一、aspose.pdf

• 文档 https://docs.aspose.com/pdf/java/

1、按段落分段

/*** docx文本按段分段*/
public static void main(String[] args) {int i = 1;try {// 打开文件流FileInputStream file = new FileInputStream("I:\\范文.docx");// 创建 Word 文档对象XWPFDocument doc = new XWPFDocument(file);// 获取所有段落for (XWPFParagraph para : doc.getParagraphs()) {// 输出段落文本if (!para.getText().equals("")) {System.out.println(i++ + ":" + para.getText());}}// 关闭文件流file.close();} catch (IOException e) {e.printStackTrace();}
}

2、按句子分段

其他

word转pdf工具之aspose

<dependency><groupId>com.aspose</groupId><artifactId>aspose-words-crack</artifactId><version>21.1</version></dependency><dependency><groupId>com.aspose</groupId><artifactId>aspose-slides</artifactId><version>18.7</version></dependency><dependency><groupId>com.aspose</groupId><artifactId>aspose-cell</artifactId><version>18.9</version></dependency>

操作pdf其它api依赖

<dependency><groupId>com.itextpdf</groupId><artifactId>itext7-core</artifactId><version>7.1.15</version>
</dependency>

<dependency><groupId>org.apache.pdfbox</groupId><artifactId>pdfbox</artifactId><version>1.8.10</version>
</dependency>

二、PDFBOX

1、提取pdf指定页码的数据

public static void main(String[] args) throws IOException {String pdfPath = "C:\\Users\\Fushihao\\Desktop\\pdf\\test.pdf";int pageIndex = 4; // 指定要提取文本的页面号码// 加载 PDF 文件PDDocument document = PDDocument.load(new File(pdfPath));// 提取指定页面的文本PDFTextStripper stripper = new PDFTextStripper();stripper.setStartPage(pageIndex + 1);stripper.setEndPage(pageIndex + 1);String pageText = stripper.getText(document);// 输出文本到控制台System.out.println(pageText);// 关闭 PDF 文件document.close();
}

<dependency><groupId>org.apache.pdfbox</groupId><artifactId>pdfbox</artifactId><version>1.8.10</version>
</dependency>

2、获取 PDF 字数

public static int getPdfWords(File file) throws IOException {// 加载文件PDDocument document = PDDocument.load(file);PDFTextStripper stripper = new PDFTextStripper();// 获取字数String text = stripper.getText(document);// 关闭document.close();// 去除特殊符号返回字数return text.replaceAll("[\\r\\n\\t ]+", "").length();
}