序
pdfbox自带的转换html的方法效果不是太好,pdfdom是基于pdfbox的,在此之上加强了转换html的能力。
maven
net.sf.cssbox
pdf2dom
1.6
org.apache.pdfbox
pdfbox
2.0.4
org.apache.pdfbox
pdfbox-tools
2.0.4
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);
}
doc