How to extract pages from a PDF (free, no upload required)

pip install pypdf

from pypdf import PdfReader, PdfWriter
 
def extract_pages(input_path: str, output_path: str, pages_to_keep: list[int]) -> None:
    """
    Extract specific pages from a PDF into a new file.
    
    Args:
        input_path: Path to the source PDF
        output_path: Path for the output PDF
        pages_to_keep: 0-indexed list of page numbers to include
    """
    reader = PdfReader(input_path)
    writer = PdfWriter()
 
    for i in pages_to_keep:
        writer.add_page(reader.pages[i])
 
    with open(output_path, "wb") as f:
        writer.write(f)
 
# Extract pages 2, 4, 5, 6, and 9 (0-indexed)
extract_pages("report.pdf", "extract.pdf", [2, 4, 5, 6, 9])

def parse_page_range(spec: str, total_pages: int) -> list[int]:
    """
    Convert a range string like "1,3-5,8" to a 0-indexed list.
    
    Input uses 1-based page numbers (as shown in PDF viewers).
    """
    indices = []
    for part in spec.split(","):
        part = part.strip()
        if "-" in part:
            start, end = part.split("-")
            indices.extend(range(int(start) - 1, int(end)))
        else:
            indices.append(int(part) - 1)
    return [i for i in indices if 0 <= i < total_pages]
 
# Extract pages "1,3-5,9" from a 20-page PDF
extract_pages("input.pdf", "output.pdf", parse_page_range("1,3-5,9", 20))

from pypdf import PdfReader, PdfWriter
 
def extract_odd_pages(input_path: str, output_path: str) -> None:
    reader = PdfReader(input_path)
    writer = PdfWriter()
 
    for i in range(0, len(reader.pages), 2):
        writer.add_page(reader.pages[i])
 
    with open(output_path, "wb") as f:
        writer.write(f)

npm install pdf-lib

import { PDFDocument } from "pdf-lib";
import { readFileSync, writeFileSync } from "fs";
 
async function extractPages(
  inputPath: string,
  outputPath: string,
  pageIndices: number[] // 0-indexed
): Promise<void> {
  const srcBytes = readFileSync(inputPath);
  const srcDoc = await PDFDocument.load(srcBytes);
  const outDoc = await PDFDocument.create();
 
  const pages = await outDoc.copyPages(srcDoc, pageIndices);
  for (const page of pages) {
    outDoc.addPage(page);
  }
 
  const outBytes = await outDoc.save();
  writeFileSync(outputPath, outBytes);
}
 
// Extract pages 0, 2, 3, 4, and 8 (0-indexed)
await extractPages("report.pdf", "extract.pdf", [0, 2, 3, 4, 8]);

function parsePageRange(spec: string, totalPages: number): number[] {
  const indices: number[] = [];
  for (const part of spec.split(",")) {
    const trimmed = part.trim();
    if (trimmed.includes("-")) {
      const [start, end] = trimmed.split("-").map(Number);
      for (let i = start - 1; i < end; i++) {
        if (i >= 0 && i < totalPages) indices.push(i);
      }
    } else {
      const i = Number(trimmed) - 1;
      if (i >= 0 && i < totalPages) indices.push(i);
    }
  }
  return indices;
}
 
// Extract "1,3-5,9" from a document
const doc = await PDFDocument.load(readFileSync("input.pdf"));
const indices = parsePageRange("1,3-5,9", doc.getPageCount());
await extractPages("input.pdf", "output.pdf", indices);

import express from "express";
import { PDFDocument } from "pdf-lib";
import multer from "multer";
 
const upload = multer({ storage: multer.memoryStorage() });
const app = express();
 
app.post("/extract-pages", upload.single("pdf"), async (req, res) => {
  const pagesSpec = req.body.pages as string; // e.g. "1,3-5,8"
 
  const srcDoc = await PDFDocument.load(req.file!.buffer);
  const total = srcDoc.getPageCount();
  const indices = parsePageRange(pagesSpec, total);
 
  const outDoc = await PDFDocument.create();
  const copied = await outDoc.copyPages(srcDoc, indices);
  for (const page of copied) outDoc.addPage(page);
 
  const outBytes = await outDoc.save();
  res.setHeader("Content-Type", "application/pdf");
  res.send(Buffer.from(outBytes));
});

# Extract pages 3, 5, and 7-10 into a new file
pdftk input.pdf cat 3 5 7-10 output extract.pdf
 
# Extract pages 1-4 and 8-end
pdftk input.pdf cat 1-4 8-end output extract.pdf

# Extract pages 3, 5, and 7-10
qpdf input.pdf --pages input.pdf 3,5,7-10 -- extract.pdf
 
# Extract the first 5 pages
qpdf input.pdf --pages input.pdf 1-5 -- extract.pdf

import os
from pathlib import Path
from pypdf import PdfReader, PdfWriter
 
def batch_extract(
    input_dir: str,
    output_dir: str,
    pages_to_keep: list[int]
) -> dict[str, str]:
    """
    Extract the same page subset from all PDFs in a directory.
    Returns a dict mapping filename to 'ok' or an error message.
    """
    results = {}
    Path(output_dir).mkdir(parents=True, exist_ok=True)
    pages_set = set(pages_to_keep)
 
    for pdf_path in Path(input_dir).glob("*.pdf"):
        try:
            reader = PdfReader(str(pdf_path))
            writer = PdfWriter()
            for i in sorted(pages_set):
                if i < len(reader.pages):
                    writer.add_page(reader.pages[i])
            out = Path(output_dir) / pdf_path.name
            with open(out, "wb") as f:
                writer.write(f)
            results[pdf_path.name] = "ok"
        except Exception as e:
            results[pdf_path.name] = str(e)
 
    return results
 
# Extract page 0 (cover) and page 1 (summary) from every PDF in /reports
results = batch_extract("/reports", "/reports/summaries", [0, 1])
for name, status in results.items():
    print(f"{name}: {status}")

// Generate a report that includes only the executive summary section
const response = await fetch("https://pdf4.dev/api/v1/render", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    Authorization: `Bearer ${process.env.PDF4_API_KEY}`,
  },
  body: JSON.stringify({
    template_id: "quarterly-report",
    data: {
      showExecutiveSummary: true,
      showFullData: false,
      showAppendix: false,
      quarter: "Q1 2026",
    },
  }),
});
 
const pdfBuffer = await response.arrayBuffer();