apache pdfbox
转 http://www.blogjava.net/sxyx2008/archive/2010/07/23/326890.html轻松使用apache pdfbox将pdf文件生成图
近期在项目中使用到了大量的报表开发，需要将html页面中的表格内容导出到pdf word excel和图片，前三者都比较好实现。唯独后者生成图片使用ImageIo操作时生成的图片有点惨不忍睹。经过大量google后发现，pdfbox这个组件不错，可以将pdf文件轻松生成图片。这不问题解决了，但在使用过程中不然，受到了很多致命性的打击。pdfbox在处理中文pdf的时候就会表现的比较脆弱点。但对英文版的pdf导出图片，那是杠杠的。尽管这样，还是记录一下，毕竟这方面的资料很少。我几乎搜遍了整个google，baidu才搜集到那么一点点资料。这里跟大家分享下。 所依赖的JAR： commons-logging-1.1.1.jar fontbox-1.2.1.jar pdfbox-1.2.1.jar 示例代码：
/**//** Licensed to the Apache Software Foundation (ASF) under one or more* contributor license agreements.See the NOTICE file distributed with* this work for additional information regarding copyright ownership.* The ASF licenses this file to You under the Apache License, Version 2.0* (the "License"); you may not use this file except in compliance with* the License.You may obtain a copy of the License at** http://www.apache.org/licenses/LICENSE-2.0** Unless required by applicable law or agreed to in writing, software* distributed under the License is distributed on an "AS IS" BASIS,* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.* See the License for the specific language governing permissions and* limitations under the License.*/ package com.future.pdfbox.image;import java.awt.image.BufferedImage; import java.io.File; import java.io.FileOutputStream; import java.io.IOException; import java.util.Iterator; import java.util.List;import javax.imageio.IIOImage; import javax.imageio.ImageIO; import javax.imageio.ImageWriter; import javax.imageio.stream.ImageOutputStream;import org.apache.pdfbox.pdmodel.PDDocument; import org.apache.pdfbox.pdmodel.PDPage;public class ExtractImages{ public static void main(String[] args) throws IOException { PDDocument doc = PDDocument.load("F:\\1.pdf"); int pageCount = doc.getPageCount(); System.out.println(pageCount); List pages = doc.getDocumentCatalog().getAllPages(); for(int i=0;iConfig Build Path->Add Jars”命令，把工程lib目录下面的包都加入工程的Build Path。
4、使用PDFBox解析PDF内容
在刚刚创建的Eclipse工程中，创建一个ch7.pdfbox包，并创建一个PdfboxTest类。该类包含一个getText方法，用于从一个PDF中获取文本信息，其代码如下。
import java.io.BufferedWriter; import java.io.FileInputStream; import java.io.FileWriter;
import org.pdfbox.pdfparser.PDFParser; import org.pdfbox.util.PDFTextStripper;
public class PdfParser {
/** * @param args */ // TODO 自动生成方法存根
public static void main(String[] args) throws Exception{ FileInputStream fis = new FileInputStream("F:\\task\\lerman-atem2001.pdf"); BufferedWriter writer = new BufferedWriter(new FileWriter("F:\\task\\pdf_change.txt")); PDFParser p = new PDFParser(fis); p.parse(); PDFTextStripper ts = new PDFTextStripper(); String s = ts.getText(p.getPDDocument()); writer.write(s); System.out.println(s); fis.close(); writer.close(); } }
下面是自己按照书上的例子写的代码。
1package TestPDF.pdfbox; 2 3import java.io.File; 4import java.io.FileOutputStream; 5import java.io.IOException; 6import java.io.OutputStreamWriter; 7import java.io.Writer; 8import java.net.URL; 910import org.apache.lucene.analysis.standard.StandardAnalyzer;11import org.apache.lucene.document.Document;12import org.apache.lucene.index.IndexWriter;13import org.apache.lucene.index.Term;14import org.apache.lucene.search.IndexSearcher;15import org.apache.lucene.search.PhraseQuery;16import org.apache.lucene.search.Query;17import org.apache.lucene.search.ScoreDoc;18import org.apache.lucene.search.TermQuery;19import org.apache.lucene.search.TopDocCollector;20import org.apache.lucene.search.TopDocs;21import org.pdfbox.pdmodel.PDDocument;22import org.pdfbox.searchengine.lucene.LucenePDFDocument;23import org.pdfbox.util.PDFTextStripper;2425public class Test {2627 public void getText(String file) throws Exception{28 //是否排序29 boolean sort = false;30 //pdf文件名31 String pdfFile = file;32 //输入文本文件名称33 String textFile = null;34 //编码方式35 String encoding = "UTF-8";36 //开始提取页数37 int startPage = 1;38 //结束提取页数39 int endPage = Integer.MAX_VALUE;40 //文件输入流，输入文本文件41 Writer output = null; 42 //内存中存储的PDF Document43 PDDocument document = null;44 45 try{46 try{47 //首先当作一个URL来加载文件，如果得到异常再从本地系统装载文件48 URL url = new URL(pdfFile);49 document = PDDocument.load(url);50 String fileName = url.getFile();51 52 if(fileName.length() > 4){53 //以原来pdf名称来命名新产生的txt文件54 File outputFile = new File(fileName.substring(0, fileName.length()-4) + ".txt");55 textFile = outputFile.getName();56 } 57 }catch(Exception e){58 //如果作为URL装载得到异常则从文件系统装载59 document = PDDocument.load(pdfFile);60 if(pdfFile.length() > 4){61 textFile = pdfFile.substring(0, pdfFile.length() - 4) + ".txt";62 }63 }64 //文件输出流，写入文件到textFile65 output = new OutputStreamWriter(new FileOutputStream(textFile),encoding);66 //PDFTextStripper来提取文本67 PDFTextStripper stripper = new PDFTextStripper();68 //设置是否排序69 stripper.setSortByPosition(sort);70 //设置起始页71 stripper.setStartPage(startPage);72 //设置结束页73 stripper.setEndPage(endPage);74 //调用PDFTextStripper的writeText提取并输出文本75 stripper.writeText(document, output);76 }finally{77 if(output != null){78 output.close(); 79 }80 if(document != null){81 document.close();82 }83 } 84 }85 86 /** *//**87 * test Lucene with pdfbox88 * @throws IOException89 */90 public void LuceneTest() throws IOException{91 92 String path = "D:\\index";93 String pdfpath = "D:\\index\\Lucene.Net基本用法.pdf";94 95 IndexWriter writer = new IndexWriter(path, new StandardAnalyzer(),true);96 //writer.setMaxFieldLength(10240);97 //LucenePDFDocument返回由PDF产生的Lucene Document98 Document d = LucenePDFDocument.getDocument(new File(pdfpath));99 //System.out.println(d); 100 //写入索引 101 writer.addDocument(d); 102 writer.close(); 103 104 //读取d:\index下的索引文件，建立IndexSearcher 105 IndexSearcher searcher = new IndexSearcher(path); 106 //对索引的contents Field进行关键字Query的查找 107 Term t = new Term("contents","优"); 108 Term m = new Term("contents","化"); 109 PhraseQuery q = new PhraseQuery(); 110 q.add(t); 111 q.add(m); 112 //Query q = new TermQuery(t); 113 TopDocCollector co = new TopDocCollector(10); 114 searcher.search(q,co); 115 116 Document document; 117 TopDocs docs = co.topDocs(); 118 ScoreDoc[] doc = docs.scoreDocs; 119 //System.out.println(doc.length); 120 121 for(int i=0;i
页:
[1]