Initial commit of akmon project
This commit is contained in:
178
doc_bus/convert_to_pdf.py
Normal file
178
doc_bus/convert_to_pdf.py
Normal file
@@ -0,0 +1,178 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
融资计划书转换工具
|
||||
Convert Markdown financing plan to Word/PDF with professional formatting
|
||||
"""
|
||||
|
||||
import subprocess
|
||||
import os
|
||||
import sys
|
||||
import datetime
|
||||
import platform
|
||||
from pathlib import Path
|
||||
|
||||
def check_installed_modules():
|
||||
"""查看Python模块安装信息的命令"""
|
||||
print("=== Python模块检查命令 ===")
|
||||
print("1. 查看所有已安装模块:")
|
||||
print(" pip list")
|
||||
print(" pip freeze")
|
||||
print()
|
||||
print("2. 查看特定模块详细信息:")
|
||||
print(" pip show 模块名")
|
||||
print(" 例: pip show pandas")
|
||||
print()
|
||||
print("3. 检查模块是否可导入:")
|
||||
print(" python -c \"import 模块名; print('模块已安装')\"")
|
||||
print(" 例: python -c \"import datetime; print('datetime已安装')\"")
|
||||
print()
|
||||
print("4. 查看模块版本:")
|
||||
print(" python -c \"import 模块名; print(模块名.__version__)\"")
|
||||
print(" 例: python -c \"import pandas; print(pandas.__version__)\"")
|
||||
print()
|
||||
print("5. 搜索包含关键词的模块:")
|
||||
print(" pip list | grep 关键词")
|
||||
print(" 例: pip list | grep pandas")
|
||||
print()
|
||||
|
||||
def check_pandoc():
|
||||
"""检查Pandoc是否已安装"""
|
||||
try:
|
||||
subprocess.run(['pandoc', '--version'], check=True, capture_output=True)
|
||||
return True
|
||||
except (subprocess.CalledProcessError, FileNotFoundError):
|
||||
return False
|
||||
|
||||
def check_latex_engine():
|
||||
"""检查LaTeX引擎(xelatex)是否可用"""
|
||||
try:
|
||||
subprocess.run(['xelatex', '-version'], check=True, capture_output=True)
|
||||
return True
|
||||
except (subprocess.CalledProcessError, FileNotFoundError):
|
||||
return False
|
||||
|
||||
def convert_to_word(input_file, output_file):
|
||||
"""转换为Word格式"""
|
||||
cmd = [
|
||||
'pandoc',
|
||||
input_file,
|
||||
'-o', output_file,
|
||||
'--from', 'markdown',
|
||||
'--to', 'docx',
|
||||
'--highlight-style', 'tango',
|
||||
'--table-of-contents',
|
||||
'--toc-depth', '3',
|
||||
'--number-sections',
|
||||
'--metadata', 'title=骅锋科技股份有限公司融资计划书',
|
||||
'--metadata', 'author=骅锋科技股份有限公司',
|
||||
'--metadata', 'date=' + datetime.datetime.now().strftime('%Y年%m月%d日')
|
||||
]
|
||||
|
||||
# 如果存在自定义模板，使用模板
|
||||
template_path = Path('template.docx')
|
||||
if template_path.exists():
|
||||
cmd.extend(['--reference-doc', str(template_path)])
|
||||
|
||||
return subprocess.run(cmd, check=True)
|
||||
|
||||
def convert_to_pdf(input_file, output_file):
|
||||
"""使用pandoc和LaTeX转换为PDF格式"""
|
||||
cmd = [
|
||||
'pandoc',
|
||||
input_file,
|
||||
'-o', output_file,
|
||||
'--from', 'markdown',
|
||||
'--to', 'pdf',
|
||||
'--pdf-engine', 'xelatex',
|
||||
'--highlight-style', 'tango',
|
||||
'--table-of-contents',
|
||||
'--toc-depth', '3',
|
||||
'--number-sections',
|
||||
'--metadata', 'title=骅锋科技股份有限公司融资计划书',
|
||||
'--metadata', 'author=骅锋科技股份有限公司',
|
||||
'--metadata', 'documentclass=report',
|
||||
'--metadata', 'geometry=a4paper,margin=2cm',
|
||||
'--metadata', 'fontsize=12pt',
|
||||
'--metadata', 'mainfont=Microsoft YaHei',
|
||||
'--metadata', 'CJKmainfont=Microsoft YaHei'
|
||||
]
|
||||
|
||||
return subprocess.run(cmd, check=True, capture_output=True)
|
||||
|
||||
def convert_docx_to_pdf_windows(docx_path, pdf_path):
|
||||
"""[Windows Fallback] 使用PowerShell将DOCX转换为PDF (需要安装MS Word)"""
|
||||
if platform.system() != "Windows":
|
||||
return False
|
||||
|
||||
print("... 正在尝试使用MS Word将DOCX转换为PDF作为备选方案 ...")
|
||||
|
||||
script = f"""
|
||||
$word = New-Object -ComObject Word.Application
|
||||
$word.Visible = $false
|
||||
$doc = $word.Documents.Open('{os.path.abspath(docx_path)}')
|
||||
$doc.SaveAs('{os.path.abspath(pdf_path)}', 17) # 17 corresponds to wdFormatPDF
|
||||
$doc.Close()
|
||||
$word.Quit()
|
||||
"""
|
||||
try:
|
||||
subprocess.run(["powershell", "-Command", script], check=True, capture_output=True)
|
||||
print(f"✅ PDF文档已通过Word生成: {pdf_path}")
|
||||
return True
|
||||
except (subprocess.CalledProcessError, FileNotFoundError) as e:
|
||||
print("❌ 使用Word转换PDF失败。请确保已安装Microsoft Word。")
|
||||
print(f" 错误详情: {e}")
|
||||
return False
|
||||
|
||||
def main():
|
||||
"""主函数"""
|
||||
|
||||
# 检查Pandoc
|
||||
if not check_pandoc():
|
||||
print("错误：未找到Pandoc")
|
||||
print("请从以下网址安装Pandoc：https://pandoc.org/installing.html")
|
||||
check_installed_modules() # 显示模块检查命令
|
||||
return 1
|
||||
|
||||
input_file = 'rongzi_deepseek.md'
|
||||
word_output = 'rongzi_deepseek_plan.docx'
|
||||
|
||||
# 检查输入文件
|
||||
if not os.path.exists(input_file):
|
||||
print(f"错误：找不到输入文件 {input_file}")
|
||||
return 1
|
||||
|
||||
try:
|
||||
print(f"正在将 {input_file} 转换为Word格式...")
|
||||
convert_to_word(input_file, word_output)
|
||||
print(f"✅ Word文档已生成: {word_output}")
|
||||
|
||||
except subprocess.CalledProcessError as e:
|
||||
print(f"转换失败: {e}")
|
||||
return 1
|
||||
except Exception as e:
|
||||
print(f"未知错误: {e}")
|
||||
return 1
|
||||
|
||||
return 0
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main())
|
||||
print("⚠️ 未找到xelatex引擎。PDF将通过备选方案生成。")
|
||||
print(" 为了获得最佳PDF输出质量，建议安装LaTeX发行版 (如 MiKTeX for Windows)。")
|
||||
if not convert_docx_to_pdf_windows(word_output, pdf_output):
|
||||
print(" 无法生成PDF文件。")
|
||||
|
||||
print("\n转换完成！")
|
||||
|
||||
except subprocess.CalledProcessError as e:
|
||||
print(f"转换失败: {e}")
|
||||
return 1
|
||||
except Exception as e:
|
||||
print(f"未知错误: {e}")
|
||||
return 1
|
||||
|
||||
return 0
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main())
|
||||
Reference in New Issue
Block a user