如何从.doc和.docx文件中提取纯文本？

unzip -p some.docx word/document.xml | sed -e \'s/<[^>]\\{1,\\}>//g; s/[^[:print:]]\\{1,\\}//g\'

libreoffice --headless --convert-to \"txt:Text (encoded):UTF8\" mydocument.doc

.doc

.docx

.xls

.xlsx

.ppt

.pptx

.doc

.docx

import java.io.FileInputStream;
import java.io.FileWriter;
import java.io.IOException;

import org.apache.poi.POITextExtractor;
import org.apache.poi.extractor.ExtractorFactory;
import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
import org.apache.xmlbeans.XmlException;

public class WordToTextConverter {
    public static void main(String[] args) {
        try {
            convertWordToText(args[0], args[1]);
        } catch (ArrayIndexOutOfBoundsException aiobe) {
            System.out.println(\"Usage: java WordToTextConverter <word_file> <text_file>\");
        }
    }

    public static void convertWordToText(String src, String desc) {
        try {
            FileInputStream fs = new FileInputStream(src);
            final POITextExtractor extractor = ExtractorFactory.createExtractor(fs);
            FileWriter fw = new FileWriter(desc);
            fw.write(extractor.getText());
            fw.flush();
            fs.close();
            fw.close();

        } catch (IOException | OpenXML4JException | XmlException e) {
            e.printStackTrace();
        }
    }
}


# Maven dependencies (pom.xml):

<?xml version=\"1.0\" encoding=\"UTF-8\"?>
<project xmlns=\"http://maven.apache.org/POM/4.0.0\"
xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\"
xsi:schemaLocation=\"http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd\">
<modelVersion>4.0.0</modelVersion>

<groupId>my.wordconv</groupId>
<artifactId>my.wordconv.converter</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi</artifactId>
        <version>3.17</version>
    </dependency>
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-ooxml</artifactId>
        <version>3.17</version>
    </dependency>
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-scratchpad</artifactId>
        <version>3.17</version>
    </dependency>
</dependencies>
</project>

java -jar tika-app-1.4.jar --text ./my-document.doc

# open word in less (ie worl document.doc)
worl() {
    DOC=$(mktemp /tmp/output.XXXXXXXXXX)
    wvText $1 $DOC
    less $DOC
    rm $DOC
}