UnstructuredHtmlEvaluator#

class langchain_community.document_loaders.url_playwright.UnstructuredHtmlEvaluator(remove_selectors: List[str] | None = None)[source]#

Evaluate the page HTML content using the unstructured library.

Initialize UnstructuredHtmlEvaluator.

Methods

__init__([remove_selectors])

Initialize UnstructuredHtmlEvaluator.

evaluate(page, browser, response)

Synchronously process the HTML content of the page.

evaluate_async(page, browser, response)

Asynchronously process the HTML content of the page.

Parameters:

remove_selectors (List[str] | None) –

__init__(remove_selectors: List[str] | None = None)[source]#

Initialize UnstructuredHtmlEvaluator.

Parameters:

remove_selectors (List[str] | None) –

evaluate(page: Page, browser: Browser, response: Response) str[source]#

Synchronously process the HTML content of the page.

Parameters:
  • page (Page) –

  • browser (Browser) –

  • response (Response) –

Return type:

str

async evaluate_async(page: AsyncPage, browser: AsyncBrowser, response: AsyncResponse) str[source]#

Asynchronously process the HTML content of the page.

Parameters:
  • page (AsyncPage) –

  • browser (AsyncBrowser) –

  • response (AsyncResponse) –

Return type:

str