使用itext查找PDF关键字具体坐标-亲测有效

该代码示例展示了如何在Java中使用iTextPDF库从PDF文档中读取内容并找到特定关键字的位置,包括页码、X轴和Y轴坐标。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

项目里需要引入的pom

 <dependency>
            <groupId>cn.hutool</groupId>
            <artifactId>hutool-all</artifactId>
            <version>5.5.1</version>
        </dependency>

    <!-- https://mvnrepository.com/artifact/com.itextpdf/itextpdf -->
   	<dependency>
   		<groupId>com.itextpdf</groupId>
   		<artifactId>itextpdf</artifactId>
   		<version>5.5.13.2</version>
   	</dependency>

<!-- https://mvnrepository.com/artifact/com.itextpdf/itext-asian -->
<dependency>
	<groupId>com.itextpdf</groupId>
	<artifactId>itext-asian</artifactId>
	<version>5.2.0</version>
</dependency>
package com.cn.ImageAndPdf;
import com.itextpdf.awt.geom.Rectangle2D.Float;
import com.itextpdf.text.pdf.PdfDictionary;
import com.itextpdf.text.pdf.PdfName;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.parser.*;
 
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
 
/**
 * 消失的太阳
 */
public class MyTest {
 
    public static void main(String[] args) throws IOException {
        //1.给定文件
        File pdfFile = new File("C:\\e62ef845-0edb-45bb-b57a-4f73c65e3625.pdf");
        //2.定义一个byte数组,长度为文件的长度
        byte[] pdfData = new byte[(int) pdfFile.length()];
 
        //3.IO流读取文件内容到byte数组
        FileInputStream inputStream = null;
        try {
            inputStream = new FileInputStream(pdfFile);
            inputStream.read(pdfData);
        } catch (IOException e) {
            throw e;
        } finally {
            if (inputStream != null) {
                try {
                    inputStream.close();
                } catch (IOException e) {
                }
            }
        }
 
        //4.指定关键字
        String keyword = "甲方法定代理人或代理人";
 
        //5.调用方法,给定关键字和文件
        List<float[]> positions = findKeywordPostions(pdfData, keyword);
 
        //6.返回值类型是  List<float[]> 每个list元素代表一个匹配的位置,分别为 float[0]所在页码  float[1]所在x轴 float[2]所在y轴
        System.out.println("total:" + positions.size());
        if (positions != null && positions.size() > 0) {
            for (float[] position : positions) {
                System.out.print("pageNum: " + (int) position[0]);
                System.out.print("\tx: " + position[1]);
                System.out.println("\ty: " + position[2]);
            }
        }
    }
 
    /**
     * findKeywordPostions
     * @param pdfData     通过IO流 PDF文件转化的byte数组
     * @param keyword     关键字
     * @return List<float [ ]> : float[0]:pageNum float[1]:x float[2]:y
     * @throws IOException
     */
    public static List<float[]> findKeywordPostions(byte[] pdfData, String keyword) throws IOException {
        List<float[]> result = new ArrayList<>();
        List<PdfPageContentPositions> pdfPageContentPositions = getPdfContentPostionsList(pdfData);
 
        for (PdfPageContentPositions pdfPageContentPosition : pdfPageContentPositions) {
            List<float[]> charPositions = findPositions(keyword, pdfPageContentPosition);
            if (charPositions == null || charPositions.size() < 1) {
                continue;
            }
            result.addAll(charPositions);
        }
        return result;
    }
 
    private static List<PdfPageContentPositions> getPdfContentPostionsList(byte[] pdfData) throws IOException {
        PdfReader reader = new PdfReader(pdfData);
 
        List<PdfPageContentPositions> result = new ArrayList<>();
 
        int pages = reader.getNumberOfPages();
        for (int pageNum = 1; pageNum <= pages; pageNum++) {
            float width = reader.getPageSize(pageNum).getWidth();
            float height = reader.getPageSize(pageNum).getHeight();
 
            PdfRenderListener pdfRenderListener = new PdfRenderListener(pageNum, width, height);
 
            //解析pdf,定位位置
            PdfContentStreamProcessor processor = new PdfContentStreamProcessor(pdfRenderListener);
            PdfDictionary pageDic = reader.getPageN(pageNum);
            PdfDictionary resourcesDic = pageDic.getAsDict(PdfName.RESOURCES);
            try {
                processor.processContent(ContentByteUtils.getContentBytesForPage(reader, pageNum), resourcesDic);
            } catch (IOException e) {
                reader.close();
                throw e;
            }
 
            String content = pdfRenderListener.getContent();
            List<CharPosition> charPositions = pdfRenderListener.getcharPositions();
 
            List<float[]> positionsList = new ArrayList<>();
            for (CharPosition charPosition : charPositions) {
                float[] positions = new float[]{charPosition.getPageNum(), charPosition.getX(), charPosition.getY()};
                positionsList.add(positions);
            }
 
            PdfPageContentPositions pdfPageContentPositions = new PdfPageContentPositions();
            pdfPageContentPositions.setContent(content);
            pdfPageContentPositions.setPostions(positionsList);
 
            result.add(pdfPageContentPositions);
        }
        reader.close();
        return result;
    }
 
    private static List<float[]> findPositions(String keyword, PdfPageContentPositions pdfPageContentPositions) {
 
        List<float[]> result = new ArrayList<>();
 
        String content = pdfPageContentPositions.getContent();
        List<float[]> charPositions = pdfPageContentPositions.getPositions();
 
        for (int pos = 0; pos < content.length(); ) {
            int positionIndex = content.indexOf(keyword, pos);
            if (positionIndex == -1) {
                break;
            }
            float[] postions = charPositions.get(positionIndex);
            result.add(postions);
            pos = positionIndex + 1;
        }
        return result;
    }
 
    private static class PdfPageContentPositions {
        private String content;
        private List<float[]> positions;
 
        public String getContent() {
            return content;
        }
 
        public void setContent(String content) {
            this.content = content;
        }
 
        public List<float[]> getPositions() {
            return positions;
        }
 
        public void setPostions(List<float[]> positions) {
            this.positions = positions;
        }
    }
 
    private static class PdfRenderListener implements RenderListener {
        private int pageNum;
        private float pageWidth;
        private float pageHeight;
        private StringBuilder contentBuilder = new StringBuilder();
        private List<CharPosition> charPositions = new ArrayList<>();
 
        public PdfRenderListener(int pageNum, float pageWidth, float pageHeight) {
            this.pageNum = pageNum;
            this.pageWidth = pageWidth;
            this.pageHeight = pageHeight;
        }
 
        public void beginTextBlock() {
        }
 
        public void renderText(TextRenderInfo renderInfo) {
            List<TextRenderInfo> characterRenderInfos = renderInfo.getCharacterRenderInfos();
            for (TextRenderInfo textRenderInfo : characterRenderInfos) {
                String word = textRenderInfo.getText();
                if (word.length() > 1) {
                    word = word.substring(word.length() - 1, word.length());
                }
                Float rectangle = textRenderInfo.getAscentLine().getBoundingRectange();
 
                float x = (float)rectangle.getX();
                float y = (float)rectangle.getY();
//                float x = (float)rectangle.getCenterX();
//                float y = (float)rectangle.getCenterY();
//                double x = rectangle.getMinX();
//                double y = rectangle.getMaxY();
 
                //这两个是关键字在所在页面的XY轴的百分比
                float xPercent = Math.round(x / pageWidth * 10000) / 10000f;
                float yPercent = Math.round((1 - y / pageHeight) * 10000) / 10000f;
 
//                CharPosition charPosition = new CharPosition(pageNum, xPercent, yPercent);
                CharPosition charPosition = new CharPosition(pageNum, (float)x, (float)y);
                charPositions.add(charPosition);
                contentBuilder.append(word);
            }
        }
 
        public void endTextBlock() {
        }
 
        public void renderImage(ImageRenderInfo renderInfo) {
        }
 
        public String getContent() {
            return contentBuilder.toString();
        }
 
        public List<CharPosition> getcharPositions() {
            return charPositions;
        }
    }
 
    private static class CharPosition {
        private int pageNum = 0;
        private float x = 0;
        private float y = 0;
 
        public CharPosition(int pageNum, float x, float y) {
            this.pageNum = pageNum;
            this.x = x;
            this.y = y;
        }
 
        public int getPageNum() {
            return pageNum;
        }
 
        public float getX() {
            return x;
        }
 
        public float getY() {
            return y;
        }
 
        @Override
        public String toString() {
            return "[pageNum=" + this.pageNum + ",x=" + this.x + ",y=" + this.y + "]";
        }
    }
}

效果截图

在这里插入图片描述

评论 6
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

夜空繁星vv

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值