langchain.document_loaders.browserless.BrowserlessLoader¶

class langchain.document_loaders.browserless.BrowserlessLoader(api_token: str, urls: Union[str, List[str]], text_content: bool = True)[source]¶

Bases: BaseLoader

Loads the content of webpages using Browserless’ /content endpoint

Initialize with API token and the URLs to scrape

Methods

__init__(api_token, urls[, text_content])

Initialize with API token and the URLs to scrape

lazy_load()

Lazy load Documents from URLs.

load()

Load Documents from URLs.

load_and_split([text_splitter])

Load Documents and split into chunks.

Attributes

api_token

Browserless API token.

urls

List of URLs to scrape.
lazy_load() → Iterator[Document][source]¶

Lazy load Documents from URLs.

load() → List[Document][source]¶

Load Documents from URLs.

load_and_split(text_splitter: Optional[TextSplitter] = None) → List[Document]¶

Load Documents and split into chunks. Chunks are returned as Documents.

Parameters

text_splitter – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.

Returns

List of Documents.

api_token¶

Browserless API token.

urls¶

List of URLs to scrape.

Examples using BrowserlessLoader¶