Basic document loader for HTML (.html, .htm) files.

Text extraction strategy

  1. <script> and <style> blocks are removed entirely.
  2. Block-level elements (<p>, <div>, <h1><h6>, etc.) are replaced with newline characters to preserve paragraph structure.
  3. All remaining HTML tags are stripped.
  4. A common subset of HTML entities is decoded.
  5. Excessive whitespace is collapsed.

Metadata

  • title — extracted from the <title> element when present.
  • wordCount — approximate count of words in the extracted text.
  • source — absolute file path (when loaded from disk).

Implements

Example

const loader = new HtmlLoader();
const doc = await loader.load('/public/index.html');
console.log(doc.metadata.title); // e.g. 'Welcome to AgentOS'

Implements

Constructors

Methods

Properties

Constructors

Methods

  • Returns true when this loader is capable of handling source.

    For string sources the check is purely extension-based. For Buffer sources the loader may inspect magic bytes when relevant.

    Parameters

    • source: string | Buffer<ArrayBufferLike>

      Absolute file path or raw bytes.

    Returns boolean

  • Parses source and returns a normalised LoadedDocument.

    When source is a string the loader treats it as an absolute (or resolvable) file path and reads the file from disk. When source is a Buffer the loader parses the bytes directly and derives as much metadata as possible from the buffer content alone.

    Parameters

    • source: string | Buffer<ArrayBufferLike>

      Absolute file path OR raw document bytes.

    • Optional _options: LoadOptions

      Optional hints such as a format override.

    Returns Promise<LoadedDocument>

    A promise resolving to the fully-populated LoadedDocument.

    Throws

    When the file cannot be read or the format is not parsable.

Properties

supportedExtensions: string[] = ...

File extensions this loader handles, each with a leading dot.

Used by LoaderRegistry to route file paths to the correct loader.

Example

['.md', '.mdx']