ai.platon.pulsar.common.extractor.TextDocument.kt Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of pulsar-common Show documentation

There is a newer version: 2.1.0

package ai.platon.pulsar.common.extractor

/**
 * Represents a text document extracted from a text page, such as a news article.
 * */
open class TextDocument(
    /**
     * The url of the document.
     * */
    val url: String,
    /**
     * The title of the document, which is in  tag.
     * */
    var pageTitle: String? = null,
    /**
     * The title of the content, which is extracted from the text content.
     * */
    var contentTitle: String? = null,
    /**
     * The extracted text content of the document, which is usually with links, ads and other irrelevant contents removed.
     * */
    var textContent: String? = null,
    /**
     * The extracted fields.
     * */
    var additionalFields: Map<String, String>? = null
)
</code></pre>    <br/>
    <br/>
<div class='clear'></div>
</main>
</div>
<br/><br/>
    <div class="align-center">© 2015 - 2025 <a href="/legal-notice.php">Weber Informatics LLC</a> | <a href="/data-protection.php">Privacy Policy</a></div>
<br/><br/><br/><br/><br/><br/>
</body>
</html>