解析pdf表格 压缩pdf文件

<repositories>
	    <repository>
            <id>AsposeJavaAPI</id>
            <name>Aspose Java API</name>
            <url>http://repository.aspose.com/repo</url>
        </repository>
</repositories>

<dependency>
		    <groupId>com.aspose</groupId>
		    <artifactId>aspose-pdf</artifactId>
		    <version>22.5</version>
</dependency>

import java.util.List;

import com.aspose.pdf.AbsorbedTable;
import com.aspose.pdf.Document;
import com.aspose.pdf.Field;
import com.aspose.pdf.Page;
import com.aspose.pdf.PageCollection;
import com.aspose.pdf.TableAbsorber;
import com.aspose.pdf.TextFragmentCollection;

public class PdfHelper {

	public static void parse(String filePath) {

		// Open document
		Document pdf = new Document(filePath);
		Field[] fields = pdf.getForm().getFields();
		for (int i = 0; i < fields.length; i++) {
			System.out.println("Form field: " + fields[i].getFullName());
			System.out.println("Form field: " + fields[i].getValue());
		}

		PageCollection pc = pdf.getPages();

		Page page = pc.get_Item(38);

		TableAbsorber ta = new TableAbsorber();
		ta.visit(page);

		List<AbsorbedTable> ts = ta.getTableList();

		int[] table = new int[2];

		// 开始循环表格
		ts.forEach(s -> {
			// s.getRowList().get(0).getCellList().get(0).getTextFragments().get_Item(0).getText();
			// 行
			s.getRowList().stream().forEach(row -> {
				table[0]++;

				// 列
				table[1] = 0;
				row.getCellList().stream().forEach(cell -> {
					table[1]++;

					TextFragmentCollection textFragmentC = cell.getTextFragments();

					StringBuffer sb = new StringBuffer();
					textFragmentC.forEach(tf -> {

						String txt = tf.getText();
						sb.append(txt);

					});
					System.out.println(String.format("%d,%d===>%s", table[0], table[1], sb.toString()));

				});

			});

		});

		pdf.close();

	}

	public static void optimize(String source, String target) {
		Document doc = new Document(source);
		// 设置压缩属性
		Document.OptimizationOptions opt = new Document.OptimizationOptions();
		// 删除PDF不必要的对象
		opt.setRemoveUnusedObjects(true);
		// 链接重复流
		opt.setLinkDuplcateStreams(false);
		// 删除未使用的流
		opt.setRemoveUnusedStreams(false);
		// 删除不必要的字体
		opt.setUnembedFonts(true);
		// 压缩PDF中的图片
		opt.setCompressImages(true);
		// 图片压缩比， 0 到100可选，越低压缩比越大
		opt.setImageQuality(80);
		doc.optimizeResources(opt);
		// 优化web的PDF文档
		doc.optimize();
		doc.save(target);
	}

	public static void main(String[] args) {
		//解析pdf 表格
		parse("/your/file/path/**.pdf");

		//pdf压缩
		String source = "/your/file/path/source.pdf";
		String target = "/your/file/path/target.pdf";
		optimize(source, target);
	}

}