@crawlee/browser 3.17.1-beta.54 → 3.17.1-beta.56

package/index.mjs

@@ -50,6 +50,7 @@ export const RequestQueue = mod.RequestQueue;
 export const RequestQueueV1 = mod.RequestQueueV1;
 export const RequestQueueV2 = mod.RequestQueueV2;
 export const RequestState = mod.RequestState;
+export const RequestValidationError = mod.RequestValidationError;
 export const RetryRequestError = mod.RetryRequestError;
 export const Router = mod.Router;
 export const STATE_PERSISTENCE_KEY = mod.STATE_PERSISTENCE_KEY;
@@ -79,6 +80,7 @@ export const createDeserialize = mod.createDeserialize;
 export const createEventLoopLoadSignal = mod.createEventLoopLoadSignal;
 export const createRequestOptions = mod.createRequestOptions;
 export const createRequests = mod.createRequests;
+export const defaultRoute = mod.defaultRoute;
 export const deserializeArray = mod.deserializeArray;
 export const enqueueLinks = mod.enqueueLinks;
 export const evaluateLoadSignalSample = mod.evaluateLoadSignalSample;
@@ -100,5 +102,6 @@ export const tryAbsoluteURL = mod.tryAbsoluteURL;
 export const updateEnqueueLinksPatternCache = mod.updateEnqueueLinksPatternCache;
 export const useState = mod.useState;
 export const validateGlobPattern = mod.validateGlobPattern;
+export const validateUserData = mod.validateUserData;
 export const validators = mod.validators;
 export const withCheckedStorageAccess = mod.withCheckedStorageAccess;

package/internals/browser-crawler.d.ts

@@ -331,6 +331,11 @@ export declare abstract class BrowserCrawler<InternalBrowserPoolOptions extends
     protected _cleanupContext(crawlingContext: Context): Promise<void>;
     private containsSelectors;
     protected isRequestBlocked(crawlingContext: Context): Promise<string | false>;
+    /**
+     * `BrowserCrawler` hands `BasicCrawler` a wrapper that opens a page before delegating, and keeps the user's
+     * own handler in `userProvidedRequestHandler` — so resolve router-aware metadata against that instead.
+     */
+    protected get userRequestHandler(): RequestHandler<Context>;
     /**
      * Wrapper around requestHandler that opens and closes pages etc.
      */

package/internals/browser-crawler.js

@@ -220,6 +220,13 @@ class BrowserCrawler extends basic_1.BasicCrawler {
             return `Received blocked status code: ${blockedStatusCode}`;
         return false;
     }
+    /**
+     * `BrowserCrawler` hands `BasicCrawler` a wrapper that opens a page before delegating, and keeps the user's
+     * own handler in `userProvidedRequestHandler` — so resolve router-aware metadata against that instead.
+     */
+    get userRequestHandler() {
+        return this.userProvidedRequestHandler;
+    }
     /**
      * Wrapper around requestHandler that opens and closes pages etc.
      */

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/browser",
-    "version": "3.17.1-beta.54",
+    "version": "3.17.1-beta.56",
     "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": "3.17.1-beta.54",
-        "@crawlee/browser-pool": "3.17.1-beta.54",
-        "@crawlee/types": "3.17.1-beta.54",
-        "@crawlee/utils": "3.17.1-beta.54",
+        "@crawlee/basic": "3.17.1-beta.56",
+        "@crawlee/browser-pool": "3.17.1-beta.56",
+        "@crawlee/types": "3.17.1-beta.56",
+        "@crawlee/utils": "3.17.1-beta.56",
         "ow": "^0.28.1",
         "tslib": "^2.4.0",
         "type-fest": "^4.0.0"
@@ -81,5 +81,5 @@
             }
         }
     },
-    "gitHead": "45d0756fd5f016539d6e2f80f72340a652ddc48f"
+    "gitHead": "aaf56f1d6905d06fe18a93bbd2d7695a581d57cf"
 }