Add Excel to Markdown converter with support for multiple sheets and customizable output
This commit is contained in:
350
excel_to_markdown.py
Normal file
350
excel_to_markdown.py
Normal file
@@ -0,0 +1,350 @@
|
||||
"""
|
||||
Excel to Markdown Converter
|
||||
|
||||
将Excel文件转换为Markdown格式的表格,包含行号和列号(英文字母)。
|
||||
"""
|
||||
|
||||
import pandas as pd
|
||||
import argparse
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
def number_to_excel_col(n):
|
||||
"""将数字转换为Excel列号(A, B, ..., Z, AA, AB, ...)"""
|
||||
result = ""
|
||||
while n > 0:
|
||||
n -= 1
|
||||
result = chr(n % 26 + ord('A')) + result
|
||||
n //= 26
|
||||
return result
|
||||
|
||||
|
||||
def excel_to_markdown(input_file, output_file=None, sheet_name=0, include_row_numbers=True, include_col_numbers=True):
|
||||
"""
|
||||
将Excel文件转换为Markdown表格
|
||||
|
||||
Args:
|
||||
input_file: 输入的Excel文件路径
|
||||
output_file: 输出的Markdown文件路径(可选,默认为同名.md文件)
|
||||
sheet_name: 工作表名称或索引,或列表(默认为第一个工作表)
|
||||
include_row_numbers: 是否包含行号
|
||||
include_col_numbers: 是否包含列号
|
||||
"""
|
||||
input_path = Path(input_file)
|
||||
|
||||
if not input_path.exists():
|
||||
print(f"错误: 文件 '{input_file}' 不存在")
|
||||
return False
|
||||
|
||||
# 设置默认输出文件名
|
||||
if output_file is None:
|
||||
output_file = input_path.with_suffix('.md')
|
||||
else:
|
||||
output_file = Path(output_file)
|
||||
|
||||
try:
|
||||
# 读取Excel文件
|
||||
print(f"正在读取文件: {input_file}")
|
||||
|
||||
# 获取所有工作表名称(用于索引转换)
|
||||
xls = pd.ExcelFile(input_file)
|
||||
all_sheet_names = xls.sheet_names
|
||||
|
||||
# 将索引转换为实际的工作表名称
|
||||
def resolve_sheet_name(name):
|
||||
if isinstance(name, int):
|
||||
if 0 <= name < len(all_sheet_names):
|
||||
return all_sheet_names[name]
|
||||
else:
|
||||
raise ValueError(f"工作表索引 {name} 超出范围")
|
||||
return name
|
||||
|
||||
# 处理多个工作表的情况
|
||||
if isinstance(sheet_name, (list, tuple)):
|
||||
# 转换索引为名称
|
||||
resolved_names = [resolve_sheet_name(s) for s in sheet_name]
|
||||
dfs = pd.read_excel(input_file, sheet_name=resolved_names, header=None)
|
||||
# 如果只有一个工作表,转换为单个DataFrame
|
||||
if len(resolved_names) == 1:
|
||||
dfs = {resolved_names[0]: dfs}
|
||||
sheet_name = resolved_names
|
||||
else:
|
||||
resolved_name = resolve_sheet_name(sheet_name)
|
||||
df = pd.read_excel(input_file, sheet_name=resolved_name, header=None)
|
||||
dfs = {resolved_name: df}
|
||||
sheet_name = resolved_name
|
||||
|
||||
# 生成所有工作表的Markdown内容
|
||||
all_sheets_content = {}
|
||||
|
||||
for sheet_key, df in dfs.items():
|
||||
# 转换数据为字符串,处理NaN值
|
||||
df = df.fillna('')
|
||||
df = df.astype(str)
|
||||
|
||||
# 生成Markdown表格
|
||||
markdown_lines = []
|
||||
|
||||
# 添加工作表标题
|
||||
sheet_title = f"工作表: {sheet_key}"
|
||||
markdown_lines.append(f"## {sheet_title}\n")
|
||||
|
||||
# 添加列号行
|
||||
if include_col_numbers:
|
||||
col_headers = [''] if include_row_numbers else []
|
||||
col_headers.extend(number_to_excel_col(i + 1) for i in range(len(df.columns)))
|
||||
markdown_lines.append('| ' + ' | '.join(col_headers) + ' |')
|
||||
markdown_lines.append('| ' + ' | '.join(['---' for _ in col_headers]) + ' |')
|
||||
|
||||
# 添加数据行
|
||||
for idx, row in df.iterrows():
|
||||
row_data = []
|
||||
if include_row_numbers:
|
||||
row_data.append(str(idx + 1))
|
||||
row_data.extend(row)
|
||||
markdown_lines.append('| ' + ' | '.join(row_data) + ' |')
|
||||
|
||||
# 添加统计信息
|
||||
markdown_lines.append(f"\n**统计信息:**")
|
||||
markdown_lines.append(f"- 总行数: {len(df)}")
|
||||
markdown_lines.append(f"- 总列数: {len(df.columns)}")
|
||||
markdown_lines.append(f"- 数据范围: A1:{number_to_excel_col(len(df.columns))}{len(df)}")
|
||||
|
||||
all_sheets_content[sheet_key] = '\n'.join(markdown_lines)
|
||||
|
||||
# 写入文件
|
||||
if len(dfs) == 1:
|
||||
# 单个工作表:直接写入
|
||||
sheet_key = list(dfs.keys())[0]
|
||||
output_content = f"# {input_path.stem}\n\n"
|
||||
output_content += f"从 `{input_file}` (工作表: {sheet_key}) 转换\n\n"
|
||||
output_content += all_sheets_content[sheet_key]
|
||||
output_file.write_text(output_content, encoding='utf-8')
|
||||
|
||||
print(f"✓ 转换成功!")
|
||||
print(f" 输入文件: {input_file}")
|
||||
print(f" 输出文件: {output_file}")
|
||||
print(f" 工作表: {sheet_key}")
|
||||
print(f" 行数: {len(dfs[sheet_key])}, 列数: {len(dfs[sheet_key].columns)}")
|
||||
else:
|
||||
return all_sheets_content, dfs, input_path, input_file
|
||||
|
||||
except Exception as e:
|
||||
print(f"错误: {str(e)}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
return False
|
||||
|
||||
|
||||
def convert_multiple_sheets(input_file, output_file=None, sheet_names=None, include_row_numbers=True, include_col_numbers=True, merge_to_one_file=True):
|
||||
"""
|
||||
转换多个工作表
|
||||
|
||||
Args:
|
||||
input_file: 输入的Excel文件路径
|
||||
output_file: 输出的Markdown文件路径
|
||||
sheet_names: 工作表名称或索引列表
|
||||
include_row_numbers: 是否包含行号
|
||||
include_col_numbers: 是否包含列号
|
||||
merge_to_one_file: 是否合并到一个文件(True)或分别输出(False)
|
||||
"""
|
||||
input_path = Path(input_file)
|
||||
|
||||
if not input_path.exists():
|
||||
print(f"错误: 文件 '{input_file}' 不存在")
|
||||
return False
|
||||
|
||||
# 设置默认输出文件名
|
||||
if output_file is None:
|
||||
output_file = input_path.with_suffix('.md')
|
||||
else:
|
||||
output_file = Path(output_file)
|
||||
|
||||
try:
|
||||
# 读取Excel文件
|
||||
print(f"正在读取文件: {input_file}")
|
||||
|
||||
# 获取所有工作表名称
|
||||
xls = pd.ExcelFile(input_file)
|
||||
all_sheet_names = xls.sheet_names
|
||||
|
||||
if sheet_names is None or len(sheet_names) == 0:
|
||||
# 读取所有工作表
|
||||
sheet_names = all_sheet_names
|
||||
print(f"找到 {len(sheet_names)} 个工作表")
|
||||
else:
|
||||
# 将索引转换为实际的工作表名称
|
||||
resolved_names = []
|
||||
for name in sheet_names:
|
||||
if isinstance(name, int):
|
||||
# 索引转换为名称
|
||||
if 0 <= name < len(all_sheet_names):
|
||||
resolved_names.append(all_sheet_names[name])
|
||||
else:
|
||||
print(f"警告: 工作表索引 {name} 超出范围,已跳过")
|
||||
else:
|
||||
# 直接使用名称
|
||||
resolved_names.append(name)
|
||||
sheet_names = resolved_names
|
||||
|
||||
# 使用实际的工作表名称读取数据
|
||||
dfs = pd.read_excel(input_file, sheet_name=sheet_names, header=None)
|
||||
|
||||
# 确保返回的是字典格式
|
||||
if not isinstance(dfs, dict):
|
||||
dfs = {sheet_names[0]: dfs}
|
||||
|
||||
# 生成所有工作表的Markdown内容
|
||||
all_sheets_content = {}
|
||||
|
||||
for sheet_key, df in dfs.items():
|
||||
# 转换数据为字符串,处理NaN值
|
||||
df = df.fillna('')
|
||||
df = df.astype(str)
|
||||
|
||||
# 生成Markdown表格
|
||||
markdown_lines = []
|
||||
|
||||
# 添加工作表标题
|
||||
sheet_title = f"工作表: {sheet_key}"
|
||||
markdown_lines.append(f"## {sheet_title}\n")
|
||||
|
||||
# 添加列号行
|
||||
if include_col_numbers:
|
||||
col_headers = [''] if include_row_numbers else []
|
||||
col_headers.extend(number_to_excel_col(i + 1) for i in range(len(df.columns)))
|
||||
markdown_lines.append('| ' + ' | '.join(col_headers) + ' |')
|
||||
markdown_lines.append('| ' + ' | '.join(['---' for _ in col_headers]) + ' |')
|
||||
|
||||
# 添加数据行
|
||||
for idx, row in df.iterrows():
|
||||
row_data = []
|
||||
if include_row_numbers:
|
||||
row_data.append(str(idx + 1))
|
||||
row_data.extend(row)
|
||||
markdown_lines.append('| ' + ' | '.join(row_data) + ' |')
|
||||
|
||||
# 添加统计信息
|
||||
markdown_lines.append(f"\n**统计信息:**")
|
||||
markdown_lines.append(f"- 总行数: {len(df)}")
|
||||
markdown_lines.append(f"- 总列数: {len(df.columns)}")
|
||||
markdown_lines.append(f"- 数据范围: A1:{number_to_excel_col(len(df.columns))}{len(df)}")
|
||||
|
||||
all_sheets_content[sheet_key] = '\n'.join(markdown_lines)
|
||||
|
||||
# 写入文件
|
||||
if merge_to_one_file:
|
||||
# 合并到一个文件
|
||||
output_content = f"# {input_path.stem}\n\n"
|
||||
output_content += f"从 `{input_file}` 转换,共 {len(dfs)} 个工作表\n\n"
|
||||
output_content += "---\n\n"
|
||||
|
||||
for sheet_key in sheet_names:
|
||||
if sheet_key in all_sheets_content:
|
||||
output_content += all_sheets_content[sheet_key] + "\n\n---\n\n"
|
||||
|
||||
output_file.write_text(output_content, encoding='utf-8')
|
||||
|
||||
print(f"✓ 转换成功!")
|
||||
print(f" 输入文件: {input_file}")
|
||||
print(f" 输出文件: {output_file}")
|
||||
print(f" 工作表数量: {len(dfs)}")
|
||||
for sheet_key in sheet_names:
|
||||
if sheet_key in dfs:
|
||||
print(f" - {sheet_key}: {len(dfs[sheet_key])}行 x {len(dfs[sheet_key].columns)}列")
|
||||
else:
|
||||
# 分别输出到多个文件
|
||||
output_stem = output_file.stem
|
||||
output_suffix = output_file.suffix
|
||||
output_dir = output_file.parent
|
||||
|
||||
for sheet_key in sheet_names:
|
||||
if sheet_key not in all_sheets_content:
|
||||
continue
|
||||
|
||||
# 为每个工作表创建单独的文件
|
||||
sheet_filename = f"{output_stem}_{sheet_key}{output_suffix}"
|
||||
sheet_output_file = output_dir / sheet_filename
|
||||
|
||||
output_content = f"# {input_path.stem} - {sheet_key}\n\n"
|
||||
output_content += f"从 `{input_file}` (工作表: {sheet_key}) 转换\n\n"
|
||||
output_content += all_sheets_content[sheet_key]
|
||||
|
||||
sheet_output_file.write_text(output_content, encoding='utf-8')
|
||||
|
||||
print(f"✓ 转换成功!")
|
||||
print(f" 输入文件: {input_file}")
|
||||
print(f" 输出目录: {output_dir}")
|
||||
print(f" 工作表数量: {len(dfs)}")
|
||||
for sheet_key in sheet_names:
|
||||
if sheet_key in dfs:
|
||||
sheet_filename = f"{output_stem}_{sheet_key}{output_suffix}"
|
||||
print(f" - {sheet_key} -> {sheet_filename} ({len(dfs[sheet_key])}行 x {len(dfs[sheet_key].columns)}列)")
|
||||
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
print(f"错误: {str(e)}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
return False
|
||||
|
||||
|
||||
# ============================================================
|
||||
# 配置区域 - 直接修改下面的参数
|
||||
# ============================================================
|
||||
|
||||
# 输入文件路径(必填)
|
||||
INPUT_FILE = r"D:\python\playwrite\data\YTHN-100.A0.532-BOM-1.2版.xlsx"
|
||||
|
||||
# 输出文件路径(可选,默认为输入文件同名.md文件)
|
||||
OUTPUT_FILE = None # 或指定 r"D:\path\to\output.md"
|
||||
|
||||
# 工作表名称或索引(可选,默认为0即第一个工作表)
|
||||
# 可以是单个值: 0 或 "Sheet1"
|
||||
# 可以是列表: [0, 1, 2] 或 ["Sheet1", "Sheet2", "Sheet3"]
|
||||
# 可以是 None 表示读取所有工作表
|
||||
SHEET_NAMES = [0, 1,2,3] # 指定多个工作表索引
|
||||
|
||||
# 是否包含行号(可选,默认为True)
|
||||
INCLUDE_ROW_NUMBERS = True
|
||||
|
||||
# 是否包含列号(可选,默认为True)
|
||||
INCLUDE_COL_NUMBERS = True
|
||||
|
||||
# 如果指定了多个工作表,是否合并到一个文件(可选,默认为True)
|
||||
# True: 所有工作表合并到一个文件
|
||||
# False: 每个工作表生成单独的文件(文件名格式: 原文件名_工作表名.md)
|
||||
MULTI_SHEETS_TO_ONE_FILE = True
|
||||
|
||||
# ============================================================
|
||||
|
||||
|
||||
def main():
|
||||
"""主函数 - 使用上方配置区域定义的参数"""
|
||||
# 判断是否为多个工作表
|
||||
if isinstance(SHEET_NAMES, list) and len(SHEET_NAMES) > 1:
|
||||
# 多个工作表
|
||||
convert_multiple_sheets(
|
||||
input_file=INPUT_FILE,
|
||||
output_file=OUTPUT_FILE,
|
||||
sheet_names=SHEET_NAMES,
|
||||
include_row_numbers=INCLUDE_ROW_NUMBERS,
|
||||
include_col_numbers=INCLUDE_COL_NUMBERS,
|
||||
merge_to_one_file=MULTI_SHEETS_TO_ONE_FILE
|
||||
)
|
||||
else:
|
||||
# 单个工作表
|
||||
sheet_name = SHEET_NAMES if isinstance(SHEET_NAMES, list) and len(SHEET_NAMES) == 1 else SHEET_NAMES
|
||||
excel_to_markdown(
|
||||
input_file=INPUT_FILE,
|
||||
output_file=OUTPUT_FILE,
|
||||
sheet_name=sheet_name,
|
||||
include_row_numbers=INCLUDE_ROW_NUMBERS,
|
||||
include_col_numbers=INCLUDE_COL_NUMBERS
|
||||
)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
Reference in New Issue
Block a user