Java 解析pdf内容

pom.xml

        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.4</version>
        </dependency>
        
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>fontbox</artifactId>
            <version>2.0.8</version>
        </dependency>

 

 代码

 public void pdfTest() {
        try {
            // 是否排序
            boolean sort = false;
            // 开始提取页数
            int startPage = 1;
            // 结束提取页数
            int endPage = Integer.MAX_VALUE;
            String content = null;
            PrintWriter writer = null;
            //pdf文本路径
            String path = "C:\Users\Administrator\Desktop\123.pdf";
            //输出txt文本路径
            String target="C:\Users\Administrator\Desktop\123.txt";
            PDDocument document = PDDocument.load(new File(path));
            PDFTextStripper pts = new PDFTextStripper();
            endPage = document.getNumberOfPages();
            System.out.println("Total Page: " + endPage);
            pts.setStartPage(startPage);
            pts.setEndPage(endPage);
            try {
                //content就是从pdf中解析出来的文本
                content = pts.getText(document);
                writer = new PrintWriter(new FileOutputStream(target));
                writer.write(content);// 写入文件内容
                writer.flush();
                writer.close();
            } catch (Exception e) {
                throw e;
            }finally {
                if (null != document)
                    document.close();
            }
            System.out.println("Get PDF Content ...");
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

 svn checkout http://svn.apache.org/repos/asf/pdfbox/trunk/examples

觉得辛苦就扫一扫：