@crawlee/puppeteer 3.13.3-beta.9 → 3.13.3

package/internals/enqueue-links/click-elements.d.ts

@@ -12,13 +12,13 @@ export interface EnqueueLinksByClickingElementsOptions {
      */
     requestQueue: RequestProvider;
     /**
-     * A CSS selector matching elements to be clicked on. Unlike in {@apilink enqueueLinks}, there is no default
+     * A CSS selector matching elements to be clicked on. Unlike in {@link enqueueLinks}, there is no default
      * value. This is to prevent suboptimal use of this function by using it too broadly.
      */
     selector: string;
-    /** Sets {@apilink Request.userData} for newly enqueued requests. */
+    /** Sets {@link Request.userData} for newly enqueued requests. */
     userData?: Dictionary;
-    /** Sets {@apilink Request.label} for newly enqueued requests. */
+    /** Sets {@link Request.label} for newly enqueued requests. */
     label?: string;
     /**
      * Click options for use in Puppeteer's click handler.
@@ -29,7 +29,7 @@ export interface EnqueueLinksByClickingElementsOptions {
      * containing glob pattern strings matching the URLs to be enqueued.
      *
      * The plain objects must include at least the `glob` property, which holds the glob pattern string.
-     * All remaining keys will be used as request options for the corresponding enqueued {@apilink Request} objects.
+     * All remaining keys will be used as request options for the corresponding enqueued {@link Request} objects.
      *
      * The matching is always case-insensitive.
      * If you need case-sensitive matching, use `regexps` property directly.
@@ -44,7 +44,7 @@ export interface EnqueueLinksByClickingElementsOptions {
      * containing regular expressions matching the URLs to be enqueued.
      *
      * The plain objects must include at least the `regexp` property, which holds the regular expression.
-     * All remaining keys will be used as request options for the corresponding enqueued {@apilink Request} objects.
+     * All remaining keys will be used as request options for the corresponding enqueued {@link Request} objects.
      *
      * If `regexps` is an empty array or `undefined`, then the function
      * enqueues all the intercepted navigation requests produced by the page
@@ -55,11 +55,11 @@ export interface EnqueueLinksByClickingElementsOptions {
      * *NOTE:* In future versions of SDK the options will be removed.
      * Please use `globs` or `regexps` instead.
      *
-     * An array of {@apilink PseudoUrl} strings or plain objects
-     * containing {@apilink PseudoUrl} strings matching the URLs to be enqueued.
+     * An array of {@link PseudoUrl} strings or plain objects
+     * containing {@link PseudoUrl} strings matching the URLs to be enqueued.
      *
      * The plain objects must include at least the `purl` property, which holds the pseudo-URL pattern string.
-     * All remaining keys will be used as request options for the corresponding enqueued {@apilink Request} objects.
+     * All remaining keys will be used as request options for the corresponding enqueued {@link Request} objects.
      *
      * With a pseudo-URL string, the matching is always case-insensitive.
      * If you need case-sensitive matching, use `regexps` property directly.
@@ -72,7 +72,7 @@ export interface EnqueueLinksByClickingElementsOptions {
      */
     pseudoUrls?: PseudoUrlInput[];
     /**
-     * Just before a new {@apilink Request} is constructed and enqueued to the {@apilink RequestQueue}, this function can be used
+     * Just before a new {@link Request} is constructed and enqueued to the {@link RequestQueue}, this function can be used
      * to remove it or modify its contents such as `userData`, `payload` or, most importantly `uniqueKey`. This is useful
      * when you need to enqueue multiple `Requests` to the queue that share the same URL, but differ in methods or payloads,
      * or to dynamically update or create `userData`.
@@ -120,7 +120,7 @@ export interface EnqueueLinksByClickingElementsOptions {
      * If set to `true`:
      *   - while adding the request to the queue: the request will be added to the foremost position in the queue.
      *   - while reclaiming the request: the request will be placed to the beginning of the queue, so that it's returned
-     *   in the next call to {@apilink RequestQueue.fetchNextRequest}.
+     *   in the next call to {@link RequestQueue.fetchNextRequest}.
      * By default, it's put to the end of the queue.
      * @default false
      */
@@ -136,12 +136,12 @@ export interface EnqueueLinksByClickingElementsOptions {
  * clicks all those elements using a mouse move and a left mouse button click and intercepts
  * all the navigation requests that are subsequently produced by the page. The intercepted
  * requests, including their methods, headers and payloads are then enqueued to a provided
- * {@apilink RequestQueue}. This is useful to crawl JavaScript heavy pages where links are not available
+ * {@link RequestQueue}. This is useful to crawl JavaScript heavy pages where links are not available
  * in `href` elements, but rather navigations are triggered in click handlers.
- * If you're looking to find URLs in `href` attributes of the page, see {@apilink enqueueLinks}.
+ * If you're looking to find URLs in `href` attributes of the page, see {@link enqueueLinks}.
  *
- * Optionally, the function allows you to filter the target links' URLs using an array of {@apilink PseudoUrl} objects
- * and override settings of the enqueued {@apilink Request} objects.
+ * Optionally, the function allows you to filter the target links' URLs using an array of {@link PseudoUrl} objects
+ * and override settings of the enqueued {@link Request} objects.
  *
  * **IMPORTANT**: To be able to do this, this function uses various mutations on the page,
  * such as changing the Z-index of elements being clicked and their visibility. Therefore,
@@ -170,7 +170,7 @@ export interface EnqueueLinksByClickingElementsOptions {
  * });
  * ```
  *
- * @returns Promise that resolves to {@apilink BatchAddRequestsResult} object.
+ * @returns Promise that resolves to {@link BatchAddRequestsResult} object.
  */
 export declare function enqueueLinksByClickingElements(options: EnqueueLinksByClickingElementsOptions): Promise<BatchAddRequestsResult>;
 interface WaitForPageIdleOptions {

package/internals/enqueue-links/click-elements.js

@@ -17,12 +17,12 @@ const log = log_1.default.child({ prefix: 'Puppeteer Click Elements' });
  * clicks all those elements using a mouse move and a left mouse button click and intercepts
  * all the navigation requests that are subsequently produced by the page. The intercepted
  * requests, including their methods, headers and payloads are then enqueued to a provided
- * {@apilink RequestQueue}. This is useful to crawl JavaScript heavy pages where links are not available
+ * {@link RequestQueue}. This is useful to crawl JavaScript heavy pages where links are not available
  * in `href` elements, but rather navigations are triggered in click handlers.
- * If you're looking to find URLs in `href` attributes of the page, see {@apilink enqueueLinks}.
+ * If you're looking to find URLs in `href` attributes of the page, see {@link enqueueLinks}.
  *
- * Optionally, the function allows you to filter the target links' URLs using an array of {@apilink PseudoUrl} objects
- * and override settings of the enqueued {@apilink Request} objects.
+ * Optionally, the function allows you to filter the target links' URLs using an array of {@link PseudoUrl} objects
+ * and override settings of the enqueued {@link Request} objects.
  *
  * **IMPORTANT**: To be able to do this, this function uses various mutations on the page,
  * such as changing the Z-index of elements being clicked and their visibility. Therefore,
@@ -51,7 +51,7 @@ const log = log_1.default.child({ prefix: 'Puppeteer Click Elements' });
  * });
  * ```
  *
- * @returns Promise that resolves to {@apilink BatchAddRequestsResult} object.
+ * @returns Promise that resolves to {@link BatchAddRequestsResult} object.
  */
 async function enqueueLinksByClickingElements(options) {
     (0, ow_1.default)(options, ow_1.default.object.exactShape({

package/internals/puppeteer-crawler.d.ts

@@ -18,7 +18,7 @@ export interface PuppeteerCrawlerOptions extends BrowserCrawlerOptions<Puppeteer
     browserPlugins: [PuppeteerPlugin];
 }> {
     /**
-     * Options used by {@apilink launchPuppeteer} to start new Puppeteer instances.
+     * Options used by {@link launchPuppeteer} to start new Puppeteer instances.
      */
     launchContext?: PuppeteerLaunchContext;
     /**
@@ -36,7 +36,7 @@ export interface PuppeteerCrawlerOptions extends BrowserCrawlerOptions<Puppeteer
      * ```
      *
      * Modyfing `pageOptions` is supported only in Playwright incognito.
-     * See {@apilink PrePageCreateHook}
+     * See {@link PrePageCreateHook}
      */
     preNavigationHooks?: PuppeteerHook[];
     /**
@@ -64,27 +64,27 @@ export interface PuppeteerCrawlerOptions extends BrowserCrawlerOptions<Puppeteer
  *
  * Since `PuppeteerCrawler` uses headless Chrome to download web pages and extract data,
  * it is useful for crawling of websites that require to execute JavaScript.
- * If the target website doesn't need JavaScript, consider using {@apilink CheerioCrawler},
+ * If the target website doesn't need JavaScript, consider using {@link CheerioCrawler},
  * which downloads the pages using raw HTTP requests and is about 10x faster.
  *
- * The source URLs are represented using {@apilink Request} objects that are fed from
- * {@apilink RequestList} or {@apilink RequestQueue} instances provided by the {@apilink PuppeteerCrawlerOptions.requestList}
- * or {@apilink PuppeteerCrawlerOptions.requestQueue} constructor options, respectively.
+ * The source URLs are represented using {@link Request} objects that are fed from
+ * {@link RequestList} or {@link RequestQueue} instances provided by the {@link PuppeteerCrawlerOptions.requestList}
+ * or {@link PuppeteerCrawlerOptions.requestQueue} constructor options, respectively.
  *
- * If both {@apilink PuppeteerCrawlerOptions.requestList} and {@apilink PuppeteerCrawlerOptions.requestQueue} are used,
- * the instance first processes URLs from the {@apilink RequestList} and automatically enqueues all of them
- * to {@apilink RequestQueue} before it starts their processing. This ensures that a single URL is not crawled multiple times.
+ * If both {@link PuppeteerCrawlerOptions.requestList} and {@link PuppeteerCrawlerOptions.requestQueue} are used,
+ * the instance first processes URLs from the {@link RequestList} and automatically enqueues all of them
+ * to {@link RequestQueue} before it starts their processing. This ensures that a single URL is not crawled multiple times.
  *
- * The crawler finishes when there are no more {@apilink Request} objects to crawl.
+ * The crawler finishes when there are no more {@link Request} objects to crawl.
  *
- * `PuppeteerCrawler` opens a new Chrome page (i.e. tab) for each {@apilink Request} object to crawl
- * and then calls the function provided by user as the {@apilink PuppeteerCrawlerOptions.requestHandler} option.
+ * `PuppeteerCrawler` opens a new Chrome page (i.e. tab) for each {@link Request} object to crawl
+ * and then calls the function provided by user as the {@link PuppeteerCrawlerOptions.requestHandler} option.
  *
  * New pages are only opened when there is enough free CPU and memory available,
- * using the functionality provided by the {@apilink AutoscaledPool} class.
- * All {@apilink AutoscaledPool} configuration options can be passed to the {@apilink PuppeteerCrawlerOptions.autoscaledPoolOptions}
+ * using the functionality provided by the {@link AutoscaledPool} class.
+ * All {@link AutoscaledPool} configuration options can be passed to the {@link PuppeteerCrawlerOptions.autoscaledPoolOptions}
  * parameter of the `PuppeteerCrawler` constructor. For user convenience, the `minConcurrency` and `maxConcurrency`
- * {@apilink AutoscaledPoolOptions} are available directly in the `PuppeteerCrawler` constructor.
+ * {@link AutoscaledPoolOptions} are available directly in the `PuppeteerCrawler` constructor.
  *
  * Note that the pool of Puppeteer instances is internally managed by the [BrowserPool](https://github.com/apify/browser-pool) class.
  *
@@ -214,9 +214,9 @@ export declare class PuppeteerCrawler extends BrowserCrawler<{
     protected _navigationHandler(crawlingContext: PuppeteerCrawlingContext, gotoOptions: DirectNavigationOptions): Promise<HTTPResponse | null>;
 }
 /**
- * Creates new {@apilink Router} instance that works based on request labels.
- * This instance can then serve as a `requestHandler` of your {@apilink PuppeteerCrawler}.
- * Defaults to the {@apilink PuppeteerCrawlingContext}.
+ * Creates new {@link Router} instance that works based on request labels.
+ * This instance can then serve as a `requestHandler` of your {@link PuppeteerCrawler}.
+ * Defaults to the {@link PuppeteerCrawlingContext}.
  *
  * > Serves as a shortcut for using `Router.create<PuppeteerCrawlingContext>()`.
  *

package/internals/puppeteer-crawler.js

@@ -15,27 +15,27 @@ const puppeteer_utils_1 = require("./utils/puppeteer_utils");
  *
  * Since `PuppeteerCrawler` uses headless Chrome to download web pages and extract data,
  * it is useful for crawling of websites that require to execute JavaScript.
- * If the target website doesn't need JavaScript, consider using {@apilink CheerioCrawler},
+ * If the target website doesn't need JavaScript, consider using {@link CheerioCrawler},
  * which downloads the pages using raw HTTP requests and is about 10x faster.
  *
- * The source URLs are represented using {@apilink Request} objects that are fed from
- * {@apilink RequestList} or {@apilink RequestQueue} instances provided by the {@apilink PuppeteerCrawlerOptions.requestList}
- * or {@apilink PuppeteerCrawlerOptions.requestQueue} constructor options, respectively.
+ * The source URLs are represented using {@link Request} objects that are fed from
+ * {@link RequestList} or {@link RequestQueue} instances provided by the {@link PuppeteerCrawlerOptions.requestList}
+ * or {@link PuppeteerCrawlerOptions.requestQueue} constructor options, respectively.
  *
- * If both {@apilink PuppeteerCrawlerOptions.requestList} and {@apilink PuppeteerCrawlerOptions.requestQueue} are used,
- * the instance first processes URLs from the {@apilink RequestList} and automatically enqueues all of them
- * to {@apilink RequestQueue} before it starts their processing. This ensures that a single URL is not crawled multiple times.
+ * If both {@link PuppeteerCrawlerOptions.requestList} and {@link PuppeteerCrawlerOptions.requestQueue} are used,
+ * the instance first processes URLs from the {@link RequestList} and automatically enqueues all of them
+ * to {@link RequestQueue} before it starts their processing. This ensures that a single URL is not crawled multiple times.
  *
- * The crawler finishes when there are no more {@apilink Request} objects to crawl.
+ * The crawler finishes when there are no more {@link Request} objects to crawl.
  *
- * `PuppeteerCrawler` opens a new Chrome page (i.e. tab) for each {@apilink Request} object to crawl
- * and then calls the function provided by user as the {@apilink PuppeteerCrawlerOptions.requestHandler} option.
+ * `PuppeteerCrawler` opens a new Chrome page (i.e. tab) for each {@link Request} object to crawl
+ * and then calls the function provided by user as the {@link PuppeteerCrawlerOptions.requestHandler} option.
  *
  * New pages are only opened when there is enough free CPU and memory available,
- * using the functionality provided by the {@apilink AutoscaledPool} class.
- * All {@apilink AutoscaledPool} configuration options can be passed to the {@apilink PuppeteerCrawlerOptions.autoscaledPoolOptions}
+ * using the functionality provided by the {@link AutoscaledPool} class.
+ * All {@link AutoscaledPool} configuration options can be passed to the {@link PuppeteerCrawlerOptions.autoscaledPoolOptions}
  * parameter of the `PuppeteerCrawler` constructor. For user convenience, the `minConcurrency` and `maxConcurrency`
- * {@apilink AutoscaledPoolOptions} are available directly in the `PuppeteerCrawler` constructor.
+ * {@link AutoscaledPoolOptions} are available directly in the `PuppeteerCrawler` constructor.
  *
  * Note that the pool of Puppeteer instances is internally managed by the [BrowserPool](https://github.com/apify/browser-pool) class.
  *
@@ -128,9 +128,9 @@ Object.defineProperty(PuppeteerCrawler, "optionsShape", {
     }
 });
 /**
- * Creates new {@apilink Router} instance that works based on request labels.
- * This instance can then serve as a `requestHandler` of your {@apilink PuppeteerCrawler}.
- * Defaults to the {@apilink PuppeteerCrawlingContext}.
+ * Creates new {@link Router} instance that works based on request labels.
+ * This instance can then serve as a `requestHandler` of your {@link PuppeteerCrawler}.
+ * Defaults to the {@link PuppeteerCrawlingContext}.
  *
  * > Serves as a shortcut for using `Router.create<PuppeteerCrawlingContext>()`.
  *

package/internals/utils/puppeteer_utils.d.ts

@@ -119,7 +119,7 @@ export declare function injectJQuery(page: Page, options?: {
     surviveNavigations?: boolean;
 }): Promise<unknown>;
 /**
- * Returns Cheerio handle for `page.content()`, allowing to work with the data same way as with {@apilink CheerioCrawler}.
+ * Returns Cheerio handle for `page.content()`, allowing to work with the data same way as with {@link CheerioCrawler}.
  *
  * **Example usage:**
  * ```javascript
@@ -211,7 +211,7 @@ export declare function cacheResponses(page: Page, cache: Dictionary<Partial<Res
  * }
  * ```
  * Where `page` is a Puppeteer [`Page`](https://pptr.dev/api/puppeteer.page)
- * and `request` is a {@apilink Request}.
+ * and `request` is a {@link Request}.
  *
  * The function is compiled by using the `scriptString` parameter as the function's body,
  * so any limitations to function bodies apply. Return value of the compiled function
@@ -368,7 +368,7 @@ export interface PuppeteerContextUtils {
      */
     waitForSelector(selector: string, timeoutMs?: number): Promise<void>;
     /**
-     * Returns Cheerio handle for `page.content()`, allowing to work with the data same way as with {@apilink CheerioCrawler}.
+     * Returns Cheerio handle for `page.content()`, allowing to work with the data same way as with {@link CheerioCrawler}.
      * When provided with the `selector` argument, it waits for it to be available first.
      *
      * **Example usage:**
@@ -385,12 +385,12 @@ export interface PuppeteerContextUtils {
      * clicks all those elements using a mouse move and a left mouse button click and intercepts
      * all the navigation requests that are subsequently produced by the page. The intercepted
      * requests, including their methods, headers and payloads are then enqueued to a provided
-     * {@apilink RequestQueue}. This is useful to crawl JavaScript heavy pages where links are not available
+     * {@link RequestQueue}. This is useful to crawl JavaScript heavy pages where links are not available
      * in `href` elements, but rather navigations are triggered in click handlers.
-     * If you're looking to find URLs in `href` attributes of the page, see {@apilink enqueueLinks}.
+     * If you're looking to find URLs in `href` attributes of the page, see {@link enqueueLinks}.
      *
-     * Optionally, the function allows you to filter the target links' URLs using an array of {@apilink PseudoUrl} objects
-     * and override settings of the enqueued {@apilink Request} objects.
+     * Optionally, the function allows you to filter the target links' URLs using an array of {@link PseudoUrl} objects
+     * and override settings of the enqueued {@link Request} objects.
      *
      * **IMPORTANT**: To be able to do this, this function uses various mutations on the page,
      * such as changing the Z-index of elements being clicked and their visibility. Therefore,
@@ -419,7 +419,7 @@ export interface PuppeteerContextUtils {
      * });
      * ```
      *
-     * @returns Promise that resolves to {@apilink BatchAddRequestsResult} object.
+     * @returns Promise that resolves to {@link BatchAddRequestsResult} object.
      */
     enqueueLinksByClickingElements(options: Omit<EnqueueLinksByClickingElementsOptions, 'page' | 'requestQueue'>): Promise<BatchAddRequestsResult>;
     /**
@@ -490,7 +490,7 @@ export interface PuppeteerContextUtils {
      * }
      * ```
      * Where `page` is a Puppeteer [`Page`](https://pptr.dev/api/puppeteer.page)
-     * and `request` is a {@apilink Request}.
+     * and `request` is a {@link Request}.
      *
      * The function is compiled by using the `scriptString` parameter as the function's body,
      * so any limitations to function bodies apply. Return value of the compiled function

package/internals/utils/puppeteer_utils.js

@@ -116,7 +116,7 @@ async function injectJQuery(page, options) {
     return injectFile(page, jqueryPath, { surviveNavigations: options?.surviveNavigations ?? true });
 }
 /**
- * Returns Cheerio handle for `page.content()`, allowing to work with the data same way as with {@apilink CheerioCrawler}.
+ * Returns Cheerio handle for `page.content()`, allowing to work with the data same way as with {@link CheerioCrawler}.
  *
  * **Example usage:**
  * ```javascript
@@ -309,7 +309,7 @@ async function cacheResponses(page, cache, responseUrlRules) {
  * }
  * ```
  * Where `page` is a Puppeteer [`Page`](https://pptr.dev/api/puppeteer.page)
- * and `request` is a {@apilink Request}.
+ * and `request` is a {@link Request}.
  *
  * The function is compiled by using the `scriptString` parameter as the function's body,
  * so any limitations to function bodies apply. Return value of the compiled function

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/puppeteer",
-    "version": "3.13.3-beta.9",
+    "version": "3.13.3",
     "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.",
     "engines": {
         "node": ">=16.0.0"
@@ -55,10 +55,10 @@
     "dependencies": {
         "@apify/datastructures": "^2.0.0",
         "@apify/log": "^2.4.0",
-        "@crawlee/browser": "3.13.3-beta.9",
-        "@crawlee/browser-pool": "3.13.3-beta.9",
-        "@crawlee/types": "3.13.3-beta.9",
-        "@crawlee/utils": "3.13.3-beta.9",
+        "@crawlee/browser": "3.13.3",
+        "@crawlee/browser-pool": "3.13.3",
+        "@crawlee/types": "3.13.3",
+        "@crawlee/utils": "3.13.3",
         "cheerio": "1.0.0-rc.12",
         "devtools-protocol": "*",
         "idcac-playwright": "^0.1.2",
@@ -81,5 +81,5 @@
             }
         }
     },
-    "gitHead": "b15fa18267747df8d3e9ef4dde29e139187ab684"
+    "gitHead": "279cadbd3cd6342f36cc4d841e07b999e472420d"
 }