java提取pdf文字坐标

提取pdf文字坐标再pdf转换成对应图片大小像素坐标

pdfbox：2.0.15提取pdf文字

package com.exampl.pdf;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.TextPosition;

import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.*;
import java.util.ArrayList;
import java.util.List;

public class PdfPage extends PDFTextStripper {

private int dip = 96; //图片dpi
private int i = 0; //行号
private int count = 0; //顺序号
private int pageinde; //页码
private boolean separator;
private Page page = new Page(); //存储结果集
private List<List<TextPosition>> TextPositionLine = new ArrayList<>();
private List<List<TextPosition>> lastTextPositionLine = new ArrayList<>();
private List<List<List<TextPosition>>> TextPosition = new ArrayList<>();

public Page getPage() {
    writeText();
    return page;
}

public void setPage(Page page) {
    this.page = page;
}

public PdfPage(int pageinde, String pdf) throws Exception {
    this.pageinde = pageinde;
    pdfIndex(pageinde, pdf);
}

void pdfIndex(int page, String path) throws Exception {
    PDDocument pdd = PDDocument.load(new File(path));
    this.setSortByPosition(true);
    this.stripPage(pdd, page);
    OutputStream byteArrayOutputStream = new FileOutputStream(new File("D:\\img\\" + page + ".jpg"));
    PDFRenderer renderer = new PDFRenderer(pdd);
    BufferedImage image = renderer.renderImageWithDPI(page, this.dip);
    ImageIO.write(image, "JPG", byteArrayOutputStream);
    byteArrayOutputStream.close();
    byteArrayOutputStream.flush();
}

//查找每行坐标文字
void stripPage(PDDocument pdd, int pageNr) throws IOException {
    this.setStartPage(pageNr + 1);
    this.setEndPage(pageNr + 1);
    Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
    writeText(pdd, dummy);
}

//计算每个文字坐标大小并保存到words和rows
@Override
protected void writeString(String string, List<TextPosition> textPositions) {
    if (separator) { //separator判断是否换行
        TextPosition.add(TextPositionLine);
        TextPositionLine = new ArrayList<>();
    }
    separator = true;
    TextPositionLine.add(textPositions);
    lastTextPositionLine = TextPositionLine;
}

@Override
protected void writeWordSeparator() {
    separator = false; //如果换行会调用writeWordSeparator方法设置separator变量
}

void writeText() {
    TextPosition.add(lastTextPositionLine);//最后一行文字添加进去
    for (List<List<TextPosition>> lists : TextPosition) {
        List<PdfJson> row = new ArrayList<>();
        for (List<TextPosition> line : lists) {
            for (TextPosition text : line) {
                PdfJson pdfJson = new PdfJson();
                //乘以dip除以72转换成图片坐标位置
                pdfJson.setX1(text.getX() * this.dip / 72); //左x坐标
                pdfJson.setX2(text.getEndX() * this.dip / 72); //右x坐标
                pdfJson.setY1(text.getY() * this.dip / 72); //下y坐标
                pdfJson.setY2((text.getY() * this.dip / 72) - text.getFontSize() - 5); //上y坐标 由于拿出来文字高端矮了一点 减5提高文字高度
                pdfJson.setText(text.getUnicode());
                pdfJson.setRowIndex(i); //设置行号
                pdfJson.setWordIndex(line.indexOf(text)); //设置每行当前文字在第几位
                pdfJson.setIndex(this.count); //当前文字在所有文字中排第几位
                pdfJson.setPageIndex(this.pageinde); //设置pdf页码
                page.getWords().add(pdfJson);
                row.add(pdfJson);
                this.count++;
            }
        }
        page.getRows().add(row);
        this.i++;
    }
}

}

重写writeLine方法里面writeString和writeWordSeparator方法大家可以研究下逻辑

贴上前端展示效果由于pdf涉密处理掉了部分