Java的bfopdf解析

开源包下载地址: http://bfo.com/products/download.jsp

例子:

import java.io.File;
import java.io.IOException;

import org.faceless.pdf2.PDF;
import org.faceless.pdf2.PDFParser;
import org.faceless.pdf2.PDFReader;
import org.faceless.pdf2.PageExtractor;

public class Test {
	public static void main(String[] args) throws IOException {
		// PDF文档路径
		String filepath = "rayln的博客文章 (1).pdf";
		// PDFReader对象建立
		PDFReader reader = new PDFReader(new File(filepath));
		// 建立PDF文档对象
		PDF pdf = new PDF(reader);
		// 建立文档解析对象
		PDFParser parser = new PDFParser(pdf);
		for (int i = 0; i < pdf.getNumberOfPages(); i++) {
			PageExtractor extractor = parser.getPageExtractor(i);
			System.out.println("=========start================");
			System.out.println(extractor.getTextInDisplayOrder().toArray()[1]);
			//System.out.println(extractor.getTextAsStringBuffer());
			System.out.println("=========end================");
		}
	}
}