Files
md2pdf/md2doc.py
T

39 lines
1.3 KiB
Python

#!/usr/bin/env python3
"""
Convert markdown files to DOCX (Microsoft Word).
Usage:
md2doc.py input.md # Creates input.docx in same directory
md2doc.py input.md -o output.docx # Specify output file
md2doc.py docs/ # Convert all .md files in directory
md2doc.py docs/ -o docx_output/
md2doc.py input.md --style mono # Use monospace style
Requires: pip install python-docx markdown beautifulsoup4 lxml
"""
import argparse
import sys
from pathlib import Path
def _bulletize(text: str) -> str:
"""Turn markdown "- " list markers into bullets, skipping code/HTML blocks.
Copied verbatim from md2pdf.py per spec §3.3.
"""
import re
out, in_fence, in_html = [], False, False
for line in text.split("\n"):
stripped = line.lstrip()
if stripped.startswith("```") or stripped.startswith("~~~"):
in_fence = not in_fence
elif not in_fence:
if re.match(r"^<(table|div|section|figure)\b", stripped, re.I):
in_html = True
elif re.match(r"^</(table|div|section|figure)>", stripped, re.I):
in_html = False
if not in_fence and not in_html and line.startswith("- "):
line = "• " + line[2:]
out.append(line)
return "\n".join(out)