@crawlee/jsdom 3.13.3-beta.12 → 3.13.3-beta.14

package/internals/jsdom-crawler.d.ts

@@ -39,7 +39,7 @@ JSONData extends Dictionary = any> extends InternalHttpCrawlingContext<UserData,
      */
     waitForSelector(selector: string, timeoutMs?: number): Promise<void>;
     /**
-     * Returns Cheerio handle, allowing to work with the data same way as with {@apilink CheerioCrawler}.
+     * Returns Cheerio handle, allowing to work with the data same way as with {@link CheerioCrawler}.
      * When provided with the `selector` argument, it will first look for the selector with a 5s timeout.
      *
      * **Example usage:**
@@ -186,9 +186,9 @@ interface EnqueueLinksInternalOptions {
 // @ts-ignore optional peer dependency or compatibility with es2022
 export declare function domCrawlerEnqueueLinks({ options, window, requestQueue, robotsTxtFile, onSkippedRequest, originalRequestUrl, finalRequestUrl, }: EnqueueLinksInternalOptions): Promise<import("@crawlee/types").BatchAddRequestsResult>;
 /**
- * Creates new {@apilink Router} instance that works based on request labels.
- * This instance can then serve as a `requestHandler` of your {@apilink JSDOMCrawler}.
- * Defaults to the {@apilink JSDOMCrawlingContext}.
+ * Creates new {@link Router} instance that works based on request labels.
+ * This instance can then serve as a `requestHandler` of your {@link JSDOMCrawler}.
+ * Defaults to the {@link JSDOMCrawlingContext}.
  *
  * > Serves as a shortcut for using `Router.create<JSDOMCrawlingContext>()`.
  *

package/internals/jsdom-crawler.js

@@ -19,10 +19,10 @@ const utilities_1 = require("@apify/utilities");
  *
  * Since `JSDOMCrawler` uses raw HTTP requests to download web pages,
  * it is very fast and efficient on data bandwidth. However, if the target website requires JavaScript
- * to display the content, you might need to use {@apilink PuppeteerCrawler} or {@apilink PlaywrightCrawler} instead,
+ * to display the content, you might need to use {@link PuppeteerCrawler} or {@link PlaywrightCrawler} instead,
  * because it loads the pages using full-featured headless Chrome browser.
  *
- * Alternatively, you can use {@apilink JSDOMCrawlerOptions.runScripts} to run website scripts in Node.
+ * Alternatively, you can use {@link JSDOMCrawlerOptions.runScripts} to run website scripts in Node.
  * JSDOM does not implement all the standards, so websites can break.
  *
  * **Limitation**:
@@ -30,18 +30,18 @@ const utilities_1 = require("@apify/utilities");
  *
  * `JSDOMCrawler` downloads each URL using a plain HTTP request,
  * parses the HTML content using [JSDOM](https://www.npmjs.com/package/jsdom)
- * and then invokes the user-provided {@apilink JSDOMCrawlerOptions.requestHandler} to extract page data
+ * and then invokes the user-provided {@link JSDOMCrawlerOptions.requestHandler} to extract page data
  * using the `window` object.
  *
- * The source URLs are represented using {@apilink Request} objects that are fed from
- * {@apilink RequestList} or {@apilink RequestQueue} instances provided by the {@apilink JSDOMCrawlerOptions.requestList}
- * or {@apilink JSDOMCrawlerOptions.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 JSDOMCrawlerOptions.requestList}
+ * or {@link JSDOMCrawlerOptions.requestQueue} constructor options, respectively.
  *
- * If both {@apilink JSDOMCrawlerOptions.requestList} and {@apilink JSDOMCrawlerOptions.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 JSDOMCrawlerOptions.requestList} and {@link JSDOMCrawlerOptions.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.
  *
  * We can use the `preNavigationHooks` to adjust `gotOptions`:
  *
@@ -56,15 +56,15 @@ const utilities_1 = require("@apify/utilities");
  * By default, `JSDOMCrawler` only processes web pages with the `text/html`
  * and `application/xhtml+xml` MIME content types (as reported by the `Content-Type` HTTP header),
  * and skips pages with other content types. If you want the crawler to process other content types,
- * use the {@apilink JSDOMCrawlerOptions.additionalMimeTypes} constructor option.
+ * use the {@link JSDOMCrawlerOptions.additionalMimeTypes} constructor option.
  * Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.
- * For more details, see {@apilink JSDOMCrawlerOptions.requestHandler}.
+ * For more details, see {@link JSDOMCrawlerOptions.requestHandler}.
  *
  * New requests are only dispatched 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 `autoscaledPoolOptions`
+ * using the functionality provided by the {@link AutoscaledPool} class.
+ * All {@link AutoscaledPool} configuration options can be passed to the `autoscaledPoolOptions`
  * parameter of the `CheerioCrawler` constructor. For user convenience, the `minConcurrency` and `maxConcurrency`
- * {@apilink AutoscaledPool} options are available directly in the `CheerioCrawler` constructor.
+ * {@link AutoscaledPool} options are available directly in the `CheerioCrawler` constructor.
  *
  * **Example usage:**
  *
@@ -285,9 +285,9 @@ function extractUrlsFromWindow(window, selector, baseUrl) {
         .filter((href) => href !== undefined && href !== '');
 }
 /**
- * Creates new {@apilink Router} instance that works based on request labels.
- * This instance can then serve as a `requestHandler` of your {@apilink JSDOMCrawler}.
- * Defaults to the {@apilink JSDOMCrawlingContext}.
+ * Creates new {@link Router} instance that works based on request labels.
+ * This instance can then serve as a `requestHandler` of your {@link JSDOMCrawler}.
+ * Defaults to the {@link JSDOMCrawlingContext}.
  *
  * > Serves as a shortcut for using `Router.create<JSDOMCrawlingContext>()`.
  *

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/jsdom",
-    "version": "3.13.3-beta.12",
+    "version": "3.13.3-beta.14",
     "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"
@@ -55,9 +55,9 @@
     "dependencies": {
         "@apify/timeout": "^0.3.0",
         "@apify/utilities": "^2.7.10",
-        "@crawlee/http": "3.13.3-beta.12",
-        "@crawlee/types": "3.13.3-beta.12",
-        "@crawlee/utils": "3.13.3-beta.12",
+        "@crawlee/http": "3.13.3-beta.14",
+        "@crawlee/types": "3.13.3-beta.14",
+        "@crawlee/utils": "3.13.3-beta.14",
         "@types/jsdom": "^21.0.0",
         "cheerio": "1.0.0-rc.12",
         "jsdom": "^26.0.0",
@@ -71,5 +71,5 @@
             }
         }
     },
-    "gitHead": "fac14d5b8671e2984cff9dddb6031f6ed5b1a372"
+    "gitHead": "d674153898c9175c06767a98121892d0b6fd86ff"
 }