@spider-cloud/spider-client 0.1.69 → 0.1.71

package/README.md

@@ -45,7 +45,6 @@ app
 const crawlParams = {
   limit: 5,
   proxy_enabled: true,
-  store_data: false,
   metadata: false,
   request: "http",
 };
@@ -73,7 +72,6 @@ const url = "https://spider.cloud";
 // Crawl a website
 const crawlParams = {
   limit: 5,
-  store_data: false,
   metadata: true,
   request: "http",
 };
@@ -140,9 +138,6 @@ spider
 - **`links(url, params)`**: Retrieve all links from the specified URL with optional parameters.
 - **`screenshot(url, params)`**: Take a screenshot of the specified URL.
 - **`transform(data, params)`**: Perform a fast HTML transformation to markdown or text.
-- **`extractContacts(url, params)`**: Extract contact information from the specified URL.
-- **`label(url, params)`**: Apply labeling to data extracted from the specified URL.
-- **`getCrawlState(url, params)`**: Check the website crawl state.
 - **`getCredits()`**: Retrieve account's remaining credits.
 - **`getData(table, params)`**: Retrieve data records from the DB.
 - **`deleteData(table, params)`**: Delete records from the DB.

package/dist/client.d.ts

@@ -89,27 +89,6 @@ export declare class Spider {
         html: string;
         url?: string;
     }[], params?: RequestParamsTransform): Promise<any>;
-    /**
-     * Extracts leads from a website.
-     * @param {string} url - The URL from which to extract contacts.
-     * @param {GenericParams} [params={}] - Configuration parameters for the extraction.
-     * @returns {Promise<any>} The contact information extracted.
-     */
-    extractContacts(url: string, params?: GenericParams): Promise<any>;
-    /**
-     * Applies labeling to data extracted from a specified URL.
-     * @param {string} url - The URL to label.
-     * @param {GenericParams} [params={}] - Configuration parameters for labeling.
-     * @returns {Promise<any>} The labeled data.
-     */
-    label(url: string, params?: GenericParams): Promise<any>;
-    /**
-     * Check the crawl state of the website.
-     * @param {string} url - The URL to check.
-     * @param {GenericParams} [params={}] - Configuration parameters for crawl state. Can also pass in "domain" instead of the url to query.
-     * @returns {Promise<any>} The crawl state data.
-     */
-    getCrawlState(url: string, params?: GenericParams): Promise<any>;
     /**
      * Create a signed url to download files from the storage.
      * @param {string} [domain] - The domain for the user's storage. If not provided, downloads all files.

package/dist/client.js

@@ -153,45 +153,15 @@ class Spider {
      * @param {object} [params={}] - Configuration parameters for the transformation.
      * @returns {Promise<any>} The transformation result.
      */
-    async transform(data, params = { data: [] }) {
+    async transform(data, params) {
         var _a;
         return this._apiPost(config_1.APIRoutes.Transform, {
-            ...params,
-            data: params.data && Array.isArray(params.data) && ((_a = params.data) === null || _a === void 0 ? void 0 : _a.length)
+            ...(params ? params : {}),
+            data: (params === null || params === void 0 ? void 0 : params.data) && Array.isArray(params.data) && ((_a = params.data) === null || _a === void 0 ? void 0 : _a.length)
                 ? params.data
                 : data,
         });
     }
-    /**
-     * Extracts leads from a website.
-     * @param {string} url - The URL from which to extract contacts.
-     * @param {GenericParams} [params={}] - Configuration parameters for the extraction.
-     * @returns {Promise<any>} The contact information extracted.
-     */
-    async extractContacts(url, params = {}) {
-        return this._apiPost(config_1.APIRoutes.PiplineExtractLeads, {
-            url: url,
-            ...params,
-        });
-    }
-    /**
-     * Applies labeling to data extracted from a specified URL.
-     * @param {string} url - The URL to label.
-     * @param {GenericParams} [params={}] - Configuration parameters for labeling.
-     * @returns {Promise<any>} The labeled data.
-     */
-    async label(url, params = {}) {
-        return this._apiPost(config_1.APIRoutes.PiplineLabel, { url: url, ...params });
-    }
-    /**
-     * Check the crawl state of the website.
-     * @param {string} url - The URL to check.
-     * @param {GenericParams} [params={}] - Configuration parameters for crawl state. Can also pass in "domain" instead of the url to query.
-     * @returns {Promise<any>} The crawl state data.
-     */
-    async getCrawlState(url, params = {}) {
-        return this._apiPost(config_1.APIRoutes.DataCrawlState, { url: url, ...params });
-    }
     /**
      * Create a signed url to download files from the storage.
      * @param {string} [domain] - The domain for the user's storage. If not provided, downloads all files.

package/dist/config.d.ts

@@ -271,18 +271,10 @@ export interface SpiderParams {
      * The user agent string to be used for the request.
      */
     user_agent?: string;
-    /**
-     * Specifies whether the response data should be stored.
-     */
-    store_data?: boolean;
     /**
      * Use webhooks to send data.
      */
     webhooks?: WebhookSettings;
-    /**
-     * Configuration settings for GPT (general purpose texture mappings).
-     */
-    gpt_config?: Record<string, any>;
     /**
      * Specifies whether to use fingerprinting protection.
      */
@@ -395,7 +387,7 @@ export interface SpiderParams {
      */
     evaluate_on_new_document?: string;
     /**
-     * Runs the request using lite_mode:Lite mode reduces data transfer costs by 70%, with trade-offs in speed, accuracy,
+     * Runs the request using lite_mode:Lite mode reduces data transfer costs by 50%, with trade-offs in speed, accuracy,
      * geo-targeting, and reliability. It’s best suited for non-urgent data collection or when
      * targeting websites with minimal anti-bot protections.
      */
@@ -421,7 +413,7 @@ export interface SpiderParams {
      */
     proxy?: Proxy;
     /**
-     * Use a remote proxy at ~70% reduced cost for file downloads.
+     * Use a remote proxy at ~50% reduced cost for file downloads.
      * This requires bringing your own proxy (e.g., static IP tunnel).
      */
     remote_proxy?: string;
@@ -504,8 +496,6 @@ export declare enum APIRoutes {
     Screenshot = "screenshot",
     Search = "search",
     Transform = "transform",
-    PiplineExtractLeads = "pipeline/extract-contacts",
-    PiplineLabel = "pipeline/label",
     Data = "data",
     DataCrawlState = "data/crawl_state",
     DataSignUrl = "data/sign-url",

package/dist/config.js

@@ -40,10 +40,6 @@ var APIRoutes;
     APIRoutes["Search"] = "search";
     // Transform HTML to markdown or text.
     APIRoutes["Transform"] = "transform";
-    // Pipeline extract leads for a website - emails, phones, etc.
-    APIRoutes["PiplineExtractLeads"] = "pipeline/extract-contacts";
-    // Pipeline label a website by category using AI and metadata.
-    APIRoutes["PiplineLabel"] = "pipeline/label";
     // Dynamic collection routes.
     APIRoutes["Data"] = "data";
     // The last crawl state of a website.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@spider-cloud/spider-client",
-  "version": "0.1.69",
+  "version": "0.1.71",
   "description": "Isomorphic Javascript SDK for Spider Cloud services",
   "scripts": {
     "test": "node --import tsx  --test __tests__/*test.ts",