Package dev.langchain4j.data.document.loader.playwright

Class PlaywrightDocumentLoader

java.lang.Object

dev.langchain4j.data.document.loader.playwright.PlaywrightDocumentLoader

All Implemented Interfaces:

AutoCloseable

public class PlaywrightDocumentLoader
extends Object
implements AutoCloseable

Utility class for loading web documents using Playwright. Returns a Document object containing the content of the Web page.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	PlaywrightDocumentLoader.Builder

Method Summary

Modifier and Type	Method	Description
static PlaywrightDocumentLoader.Builder	builder()
void	close()	Closes the underlying Browser instance.
Document	load(String url)	Loads a Document from the specified URL by fetching its HTML content.
Document	load(String url, DocumentParser documentParser)	Loads a Document from the specified URL by fetching its HTML content and parsing it using the provided DocumentParser.
String	pageContent(String url)	Loads the HTML content of a web page from the specified URL using Playwright.

Methods inherited from class java.lang.Object

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

Method Details

load

public Document load(String url)

Loads a Document from the specified URL by fetching its HTML content.

This method fetches the page content using pageContent(url), and then wraps it into a Document with metadata indicating the source URL.

Parameters:

url - the URL of the web page to load; must not be null

Returns:

a Document instance containing the HTML content and metadata

Throws:

NullPointerException - if the provided url is null

RuntimeException - if the document fails to load due to an underlying content fetch issue

load

public Document load(String url,
 DocumentParser documentParser)

Loads a Document from the specified URL by fetching its HTML content and parsing it using the provided DocumentParser.

This method delegates content parsing to the given parser and adds the source URL to the document's metadata.

Parameters:

url - the URL of the web page to load; must not be null

documentParser - the parser used to convert raw HTML content into a Document; must not be null

Returns:

a Document parsed from the web page content, with metadata including the URL

Throws:

NullPointerException - if url or documentParser is null

RuntimeException - if the document content cannot be loaded or parsed

pageContent

public String pageContent(String url)

Loads the HTML content of a web page from the specified URL using Playwright.

This method opens a new page in the browser, navigates to the given URL, waits for the DOM content to be fully loaded, and returns the full HTML content of the page.

Parameters:

url - the URL of the web page to load; must not be null

Returns:

the full HTML content of the page as a String

Throws:

NullPointerException - if the provided url is null

RuntimeException - if the page fails to load or an unexpected error occurs during navigation

close

public void close()

Closes the underlying Browser instance.

Specified by:

close in interface AutoCloseable

builder

public static PlaywrightDocumentLoader.Builder builder()