读取PDF文件jar引用
<dependency>
<groupid>org.apache.pdfbox</groupid>
pdfbox</artifactid>
<version>1.8.13</version>
</dependency>
读取WORD文件jar引用
<dependency>
<groupid>org.apache.poi</groupid>
poi-scratchpad</artifactid>
<version>3.16-beta1</version>
</dependency>
<dependency>
<groupid>org.apache.poi</groupid>
poi</artifactid>
<version>3.16-beta1</version>
</dependency>
读取WORD文件方法
/**
*
* @Title: getTextFromWord
* @Description: 读取word
* @param filePath
* 文件路径
* @return: String 读出的Word的内容
*/
public static String getTextFromWord(String filePath) {
String result = null;
File file = new File(filePath);
FileInputStream fis = null;
try {
fis = new FileInputStream(file);
@SuppressWarnings("resource")
WordExtractor wordExtractor = new WordExtractor(fis);
result = wordExtractor.getText();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
if (fis != null) {
try {
fis.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
return result;
}
读取PDF文件方法
/**
*
* @Title: getTextFromPdf
* @Description: 读取pdf文件内容
* @param filePath
* @return: 读出的pdf的内容
*/
public static String getTextFromPdf(String filePath) {
String result = null;
FileInputStream is = null;
PDDocument document = null;
try {
is = new FileInputStream(filePath);
PDFParser parser = new PDFParser(is);
parser.parse();
document = parser.getPDDocument();
PDFTextStripper stripper = new PDFTextStripper();
result = stripper.getText(document);
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
if (is != null) {
try {
is.close();
} catch (IOException e) {
e.printStackTrace();
}
}
if (document != null) {
try {
document.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
return result;
}
希望本篇实例代码可以帮到您
亿速云「云服务器」,即开即用、新一代英特尔至强铂金CPU、三副本存储NVMe SSD云盘,价格低至29元/月。点击查看>>
免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。