@spider-cloud/spider-client 0.0.21 → 0.0.22

package/README.md

@@ -95,8 +95,10 @@ spider
 
 - **`scrapeUrl(url, params)`**: Scrape data from a specified URL. Optional parameters can be passed to customize the scraping behavior.
 - **`crawlUrl(url, params, stream)`**: Begin crawling from a specific URL with optional parameters for customization and an optional streaming response.
+- **`search(q, params)`**: Perform a search and gather a list of websites to start crawling and collect resources.
 - **`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.

package/dist/client.d.ts

@@ -64,6 +64,23 @@ export declare class Spider {
      * @returns {Promise<any>} The screenshot data.
      */
     screenshot(url: string, params?: {}): Promise<any>;
+    /**
+     *  Perform a search and gather a list of websites to start crawling and collect resources.
+     * @param {string} search - The search query.
+     * @param {object} [params={}] - Configuration parameters for the search.
+     * @returns {Promise<any>} The result of the crawl, either structured data or a Response object if streaming.
+     */
+    search(q: string, params?: {}): Promise<any>;
+    /**
+     *  Transform HTML to Markdown or text. You can send up to 10MB of data at once.
+     * @param {object} data - The data to trasnform, a list of objects with the key 'html' and optional 'url' key for readability.
+     * @param {object} [params={}] - Configuration parameters for the transformation.
+     * @returns {Promise<any>} The transformation result.
+     */
+    transform(data: {
+        html: string;
+        url?: string;
+    }[], params?: {}): Promise<any>;
     /**
      * Extracts contact information from the specified URL.
      * @param {string} url - The URL from which to extract contacts.

package/dist/client.js

@@ -114,6 +114,24 @@ class Spider {
     async screenshot(url, params = {}) {
         return this._apiPost("screenshot", { url: url, ...params });
     }
+    /**
+     *  Perform a search and gather a list of websites to start crawling and collect resources.
+     * @param {string} search - The search query.
+     * @param {object} [params={}] - Configuration parameters for the search.
+     * @returns {Promise<any>} The result of the crawl, either structured data or a Response object if streaming.
+     */
+    async search(q, params = {}) {
+        return this._apiPost("search", { search: q, ...params });
+    }
+    /**
+     *  Transform HTML to Markdown or text. You can send up to 10MB of data at once.
+     * @param {object} data - The data to trasnform, a list of objects with the key 'html' and optional 'url' key for readability.
+     * @param {object} [params={}] - Configuration parameters for the transformation.
+     * @returns {Promise<any>} The transformation result.
+     */
+    async transform(data, params = {}) {
+        return this._apiPost("transform", { data, ...params });
+    }
     /**
      * Extracts contact information from the specified URL.
      * @param {string} url - The URL from which to extract contacts.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@spider-cloud/spider-client",
-  "version": "0.0.21",
+  "version": "0.0.22",
   "description": "A Javascript SDK for Spider Cloud services",
   "scripts": {
     "test": "jest",