@crawlee/http 3.13.3-beta.9 → 3.13.3

package/internals/file-download.d.ts

@@ -29,15 +29,15 @@ JSONData extends Dictionary = any> = RequestHandler<FileDownloadCrawlingContext<
  *
  * Since `FileDownload` uses raw HTTP requests to download the files, it is very fast and bandwidth-efficient.
  * However, it doesn't parse the content - if you need to e.g. extract data from the downloaded files,
- * you might need to use {@apilink CheerioCrawler}, {@apilink PuppeteerCrawler} or {@apilink PlaywrightCrawler} instead.
+ * you might need to use {@link CheerioCrawler}, {@link PuppeteerCrawler} or {@link PlaywrightCrawler} instead.
  *
- * `FileCrawler` downloads each URL using a plain HTTP request and then invokes the user-provided {@apilink FileDownloadOptions.requestHandler} where the user can specify what to do with the downloaded data.
+ * `FileCrawler` downloads each URL using a plain HTTP request and then invokes the user-provided {@link FileDownloadOptions.requestHandler} where the user can specify what to do with the downloaded data.
  *
- * The source URLs are represented using {@apilink Request} objects that are fed from {@apilink RequestList} or {@apilink RequestQueue} instances provided by the {@apilink FileDownloadOptions.requestList} or {@apilink FileDownloadOptions.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 FileDownloadOptions.requestList} or {@link FileDownloadOptions.requestQueue} constructor options, respectively.
  *
- * If both {@apilink FileDownloadOptions.requestList} and {@apilink FileDownloadOptions.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 FileDownloadOptions.requestList} and {@link FileDownloadOptions.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`:
  *
@@ -49,7 +49,7 @@ JSONData extends Dictionary = any> = RequestHandler<FileDownloadCrawlingContext<
  * ]
  * ```
  *
- * 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` parameter of the `FileCrawler` constructor. For user convenience, the `minConcurrency` and `maxConcurrency` {@apilink AutoscaledPool} options are available directly in the `FileCrawler` constructor.
+ * New requests are only dispatched when there is enough free CPU and memory available, using the functionality provided by the {@link AutoscaledPool} class. All {@link AutoscaledPool} configuration options can be passed to the `autoscaledPoolOptions` parameter of the `FileCrawler` constructor. For user convenience, the `minConcurrency` and `maxConcurrency` {@link AutoscaledPool} options are available directly in the `FileCrawler` constructor.
  *
  * ## Example usage
  *
@@ -74,9 +74,9 @@ export declare class FileDownload extends HttpCrawler<FileDownloadCrawlingContex
     private streamRequestHandler;
 }
 /**
- * Creates new {@apilink Router} instance that works based on request labels.
- * This instance can then serve as a `requestHandler` of your {@apilink FileDownload}.
- * Defaults to the {@apilink FileDownloadCrawlingContext}.
+ * Creates new {@link Router} instance that works based on request labels.
+ * This instance can then serve as a `requestHandler` of your {@link FileDownload}.
+ * Defaults to the {@link FileDownloadCrawlingContext}.
  *
  * > Serves as a shortcut for using `Router.create<FileDownloadCrawlingContext>()`.
  *

package/internals/file-download.js

@@ -10,15 +10,15 @@ const index_1 = require("../index");
  *
  * Since `FileDownload` uses raw HTTP requests to download the files, it is very fast and bandwidth-efficient.
  * However, it doesn't parse the content - if you need to e.g. extract data from the downloaded files,
- * you might need to use {@apilink CheerioCrawler}, {@apilink PuppeteerCrawler} or {@apilink PlaywrightCrawler} instead.
+ * you might need to use {@link CheerioCrawler}, {@link PuppeteerCrawler} or {@link PlaywrightCrawler} instead.
  *
- * `FileCrawler` downloads each URL using a plain HTTP request and then invokes the user-provided {@apilink FileDownloadOptions.requestHandler} where the user can specify what to do with the downloaded data.
+ * `FileCrawler` downloads each URL using a plain HTTP request and then invokes the user-provided {@link FileDownloadOptions.requestHandler} where the user can specify what to do with the downloaded data.
  *
- * The source URLs are represented using {@apilink Request} objects that are fed from {@apilink RequestList} or {@apilink RequestQueue} instances provided by the {@apilink FileDownloadOptions.requestList} or {@apilink FileDownloadOptions.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 FileDownloadOptions.requestList} or {@link FileDownloadOptions.requestQueue} constructor options, respectively.
  *
- * If both {@apilink FileDownloadOptions.requestList} and {@apilink FileDownloadOptions.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 FileDownloadOptions.requestList} and {@link FileDownloadOptions.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`:
  *
@@ -30,7 +30,7 @@ const index_1 = require("../index");
  * ]
  * ```
  *
- * 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` parameter of the `FileCrawler` constructor. For user convenience, the `minConcurrency` and `maxConcurrency` {@apilink AutoscaledPool} options are available directly in the `FileCrawler` constructor.
+ * New requests are only dispatched when there is enough free CPU and memory available, using the functionality provided by the {@link AutoscaledPool} class. All {@link AutoscaledPool} configuration options can be passed to the `autoscaledPoolOptions` parameter of the `FileCrawler` constructor. For user convenience, the `minConcurrency` and `maxConcurrency` {@link AutoscaledPool} options are available directly in the `FileCrawler` constructor.
  *
  * ## Example usage
  *
@@ -130,9 +130,9 @@ class FileDownload extends index_1.HttpCrawler {
 }
 exports.FileDownload = FileDownload;
 /**
- * Creates new {@apilink Router} instance that works based on request labels.
- * This instance can then serve as a `requestHandler` of your {@apilink FileDownload}.
- * Defaults to the {@apilink FileDownloadCrawlingContext}.
+ * Creates new {@link Router} instance that works based on request labels.
+ * This instance can then serve as a `requestHandler` of your {@link FileDownload}.
+ * Defaults to the {@link FileDownloadCrawlingContext}.
  *
  * > Serves as a shortcut for using `Router.create<FileDownloadCrawlingContext>()`.
  *

package/internals/http-crawler.d.ts

@@ -21,7 +21,7 @@ export type HttpErrorHandler<UserData extends Dictionary = any, // with default
 JSONData extends JsonValue = any> = ErrorHandler<HttpCrawlingContext<UserData, JSONData>>;
 export interface HttpCrawlerOptions<Context extends InternalHttpCrawlingContext = InternalHttpCrawlingContext> extends BasicCrawlerOptions<Context> {
     /**
-     * An alias for {@apilink HttpCrawlerOptions.requestHandler}
+     * An alias for {@link HttpCrawlerOptions.requestHandler}
      * Soon to be removed, use `requestHandler` instead.
      * @deprecated
      */
@@ -54,7 +54,7 @@ export interface HttpCrawlerOptions<Context extends InternalHttpCrawlingContext
      * ```
      *
      * Modyfing `pageOptions` is supported only in Playwright incognito.
-     * See {@apilink PrePageCreateHook}
+     * See {@link PrePageCreateHook}
      */
     preNavigationHooks?: InternalHttpHook<Context>[];
     /**
@@ -80,7 +80,7 @@ export interface HttpCrawlerOptions<Context extends InternalHttpCrawlingContext
      * Sadly, there are some websites which use invalid headers. Those are encoded using the UTF-8 encoding.
      * If those sites actually use a different encoding, the response will be corrupted. You can use
      * `suggestResponseEncoding` to fall back to a certain encoding, if you know that your target website uses it.
-     * To force a certain encoding, disregarding the response headers, use {@apilink HttpCrawlerOptions.forceResponseEncoding}
+     * To force a certain encoding, disregarding the response headers, use {@link HttpCrawlerOptions.forceResponseEncoding}
      * ```
      * // Will fall back to windows-1250 encoding if none found
      * suggestResponseEncoding: 'windows-1250'
@@ -90,7 +90,7 @@ export interface HttpCrawlerOptions<Context extends InternalHttpCrawlingContext
     /**
      * By default this crawler will extract correct encoding from the HTTP response headers. Use `forceResponseEncoding`
      * to force a certain encoding, disregarding the response headers.
-     * To only provide a default for missing encodings, use {@apilink HttpCrawlerOptions.suggestResponseEncoding}
+     * To only provide a default for missing encodings, use {@link HttpCrawlerOptions.suggestResponseEncoding}
      * ```
      * // Will force windows-1250 encoding even if headers say otherwise
      * forceResponseEncoding: 'windows-1250'
@@ -160,7 +160,7 @@ Crawler = HttpCrawler<any>> extends CrawlingContext<Crawler, UserData> {
      */
     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 will throw if it's not available.
      *
      * **Example usage:**
@@ -183,20 +183,20 @@ JSONData extends JsonValue = any> = RequestHandler<HttpCrawlingContext<UserData,
  * or from a dynamic queue of URLs enabling recursive crawling of websites.
  *
  * 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.
  *
  * This crawler downloads each URL using a plain HTTP request and doesn't do any HTML parsing.
  *
- * The source URLs are represented using {@apilink Request} objects that are fed from
- * {@apilink RequestList} or {@apilink RequestQueue} instances provided by the {@apilink HttpCrawlerOptions.requestList}
- * or {@apilink HttpCrawlerOptions.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 HttpCrawlerOptions.requestList}
+ * or {@link HttpCrawlerOptions.requestQueue} constructor options, respectively.
  *
- * If both {@apilink HttpCrawlerOptions.requestList} and {@apilink HttpCrawlerOptions.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 HttpCrawlerOptions.requestList} and {@link HttpCrawlerOptions.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`:
  *
@@ -211,15 +211,15 @@ JSONData extends JsonValue = any> = RequestHandler<HttpCrawlingContext<UserData,
  * By default, this crawler 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 HttpCrawlerOptions.additionalMimeTypes} constructor option.
+ * use the {@link HttpCrawlerOptions.additionalMimeTypes} constructor option.
  * Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.
- * For details, see {@apilink HttpCrawlerOptions.requestHandler}.
+ * For details, see {@link HttpCrawlerOptions.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 constructor. For user convenience, the `minConcurrency` and `maxConcurrency`
- * {@apilink AutoscaledPool} options are available directly in the constructor.
+ * {@link AutoscaledPool} options are available directly in the constructor.
  *
  * **Example usage:**
  *
@@ -247,7 +247,7 @@ JSONData extends JsonValue = any> = RequestHandler<HttpCrawlingContext<UserData,
 export declare class HttpCrawler<Context extends InternalHttpCrawlingContext<any, any, HttpCrawler<Context>>> 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;
@@ -496,9 +496,9 @@ interface RequestFunctionOptions {
     gotOptions: OptionsInit;
 }
 /**
- * Creates new {@apilink Router} instance that works based on request labels.
- * This instance can then serve as a `requestHandler` of your {@apilink HttpCrawler}.
- * Defaults to the {@apilink HttpCrawlingContext}.
+ * Creates new {@link Router} instance that works based on request labels.
+ * This instance can then serve as a `requestHandler` of your {@link HttpCrawler}.
+ * Defaults to the {@link HttpCrawlingContext}.
  *
  * > Serves as a shortcut for using `Router.create<HttpCrawlingContext>()`.
  *

package/internals/http-crawler.js

@@ -36,20 +36,20 @@ const HTTP_OPTIMIZED_AUTOSCALED_POOL_OPTIONS = {
  * or from a dynamic queue of URLs enabling recursive crawling of websites.
  *
  * 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.
  *
  * This crawler downloads each URL using a plain HTTP request and doesn't do any HTML parsing.
  *
- * The source URLs are represented using {@apilink Request} objects that are fed from
- * {@apilink RequestList} or {@apilink RequestQueue} instances provided by the {@apilink HttpCrawlerOptions.requestList}
- * or {@apilink HttpCrawlerOptions.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 HttpCrawlerOptions.requestList}
+ * or {@link HttpCrawlerOptions.requestQueue} constructor options, respectively.
  *
- * If both {@apilink HttpCrawlerOptions.requestList} and {@apilink HttpCrawlerOptions.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 HttpCrawlerOptions.requestList} and {@link HttpCrawlerOptions.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`:
  *
@@ -64,15 +64,15 @@ const HTTP_OPTIMIZED_AUTOSCALED_POOL_OPTIONS = {
  * By default, this crawler 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 HttpCrawlerOptions.additionalMimeTypes} constructor option.
+ * use the {@link HttpCrawlerOptions.additionalMimeTypes} constructor option.
  * Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.
- * For details, see {@apilink HttpCrawlerOptions.requestHandler}.
+ * For details, see {@link HttpCrawlerOptions.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 constructor. For user convenience, the `minConcurrency` and `maxConcurrency`
- * {@apilink AutoscaledPool} options are available directly in the constructor.
+ * {@link AutoscaledPool} options are available directly in the constructor.
  *
  * **Example usage:**
  *
@@ -123,7 +123,7 @@ class HttpCrawler 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", {
@@ -699,9 +699,9 @@ function parseContentTypeFromResponse(response) {
     };
 }
 /**
- * Creates new {@apilink Router} instance that works based on request labels.
- * This instance can then serve as a `requestHandler` of your {@apilink HttpCrawler}.
- * Defaults to the {@apilink HttpCrawlingContext}.
+ * Creates new {@link Router} instance that works based on request labels.
+ * This instance can then serve as a `requestHandler` of your {@link HttpCrawler}.
+ * Defaults to the {@link HttpCrawlingContext}.
  *
  * > Serves as a shortcut for using `Router.create<HttpCrawlingContext>()`.
  *

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/http",
-    "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"
@@ -55,9 +55,9 @@
     "dependencies": {
         "@apify/timeout": "^0.3.0",
         "@apify/utilities": "^2.7.10",
-        "@crawlee/basic": "3.13.3-beta.9",
-        "@crawlee/types": "3.13.3-beta.9",
-        "@crawlee/utils": "3.13.3-beta.9",
+        "@crawlee/basic": "3.13.3",
+        "@crawlee/types": "3.13.3",
+        "@crawlee/utils": "3.13.3",
         "@types/content-type": "^1.1.5",
         "cheerio": "1.0.0-rc.12",
         "content-type": "^1.0.4",
@@ -75,5 +75,5 @@
             }
         }
     },
-    "gitHead": "b15fa18267747df8d3e9ef4dde29e139187ab684"
+    "gitHead": "279cadbd3cd6342f36cc4d841e07b999e472420d"
 }