PDF 提取图片

复制import fitz  # PyMuPDF

# 打开 PDF，提取所有嵌入图片
pdf_path = "input.pdf"
doc = fitz.open(pdf_path)

for page_num in range(len(doc)):
    page = doc[page_num]
    images = page.get_images(full=True)
    for img_idx, img in enumerate(images):
        xref = img[0]
        base_image = doc.extract_image(xref)
        image_bytes = base_image["image"]
        ext = base_image["ext"]  # png / jpg / jpeg / etc
        with open(f"page{page_num+1}_img{img_idx+1}.{ext}", "wb") as f:
            f.write(image_bytes)

doc.close()
print(f"提取完成，共处理 {len(doc)} 页")

复制package main

import (
	"fmt"
	"os"
	"path/filepath"

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

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

	// 遍历每一页提取嵌入图片
	for n := 0; n < doc.NumPage(); n++ {
		images, err := doc.PageImages(n)
		if err != nil {
			continue
		}
		for i, img := range images {
			ext := filepath.Ext(img.Path)
			outPath := fmt.Sprintf("page%d_img%d%s", n+1, i+1, ext)
			os.WriteFile(outPath, img.Image, 0644)
		}
	}
	fmt.Println("提取完成")
}

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

async function extractImages(pdfPath) {
  const pdfBytes = fs.readFileSync(pdfPath);
  const doc = await PDFDocument.load(pdfBytes);

  // 遍历页面提取嵌入图片（需配合 pdfjs-dist 解析实际图像流）
  const pages = doc.getPages();
  for (let i = 0; i < pages.length; i++) {
    const page = pages[i];
    const resources = page.node.Resources();
    if (!resources || !resources.XObject) continue;

    const xObjects = resources.XObject();
    const names = Object.keys(xObjects);
    for (let j = 0; j < names.length; j++) {
      const xObj = xObjects[names[j]];
      if (xObj.Subtype() === 'Image') {
        const imgBytes = xObj.getStream();
        fs.writeFileSync(`page${i+1}_img${j+1}.png`, imgBytes);
      }
    }
  }
  console.log('提取完成');
}

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