
|
||||||
|
def main():
|
||||||
|
input_file = "data/导出文件.xlsx"
|
||||||
|
output_file = "data/导出文件_转换.xlsx"
|
||||||
|
|
||||||
|
# 如果输出文件存在,先删除
|
||||||
|
if os.path.exists(output_file):
|
||||||
|
try:
|
||||||
|
os.remove(output_file)
|
||||||
|
except PermissionError:
|
||||||
|
print(f"警告: 无法删除 {output_file},可能文件被其他程序打开")
|
||||||
|
output_file = "data/导出文件_转换_new.xlsx"
|
||||||
|
|
||||||
|
print("=" * 80)
|
||||||
|
print("开始转换 Excel 数据")
|
||||||
|
print("=" * 80)
|
||||||
|
|
||||||
|
# 读取工作表
|
||||||
|
wb = openpyxl.load_workbook(input_file)
|
||||||
|
ws = wb.active
|
||||||
|
|
||||||
|
# 解析订单数据
|
||||||
|
orders = parse_sheet(ws)
|
||||||
|
|
||||||
|
print(f"\n\n共解析到 {len(orders)} 个订单")
|
||||||
|
|
||||||
|
# 打印每个订单的摘要
|
||||||
|
for i, order in enumerate(orders, 1):
|
||||||
|
order_info = order['order_info']
|
||||||
|
materials = order['materials']
|
||||||
|
print(f"\n订单 {i}:")
|
||||||
|
print(f" 备料计划单号: {order_info.get('备料计划单号', 'N/A')}")
|
||||||
|
print(f" 来源单号: {order_info.get('来源单号', 'N/A')}")
|
||||||
|
print(f" 产品编码: {order_info.get('产品编码', 'N/A')}")
|
||||||
|
print(f" 产品名称: {order_info.get('产品名称', 'N/A')}")
|
||||||
|
print(f" 计划数量: {order_info.get('计划数量', 'N/A')}")
|
||||||
|
print(f" 物料数量: {len(materials)}")
|
||||||
|
|
||||||
|
# 转换为 DataFrame
|
||||||
|
df = convert_to_dataframe(orders)
|
||||||
|
|
||||||
|
print(f"\n转换后的数据形状: {df.shape}")
|
||||||
|
|
||||||
|
if not df.empty:
|
||||||
|
print(f"列名: {list(df.columns)}")
|
||||||
|
|
||||||
|
# 保存为 Excel
|
||||||
|
df.to_excel(output_file, index=False)
|
||||||
|
print(f"\n数据已保存到: {output_file}")
|
||||||
|
|
||||||
|
# 显示前几行数据
|
||||||
|
print("\n数据预览:")
|
||||||
|
pd.set_option('display.max_columns', None)
|
||||||
|
pd.set_option('display.width', 200)
|
||||||
|
pd.set_option('display.max_colwidth', 30)
|
||||||
|
print(df.head(20))
|
||||||
|
pd.reset_option('display.max_columns')
|
||||||
|
pd.reset_option('display.width')
|
||||||
|
pd.reset_option('display.max_colwidth')
|
||||||
|
else:
|
||||||
|
print("警告: 没有数据可保存")
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
Reference in New Issue
Block a user