Package org.springframework.ai.reader.jsoup

Class JsoupDocumentReader

java.lang.Object

org.springframework.ai.reader.jsoup.JsoupDocumentReader

All Implemented Interfaces:

Supplier<List<Document>>, DocumentReader

public class JsoupDocumentReader
extends Object
implements DocumentReader

Reads HTML documents and extracts text content using JSoup. This reader provides options for selecting specific HTML elements to extract, handling links, and extracting metadata. It leverages the JSoup library for parsing HTML.

Author:

Alexandros Pappas

See Also:

• JSoup Website

Constructor Summary

Constructors

Constructor	Description
JsoupDocumentReader(String htmlResource)
JsoupDocumentReader(String htmlResource, JsoupDocumentReaderConfig config)
JsoupDocumentReader(org.springframework.core.io.Resource htmlResource)
JsoupDocumentReader(org.springframework.core.io.Resource htmlResource, JsoupDocumentReaderConfig config)

Method Summary

Modifier and Type	Method	Description
List<Document>	get()

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface org.springframework.ai.document.DocumentReader

read

Constructor Details

JsoupDocumentReader

public JsoupDocumentReader(String htmlResource)

JsoupDocumentReader

public JsoupDocumentReader(org.springframework.core.io.Resource htmlResource)

JsoupDocumentReader

public JsoupDocumentReader(String htmlResource,
 JsoupDocumentReaderConfig config)

JsoupDocumentReader

public JsoupDocumentReader(org.springframework.core.io.Resource htmlResource,
 JsoupDocumentReaderConfig config)

Method Details

get

public List<Document> get()

Specified by:

get in interface Supplier<List<Document>>