word、pdf文档内容提取工具类

word、pdf文档内容提取工具类

1.依赖

<dependency><groupId>org.apache.poi</groupId><artifactId>poi</artifactId><version>5.2.5</version>
</dependency>
<dependency><groupId>org.apache.poi</groupId><artifactId>poi-scratchpad</artifactId><version>5.2.5</version>
</dependency>
<dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml</artifactId><version>5.2.5</version> <!-- 如果有 DOCX 相关 -->
</dependency>
<dependency><groupId>org.apache.pdfbox</groupId><artifactId>pdfbox</artifactId><version>3.0.5</version>
</dependency>

2.代码

import cn.hutool.core.util.StrUtil;
import org.apache.pdfbox.Loader;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.nio.charset.StandardCharsets;
import java.util.List;
import java.util.Locale;
/**
* @Description 文档提取工具类
* @Date 2025/9/29 17:32
*/public class DocumentTextExtractUtil {public static String extractText(InputStream inputStream, String fileType) throws IOException {if (inputStream == null) return "";if (StrUtil.isBlank(fileType)) throw new IllegalArgumentException("文件类型不能为空");String ft = normalizeFileType(fileType);byte[] data = toByteArray(inputStream);return switch (ft) {case "pdf" -> extractPdfText(data);case "docx" -> extractDocxText(data);case "doc" -> extractDocText(data);default -> new String(data, StandardCharsets.UTF_8);};}private static String normalizeFileType(String fileType) {String ft = fileType.trim().toLowerCase(Locale.ROOT);if (ft.startsWith(".")) ft = ft.substring(1);if (ft.contains("/")) {ft = ft.substring(ft.indexOf('/') + 1);if (ft.contains("+")) ft = ft.substring(0, ft.indexOf('+'));}return ft;}private static String extractPdfText(byte[] data) throws IOException {try (PDDocument doc = Loader.loadPDF(data)) { // 3.x 用 Loader.loadPDFPDFTextStripper stripper = new PDFTextStripper();stripper.setSortByPosition(true);String text = stripper.getText(doc);return text == null ? "" : text.trim();}}private static String extractDocxText(byte[] data) throws IOException {try (XWPFDocument doc = new XWPFDocument(new ByteArrayInputStream(data))) {StringBuilder sb = new StringBuilder();List<XWPFParagraph> paragraphs = doc.getParagraphs();for (XWPFParagraph p : paragraphs) {String t = p.getText();if (t != null && !t.isEmpty()) {sb.append(t).append('\n');}}return sb.toString().trim();}}private static String extractDocText(byte[] data) throws IOException {try (HWPFDocument doc = new HWPFDocument(new ByteArrayInputStream(data))) {WordExtractor extractor = new WordExtractor(doc);String[] paragraphs = extractor.getParagraphText();StringBuilder sb = new StringBuilder();if (paragraphs != null) {for (String p : paragraphs) {if (p == null) continue;String clean = p.replaceAll("\\u0000", "").trim();if (!clean.isEmpty()) sb.append(clean).append('\n');}}return sb.toString().trim();}}private static byte[] toByteArray(InputStream in) throws IOException {ByteArrayOutputStream baos = new ByteArrayOutputStream(8192);byte[] buf = new byte[8192];int r;while ((r = in.read(buf)) != -1) {baos.write(buf, 0, r);}return baos.toByteArray();}
}

3.如何使用

try (InputStream textStream = new ByteArrayInputStream(content)) {String text = DocumentTextExtractUtil.extractText(textStream, fileType.toLowerCase());} catch (Exception e) {log.warn("文本提取失败，文件: {}，类型: {}", fileName, fileType, e);}