PDF 拆分

复制import PyPDF2
from PyPDF2 import PdfReader, PdfWriter

# 按页拆分 PDF
input_path = "input.pdf"
reader = PdfReader(input_path)

# 将每一页保存为独立文件
for i, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    output_path = f"page_{i+1}.pdf"
    with open(output_path, "wb") as f:
        writer.write(f)
    print(f"已生成: {output_path}")

# 按张数拆分（每 3 页合并为一个文件）
reader = PdfReader(input_path)
chunk_size = 3
for start in range(0, len(reader.pages), chunk_size):
    writer = PdfWriter()
    end = min(start + chunk_size, len(reader.pages))
    for page_num in range(start, end):
        writer.add_page(reader.pages[page_num])
    output_path = f"chunk_{start//chunk_size + 1}.pdf"
    with open(output_path, "wb") as f:
        writer.write(f)
    print(f"已生成: {output_path}")

复制package main

import (
	"fmt"
	"os"
	"github.com/pdfcpu/pdfcpu/pkg/api"
	"github.com/pdfcpu/pdfcpu/pkg/pdfcpu"
)

func main() {
	// 按页拆分：每页一个独立文件
	inputFile := "input.pdf"
	outDir := "output_pages"
	os.MkdirAll(outDir, 0755)

	// 读取 PDF 页数
	ctx, err := api.ReadContextFile(inputFile, nil)
	if err != nil {
		panic(err)
	}

	for i := 1; i <= ctx.PageCount; i++ {
		// 提取单页
		selectedPages := []int{i}
		outputFile := fmt.Sprintf("%s/page_%d.pdf", outDir, i)
		err := api.ExtractPagesFile(inputFile, outputFile, selectedPages, nil)
		if err != nil {
			fmt.Printf("提取第 %d 页失败: %v\n", i, err)
			continue
		}
		fmt.Printf("已生成: %s\n", outputFile)
	}

	// 按张数拆分（每 3 页一组）
	chunkSize := 3
	for start := 1; start <= ctx.PageCount; start += chunkSize {
		end := start + chunkSize - 1
		if end > ctx.PageCount {
			end = ctx.PageCount
		}
		selectedPages := make([]int, 0)
		for p := start; p <= end; p++ {
			selectedPages = append(selectedPages, p)
		}
		outputFile := fmt.Sprintf("%s/chunk_%d.pdf", outDir, (start-1)/chunkSize+1)
		err := api.ExtractPagesFile(inputFile, outputFile, selectedPages, nil)
		if err != nil {
			fmt.Printf("提取第 %d-%d 页失败: %v\n", start, end, err)
			continue
		}
		fmt.Printf("已生成: %s\n", outputFile)
	}
}

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

async function splitPDF(inputPath) {
  const pdfBytes = fs.readFileSync(inputPath);
  const pdfDoc = await PDFDocument.load(pdfBytes);
  const pageCount = pdfDoc.getPageCount();

  // 按页拆分：每页一个独立文件
  for (let i = 0; i < pageCount; i++) {
    const newDoc = await PDFDocument.create();
    const [copiedPage] = await newDoc.copyPages(pdfDoc, [i]);
    newDoc.addPage(copiedPage);
    const outputBytes = await newDoc.save();
    fs.writeFileSync(`page_${i + 1}.pdf`, outputBytes);
    console.log(`已生成: page_${i + 1}.pdf`);
  }

  // 按张数拆分（每 3 页合并为一个文件）
  const chunkSize = 3;
  for (let start = 0; start < pageCount; start += chunkSize) {
    const newDoc = await PDFDocument.create();
    const end = Math.min(start + chunkSize, pageCount);
    const pageIndices = Array.from({ length: end - start }, (_, i) => start + i);
    const copiedPages = await newDoc.copyPages(pdfDoc, pageIndices);
    copiedPages.forEach(page => newDoc.addPage(page));
    const outputBytes = await newDoc.save();
    const chunkNum = Math.floor(start / chunkSize) + 1;
    fs.writeFileSync(`chunk_${chunkNum}.pdf`, outputBytes);
    console.log(`已生成: chunk_${chunkNum}.pdf`);
  }
}

splitPDF('input.pdf').catch(console.error);