langchain.js
    Preparing search index...

    Class CollegeConfidentialLoader

    A document loader specifically designed for loading documents from the College Confidential website. It extends the CheerioWebBaseLoader.

    const loader = new CollegeConfidentialLoader("https:exampleurl.com");
    const docs = await loader.load();
    console.log({ docs });

    Hierarchy (View Summary)

    Index

    Constructors

    constructor

    Properties

    caller headers? selector? textDecoder? timeout webPath

    Methods

    load scrape _scrape imports scrapeAll

    Constructors

    Properties

    caller: AsyncCaller
    headers?: HeadersInit
    selector?: SelectorType
    textDecoder?: TextDecoder
    timeout: number
    webPath: string

    Methods

    • Overrides the base load() method to extract the text content from the loaded document using a specific selector for the College Confidential website. It creates a Document instance with the extracted text and metadata, and returns an array containing the Document instance.

      Returns Promise<Document[]>

      An array containing a Document instance with the extracted text and metadata from the loaded College Confidential web document.

    • Fetches the web document from the webPath and loads it using Cheerio. It returns a CheerioAPI instance.

      Returns Promise<CheerioAPI>

      A Promise that resolves to a CheerioAPI instance.

    Static_scrape

    • _scrape(
          url: string,
          caller: AsyncCaller,
          timeout: undefined | number,
          textDecoder?: TextDecoder,
          options?: CheerioOptions & { headers?: HeadersInit },
      ): Promise<CheerioAPI>

      Parameters

      • url: string
      • caller: AsyncCaller
      • timeout: undefined | number
      • OptionaltextDecoder: TextDecoder
      • Optionaloptions: CheerioOptions & { headers?: HeadersInit }

      Returns Promise<CheerioAPI>

    • A static method that dynamically imports the Cheerio library and returns the load function. If the import fails, it throws an error.

      Returns Promise<
          {
              load: (
                  content: string | Buffer<ArrayBufferLike> | AnyNode | AnyNode[],
                  options?: null | CheerioOptions,
                  isDocument?: boolean,
              ) => CheerioAPI;
          },
      >

      A Promise that resolves to an object containing the load function from the Cheerio library.

    • Fetches web documents from the given array of URLs and loads them using Cheerio. It returns an array of CheerioAPI instances.

      Parameters

      • urls: string[]

        An array of URLs to fetch and load.

      • caller: AsyncCaller
      • timeout: undefined | number
      • OptionaltextDecoder: TextDecoder
      • Optionaloptions: CheerioOptions & { headers?: HeadersInit }

      Returns Promise<CheerioAPI[]>

      A Promise that resolves to an array of CheerioAPI instances.

    Settings

    Member Visibility

    On This Page

    Constructors
    Properties
    Methods