序
pdfbox自帶的轉換html的方法效果不是太好锋喜，pdfdom是基于pdfbox的逻炊，在此之上加強了轉換html的能力梯投。
maven
<dependency>
<groupId>net.sf.cssbox</groupId>
<artifactId>pdf2dom</artifactId>
<version>1.6</version>
</dependency>
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>2.0.4</version>
</dependency>
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox-tools</artifactId>
<version>2.0.4</version>
</dependency>
使用
public void generateHTMLFromPDF(String filename) throws IOException, ParserConfigurationException {
PDDocument pdf = PDDocument.load(new File(filename));
Writer output = new PrintWriter("pdf.html", "utf-8");
new PDFDomTree().writeText(pdf, output);
output.close();
}
或者
public void convertPdf2Html(File input,Writer out) throws IOException, ParserConfigurationException {
PDDocument pdf = PDDocument.load(input);
PDFDomTree tree = new PDFDomTree();
tree.writeText(pdf,out);
}
