PDF Merger Tool
This utility combines multiple PDF files into a single document. It accepts individual file paths or directories as input and merges them in the order provided.
Modules Used:
- pypdf: To handle PDF reading and writing operations.
- argparse: To handle command-line arguments for input files and output destination.
- pathlib: For robust file path handling and directory iteration.
Installation
pip install pypdfThe Code
Save this as merge_pdfs.py.
import argparse
from pathlib import Path
from pypdf import PdfWriter
import sys
def merge_pdfs(inputs, output):
merger = PdfWriter()
count = 0
print(f"Starting merge process...")
for input_path in inputs:
path = Path(input_path)
files_to_add = []
# Handle directories (add all PDFs inside)
if path.is_dir():
# Sort to ensure consistent order
files_to_add = sorted(path.glob("*.pdf"))
# Handle individual files
elif path.is_file() and path.suffix.lower() == ".pdf":
files_to_add = [path]
else:
print(f"Warning: Skipping '{input_path}' (not a PDF or directory)")
continue
# Append files to the merger
for pdf in files_to_add:
try:
print(f" + Adding: {pdf.name}")
merger.append(pdf)
count += 1
except Exception as e:
print(f" ! Error adding {pdf.name}: {e}")
if count == 0:
print("No valid PDF files found to merge.")
return
# Write the final file
try:
merger.write(output)
merger.close()
print(f"\nSuccess! Merged {count} files into '{output}'")
except Exception as e:
print(f"Error writing output file: {e}")
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="PDF Merger Utility")
parser.add_argument("inputs", nargs="+", help="Input PDF files or directories")
parser.add_argument("-o", "--output", default="merged_output.pdf", help="Output filename (default: merged_output.pdf)")
args = parser.parse_args()
merge_pdfs(args.inputs, args.output)Usage
# Merge specific files
python merge_pdfs.py cover.pdf chapter1.pdf chapter2.pdf -o book.pdf
# Merge all PDFs in a directory
python merge_pdfs.py ./documents -o archive.pdf
# Mix files and directories
python merge_pdfs.py intro.pdf ./chapters appendix.pdf