java实现查找PDF关键字所在页码及其坐标
1、因为最近有这方面的需求，用过之后记录一下。
2、此功能跟PDF中Ctrl+F性质一样，如果PDF中为图片形式的不支持定位到关键字。
importcom.itextpdf.awt.geom.Rectangle2D.Float;
importcom.itextpdf.text.pdf.PdfDictionary;
importcom.itextpdf.text.pdf.PdfName;
importcom.itextpdf.text.pdf.PdfReader;
importcom.itextpdf.text.pdf.parser.*;
importjava.io.File;
importjava.io.FileInputStream;
importjava.io.IOException;
importjava.util.ArrayList;
importjava.util.List;
/**
*消失的太阳
*/
publicclassMyTest{
publicstaticvoidmain(String[]args)throwsIOException{
//1.给定文件
FilepdfFile=newFile("D://test.pdf");
//2.定义一个byte数组，长度为文件的长度
byte[]pdfData=newbyte[(int)pdfFile.length()];
//3.IO流读取文件内容到byte数组
FileInputStreaminputStream=null;
try{
inputStream=newFileInputStream(pdfFile);
inputStream.read(pdfData);
}catch(IOExceptione){
throwe;
}finally{
if(inputStream!=null){
try{
inputStream.close();
}catch(IOExceptione){
}
}
}
//4.指定关键字
Stringkeyword="消失的太阳：";
//5.调用方法，给定关键字和文件
Listpositions=findKeywordPostions(pdfData,keyword);
//6.返回值类型是List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
*@parampdfData通过IO流PDF文件转化的byte数组
*@paramkeyword关键字
*@returnList:float[0]:pageNumfloat[1]:xfloat[2]:y
*@throwsIOException
*/
publicstaticListfindKeywordPostions(byte[]pdfData,Stringkeyword)throwsIOException{
Listresult=newArrayList<>();
ListpdfPageContentPositions=getPdfContentPostionsList(pdfData);
for(PdfPageContentPositionspdfPageContentPosition:pdfPageContentPositions){
ListcharPositions=findPositions(keyword,pdfPageContentPosition);
if(charPositions==null||charPositions.size()<1){
continue;
}
result.addAll(charPositions);
}
returnresult;
}
privatestaticListgetPdfContentPostionsList(byte[]pdfData)throwsIOException{
PdfReaderreader=newPdfReader(pdfData);
Listresult=newArrayList<>();
intpages=reader.getNumberOfPages();
for(intpageNum=1;pageNum<=pages;pageNum++){
floatwidth=reader.getPageSize(pageNum).getWidth();
floatheight=reader.getPageSize(pageNum).getHeight();
PdfRenderListenerpdfRenderListener=newPdfRenderListener(pageNum,width,height);
//解析pdf，定位位置
PdfContentStreamProcessorprocessor=newPdfContentStreamProcessor(pdfRenderListener);
PdfDictionarypageDic=reader.getPageN(pageNum);
PdfDictionaryresourcesDic=pageDic.getAsDict(PdfName.RESOURCES);
try{
processor.processContent(ContentByteUtils.getContentBytesForPage(reader,pageNum),resourcesDic);
}catch(IOExceptione){
reader.close();
throwe;
}
Stringcontent=pdfRenderListener.getContent();
ListcharPositions=pdfRenderListener.getcharPositions();
ListpositionsList=newArrayList<>();
for(CharPositioncharPosition:charPositions){
float[]positions=newfloat[]{charPosition.getPageNum(),charPosition.getX(),charPosition.getY()};
positionsList.add(positions);
}
PdfPageContentPositionspdfPageContentPositions=newPdfPageContentPositions();
pdfPageContentPositions.setContent(content);
pdfPageContentPositions.setPostions(positionsList);
result.add(pdfPageContentPositions);
}
reader.close();
returnresult;
}
privatestaticListfindPositions(Stringkeyword,PdfPageContentPositionspdfPageContentPositions){
Listresult=newArrayList<>();
Stringcontent=pdfPageContentPositions.getContent();
ListcharPositions=pdfPageContentPositions.getPositions();
for(intpos=0;pospositions;
publicStringgetContent(){
returncontent;
}
publicvoidsetContent(Stringcontent){
this.content=content;
}
publicListgetPositions(){
returnpositions;
}
publicvoidsetPostions(Listpositions){
this.positions=positions;
}
}
privatestaticclassPdfRenderListenerimplementsRenderListener{
privateintpageNum;
privatefloatpageWidth;
privatefloatpageHeight;
privateStringBuildercontentBuilder=newStringBuilder();
privateListcharPositions=newArrayList<>();
publicPdfRenderListener(intpageNum,floatpageWidth,floatpageHeight){
this.pageNum=pageNum;
this.pageWidth=pageWidth;
this.pageHeight=pageHeight;
}
publicvoidbeginTextBlock(){
}
publicvoidrenderText(TextRenderInforenderInfo){
ListcharacterRenderInfos=renderInfo.getCharacterRenderInfos();
for(TextRenderInfotextRenderInfo:characterRenderInfos){
Stringword=textRenderInfo.getText();
if(word.length()>1){
word=word.substring(word.length()-1,word.length());
}
Floatrectangle=textRenderInfo.getAscentLine().getBoundingRectange();
floatx=(float)rectangle.getX();
floaty=(float)rectangle.getY();
//floatx=(float)rectangle.getCenterX();
//floaty=(float)rectangle.getCenterY();
//doublex=rectangle.getMinX();
//doubley=rectangle.getMaxY();
//这两个是关键字在所在页面的XY轴的百分比
floatxPercent=Math.round(x/pageWidth*10000)/10000f;
floatyPercent=Math.round((1-y/pageHeight)*10000)/10000f;
//CharPositioncharPosition=newCharPosition(pageNum,xPercent,yPercent);
CharPositioncharPosition=newCharPosition(pageNum,(float)x,(float)y);
charPositions.add(charPosition);
contentBuilder.append(word);
}
}
publicvoidendTextBlock(){
}
publicvoidrenderImage(ImageRenderInforenderInfo){
}
publicStringgetContent(){
returncontentBuilder.toString();
}
publicListgetcharPositions(){
returncharPositions;
}
}
privatestaticclassCharPosition{
privateintpageNum=0;
privatefloatx=0;
privatefloaty=0;
publicCharPosition(intpageNum,floatx,floaty){
this.pageNum=pageNum;
this.x=x;
this.y=y;
}
publicintgetPageNum(){
returnpageNum;
}
publicfloatgetX(){
returnx;
}
publicfloatgetY(){
returny;
}
@Override
publicStringtoString(){
return"[pageNum="+this.pageNum+",x="+this.x+",y="+this.y+"]";
}
}
}
总结
以上所述是小编给大家介绍的java实现查找PDF关键字所在页码及其坐标,希望对大家有所帮助，如果大家有任何疑问请给我留言，小编会及时回复大家的。在此也非常感谢大家对毛票票网站的支持！
如果你觉得本文对你有帮助，欢迎转载，烦请注明出处，谢谢！