pdf与word查找关键并生成关键字高亮的新文件

需要依赖

<dependency>
	<groupId>org.apache.pdfbox</groupId>
	<artifactId>pdfbox</artifactId>
	<version>2.0.6</version>
</dependency>
<dependency>
	<groupId>e-iceblue</groupId>
	<artifactId>free.spire.doc</artifactId>
	<version>2.7.3</version>
</dependency>
<!-- PDF识别  -->
<dependency>
    <groupId>e-iceblue</groupId>
    <artifactId>spire.pdf.free</artifactId>
    <version>2.2.2</version>
</dependency>

查找关键并生成关键字高亮的新文件

package cn.com.demo.util;

import java.awt.Color;
import java.io.File;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.PDFTextStripperByArea;

import com.spire.doc.Document;
import com.spire.doc.FileFormat;
import com.spire.doc.Section;
import com.spire.doc.documents.TextSelection;
import com.spire.pdf.PdfDocument;
import com.spire.pdf.PdfPageBase;
import com.spire.pdf.general.find.PdfTextFind;

public class KeyWordFromOfficeAndSaveFile {

	/**
	 * 通过关键字查找内容-PDF
	 * @param sourceFileName
	 * @param keyWord
	 * @return
	 */
	public static String getContentByKeyWord(String sourceFileName, String keyWord) {
		int count = 0;
		boolean flag = false;
		StringBuffer buffer = new StringBuffer();
		Document doc = new Document(sourceFileName);
		for (int i = 0; i < doc.getSections().getCount(); i++) {
			if (flag) {
				break;
			}
			Section p = doc.getSections().get(i);
			for (int j = 0; j < p.getParagraphs().getCount(); j++) {
				String text = p.getParagraphs().get(j).getText();
				if (text != null && text.contains(keyWord)) {
					buffer.append(text).append("...\n");
					if (++count > 2) {
						flag = true;
						break;
					}
				}
			}
		}
		return buffer.toString();
	}

	/**
	 * 保存文件并高亮关键字-Word
	 * @param sourceFileName
	 * @param keyWord
	 * @param destFileName
	 */
	public static void saveAndHighlightWordText(String sourceFileName, String keyWord, String destFileName) {
		// 加载Word文档
		Document document = new Document(sourceFileName);

		// 查找所有“荷塘”文本
		TextSelection[] textSelections = document.findAllString(keyWord, false, false);

		// 设置高亮颜色
		for (TextSelection selection : textSelections) {
			System.out.println(selection.getSelectedText());
			selection.getAsOneRange().getCharacterFormat().setHighlightColor(Color.YELLOW);
		}

		// 保存文档
		document.saveToFile(destFileName, FileFormat.Docx_2013);
	}

	/**
	 * 保存文件并高亮关键字-PDF
	 * 
	 * @param fileName
	 * @param keyWord
	 */
	@SuppressWarnings("unchecked")
	public static void saveAndHighlightPdfText(String sourceFileName, String keyWord, String destFileName) {
		// 加载示例PDF文档
		PdfDocument pdf = new PdfDocument();
		pdf.loadFromFile(sourceFileName);
		pdf.getPages().add();
		PdfTextFind[] result = null;
		// 遍历文档页面
		for (PdfPageBase page : (Iterable<PdfPageBase>) pdf.getPages()) {
			// 查找文档中所有的"添加"字符串
			result = page.findText(keyWord).getFinds();
			for (PdfTextFind find : result) {
				try {
					// 高亮显示查找结果
					find.applyHighLight(Color.yellow);
				} catch (Exception e) {
					e.printStackTrace();
				}
			}
		}
		pdf.getPages().remove(pdf.getPages().get(pdf.getPages().getCount() - 1));
		// 保存文档
		pdf.saveToFile(destFileName);
		pdf.close();
	}

	/**
	 * 通过关键字查找内容-PDF
	 * 
	 * @param fileName
	 * @param keyWord
	 * @return
	 */
	public static String getContentByKeyPdf(String fileName, String keyWord) {
		StringBuffer buffer = null;
		try (PDDocument document = PDDocument.load(new File(fileName))) {
			document.getClass();
			if (!document.isEncrypted()) {
				PDFTextStripperByArea stripper = new PDFTextStripperByArea();
				stripper.setSortByPosition(true);
				PDFTextStripper tStripper = new PDFTextStripper();

				String pdfFileInText = tStripper.getText(document);

				String[] lines = pdfFileInText.split("\\r?\\n");
				buffer = new StringBuffer();
				int count = 0;
				for (String line : lines) {
					if (line.contains(keyWord)) {
						count++;
						buffer.append(line).append("......\n");
					}
					if (count > 2) {
						break;
					}
				}
			}
		} catch (Exception e) {
			e.printStackTrace();
		}
		System.out.println(buffer.toString());
		return buffer.toString();
	}
}