[原创] Aspose Words Word 转 TXT

用 aspose words 把 Docx/Doc 转换为 TXT, 并保留表格格式

Java

import com.aspose.words.Document;
import com.aspose.words.TxtSaveOptions;

import java.io.File;
import java.nio.file.Paths;
//import java.nio.file.Path;
import java.io.FileOutputStream;

public class Pdf2Txt {
    public static void main(String[] args)throws Exception {
        String input_path = args[0];
        String output_dir = args[1];
        txt(input_path, output_dir);

    private static void txt(String input_path, String output_dir)throws Exception {
        TxtSaveOptions txtSaveOptions = new TxtSaveOptions();
        String input_name = Paths.get(input_path).getFileName().toString();
        // System.out.println("inputfilename: " + input_name);
        String output_path = Paths.get(output_dir).resolve(input_name).toString() + ".txt";
        System.out.println("output: " + output_path);

        txtSaveOptions.setParagraphBreak("\n"); // 设置换行符
        //txtSaveOptions.setExportGeneratorName(false);
        txtSaveOptions.setPreserveTableLayout(true); //保留表格风格
        txtSaveOptions.setPrettyFormat(true); // 格式化
        txtSaveOptions.setUseHighQualityRendering(true); //高质量渲染

        Document doc = new Document(input_path);
        doc.save(output_path, txtSaveOptions);
    }
}

Python

• 安装

pip install aspose-words

• 代码

import sys
import os.path
import aspose.words as aw

op = aw.saving.TxtSaveOptions()
op.export_generator_name = False
op.paragraph_break = '\n'
op.preserve_table_layout = True
op.pretty_format = True
op.use_high_quality_rendering = True

doc = aw.Document(sys.argv[0])
filename = os.path.basename(sys.argv[0])
doc.save(os.path.join(sys.argv[1], filename) + '.txt', op)