60b6fecbb3
Move analyze_excel.py, excel_to_markdown.py, and locator_helper.py into the tools/ subdirectory to improve project organization.
64 lines
1.9 KiB
Python
64 lines
1.9 KiB
Python
"""
|
||
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')
|