网站备案查询官网大数据精准客户

🐒个人主页：信计2102罗铠威

🏅JavaEE系列专栏

📖前言：

PDF转文本的插件常用的有：pdfbox ，itextpdf 和 spire.pdf 这几个，

🎀 1. itextpdf

1.1导入itextpdf的maven依赖

        <!--2.itexpdf依赖--><dependency><groupId>com.itextpdf</groupId><artifactId>itextpdf</artifactId><version>5.5.13.3</version></dependency>

1.2 提取文本代码

import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.parser.PdfTextExtractor;
import java.io.*;public class Main_itextPdf {public static void main(String[] args) throws Exception {System.out.println("------------------------pdf提取文本开始------------------------------");// 2. 加载PDF文件File file = new File("C:/Users/Administrator/Desktop/罗铠威个人简历.pdf");PdfReader reader = new PdfReader(file.getAbsolutePath());// 3. 解析PDF文件，获取页面数据int page = 1; // 获取第一页String text = PdfTextExtractor.getTextFromPage(reader, page);System.out.println(text);// 4. 关闭PdfReaderreader.close();System.out.println("------------------------pdf提取文本结束------------------------------");}
}

1.3 pdf转换成图片代码（本地图片地址还是线上PDF的URL地址均支持）

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.*;
import java.net.URL;
import java.net.URLConnection;
import java.util.Scanner;public class Main_itextPdf {public static void main(String[] args) throws Exception {System.out.println("------------------------pdf转图片开始------------------------------");
//        InputStream inputStream = readPdfFromUrl("http://minio.xxxx/xxxx.pdf");//线上的pdf文件InputStream inputStream = new FileInputStream("C:/Users/Administrator/Desktop/罗铠威个人简历.pdf") ;byte[] bytes = streamToByte(inputStream);InputStream newStream = new ByteArrayInputStream(bytes);//将pdf流转换成png图片流InputStream imgStream = pdfToImg(newStream);//存储图片imgStream到桌面ImageIO.write(ImageIO.read(imgStream), "png", new File("C:/Users/Administrator/Desktop/1.png"));System.out.println("------------------------pdf转图片结束------------------------------");}//支持线上pdf文件地址urlpublic static InputStream readPdfFromUrl(String pdfUrl) throws IOException {URL url = new URL(pdfUrl);URLConnection connection = url.openConnection();BufferedInputStream bufferedInputStream = new BufferedInputStream(connection.getInputStream());return bufferedInputStream;}public static ByteArrayInputStream pdfToImg(InputStream pdfStream) throws Exception {// 将 InputStream 转换为 PDDocumentPDDocument document = PDDocument.load(pdfStream);// 创建 PDFRenderer 对象PDFRenderer pdfRenderer = new PDFRenderer(document);// 选择第一页面来生成图片// 可以根据需要改成遍历所有页面并保存BufferedImage bufferedImage = pdfRenderer.renderImageWithDPI(0, 300); // 0 表示第一页，300 DPI 提供高质量图像// 将 BufferedImage 转换为 InputStreamByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();ImageIO.write(bufferedImage, "PNG", byteArrayOutputStream);document.close();// 返回一个新的 InputStreamreturn new ByteArrayInputStream(byteArrayOutputStream.toByteArray());}public static byte[] streamToByte(InputStream inputStream) throws Exception {ByteArrayOutputStream buffer = new ByteArrayOutputStream();int nRead;byte[] data = new byte[1024];while ((nRead = inputStream.read(data, 0, data.length)) != -1) {buffer.write(data, 0, nRead);}buffer.flush();return buffer.toByteArray();}}