@llml-browser/types/dist/chunk-PSFQO4CP.mjs

TypeScript types and schemas for the @llml-browser API

import {
  MetadataOptionsSchema
} from "./chunk-5RX3GYMK.mjs";

// src/routers/read/index.ts
import z from "zod";
var readOptionsSchema = z.object({
  /**
   * The URL to scrape.
   * Must be a valid URL string.
   */
  url: z.string(),
  /**
   * Whether to extract metadata from the page.
   * Default: true
   */
  // default true if not set
  metadata: z.preprocess(
    (val) => val !== "false" && val !== false,
    z.boolean().optional()
  ),
  /**
   * Whether to extract markdown from the page.
   * Default: true
   */
  // default true if not set
  markdown: z.preprocess(
    (val) => val !== "false" && val !== false,
    z.boolean().optional()
  ),
  /**
   * Whether to return cleaned HTML.
   * Default: true
   */
  cleanedHtml: z.preprocess(
    (val) => val !== "false" && val !== false,
    z.boolean().optional()
  ),
  /**
   * Whether to fetch and parse robots.txt.
   * Default: false
   */
  robots: z.preprocess(
    (val) => val === "true" || val === true,
    z.boolean().optional()
  ),
  /**
   * Whether to return raw HTML.
   * Default: false
   */
  rawHtml: z.preprocess(
    (val) => val !== "false" && val !== false,
    z.boolean().optional()
  ),
  /**
   * Options for metadata extraction.
   * Controls how metadata like title, description, etc. are extracted.
   */
  metadataOptions: MetadataOptionsSchema.optional()
  /** DEPRECATED: AS WE ARE NOT USING HTMLREWRITE FOR CLEANING THE HTML FOR NOW, MAY BE REUSED THIS IN THE FUTURE
   * Options for HTML cleaning.
   * Controls how HTML is sanitized and cleaned.
   */
  // cleanedHtmlOptions: HTMLCleaningOptionsSchema.optional(),
});

export {
  readOptionsSchema
};
//# sourceMappingURL=chunk-PSFQO4CP.mjs.map