@intuned/browser-dev 2.2.3-test-build.0

package/dist/optimized-extractors/extractArray.js

@@ -0,0 +1,120 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.extractArrayFromPage = exports.extractArrayFromLocator = void 0;
+var _validators = require("./validators");
+var _formatZodError = require("../common/formatZodError");
+var _dynamicListExtractor = require("./listExtractionHelpers/dynamicListExtractor");
+var _SdkError = require("../common/SdkError");
+var _Logger = require("../common/Logger");
+const extractArrayFromPage = async (page, options) => {
+  const originalPositionStack = (0, _SdkError.captureUserStack)();
+  if (!page) {
+    throw new _SdkError.SdkError("Invalid page object, page must be an instance of playwright page", originalPositionStack);
+  }
+  const optionsValidationResults = _validators.extractArrayOptimizedInputSchema.safeParse(options);
+  if (!optionsValidationResults.success) {
+    const errors = (0, _formatZodError.formatZodError)(optionsValidationResults.error);
+    const message = `invalid extractArrayFromPage input: ${errors.join("\n")}`;
+    throw new _SdkError.SdkError(message, originalPositionStack);
+  }
+  const validOptions = optionsValidationResults.data;
+  const result = await (0, _dynamicListExtractor.dynamicListExtractor)(page, validOptions.label, {
+    itemEntityName: validOptions.itemEntityName ?? "data",
+    itemEntitySchema: validOptions.itemEntitySchema,
+    strategy: validOptions.strategy,
+    optionalPropertiesInvalidator: validOptions.optionalPropertiesInvalidator,
+    variantKey: validOptions.variantKey,
+    prompt: validOptions.prompt,
+    apiKey: validOptions.apiKey
+  });
+  if (result.isErr()) {
+    switch (result.error.type) {
+      case "InvalidSearchRegion":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Search region is invalid. Please make sure container is correct. Object extraction relies on the container when passed.`);
+        throw new _SdkError.SdkError("InvalidSearchRegion", originalPositionStack);
+      case "InvalidInput":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Invalid input: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidInput", originalPositionStack);
+      case "InvalidAddressUrl":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Invalid address url: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidAddressUrl", originalPositionStack);
+      case "InvalidExtractionResult":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Invalid extraction result: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidExtractionResult", originalPositionStack);
+      case "InvalidList":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Invalid list: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidList", originalPositionStack);
+      case "NoResultsFound":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Invalid results: No results found were found. It's probably that the page is empty.`);
+        throw new _SdkError.SdkError("NoResultsFound", originalPositionStack);
+      case "RequiredPropertyNotExtracted":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Required property not extracted: ${result.error.context}`);
+        throw new _SdkError.SdkError("RequiredPropertyNotExtracted", originalPositionStack);
+      case "Other":
+        console.log(result.error.error ?? "");
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Other error: ${result.error.error ?? result.error.context}`);
+        throw new _SdkError.SdkError("Other", originalPositionStack);
+      case "InsufficientAiCredits":
+        result.error.context && _Logger.logger.error(result.error.context);
+        return [];
+    }
+  }
+  return result.value;
+};
+exports.extractArrayFromPage = extractArrayFromPage;
+const extractArrayFromLocator = async (locator, options) => {
+  const optionsValidationResults = _validators.extractArrayOptimizedInputSchema.safeParse(options);
+  const originalPositionStack = (0, _SdkError.captureUserStack)();
+  if (!optionsValidationResults.success) {
+    const errors = (0, _formatZodError.formatZodError)(optionsValidationResults.error);
+    const message = `invalid extractArrayFromLocator input: ${errors.join("\n")}`;
+    throw new _SdkError.SdkError(message, originalPositionStack);
+  }
+  const validOptions = optionsValidationResults.data;
+  const page = await locator.page();
+  const result = await (0, _dynamicListExtractor.dynamicListExtractor)(page, validOptions.label, {
+    itemEntityName: validOptions.itemEntityName,
+    itemEntitySchema: validOptions.itemEntitySchema,
+    strategy: validOptions.strategy,
+    optionalPropertiesInvalidator: validOptions.optionalPropertiesInvalidator,
+    variantKey: validOptions.variantKey,
+    searchRegion: locator
+  });
+  if (result.isErr()) {
+    switch (result.error.type) {
+      case "InvalidSearchRegion":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Search region is invalid. Please make sure container is correct. Object extraction relies on the container when passed.`);
+        throw new Error("InvalidSearchRegion");
+      case "InvalidInput":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Invalid input: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidInput", originalPositionStack);
+      case "InvalidAddressUrl":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Invalid address url: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidAddressUrl", originalPositionStack);
+      case "InvalidExtractionResult":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Invalid extraction result: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidExtractionResult", originalPositionStack);
+      case "InvalidList":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Invalid list: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidList", originalPositionStack);
+      case "NoResultsFound":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Invalid results: No results found were found. It's probably that the page is empty.`);
+        throw new _SdkError.SdkError("NoResultsFound", originalPositionStack);
+      case "RequiredPropertyNotExtracted":
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Required property not extracted: ${result.error.context}`);
+        throw new _SdkError.SdkError("RequiredPropertyNotExtracted", originalPositionStack);
+      case "Other":
+        console.log(result.error.error ?? "");
+        _Logger.logger.error(`Optimized array extractor ${options.itemEntityName} - Other error: ${result.error.error ?? result.error.context}`);
+        throw new _SdkError.SdkError("Other", originalPositionStack);
+      case "InsufficientAiCredits":
+        console.log(result.error.context, originalPositionStack);
+        throw new _SdkError.SdkError("InsufficientAiCredits", originalPositionStack);
+    }
+  }
+  return result.value;
+};
+exports.extractArrayFromLocator = extractArrayFromLocator;

package/dist/optimized-extractors/extractObject.js

@@ -0,0 +1,104 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.extractObjectFromPage = exports.extractObjectFromLocator = void 0;
+var _validators = require("./validators");
+var _formatZodError = require("../common/formatZodError");
+var _dynamicObjectExtractor = require("./objectExtractionHelpers/dynamicObjectExtractor");
+var _SdkError = require("../common/SdkError");
+const extractObjectFromPage = async (page, options) => {
+  const originalPositionStack = (0, _SdkError.captureUserStack)();
+  const optionsValidationResults = _validators.extractObjectOptimizedInputSchema.safeParse(options);
+  if (!optionsValidationResults.success) {
+    const errors = (0, _formatZodError.formatZodError)(optionsValidationResults.error);
+    const message = `invalid extractObjectFromPage input: ${errors.join("\n")}`;
+    throw new _SdkError.SdkError(message, originalPositionStack);
+  }
+  const parsedOptions = optionsValidationResults.data;
+  const result = await (0, _dynamicObjectExtractor.dynamicObjectExtractor)(page, options.label, {
+    entityName: parsedOptions.entityName ?? "data",
+    entitySchema: parsedOptions.entitySchema,
+    strategy: parsedOptions.strategy,
+    optionalPropertiesInvalidator: parsedOptions.optionalPropertiesInvalidator,
+    variantKey: parsedOptions.variantKey,
+    prompt: parsedOptions.prompt,
+    apiKey: parsedOptions.apiKey
+  });
+  if (result.isErr()) {
+    switch (result.error.type) {
+      case "InvalidSearchRegion":
+        console.log(`Object Extractor ${options.entityName} - Search region is invalid. Please make sure container is correct. Object extraction relies on the container when passed.`);
+        throw new _SdkError.SdkError("InvalidContainer", originalPositionStack);
+      case "InvalidInput":
+        console.log(`Object Extractor ${options.entityName} - Invalid input: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidInput", originalPositionStack);
+      case "InvalidExtractionResult":
+        console.log(`Object Extractor ${options.entityName} - Invalid extraction result: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidExtractionResult", originalPositionStack);
+      case "InvalidPageState":
+        console.log(`Object Extractor ${options.entityName} - Invalid page state: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidPageState", originalPositionStack);
+      case "Other":
+        console.log(`Object Extractor ${options.entityName} - Other error: ${result.error.context}`);
+        throw new _SdkError.SdkError("Other", originalPositionStack);
+      case "RequiredPropertyNotExtracted":
+        console.log(`Object Extractor ${options.entityName} - Required property not extracted: ${result.error.context}`);
+        throw new _SdkError.SdkError("RequiredPropertyNotExtracted", originalPositionStack);
+      case "InsufficientAiCredits":
+        console.log(result.error.context);
+        throw new _SdkError.SdkError("InsufficientAiCredits", originalPositionStack);
+    }
+  }
+  return result.value;
+};
+exports.extractObjectFromPage = extractObjectFromPage;
+const extractObjectFromLocator = async (locator, options) => {
+  const originalPositionStack = (0, _SdkError.captureUserStack)();
+  const optionsValidationResults = _validators.extractObjectOptimizedInputSchema.safeParse(options);
+  if (!optionsValidationResults.success) {
+    const errors = (0, _formatZodError.formatZodError)(optionsValidationResults.error);
+    const message = `invalid extractObjectFromLocator input: ${errors.join("\n")}`;
+    throw new _SdkError.SdkError(message, originalPositionStack);
+  }
+  const data = optionsValidationResults.data;
+  const page = locator.page();
+  const result = await (0, _dynamicObjectExtractor.dynamicObjectExtractor)(page, options.label, {
+    entityName: data.entityName ?? "data",
+    entitySchema: data.entitySchema,
+    strategy: data.strategy,
+    optionalPropertiesInvalidator: data.optionalPropertiesInvalidator,
+    variantKey: data.variantKey,
+    searchRegion: locator,
+    prompt: data.prompt,
+    apiKey: data.apiKey
+  });
+  if (result.isErr()) {
+    switch (result.error.type) {
+      case "InvalidSearchRegion":
+        console.log(`Object Extractor ${options.entityName} - Search region is invalid. Please make sure container is correct. Object extraction relies on the container when passed.`);
+        throw new _SdkError.SdkError("InvalidContainer", originalPositionStack);
+      case "InvalidInput":
+        console.log(`Object Extractor ${options.entityName} - Invalid input: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidInput", originalPositionStack);
+      case "InvalidExtractionResult":
+        console.log(`Object Extractor ${options.entityName} - Invalid extraction result: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidExtractionResult", originalPositionStack);
+      case "InvalidPageState":
+        console.log(`Object Extractor ${options.entityName} - Invalid page state: ${result.error.context}`);
+        throw new _SdkError.SdkError("InvalidPageState", originalPositionStack);
+      case "Other":
+        console.log(`Object Extractor ${options.entityName} - Other error: ${result.error.context}`);
+        throw new _SdkError.SdkError("Other", originalPositionStack);
+      case "RequiredPropertyNotExtracted":
+        console.log(`Object Extractor ${options.entityName} - Required property not extracted: ${result.error.context}`);
+        throw new _SdkError.SdkError("RequiredPropertyNotExtracted", originalPositionStack);
+      case "InsufficientAiCredits":
+        console.log(result.error.context);
+        throw new _SdkError.SdkError("InsufficientAiCredits", originalPositionStack);
+    }
+  }
+  return result.value;
+};
+exports.extractObjectFromLocator = extractObjectFromLocator;

package/dist/optimized-extractors/index.d.ts

@@ -0,0 +1,397 @@
+import { Locator, Page } from "playwright-core";
+import { BasicSchema } from "./types/jsonSchema";
+
+/**
+ * this strategy will use a screenshot of the page/locator with some processing to extract the needed data.
+ * should be used when the information you're trying to extract is not present in the dom as a text but can be identified visually.
+ * @interface
+ * @property model - the model to use in the extraction process.
+ * @property  type - the type of the strategy
+ */
+export interface ImageStrategy {
+  model:
+    | "claude-3-haiku"
+    | "claude-3-haiku-20240307"
+    | "claude-3.5-sonnet"
+    | "claude-3-5-sonnet-20240620"
+    | "claude-3-5-sonnet-20241022"
+    | "claude-opus-4"
+    | "claude-opus-4-20250514"
+    | "claude-sonnet-4"
+    | "claude-sonnet-4-20250514"
+    | "gpt4-turbo"
+    | "gpt-4-turbo-2024-04-09"
+    | "gpt-4o"
+    | "gpt-4o-2024-05-13"
+    | "gpt-4o-mini"
+    | "gpt-4o-mini-2024-07-18"
+    | "gemini-1.5-pro"
+    | "gemini-1.5-pro-002"
+    | "gemini-1.5-flash-8b"
+    | "gemini-1.5-flash-8b-002"
+    | "gemini-1.5-flash"
+    | "gemini-1.5-flash-002"
+    | "gemini-2.0-flash-exp";
+  type: "IMAGE";
+}
+/**
+ * this strategy will use the html of the page/locator to extract the needed data. we filter out some of the attributes to reduce context.
+ * the attributes included are only: `aria-label` `data-name` `name` `type` `placeholder` `value` `role` `title` `href` `id` `alt`,
+ *
+ * @interface
+ * @property model - the model to use in the extraction process
+ * @property  type - the type of the strategy
+ */
+export interface HtmlStrategy {
+  model:
+    | "claude-3-haiku"
+    | "claude-3-haiku-20240307"
+    | "claude-3-5-haiku"
+    | "claude-3-5-haiku-20241022"
+    | "claude-3.5-sonnet"
+    | "claude-3-5-sonnet-20240620"
+    | "claude-3-5-sonnet-20241022"
+    | "claude-opus-4"
+    | "claude-opus-4-20250514"
+    | "claude-sonnet-4"
+    | "claude-sonnet-4-20250514"
+    | "gpt4-turbo"
+    | "gpt-4-turbo-2024-04-09"
+    | "gpt3.5-turbo"
+    | "gpt-3.5-turbo-0125"
+    | "gpt-4o"
+    | "gpt-4o-2024-05-13"
+    | "gpt-4o-mini"
+    | "gpt-4o-mini-2024-07-18"
+    | "gemini-1.5-pro"
+    | "gemini-1.5-pro-002"
+    | "gemini-1.5-flash-8b"
+    | "gemini-1.5-flash-8b-002"
+    | "gemini-1.5-flash"
+    | "gemini-1.5-flash-002"
+    | "gemini-2.0-flash-exp";
+  type: "HTML";
+}
+/**
+ * Extracts an array of structured data from a web page in an optimized way, this function will use ai for the first n times, until it collects multiple examples
+ * then it will build reliable selectors in the background to make the process more efficient
+ * @deprecated This function is deprecated and will be removed in the future.
+ * @param page - The Playwright Page object from which to extract the data.
+ * @param options.label - A label for this extraction process, used for billing and monitoring.
+ * @param options.itemEntityName - The name of the entity items being extracted, it must be between 1 and 50 characters long and can only contain letters, digits, periods, underscores, and hyphens.
+ * @param options.itemEntitySchema - The schema of the entity items being extracted.
+ * @param options.strategy - Optional. The strategy to use for extraction, if not provided, the html strategy with claude haiku will be used.
+ * @param options.prompt - Optional. A prompt to guide the extraction process.
+ * @param options.optionalPropertiesInvalidator - Optional. A function to invalidate optional properties.
+ * @param options.variantKey - Optional. A variant key for the extraction process, use this when the page has multiple variants/shapes.
+ * @param options.apiKey - Optional. An API key to use for the AI extraction. Extractions made with you API key will not be billed to your account.
+ * @returns A promise that resolves to a list of extracted data.
+ *
+ * @example
+ * ```typescript extractArrayFromPage
+ *  import { extractArrayFromPage } from "@intuned/sdk/optimized-extractors";
+ *
+ *  await page.goto("https://books.toscrape.com/")
+ *  const books = await extractArrayFromPage(page,
+ *    {
+ *      strategy: {
+ *        model: "gpt4-turbo",
+ *        type: "HTML"
+ *      },
+ *      itemEntityName: "book",
+ *      label: "books-extraction",
+ *      itemEntitySchema: {
+ *        type: "object",
+ *        required: ["name"],
+ *        properties: {
+ *          name: {
+ *            type: "string",
+ *            description: "book name",
+ *            primary: true
+ *          }
+ *        }
+ *      }
+ *    },
+ *  )
+ *
+ *  console.log(books)
+ *
+ *  // output:
+ *  // [
+ *  // ...
+ *  // { name: 'Olio' },
+ *  // { name: 'Mesaerion: The Best Science Fiction Stories 1800-1849' },
+ *  // { name: 'Libertarianism for Beginners' },
+ *  // { name: "It's Only the Himalayas" }
+ *  // ...
+ *  // ]
+ *
+ * ```
+ */
+export declare function extractArrayFromPage(
+  page: Page,
+  options: {
+    label: string;
+    itemEntityName: string;
+    itemEntitySchema: SimpleArrayItemSchema;
+    strategy?: ImageStrategy | HtmlStrategy;
+    prompt?: string;
+    optionalPropertiesInvalidator?: (
+      result: Record<string, string>[]
+    ) => string[];
+    variantKey?: string;
+    apiKey?: string;
+  }
+): Promise<Record<string, string>[]>;
+
+/**
+ * Extracts an array of structured data from a locator.
+ * @deprecated This function is deprecated and will be removed in the future.
+ * @param locator - The Playwright Locator object from which to extract the data.
+ * @param options.label - A label for this extraction process, used for billing and monitoring.
+ * @param options.itemEntityName - The name of the entity items being extracted. it must be between 1 and 50 characters long and can only contain letters, digits, periods, underscores, and hyphens.
+ * @param options.itemEntitySchema - The schema of the entity items being extracted.
+ * @param options.strategy - Optional. The strategy to use for extraction, if not provided, the html strategy with claude haiku will be used.
+ * @param options.prompt - Optional. A prompt to guide the extraction process.
+ * @param options.optionalPropertiesInvalidator - Optional. A function to invalidate optional properties.
+ * @param options.variantKey - Optional. A variant key for the extraction process.
+ * @param options.apiKey - Optional. An API key to use for the AI extraction. Extractions made with you API key will not be billed to your account.
+ * @returns A promise that resolves to a list of extracted data.
+ *
+ * @example
+ * ```typescript extractArrayFromLocator
+ *  import { extractArrayFromLocator } from "@intuned/sdk/optimized-extractors";
+ *
+ *  await page.goto("https://books.toscrape.com/")
+ *  const books = await extractArrayFromLocator(page.locator("section"),
+ *    {
+ *      itemEntityName: "book",
+ *      label: "books-extraction",
+ *      itemEntitySchema: {
+ *        type: "object",
+ *        required: ["name"],
+ *        properties: {
+ *          name: {
+ *            type: "string",
+ *            description: "book name",
+ *            primary: true
+ *          }
+ *        }
+ *      }
+ *    },
+ *  )
+ *
+ *  console.log(books)
+ *
+ *  // output:
+ *  // [
+ *  // ...
+ *  // { name: 'Olio' },
+ *  // { name: 'Mesaerion: The Best Science Fiction Stories 1800-1849' },
+ *  // { name: 'Libertarianism for Beginners' },
+ *  // { name: "It's Only the Himalayas" }
+ *  // ...
+ *  // ]
+ *
+ * ```
+ */
+export declare function extractArrayFromLocator(
+  locator: Locator,
+  options: {
+    label: string;
+    itemEntityName: string;
+    itemEntitySchema: SimpleArrayItemSchema;
+    strategy?: ImageStrategy | HtmlStrategy;
+    prompt?: string;
+    optionalPropertiesInvalidator?: (
+      result: Record<string, string>[]
+    ) => string[];
+    variantKey?: string;
+    apiKey?: string;
+  }
+): Promise<Record<string, string>[]>;
+
+/**
+ * A simple object schema with string properties.
+ * @interface SimpleObjectStringSchema
+ * @extends BasicSchema
+ * @property type - The type of the schema, which is always "string".
+ */
+interface SimpleObjectStringSchema extends BasicSchema {
+  type: "string";
+}
+
+/**
+ * A simple array schema with string properties.
+ * @interface SimpleArrayStringSchema
+ * @extends BasicSchema
+ * @property type - The type of the schema, which is always "string".
+ * @property [primary] - Optional. Indicates whether this is a primary property.
+ */
+interface SimpleArrayStringSchema extends BasicSchema {
+  type: "string";
+  primary?: boolean;
+}
+
+/**
+ * A simple object schema with properties.
+ * @interface SimpleObjectSchema
+ * @extends BasicSchema
+ * @property type - The type of the schema, which is always "object".
+ * @property properties - The properties of the object.
+ * @property required - The required properties of the object.
+ */
+export interface SimpleObjectSchema extends BasicSchema {
+  type: "object";
+  properties: Record<string, SimpleObjectStringSchema>;
+  required: string[];
+}
+
+/**
+ * A simple array item schema with properties.
+ * @interface SimpleArrayItemSchema
+ * @extends BasicSchema
+ * @property type - The type of the schema, which is always "object".
+ * @property properties - The properties of the array item.
+ * @property required - The required properties of the array item.
+ */
+export interface SimpleArrayItemSchema extends BasicSchema {
+  type: "object";
+  properties: Record<string, SimpleArrayStringSchema>;
+  required: string[];
+}
+
+/**
+ * Extracts a structured object from a web page.
+ * @deprecated This function is deprecated and will be removed in the future.
+ * @param page - The Playwright Page object from which to extract the data.
+ * @param options.label - A label for this extraction process, used for billing and monitoring.
+ * @param options.entityName - The name of the entity being extracted. it must be between 1 and 50 characters long and can only contain letters, digits, periods, underscores, and hyphens.
+ * @param options.entitySchema - The schema of the entity being extracted.
+ * @param options.strategy - Optional. The strategy to use for extraction, if not provided, the html strategy with claude haiku will be used.
+ * @param options.prompt - Optional. A prompt to guide the extraction process.
+ * @param options.optionalPropertiesInvalidator - Optional. A function to invalidate optional properties.
+ * @param options.variantKey - Optional. A variant key for the extraction process.
+ * @param options.apiKey - Optional. An API key to use for the AI extraction. Extractions made with you API key will not be billed to your account.
+ * @returns A promise that resolves to the extracted object.
+ * @example
+ * ```typescript extractObjectFromPage
+ *  import { extractObjectFromPage } from "@intuned/sdk/optimized-extractors";
+ *
+ *  await page.goto("https://books.toscrape.com/catalogue/a-light-in-the-attic_1000/index.html")
+ *  const book = await extractObjectFromPage(page,
+ *    {
+ *      entityName: "book",
+ *      label: "book-extraction",
+ *      entitySchema: {
+ *        type: "object",
+ *        required: ["name","price","reviews"],
+ *        properties: {
+ *          name: {
+ *            type: "string",
+ *            description: "book name",
+ *          },
+ *          price: {
+ *            type: "string",
+ *            description: "book price"
+ *          },
+ *          reviews: {
+ *            type: "string",
+ *            description: "Number of reviews"
+ *          }
+ *
+ *        }
+ *      }
+ *    },
+ *  )
+ *
+ *  console.log(book)
+ *
+ *  // output:
+ *  // { name: 'A Light in the Attic', price: '£51.77', reviews: '0' }
+ *
+ * ```
+ */
+export declare function extractObjectFromPage(
+  page: Page,
+  options: {
+    label: string;
+    entityName: string;
+    entitySchema: SimpleObjectSchema;
+    strategy?: ImageStrategy | HtmlStrategy;
+    prompt?: string;
+    optionalPropertiesInvalidator?: (
+      result: Record<string, string | null> | null
+    ) => string[];
+    variantKey?: string;
+    apiKey?: string;
+  }
+): Promise<Record<string, string | null> | null>;
+
+/**
+ * Extracts a structured object from a locator.
+ * @deprecated This function is deprecated and will be removed in the future.
+ * @param locator - The Playwright Locator object from which to extract the data.
+ * @param options.label - A label for this extraction process, used for billing and monitoring.
+ * @param options.entityName - The name of the entity being extracted. it must be between 1 and 50 characters long and can only contain letters, digits, periods, underscores, and hyphens.
+ * @param options.entitySchema - The schema of the entity being extracted.
+ * @param options.strategy - Optional. The strategy to use for extraction, if not provided, the html strategy with claude haiku will be used.
+ * @param options.prompt - Optional. A prompt to guide the extraction process.
+ * @param options.optionalPropertiesInvalidator - Optional. A function to invalidate optional properties.
+ * @param options.variantKey - Optional. A variant key for the extraction process.
+ * @param options.apiKey - Optional. An API key to use for the AI extraction. Extractions made with you API key will not be billed to your account.
+ * @returns A promise that resolves to the extracted object.
+ *
+ * @example
+ * ```typescript extractObjectFromLocator
+ *  import { extractObjectFromLocator } from "@intuned/sdk/optimized-extractors";
+ *
+ *  await page.goto("https://books.toscrape.com/catalogue/a-light-in-the-attic_1000/index.html")
+ *  const book = await extractObjectFromLocator(page.locator(".page_inner"),
+ *    {
+ *      entityName: "book",
+ *      label: "book-extraction",
+ *      entitySchema: {
+ *        type: "object",
+ *        required: ["name","price","reviews"],
+ *        properties: {
+ *          name: {
+ *            type: "string",
+ *            description: "book name",
+ *          },
+ *          price: {
+ *            type: "string",
+ *            description: "book price"
+ *          },
+ *          reviews: {
+ *            type: "string",
+ *            description: "Number of reviews"
+ *          }
+ *
+ *        }
+ *      }
+ *    },
+ *  )
+ *
+ *  console.log(book)
+ *
+ *  // output:
+ *  // { name: 'A Light in the Attic', price: '£51.77', reviews: '0' }
+ *
+ * ```
+ */
+export declare function extractObjectFromLocator(
+  locator: Locator,
+  options: {
+    label: string;
+    entityName: string;
+    entitySchema: SimpleObjectSchema;
+    strategy?: ImageStrategy | HtmlStrategy;
+    prompt?: string;
+    optionalPropertiesInvalidator?: (
+      result: Record<string, string | null> | null
+    ) => string[];
+    variantKey?: string;
+    apiKey?: string;
+  }
+): Promise<Record<string, string | null> | null>;

package/dist/optimized-extractors/index.js

@@ -0,0 +1,31 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+Object.defineProperty(exports, "extractArrayFromLocator", {
+  enumerable: true,
+  get: function () {
+    return _extractArray.extractArrayFromLocator;
+  }
+});
+Object.defineProperty(exports, "extractArrayFromPage", {
+  enumerable: true,
+  get: function () {
+    return _extractArray.extractArrayFromPage;
+  }
+});
+Object.defineProperty(exports, "extractObjectFromLocator", {
+  enumerable: true,
+  get: function () {
+    return _extractObject.extractObjectFromLocator;
+  }
+});
+Object.defineProperty(exports, "extractObjectFromPage", {
+  enumerable: true,
+  get: function () {
+    return _extractObject.extractObjectFromPage;
+  }
+});
+var _extractArray = require("./extractArray");
+var _extractObject = require("./extractObject");