How to Delete Pages from a PDF — Free Online Tool and Code Guide

import { PDFDocument } from 'pdf-lib';
import fs from 'fs';
 
async function deletePdfPages(inputPath, outputPath, pagesToDelete) {
  // pagesToDelete: array of 0-based page indices
  // e.g. [0, 3, 5] deletes pages 1, 4, 6 (1-indexed)
  
  const pdfBytes = fs.readFileSync(inputPath);
  const pdfDoc = await PDFDocument.load(pdfBytes);
  
  const totalPages = pdfDoc.getPageCount();
  console.log(`Total pages: ${totalPages}`);
  
  // Sort in descending order — removing from the end
  // prevents index shifting
  const sortedIndices = [...pagesToDelete].sort((a, b) => b - a);
  
  for (const index of sortedIndices) {
    if (index >= 0 && index < totalPages) {
      pdfDoc.removePage(index);
    }
  }
  
  const newBytes = await pdfDoc.save();
  fs.writeFileSync(outputPath, newBytes);
  console.log(`Deleted ${pagesToDelete.length} pages. New total: ${pdfDoc.getPageCount()}`);
}
 
// Parse a page range string like "1-3, 5, 7-9" into 0-based indices
function parsePageRange(rangeStr, totalPages) {
  const indices = new Set();
  const parts = rangeStr.split(',').map(p => p.trim());
  
  for (const part of parts) {
    if (part.includes('-')) {
      const [start, end] = part.split('-').map(Number);
      for (let i = start; i <= end; i++) {
        if (i >= 1 && i <= totalPages) {
          indices.add(i - 1); // Convert to 0-based
        }
      }
    } else {
      const n = parseInt(part);
      if (n >= 1 && n <= totalPages) {
        indices.add(n - 1);
      }
    }
  }
  
  return [...indices];
}
 
// Usage
const pdfBytes = fs.readFileSync('input.pdf');
const pdfDoc = await PDFDocument.load(pdfBytes);
const totalPages = pdfDoc.getPageCount();
 
const pagesToDelete = parsePageRange('1, 4, 6', totalPages);
await deletePdfPages('input.pdf', 'output.pdf', pagesToDelete);

from pypdf import PdfReader, PdfWriter
from typing import Union
 
def parse_page_range(range_str: str, total_pages: int) -> list[int]:
    """Parse '1-3, 5, 7-9' into list of 0-based indices."""
    indices = set()
    for part in range_str.split(','):
        part = part.strip()
        if '-' in part:
            start, end = map(int, part.split('-'))
            for i in range(start, end + 1):
                if 1 <= i <= total_pages:
                    indices.add(i - 1)
        elif part.isdigit():
            n = int(part)
            if 1 <= n <= total_pages:
                indices.add(n - 1)
    return sorted(indices)
 
def delete_pdf_pages(
    input_path: str,
    output_path: str,
    pages_to_delete: Union[str, list[int]]
) -> dict:
    reader = PdfReader(input_path)
    total = len(reader.pages)
    
    if isinstance(pages_to_delete, str):
        delete_indices = set(parse_page_range(pages_to_delete, total))
    else:
        delete_indices = set(pages_to_delete)
    
    writer = PdfWriter()
    kept = 0
    for i, page in enumerate(reader.pages):
        if i not in delete_indices:
            writer.add_page(page)
            kept += 1
    
    with open(output_path, 'wb') as f:
        writer.write(f)
    
    return {
        'original_pages': total,
        'deleted': len(delete_indices),
        'remaining': kept,
    }
 
# Usage
result = delete_pdf_pages('input.pdf', 'output.pdf', '1, 4, 6-8')
print(f"Deleted {result['deleted']} pages. {result['remaining']} pages remain.")

# Keep pages 2, 3, 5 (i.e., delete pages 1 and 4 from a 5-page PDF)
gs -dBATCH -dNOPAUSE -dSAFER \
   -sDEVICE=pdfwrite \
   -dFirstPage=2 -dLastPage=3 \
   -sOutputFile=output.pdf \
   input.pdf
 
# For non-contiguous pages, use multiple calls and merge the results
# Or use pdftk (if installed)
pdftk input.pdf cat 2 3 5 output output.pdf
 
# pdftk range syntax
pdftk input.pdf cat 2-end output output.pdf   # delete first page
pdftk input.pdf cat 1-5 7-end output out.pdf  # delete page 6

from pypdf import PdfReader, PdfWriter
 
def delete_blank_pages(input_path, output_path, threshold=100):
    """Remove pages with very little content (likely blank)."""
    reader = PdfReader(input_path)
    writer = PdfWriter()
    
    deleted = 0
    for i, page in enumerate(reader.pages):
        # Extract text — blank pages have no extractable text
        text = page.extract_text()
        
        # Check content stream length (very short = probably blank)
        content_length = 0
        if '/Contents' in page:
            contents = page['/Contents']
            if hasattr(contents, 'get_data'):
                content_length = len(contents.get_data())
        
        if len(text.strip()) < 5 and content_length < threshold:
            deleted += 1
            print(f"Removing blank page {i + 1}")
        else:
            writer.add_page(page)
    
    with open(output_path, 'wb') as f:
        writer.write(f)
    
    print(f"Removed {deleted} blank pages")
 
delete_blank_pages('input.pdf', 'no-blanks.pdf')

def delete_even_pages(input_path, output_path):
    """Delete even-numbered pages (1-indexed) — common for duplex scans."""
    reader = PdfReader(input_path)
    writer = PdfWriter()
    
    for i, page in enumerate(reader.pages):
        if (i + 1) % 2 != 0:  # Keep odd-numbered pages
            writer.add_page(page)
    
    with open(output_path, 'wb') as f:
        writer.write(f)

// Delete cover page (index 0) and back cover (last index)
const indices = [0, pdfDoc.getPageCount() - 1];
await deletePdfPages('input.pdf', 'output.pdf', indices);