Mastering Art Merging Combine P D F Technical And Creative Guide

Automation and Scripting for PDF Combination

Script Templates for Batch PDF Merging

Python (PyMuPDF - fitz)

import fitz # PyMuPDF
import os
from pathlib import Path

def merge_pdfs(input_dir: str, output_path: str) -> bool:
"""Merge all PDFs in a directory, skipping corrupt files."""
doc = fitz.open()
valid_files = 0

for pdf_path in Path(input_dir).glob("*.pdf"):
try:
temp_doc = fitz.open(pdf_path)
if temp_doc.page_count > 0:
doc.insert_pdf(temp_doc)
valid_files += 1
temp_doc.close()
except Exception as e:
print(f"Skipping {pdf_path.name}: {str(e)}")

if valid_files == 0:
raise ValueError("No valid PDFs found in directory.")
doc.save(output_path)
doc.close()
return True

# Example usage
merge_pdfs("/path/to/pdfs", "merged_output.pdf")

Key Features:

JavaScript (Node.js - pdf-merge)

const { PDFDocument } = require('pdf-lib');
const fs = require('fs');
const path = require('path');

async function mergePDFs(inputDir, outputPath) {
const pdfs = fs.readdirSync(inputDir).filter(f => f.endsWith('.pdf'));
if (pdfs.length === 0) throw new Error('No PDFs found.');

let pdfDoc = await PDFDocument.create();
let validPages = 0;

for (const pdf of pdfs) {
try {
const filePath = path.join(inputDir, pdf);
const existingPdf = await PDFDocument.load(fs.readFileSync(filePath));
const pages = existingPdf.getPages();
if (pages.length > 0) {
for (const page of pages) pdfDoc.copyPages(existingPdf, [page]);
validPages += pages.length;
}
} catch (err) {
console.error(`Skipping ${pdf}: ${err.message}`);
}
}

if (validPages === 0) throw new Error('No valid pages merged.');
const mergedBytes = await pdfDoc.save();
fs.writeFileSync(outputPath, mergedBytes);
}

mergePDFs('./pdfs', 'merged.pdf').catch(console.error);

Key Features:

Bash (Ghostscript - gs)

#!/bin/bash
input_dir="/path/to/pdfs"
output_file="merged.pdf"
temp_file=$(mktemp)

# Check for empty directory
if [ -z "$(ls -A "$input_dir")" ]; then
echo "Error: No PDFs found in $input_dir" >&2
exit 1
fi

# Merge with error handling
for pdf in "$input_dir"/*.pdf; do
if [ -f "$pdf" ]; then
gs -dNOPAUSE -dBATCH -sDEVICE=pdfwrite -sOutputFile="$temp_file" "$pdf" >/dev/null 2>&1
if [ $? -eq 0 ]; then
cat "$temp_file" > "${temp_file}.new" && mv "${temp_file}.new" "$temp_file"
else
echo "Skipping corrupt file: $pdf" >&2
fi
fi
done

# Final merge
if [ -f "$temp_file" ]; then
mv "$temp_file" "$output_file"
else
echo "Error: No valid PDFs merged." >&2
exit 1
fi

Key Features:

API Integration for PDF Merging

Adobe PDF Services (REST API - Python)

import requests
import json
from base64 import b64encode

# Authentication (OAuth2)
CREDENTIALS = {
"client_id": "YOUR_CLIENT_ID",
"client_secret": "YOUR_CLIENT_SECRET",
"access_token": None
}

def get_access_token():
auth_url = "https://api.adobe.io/auth/token"
payload = {
"grant_type": "client_credentials",
"client_id": CREDENTIALS["client_id"],
"client_secret": CREDENTIALS["client_secret"]
}
response = requests.post(auth_url, data=payload)
CREDENTIALS["access_token"] = response.json()["access_token"]
return CREDENTIALS["access_token"]

# Merge PDFs via API
def merge_with_adobe(pdf_paths, output_path):
token = get_access_token()
headers = {
"Authorization": f"Bearer {token}",
"Content-Type": "application/json"
}

# Encode PDFs as base64
files = [b64encode(open(pdf, "rb").read()).decode("utf-8") for pdf in pdf_paths]

payload = {
"files": files,
"outputFormat": "pdf"
}

response = requests.post(
"https://pdfservices.adobe.io/operation/merge",
headers=headers,
data=json.dumps(payload)
)

if response.status_code == 200:
with open(output_path, "wb") as f:
f.write(response.content)
return True
else:
raise Exception(f"API Error: {response.text}")

# Example
merge_with_adobe(["file1.pdf", "file2.pdf"], "merged_adobe.pdf")

Key Considerations:

PDFLib (C++ - Java Wrapper)

import com.pdflib.pdflib;
import java.io.*;

public class PDFLibMerger {
public static void mergePDFs(String[] inputPaths, String outputPath) throws Exception {
pdflib pdf = new pdflib();
pdf.begin_document(outputPath, "");

for (String path : inputPaths) {
try {
int pdfInput = pdf.open_pdi_file(path, "");
if (pdfInput == -1) throw new Exception("Invalid PDF: " + path);

int pageCount = pdf.pdi_get_num_pages(pdfInput);
for (int i = 1; i <= pageCount; i++) {
pdf.begin_page_ext(0, 0, 0, 0, 0, 0, " /MediaBox [0 0 612 792] /Rotate 0");
pdf.fit_pdi_page(pdfInput, i, 0, 0, "fit");
pdf.end_page_ext("");
}
pdf.close_pdi_file(pdfInput);
} catch (Exception e) {
System.err.println("Skipping " + path + ": " + e.getMessage());
}
}
pdf.end_document("");
pdf.close();
}

public static void main(String[] args) {
try {
mergePDFs(new String[]{"file1.pdf", "file2.pdf"}, "merged_pdflib.pdf");
} catch (Exception e) {
e.printStackTrace();
}
}
}

Key Considerations:

Metadata-Driven Page Reordering