java获取pdf文字坐标_Java 获取PDF关键字坐标

一、使用 itextpdf  推荐使用

com.itextpdf

itextpdf

5.5.13.1

PdfKeyWordPosition.java

package com.util;

import com.itextpdf.awt.geom.Rectangle2D;

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 org.slf4j.Logger;

import org.slf4j.LoggerFactory;

import java.io.ByteArrayOutputStream;

import java.io.FileInputStream;

import java.io.IOException;

import java.io.InputStream;

import java.util.ArrayList;

import java.util.HashMap;

import java.util.List;

import java.util.Map;

/**

* 获取pdf关键字坐标

*/

public class PdfKeyWordPosition {

private static final Logger log = LoggerFactory.getLogger(PdfKeyWordPosition.class);

/**

* 获取关键字坐标

* @param pdfData

* @param keyWord

* @return

*/

public static List> getWordsPcoordinate(byte[] pdfData, String keyWord){

List> result = new ArrayList<>();

PdfReader reader = null;

try {

// pdfData ：可以是二进制，也可以是文件路径，两种方式选择一种

reader = new PdfReader(pdfData);

//获取pdf页数

int pages = reader.getNumberOfPages();

for (int pageNum = 1; pageNum <= pages; pageNum++) {

//每页的宽度

Float width = reader.getPageSize(pageNum).getWidth();

//每页的高度

Float height = reader.getPageSize(pageNum).getHeight();

RenderListenerHelper renderListenerHelper = new RenderListenerHelper(pageNum, width, height);

//解析pdf，定位位置

PdfContentStreamProcessor processor = new PdfContentStreamProcessor(renderListenerHelper);

PdfDictionary pageDic = reader.getPageN(pageNum);

PdfDictionary resourcesDic = pageDic.getAsDict(PdfName.RESOURCES);

processor.processContent(ContentByteUtils.getContentBytesForPage(reader, pageNum), resourcesDic);

//文本内容

String content = renderListenerHelper.getContent();

//文本每个字对应的坐标

List> charPositions = renderListenerHelper.getCharPositions();

for (int i = 0; i < content.length(); i++){

//获取关键字所在位置

int keyIndex = content.indexOf(keyWord, i);

if (keyIndex == -1){

break;

}

result.add(charPositions.get(keyIndex));

i = key