@crawlee/browser 3.13.3-beta.8 → 3.13.3

package/internals/browser-crawler.d.ts

@@ -18,15 +18,15 @@ export interface BrowserCrawlerOptions<Context extends BrowserCrawlingContext =
     /**
      * Function that is called to process each request.
      *
-     * The function receives the {@apilink BrowserCrawlingContext}
+     * The function receives the {@link BrowserCrawlingContext}
      * (actual context will be enhanced with the crawler specific properties) as an argument, where:
-     * - {@apilink BrowserCrawlingContext.request|`request`} is an instance of the {@apilink Request} object
+     * - {@link BrowserCrawlingContext.request|`request`} is an instance of the {@link Request} object
      * with details about the URL to open, HTTP method etc;
-     * - {@apilink BrowserCrawlingContext.page|`page`} is an instance of the
+     * - {@link BrowserCrawlingContext.page|`page`} is an instance of the
      * Puppeteer [Page](https://pptr.dev/api/puppeteer.page) or
      * Playwright [Page](https://playwright.dev/docs/api/class-page);
-     * - {@apilink BrowserCrawlingContext.browserController|`browserController`} is an instance of the {@apilink BrowserController};
-     * - {@apilink BrowserCrawlingContext.response|`response`} is an instance of the
+     * - {@link BrowserCrawlingContext.browserController|`browserController`} is an instance of the {@link BrowserController};
+     * - {@link BrowserCrawlingContext.response|`response`} is an instance of the
      * Puppeteer [Response](https://pptr.dev/api/puppeteer.httpresponse) or
      * Playwright [Response](https://playwright.dev/docs/api/class-response),
      * which is the main resource response as returned by the respective `page.goto()` function.
@@ -34,27 +34,27 @@ export interface BrowserCrawlerOptions<Context extends BrowserCrawlingContext =
      * The function must return a promise, which is then awaited by the crawler.
      *
      * If the function throws an exception, the crawler will try to re-crawl the
-     * request later, up to the {@apilink BrowserCrawlerOptions.maxRequestRetries|`maxRequestRetries`} times.
+     * request later, up to the {@link BrowserCrawlerOptions.maxRequestRetries|`maxRequestRetries`} times.
      * If all the retries fail, the crawler calls the function
-     * provided to the {@apilink BrowserCrawlerOptions.failedRequestHandler|`failedRequestHandler`} parameter.
+     * provided to the {@link BrowserCrawlerOptions.failedRequestHandler|`failedRequestHandler`} parameter.
      * To make this work, we should **always**
      * let our function throw exceptions rather than catch them.
      * The exceptions are logged to the request using the
-     * {@apilink Request.pushErrorMessage|`Request.pushErrorMessage()`} function.
+     * {@link Request.pushErrorMessage|`Request.pushErrorMessage()`} function.
      */
     requestHandler?: BrowserRequestHandler<LoadedContext<Context>>;
     /**
      * Function that is called to process each request.
      *
-     * The function receives the {@apilink BrowserCrawlingContext}
+     * The function receives the {@link BrowserCrawlingContext}
      * (actual context will be enhanced with the crawler specific properties) as an argument, where:
-     * - {@apilink BrowserCrawlingContext.request|`request`} is an instance of the {@apilink Request} object
+     * - {@link BrowserCrawlingContext.request|`request`} is an instance of the {@link Request} object
      * with details about the URL to open, HTTP method etc;
-     * - {@apilink BrowserCrawlingContext.page|`page`} is an instance of the
+     * - {@link BrowserCrawlingContext.page|`page`} is an instance of the
      * Puppeteer [Page](https://pptr.dev/api/puppeteer.page) or
      * Playwright [Page](https://playwright.dev/docs/api/class-page);
-     * - {@apilink BrowserCrawlingContext.browserController|`browserController`} is an instance of the {@apilink BrowserController};
-     * - {@apilink BrowserCrawlingContext.response|`response`} is an instance of the
+     * - {@link BrowserCrawlingContext.browserController|`browserController`} is an instance of the {@link BrowserController};
+     * - {@link BrowserCrawlingContext.response|`response`} is an instance of the
      * Puppeteer [Response](https://pptr.dev/api/puppeteer.httpresponse) or
      * Playwright [Response](https://playwright.dev/docs/api/class-response),
      * which is the main resource response as returned by the respective `page.goto()` function.
@@ -62,13 +62,13 @@ export interface BrowserCrawlerOptions<Context extends BrowserCrawlingContext =
      * The function must return a promise, which is then awaited by the crawler.
      *
      * If the function throws an exception, the crawler will try to re-crawl the
-     * request later, up to the {@apilink BrowserCrawlerOptions.maxRequestRetries|`maxRequestRetries`} times.
+     * request later, up to the {@link BrowserCrawlerOptions.maxRequestRetries|`maxRequestRetries`} times.
      * If all the retries fail, the crawler calls the function
-     * provided to the {@apilink BrowserCrawlerOptions.failedRequestHandler|`failedRequestHandler`} parameter.
+     * provided to the {@link BrowserCrawlerOptions.failedRequestHandler|`failedRequestHandler`} parameter.
      * To make this work, we should **always**
      * let our function throw exceptions rather than catch them.
      * The exceptions are logged to the request using the
-     * {@apilink Request.pushErrorMessage|`Request.pushErrorMessage()`} function.
+     * {@link Request.pushErrorMessage|`Request.pushErrorMessage()`} function.
      *
      * @deprecated `handlePageFunction` has been renamed to `requestHandler` and will be removed in a future version.
      * @ignore
@@ -76,11 +76,11 @@ export interface BrowserCrawlerOptions<Context extends BrowserCrawlingContext =
     handlePageFunction?: BrowserRequestHandler<LoadedContext<Context>>;
     /**
      * User-provided function that allows modifying the request object before it gets retried by the crawler.
-     * It's executed before each retry for the requests that failed less than {@apilink BrowserCrawlerOptions.maxRequestRetries|`maxRequestRetries`} times.
+     * It's executed before each retry for the requests that failed less than {@link BrowserCrawlerOptions.maxRequestRetries|`maxRequestRetries`} times.
      *
-     * The function receives the {@apilink BrowserCrawlingContext}
+     * The function receives the {@link BrowserCrawlingContext}
      * (actual context will be enhanced with the crawler specific properties) as the first argument,
-     * where the {@apilink BrowserCrawlingContext.request|`request`} corresponds to the request to be retried.
+     * where the {@link BrowserCrawlingContext.request|`request`} corresponds to the request to be retried.
      * Second argument is the `Error` instance that
      * represents the last error thrown during processing of the request.
      */
@@ -88,9 +88,9 @@ export interface BrowserCrawlerOptions<Context extends BrowserCrawlingContext =
     /**
      * A function to handle requests that failed more than `option.maxRequestRetries` times.
      *
-     * The function receives the {@apilink BrowserCrawlingContext}
+     * The function receives the {@link BrowserCrawlingContext}
      * (actual context will be enhanced with the crawler specific properties) as the first argument,
-     * where the {@apilink BrowserCrawlingContext.request|`request`} corresponds to the failed request.
+     * where the {@link BrowserCrawlingContext.request|`request`} corresponds to the failed request.
      * Second argument is the `Error` instance that
      * represents the last error thrown during processing of the request.
      */
@@ -98,9 +98,9 @@ export interface BrowserCrawlerOptions<Context extends BrowserCrawlingContext =
     /**
      * A function to handle requests that failed more than `option.maxRequestRetries` times.
      *
-     * The function receives the {@apilink BrowserCrawlingContext}
+     * The function receives the {@link BrowserCrawlingContext}
      * (actual context will be enhanced with the crawler specific properties) as the first argument,
-     * where the {@apilink BrowserCrawlingContext.request|`request`} corresponds to the failed request.
+     * where the {@link BrowserCrawlingContext.request|`request`} corresponds to the failed request.
      * Second argument is the `Error` instance that
      * represents the last error thrown during processing of the request.
      *
@@ -109,7 +109,7 @@ export interface BrowserCrawlerOptions<Context extends BrowserCrawlingContext =
      */
     handleFailedRequestFunction?: BrowserErrorHandler<Context>;
     /**
-     * Custom options passed to the underlying {@apilink BrowserPool} constructor.
+     * Custom options passed to the underlying {@link BrowserPool} constructor.
      * We can tweak those to fine-tune browser management.
      */
     browserPoolOptions?: Partial<BrowserPoolOptions> & Partial<BrowserPoolHooks<__BrowserControllerReturn, __LaunchContextReturn>>;
@@ -137,7 +137,7 @@ export interface BrowserCrawlerOptions<Context extends BrowserCrawlingContext =
      * ```
      *
      * Modyfing `pageOptions` is supported only in Playwright incognito.
-     * See {@apilink PrePageCreateHook}
+     * See {@link PrePageCreateHook}
      */
     preNavigationHooks?: BrowserHook<Context>[];
     /**
@@ -169,7 +169,7 @@ export interface BrowserCrawlerOptions<Context extends BrowserCrawlingContext =
     persistCookiesPerSession?: boolean;
     /**
      * Whether to run browser in headless mode. Defaults to `true`.
-     * Can be also set via {@apilink Configuration}.
+     * Can be also set via {@link Configuration}.
      */
     headless?: boolean | 'new' | 'old';
     /**
@@ -192,45 +192,45 @@ export interface BrowserCrawlerOptions<Context extends BrowserCrawlingContext =
  *
  * Since `BrowserCrawler` uses headless (or even headful) browsers 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, we should consider using the {@apilink CheerioCrawler},
+ * If the target website doesn't need JavaScript, we should consider using the {@link CheerioCrawler},
  * which downloads the pages using raw HTTP requests and is about 10x faster.
  *
- * The source URLs are represented by the {@apilink Request} objects that are fed from the {@apilink RequestList} or {@apilink RequestQueue} instances
- * provided by the {@apilink BrowserCrawlerOptions.requestList|`requestList`} or {@apilink BrowserCrawlerOptions.requestQueue|`requestQueue`}
+ * The source URLs are represented by the {@link Request} objects that are fed from the {@link RequestList} or {@link RequestQueue} instances
+ * provided by the {@link BrowserCrawlerOptions.requestList|`requestList`} or {@link BrowserCrawlerOptions.requestQueue|`requestQueue`}
  * constructor options, respectively. If neither `requestList` nor `requestQueue` options are provided,
- * the crawler will open the default request queue either when the {@apilink BrowserCrawler.addRequests|`crawler.addRequests()`} function is called,
- * or if `requests` parameter (representing the initial requests) of the {@apilink BrowserCrawler.run|`crawler.run()`} function is provided.
+ * the crawler will open the default request queue either when the {@link BrowserCrawler.addRequests|`crawler.addRequests()`} function is called,
+ * or if `requests` parameter (representing the initial requests) of the {@link BrowserCrawler.run|`crawler.run()`} function is provided.
  *
- * If both {@apilink BrowserCrawlerOptions.requestList|`requestList`} and {@apilink BrowserCrawlerOptions.requestQueue|`requestQueue`} options are used,
- * the instance first processes URLs from the {@apilink RequestList} and automatically enqueues all of them
- * to the {@apilink RequestQueue} before it starts their processing. This ensures that a single URL is not crawled multiple times.
+ * If both {@link BrowserCrawlerOptions.requestList|`requestList`} and {@link BrowserCrawlerOptions.requestQueue|`requestQueue`} options are used,
+ * the instance first processes URLs from the {@link RequestList} and automatically enqueues all of them
+ * to the {@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.
  *
- * `BrowserCrawler` opens a new browser page (i.e. tab or window) for each {@apilink Request} object to crawl
- * and then calls the function provided by user as the {@apilink BrowserCrawlerOptions.requestHandler|`requestHandler`} option.
+ * `BrowserCrawler` opens a new browser page (i.e. tab or window) for each {@link Request} object to crawl
+ * and then calls the function provided by user as the {@link BrowserCrawlerOptions.requestHandler|`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 BrowserCrawlerOptions.autoscaledPoolOptions|`autoscaledPoolOptions`}
+ * using the functionality provided by the {@link AutoscaledPool} class.
+ * All {@link AutoscaledPool} configuration options can be passed to the {@link BrowserCrawlerOptions.autoscaledPoolOptions|`autoscaledPoolOptions`}
  * parameter of the `BrowserCrawler` constructor.
- * For user convenience, the {@apilink AutoscaledPoolOptions.minConcurrency|`minConcurrency`} and
- * {@apilink AutoscaledPoolOptions.maxConcurrency|`maxConcurrency`} options of the
- * underlying {@apilink AutoscaledPool} constructor are available directly in the `BrowserCrawler` constructor.
+ * For user convenience, the {@link AutoscaledPoolOptions.minConcurrency|`minConcurrency`} and
+ * {@link AutoscaledPoolOptions.maxConcurrency|`maxConcurrency`} options of the
+ * underlying {@link AutoscaledPool} constructor are available directly in the `BrowserCrawler` constructor.
  *
- * > *NOTE:* the pool of browser instances is internally managed by the {@apilink BrowserPool} class.
+ * > *NOTE:* the pool of browser instances is internally managed by the {@link BrowserPool} class.
  *
  * @category Crawlers
  */
 export declare abstract class BrowserCrawler<InternalBrowserPoolOptions extends BrowserPoolOptions = BrowserPoolOptions, LaunchOptions extends Dictionary | undefined = Dictionary, Context extends BrowserCrawlingContext = BrowserCrawlingContext, GoToOptions extends Dictionary = Dictionary> extends BasicCrawler<Context> {
     readonly config: Configuration;
     /**
-     * A reference to the underlying {@apilink ProxyConfiguration} class that manages the crawler's proxies.
+     * A reference to the underlying {@link ProxyConfiguration} class that manages the crawler's proxies.
      * Only available if used by the crawler.
      */
     proxyConfiguration?: ProxyConfiguration;
     /**
-     * A reference to the underlying {@apilink BrowserPool} class that manages the crawler's browsers.
+     * A reference to the underlying {@link BrowserPool} class that manages the crawler's browsers.
      */
     browserPool: BrowserPool<InternalBrowserPoolOptions>;
     launchContext: BrowserLaunchContext<LaunchOptions, unknown>;

package/internals/browser-crawler.js

@@ -18,33 +18,33 @@ const timeout_1 = require("@apify/timeout");
  *
  * Since `BrowserCrawler` uses headless (or even headful) browsers 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, we should consider using the {@apilink CheerioCrawler},
+ * If the target website doesn't need JavaScript, we should consider using the {@link CheerioCrawler},
  * which downloads the pages using raw HTTP requests and is about 10x faster.
  *
- * The source URLs are represented by the {@apilink Request} objects that are fed from the {@apilink RequestList} or {@apilink RequestQueue} instances
- * provided by the {@apilink BrowserCrawlerOptions.requestList|`requestList`} or {@apilink BrowserCrawlerOptions.requestQueue|`requestQueue`}
+ * The source URLs are represented by the {@link Request} objects that are fed from the {@link RequestList} or {@link RequestQueue} instances
+ * provided by the {@link BrowserCrawlerOptions.requestList|`requestList`} or {@link BrowserCrawlerOptions.requestQueue|`requestQueue`}
  * constructor options, respectively. If neither `requestList` nor `requestQueue` options are provided,
- * the crawler will open the default request queue either when the {@apilink BrowserCrawler.addRequests|`crawler.addRequests()`} function is called,
- * or if `requests` parameter (representing the initial requests) of the {@apilink BrowserCrawler.run|`crawler.run()`} function is provided.
+ * the crawler will open the default request queue either when the {@link BrowserCrawler.addRequests|`crawler.addRequests()`} function is called,
+ * or if `requests` parameter (representing the initial requests) of the {@link BrowserCrawler.run|`crawler.run()`} function is provided.
  *
- * If both {@apilink BrowserCrawlerOptions.requestList|`requestList`} and {@apilink BrowserCrawlerOptions.requestQueue|`requestQueue`} options are used,
- * the instance first processes URLs from the {@apilink RequestList} and automatically enqueues all of them
- * to the {@apilink RequestQueue} before it starts their processing. This ensures that a single URL is not crawled multiple times.
+ * If both {@link BrowserCrawlerOptions.requestList|`requestList`} and {@link BrowserCrawlerOptions.requestQueue|`requestQueue`} options are used,
+ * the instance first processes URLs from the {@link RequestList} and automatically enqueues all of them
+ * to the {@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.
  *
- * `BrowserCrawler` opens a new browser page (i.e. tab or window) for each {@apilink Request} object to crawl
- * and then calls the function provided by user as the {@apilink BrowserCrawlerOptions.requestHandler|`requestHandler`} option.
+ * `BrowserCrawler` opens a new browser page (i.e. tab or window) for each {@link Request} object to crawl
+ * and then calls the function provided by user as the {@link BrowserCrawlerOptions.requestHandler|`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 BrowserCrawlerOptions.autoscaledPoolOptions|`autoscaledPoolOptions`}
+ * using the functionality provided by the {@link AutoscaledPool} class.
+ * All {@link AutoscaledPool} configuration options can be passed to the {@link BrowserCrawlerOptions.autoscaledPoolOptions|`autoscaledPoolOptions`}
  * parameter of the `BrowserCrawler` constructor.
- * For user convenience, the {@apilink AutoscaledPoolOptions.minConcurrency|`minConcurrency`} and
- * {@apilink AutoscaledPoolOptions.maxConcurrency|`maxConcurrency`} options of the
- * underlying {@apilink AutoscaledPool} constructor are available directly in the `BrowserCrawler` constructor.
+ * For user convenience, the {@link AutoscaledPoolOptions.minConcurrency|`minConcurrency`} and
+ * {@link AutoscaledPoolOptions.maxConcurrency|`maxConcurrency`} options of the
+ * underlying {@link AutoscaledPool} constructor are available directly in the `BrowserCrawler` constructor.
  *
- * > *NOTE:* the pool of browser instances is internally managed by the {@apilink BrowserPool} class.
+ * > *NOTE:* the pool of browser instances is internally managed by the {@link BrowserPool} class.
  *
  * @category Crawlers
  */
@@ -70,7 +70,7 @@ class BrowserCrawler extends basic_1.BasicCrawler {
             value: config
         });
         /**
-         * A reference to the underlying {@apilink ProxyConfiguration} class that manages the crawler's proxies.
+         * A reference to the underlying {@link ProxyConfiguration} class that manages the crawler's proxies.
          * Only available if used by the crawler.
          */
         Object.defineProperty(this, "proxyConfiguration", {
@@ -80,7 +80,7 @@ class BrowserCrawler extends basic_1.BasicCrawler {
             value: void 0
         });
         /**
-         * A reference to the underlying {@apilink BrowserPool} class that manages the crawler's browsers.
+         * A reference to the underlying {@link BrowserPool} class that manages the crawler's browsers.
          */
         Object.defineProperty(this, "browserPool", {
             enumerable: true,

package/internals/browser-launcher.d.ts

@@ -11,7 +11,7 @@ export interface BrowserLaunchContext<TOptions, Launcher> extends BrowserPluginO
      */
     proxyUrl?: string;
     /**
-     * If `true` and the `executablePath` option of {@apilink BrowserLaunchContext.launchOptions|`launchOptions`} is not set,
+     * If `true` and the `executablePath` option of {@link BrowserLaunchContext.launchOptions|`launchOptions`} is not set,
      * the launcher will launch full Google Chrome browser available on the machine
      * rather than the bundled Chromium. The path to Chrome executable
      * is taken from the `CRAWLEE_CHROME_EXECUTABLE_PATH` environment variable if provided,

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/browser",
-    "version": "3.13.3-beta.8",
+    "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"
@@ -54,10 +54,10 @@
     },
     "dependencies": {
         "@apify/timeout": "^0.3.0",
-        "@crawlee/basic": "3.13.3-beta.8",
-        "@crawlee/browser-pool": "3.13.3-beta.8",
-        "@crawlee/types": "3.13.3-beta.8",
-        "@crawlee/utils": "3.13.3-beta.8",
+        "@crawlee/basic": "3.13.3",
+        "@crawlee/browser-pool": "3.13.3",
+        "@crawlee/types": "3.13.3",
+        "@crawlee/utils": "3.13.3",
         "ow": "^0.28.1",
         "tslib": "^2.4.0",
         "type-fest": "^4.0.0"
@@ -81,5 +81,5 @@
             }
         }
     },
-    "gitHead": "0bcd58dd82d533da05a2bd7a524624fa441e7a71"
+    "gitHead": "279cadbd3cd6342f36cc4d841e07b999e472420d"
 }