补充：一下代码基于maven，现将依赖的jar包单独导出
地址：pdf jar
完整代码地址 也就两个文件
java读取pdf中的纯文字，这里使用的是pdfbox工具包
maven引入如下配置
<dependency>
<groupId>net.sf.cssbox</groupId>
<artifactId>pdf2dom</artifactId>
<version>1.7</version>
</dependency>
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>2.0.12</version>
</dependency>
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox-tools</artifactId>
<version>2.0.12</version>
</dependency>
工具类直接读取
代码示例
/*
读取pdf文字
*/
@Test
public void readPdfTextTest() throws IOException {
byte[] bytes = getBytes("D:\\code\\pdf\\HashMap.pdf");
//加载PDF文档
PDDocument document = PDDocument.load(bytes);
readText(document);
} public void readText(PDDocument document) throws IOException {
PDFTextStripper stripper = new PDFTextStripper();
String text = stripper.getText(document);
System.out.println(text);
}
将pdf转换为html
效果图
代码示例
/*
pdf转换html
*/
@Test
public void pdfToHtmlTest() {
String outputPath = "D:\\code\\pdf\\HashMap.html";
byte[] bytes = getBytes("D:\\code\\pdf\\HashMap.pdf");
// try() 写在()里面会自动关闭流
try (BufferedWriter out = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(new File(outputPath)),"UTF-8"));){
//加载PDF文档
PDDocument document = PDDocument.load(bytes);
PDFDomTree pdfDomTree = new PDFDomTree();
pdfDomTree.writeText(document,out);
} catch (Exception e) {
e.printStackTrace();
}
}
/*
将文件转换为byte数组
*/
private byte[] getBytes(String filePath){
byte[] buffer = null;
try {
File file = new File(filePath);
FileInputStream fis = new FileInputStream(file);
ByteArrayOutputStream bos = new ByteArrayOutputStream(1000);
byte[] b = new byte[1000];
int n;
while ((n = fis.read(b)) != -1) {
bos.write(b, 0, n);
}
fis.close();
bos.close();
buffer = bos.toByteArray();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return buffer;
}
完整的一个上传pdf转换为HTML功能（今后转换pdf也不需要找什么第三方了，哈哈）
@RequestMapping("ud")
@Controller
public class UpAndDownController {
@RequestMapping("upload.do")
@ResponseBody
public Map<String,Object> upload(@RequestParam("file") MultipartFile file, HttpServletRequest request){
Map<String, Object> map = new HashMap<>();
map.put("code","200");
try {
PdfConvertUtil pdfConvertUtil = new PdfConvertUtil();
String pdfName = file.getOriginalFilename();
int lastIndex = pdfName.lastIndexOf(".pdf");
String fileName = pdfName.substring(0, lastIndex);
String htmlName = fileName + ".html";
String realPath = ResourceUtils.getURL("classpath:").getPath() + "/templates/file";
File f = new File(realPath);
if(!f.exists()){
f.mkdirs();
}
String htmlPath = realPath + "\\" + htmlName;
pdfConvertUtil.pdftohtml(file.getBytes(), htmlPath);
} catch (Exception e) {
map.put("code","500");
e.printStackTrace();
}
return map;
}
}
可以使用postman调试
需要设置请求头 Content-Type 指定为 application/x-www-form-urlencoded
之后选择body选择form-data，OK
如果涉及到HTML页面直接加载PDF，无需插件
可以参考下