@crawlee/cheerio 3.13.3-beta.8 → 3.13.3

package/internals/cheerio-crawler.d.ts

@@ -57,23 +57,23 @@ JSONData extends Dictionary = any> = RequestHandler<CheerioCrawlingContext<UserD
  *
  * Since `CheerioCrawler` 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.
  *
  * `CheerioCrawler` downloads each URL using a plain HTTP request,
  * parses the HTML content using [Cheerio](https://www.npmjs.com/package/cheerio)
- * and then invokes the user-provided {@apilink CheerioCrawlerOptions.requestHandler} to extract page data
+ * and then invokes the user-provided {@link CheerioCrawlerOptions.requestHandler} to extract page data
  * using a [jQuery](https://jquery.com/)-like interface to the parsed HTML DOM.
  *
- * The source URLs are represented using {@apilink Request} objects that are fed from
- * {@apilink RequestList} or {@apilink RequestQueue} instances provided by the {@apilink CheerioCrawlerOptions.requestList}
- * or {@apilink CheerioCrawlerOptions.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 CheerioCrawlerOptions.requestList}
+ * or {@link CheerioCrawlerOptions.requestQueue} constructor options, respectively.
  *
- * If both {@apilink CheerioCrawlerOptions.requestList} and {@apilink CheerioCrawlerOptions.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 CheerioCrawlerOptions.requestList} and {@link CheerioCrawlerOptions.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`:
  *
@@ -88,15 +88,15 @@ JSONData extends Dictionary = any> = RequestHandler<CheerioCrawlingContext<UserD
  * By default, `CheerioCrawler` 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 CheerioCrawlerOptions.additionalMimeTypes} constructor option.
+ * use the {@link CheerioCrawlerOptions.additionalMimeTypes} constructor option.
  * Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.
- * For more details, see {@apilink CheerioCrawlerOptions.requestHandler}.
+ * For more details, see {@link CheerioCrawlerOptions.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:**
  *
@@ -154,9 +154,9 @@ interface EnqueueLinksInternalOptions {
 // @ts-ignore optional peer dependency or compatibility with es2022
 export declare function cheerioCrawlerEnqueueLinks({ options, $, 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 CheerioCrawler}.
- * Defaults to the {@apilink CheerioCrawlingContext}.
+ * Creates new {@link Router} instance that works based on request labels.
+ * This instance can then serve as a `requestHandler` of your {@link CheerioCrawler}.
+ * Defaults to the {@link CheerioCrawlingContext}.
  *
  * > Serves as a shortcut for using `Router.create<CheerioCrawlingContext>()`.
  *

package/internals/cheerio-crawler.js

@@ -18,23 +18,23 @@ const WritableStream_1 = require("htmlparser2/lib/WritableStream");
  *
  * Since `CheerioCrawler` 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.
  *
  * `CheerioCrawler` downloads each URL using a plain HTTP request,
  * parses the HTML content using [Cheerio](https://www.npmjs.com/package/cheerio)
- * and then invokes the user-provided {@apilink CheerioCrawlerOptions.requestHandler} to extract page data
+ * and then invokes the user-provided {@link CheerioCrawlerOptions.requestHandler} to extract page data
  * using a [jQuery](https://jquery.com/)-like interface to the parsed HTML DOM.
  *
- * The source URLs are represented using {@apilink Request} objects that are fed from
- * {@apilink RequestList} or {@apilink RequestQueue} instances provided by the {@apilink CheerioCrawlerOptions.requestList}
- * or {@apilink CheerioCrawlerOptions.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 CheerioCrawlerOptions.requestList}
+ * or {@link CheerioCrawlerOptions.requestQueue} constructor options, respectively.
  *
- * If both {@apilink CheerioCrawlerOptions.requestList} and {@apilink CheerioCrawlerOptions.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 CheerioCrawlerOptions.requestList} and {@link CheerioCrawlerOptions.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`:
  *
@@ -49,15 +49,15 @@ const WritableStream_1 = require("htmlparser2/lib/WritableStream");
  * By default, `CheerioCrawler` 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 CheerioCrawlerOptions.additionalMimeTypes} constructor option.
+ * use the {@link CheerioCrawlerOptions.additionalMimeTypes} constructor option.
  * Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.
- * For more details, see {@apilink CheerioCrawlerOptions.requestHandler}.
+ * For more details, see {@link CheerioCrawlerOptions.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:**
  *
@@ -174,9 +174,9 @@ async function cheerioCrawlerEnqueueLinks({ options, $, requestQueue, robotsTxtF
     });
 }
 /**
- * Creates new {@apilink Router} instance that works based on request labels.
- * This instance can then serve as a `requestHandler` of your {@apilink CheerioCrawler}.
- * Defaults to the {@apilink CheerioCrawlingContext}.
+ * Creates new {@link Router} instance that works based on request labels.
+ * This instance can then serve as a `requestHandler` of your {@link CheerioCrawler}.
+ * Defaults to the {@link CheerioCrawlingContext}.
  *
  * > Serves as a shortcut for using `Router.create<CheerioCrawlingContext>()`.
  *

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/cheerio",
-    "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"
@@ -53,9 +53,9 @@
         "access": "public"
     },
     "dependencies": {
-        "@crawlee/http": "3.13.3-beta.8",
-        "@crawlee/types": "3.13.3-beta.8",
-        "@crawlee/utils": "3.13.3-beta.8",
+        "@crawlee/http": "3.13.3",
+        "@crawlee/types": "3.13.3",
+        "@crawlee/utils": "3.13.3",
         "cheerio": "1.0.0-rc.12",
         "htmlparser2": "^9.0.0",
         "tslib": "^2.4.0"
@@ -67,5 +67,5 @@
             }
         }
     },
-    "gitHead": "0bcd58dd82d533da05a2bd7a524624fa441e7a71"
+    "gitHead": "279cadbd3cd6342f36cc4d841e07b999e472420d"
 }