@crawlee/browser 4.0.0-beta.81 → 4.0.0-beta.82

package/internals/browser-crawler.d.ts

@@ -31,8 +31,8 @@ export interface BrowserCrawlingContext<Page extends CommonPage = CommonPage, Re
      */
     enqueueLinks: (options?: EnqueueLinksOptions) => Promise<BatchAddRequestsResult>;
 }
-export type BrowserHook<Context = BrowserCrawlingContext> = (crawlingContext: Context) => Awaitable<void | Partial<Context>>;
-export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Response extends BaseResponse = BaseResponse, Context extends BrowserCrawlingContext<Page, Response, Dictionary> = BrowserCrawlingContext<Page, Response, Dictionary>, ContextExtension = Dictionary<never>, ExtendedContext extends Context = Context & ContextExtension, InternalBrowserPoolOptions extends BrowserPoolOptions = BrowserPoolOptions, __BrowserPlugins extends BrowserPlugin[] = InferBrowserPluginArray<InternalBrowserPoolOptions['browserPlugins']>, __BrowserControllerReturn extends BrowserController = ReturnType<__BrowserPlugins[number]['createController']>, __LaunchContextReturn extends LaunchContext = ReturnType<__BrowserPlugins[number]['createLaunchContext']>> extends Omit<BasicCrawlerOptions<Context, ExtendedContext>, 'requestHandler' | 'failedRequestHandler' | 'errorHandler'> {
+export type BrowserHook<Context = BrowserCrawlingContext, ContextExtension = {}> = (crawlingContext: Context & ContextExtension) => Awaitable<void | Partial<Context>>;
+export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Response extends BaseResponse = BaseResponse, Context extends BrowserCrawlingContext<Page, Response, Dictionary> = BrowserCrawlingContext<Page, Response, Dictionary>, ContextExtension = Dictionary<never>, ExtendedContext extends Context = Context & ContextExtension, InternalBrowserPoolOptions extends BrowserPoolOptions = BrowserPoolOptions, __BrowserPlugins extends BrowserPlugin[] = InferBrowserPluginArray<InternalBrowserPoolOptions['browserPlugins']>, __BrowserControllerReturn extends BrowserController = ReturnType<__BrowserPlugins[number]['createController']>, __LaunchContextReturn extends LaunchContext = ReturnType<__BrowserPlugins[number]['createLaunchContext']>> extends Omit<BasicCrawlerOptions<Context, ContextExtension, ExtendedContext>, 'requestHandler' | 'failedRequestHandler' | 'errorHandler'> {
     launchContext?: BrowserLaunchContext<any, any>;
     /**
      * An existing browser pool instance to use. When provided, the crawler will use this pool directly instead of
@@ -124,8 +124,13 @@ export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Res
      *
      * A hook may optionally return a partial object whose properties are merged into the crawling context,
      * allowing the hook to override context members for subsequent hooks and pipeline stages.
+     *
+     * The context is built up in the following order: base context (`request`, `session`, helpers, ...) ->
+     * `extendContext` -> `preNavigationHooks` -> navigation -> `postNavigationHooks` -> `requestHandler`.
+     * This means the members added by `extendContext` are already available here, but navigation-dependent
+     * members (e.g. `page`, `response`) are not.
      */
-    preNavigationHooks?: BrowserHook<Context>[];
+    preNavigationHooks?: BrowserHook<Context, ContextExtension>[];
     /**
      * Async functions that are sequentially evaluated after the navigation. Good for checking if the navigation was successful.
      * The function accepts `crawlingContext` as the only parameter.
@@ -151,7 +156,7 @@ export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Res
      * ]
      * ```
      */
-    postNavigationHooks?: BrowserHook<Context>[];
+    postNavigationHooks?: BrowserHook<Context, ContextExtension>[];
     /**
      * Timeout in which page navigation needs to finish, in seconds.
      */

package/internals/browser-crawler.js

@@ -104,10 +104,13 @@ export class BrowserCrawler extends BasicCrawler {
                     .compose({ action: this.handleBlockedRequestByContent.bind(this) })
                     .compose({ action: this.restoreRequestState.bind(this) });
             },
-            extendContext: extendContext,
+            extendContext,
         });
         this.launchContext = launchContext;
         this.navigationTimeoutMillis = navigationTimeoutSecs * 1000;
+        // The public option hooks are extension-aware; internal storage uses the base context type
+        // (the pipeline composes hooks against the concrete context, which does not statically carry
+        // `ContextExtension`). The extension members are present at runtime regardless.
         this.preNavigationHooks = preNavigationHooks;
         this.postNavigationHooks = postNavigationHooks;
         this.ignoreIframes = ignoreIframes;

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/browser",
-    "version": "4.0.0-beta.81",
+    "version": "4.0.0-beta.82",
     "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": ">=22.0.0"
@@ -48,10 +48,10 @@
     },
     "dependencies": {
         "@apify/timeout": "^0.3.2",
-        "@crawlee/basic": "4.0.0-beta.81",
-        "@crawlee/browser-pool": "4.0.0-beta.81",
-        "@crawlee/types": "4.0.0-beta.81",
-        "@crawlee/utils": "4.0.0-beta.81",
+        "@crawlee/basic": "4.0.0-beta.82",
+        "@crawlee/browser-pool": "4.0.0-beta.82",
+        "@crawlee/types": "4.0.0-beta.82",
+        "@crawlee/utils": "4.0.0-beta.82",
         "ow": "^2.0.0",
         "tslib": "^2.8.1",
         "type-fest": "^4.41.0"
@@ -75,5 +75,5 @@
             }
         }
     },
-    "gitHead": "80dc6b4fc82237e63a51a71153809ec8dfd0cc50"
+    "gitHead": "eb1096f7c7743d124375ef011fbbadb19476822e"
 }