Java使用Spire.PDF实现对于pdf文档内容的提取

1.Spire.PDF地址

Java 提取或读取 PDF 文本内容

2.实现步骤

1.项目中引入maven依赖

<dependency>
   <groupId>e-iceblue</groupId>
   <artifactId>spire.pdf</artifactId>
   <version>10.3.4</version>
</dependency>
<repositories>
    <repository>
        <id>com.e-iceblue</id>
        <name>e-iceblue</name>
        <url>https://repo.e-iceblue.cn/repository/maven-public/</url>
    </repository>
</repositories>

2.对于本地文件进行提取

package com.XXX;

import com.spire.pdf.PdfDocument;
import com.spire.pdf.PdfPageBase;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;

public class PdfTestPoi {
    public static void main(String[] args) throws IOException {
        //创建PdfDocument实例
        PdfDocument doc = new PdfDocument();
        //加载PDF文件
        doc.loadFromFile("本地文件地址");
        //创建StringBuilder实例
        StringBuilder stringBuilder =  new StringBuilder();
        PdfPageBase page;
        //遍历PDF页面，获取每个页面的文本并添加到StringBuilder对象
        for (int i = 0; i < doc.getPages().getCount(); i++) {
            page = doc.getPages().get(i);
            stringBuilder.append(page.extractText(true));
        }
        System.out.println(stringBuilder);
        doc.close();
    }
}

3.对于网络Pdf资源进行提取

package com.vts;

import com.spire.pdf.PdfDocument;
import com.spire.pdf.PdfPageBase;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;

public class PdfTestPoi {
    public static void main(String[] args) throws IOException {
        //创建PdfDocument实例
        PdfDocument doc = new PdfDocument();
        //加载PDF文件
        URL url = new URL("网络资源地址");
        URLConnection urlConnection = url.openConnection();
        InputStream inputStream = urlConnection.getInputStream();
        doc.loadFromStream(inputStream);
        //创建StringBuilder实例
        StringBuilder stringBuilder =  new StringBuilder();
        PdfPageBase page;
        //遍历PDF页面，获取每个页面的文本并添加到StringBuilder对象
        for (int i = 0; i < doc.getPages().getCount(); i++) {
            page = doc.getPages().get(i);
            stringBuilder.append(page.extractText(true));
        }
        System.out.println(stringBuilder);
        doc.close();
    }
}