pdf_merge.py 1.7 KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950
  1. #!/usr/bin/env python3
  2. """Merge multiple PDFs into one, optionally adding a bookmark per source file."""
  3. from __future__ import annotations
  4. import argparse
  5. import json
  6. import os
  7. import sys
  8. def main() -> int:
  9. for stream in (sys.stdout, sys.stderr):
  10. try:
  11. stream.reconfigure(encoding="utf-8")
  12. except Exception:
  13. pass
  14. parser = argparse.ArgumentParser(description="Merge PDFs (pypdf).")
  15. parser.add_argument("inputs", nargs="+", help="Input PDF paths, in order")
  16. parser.add_argument("-o", "--output", required=True, help="Output PDF path")
  17. parser.add_argument("--bookmarks", action="store_true",
  18. help="Add a top-level bookmark per input file (its basename)")
  19. args = parser.parse_args()
  20. try:
  21. from pypdf import PdfReader, PdfWriter
  22. except ImportError:
  23. print("Missing dependency: 'pypdf' is not importable here; rerun with the documents interpreter $PY from the pdf skill's Prerequisites setup block", file=sys.stderr)
  24. return 2
  25. writer = PdfWriter()
  26. total = 0
  27. for path in args.inputs:
  28. reader = PdfReader(path)
  29. if reader.is_encrypted:
  30. print(f"Error: {path} is encrypted; decrypt it first with pdf_secure.py --decrypt", file=sys.stderr)
  31. return 3
  32. start = total
  33. for page in reader.pages:
  34. writer.add_page(page)
  35. total += 1
  36. if args.bookmarks:
  37. writer.add_outline_item(os.path.splitext(os.path.basename(path))[0], start)
  38. with open(args.output, "wb") as fh:
  39. writer.write(fh)
  40. print(json.dumps({"output": args.output, "inputs": len(args.inputs), "page_count": total}))
  41. return 0
  42. if __name__ == "__main__":
  43. sys.exit(main())