PDF 转图片

复制import fitz  # PyMuPDF
import os

# 将 PDF 每页转为 PNG 图片
pdf_path = "input.pdf"
output_dir = "output_pages"
os.makedirs(output_dir, exist_ok=True)

doc = fitz.open(pdf_path)
for page_num in range(len(doc)):
    page = doc.load_page(page_num)
    # 渲染为 300 DPI 的 PNG
    pix = page.get_pixmap(dpi=300)
    pix.save(f"{output_dir}/page_{page_num + 1:03d}.png")

doc.close()
print(f"共 {len(doc)} 页，已保存至 {output_dir}/")

复制package main

import (
	"fmt"
	"image/png"
	"os"

	"github.com/gen2brain/go-fitz"
)

func main() {
	doc, err := fitz.New("input.pdf")
	if err != nil {
		panic(err)
	}
	defer doc.Close()

	os.MkdirAll("output_pages", 0755)

	for i := 0; i < doc.NumPage(); i++ {
		img, err := doc.Image(i)
		if err != nil {
			panic(err)
		}
		f, _ := os.Create(fmt.Sprintf("output_pages/page_%03d.png", i+1))
		png.Encode(f, img)
		f.Close()
	}
	fmt.Printf("共 %d 页，已转换完成\n", doc.NumPage())
}

复制const fs = require('fs');
const { PDFDocument } = require('pdf-lib');
const { createCanvas, loadImage } = require('canvas');

async function pdfToImages(pdfPath, outputDir) {
  const pdfBytes = fs.readFileSync(pdfPath);
  const pdfDoc = await PDFDocument.load(pdfBytes);
  const pages = pdfDoc.getPages();

  fs.mkdirSync(outputDir, { recursive: true });

  for (let i = 0; i < pages.length; i++) {
    const page = pages[i];
    const { width, height } = page.getSize();
    const canvas = createCanvas(width, height);
    const ctx = canvas.getContext('2d');

    // 将 PDF 页面渲染到 canvas（需配合 pdfjs-dist 等渲染引擎）
    // 此处为简化示例，实际需使用 pdfjs-dist 的 renderPage 方法
    ctx.fillStyle = '#ffffff';
    ctx.fillRect(0, 0, width, height);

    const buffer = canvas.toBuffer('image/png');
    fs.writeFileSync(`${outputDir}/page_${String(i + 1).padStart(3, '0')}.png`, buffer);
  }

  console.log(`共 ${pages.length} 页，已保存至 ${outputDir}/`);
}

pdfToImages('input.pdf', 'output_pages').catch(console.error);