场景
在日常业务需求中，往往会遇到解析pdf数据获取文本的需求，常见的做法是使用 pdfbox 来做，但是它只适合做一些简单的段落文本解析，无法处理表格这种复杂类型，因为单元格中的文本有换行的情况，无法对应到我们业务具体的属性上面去。而 tabula 在它的基础上做了表格的特殊处理，使用案例如下：
引入依赖
<!-- PDF解析，内含pdfbox -->
<dependency><groupId>technology.tabula</groupId><artifactId>tabula</artifactId><version>1.0.5</version>
</dependency><dependency><groupId>com.alibaba</groupId><artifactId>fastjson</artifactId><version>2.0.53</version>
</dependency>
代码实现
package net.lab1024.sa.admin.util;import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
import lombok.extern.slf4j.Slf4j;
import org.apache.pdfbox.pdmodel.PDDocument;
import technology.tabula.*;
import technology.tabula.extractors.SpreadsheetExtractionAlgorithm;import java.io.File;
import java.util.ArrayList;
import java.util.List;@Slf4j
public class PdfUtil {public static void main(String[] args) {JSONArray jsonArray = readPdfTable("C:\\Users\\admin\\Desktop\\xxx.pdf");System.out.println(jsonArray);}/*** 解析pdf的表格** @param filePath* @return*/public static JSONArray readPdfTable(String filePath) {// 表头// todo 这里自己先定义了，使用时可读取表头的中文作为key或者将中文翻译成英文作为keyList<String> fieldList = new ArrayList<>();fieldList.add("jydh");fieldList.add("jysj");fieldList.add("jylx");fieldList.add("szqt");fieldList.add("jyfs");fieldList.add("je");fieldList.add("jydf");fieldList.add("shdh");JSONArray jsonArray = new JSONArray();// 表格提取算法SpreadsheetExtractionAlgorithm algorithm = new SpreadsheetExtractionAlgorithm();try (PDDocument document = PDDocument.load(new File(filePath))) {ObjectExtractor extractor = new ObjectExtractor(document);PageIterator pi = extractor.extract();// 遍历页while (pi.hasNext()) {Page page = pi.next();List<Table> tableList = algorithm.extract(page);// 遍历表for (Table table : tableList) {List<List<RectangularTextContainer>> rowList = table.getRows();// 遍历行for (List<RectangularTextContainer> row : rowList) {JSONObject jsonObject = new JSONObject();// 遍历列for (int i = 0; i < row.size(); i++) {RectangularTextContainer cell = row.get(i);String text = cell.getText().replace("\r", "");jsonObject.put(fieldList.get(i), text);}jsonArray.add(jsonObject);}}}} catch (Exception e) {e.printStackTrace();}return jsonArray;}}
