@crawlee/basic 4.0.0-beta.74 → 4.0.0-beta.76

package/internals/basic-crawler.js

@@ -311,6 +311,8 @@ export class BasicCrawler {
                 extendContext: options.extendContext,
             };
             this.#log = serviceLocator.getLogger().child({ prefix: this.constructor.name });
+            // Initialize the Configuration instance to avoid lazy loading in the components
+            serviceLocator.getConfiguration();
             // Store whether the user explicitly provided an ID
             this.hasExplicitId = id !== undefined;
             // Store the user-provided ID, or generate a unique one for tracking purposes (not for state key)
@@ -449,6 +451,11 @@ export class BasicCrawler {
                         }
                         throw this.unwrapError(error);
                     }
+                    finally {
+                        // Run request-scoped deferred cleanups only after the whole request lifecycle - including the user's error handler - has finished.
+                        const deferredCleanup = crawlingContext[deferredCleanupKey] ?? [];
+                        await Promise.all(deferredCleanup.map((fn) => fn().catch((cleanupError) => this.log.debug('Error in deferred cleanup', { error: cleanupError }))));
+                    }
                 },
                 isTaskReadyFunction: async () => {
                     if (isMaxPagesExceeded()) {
@@ -511,12 +518,7 @@ export class BasicCrawler {
     buildBasicContextPipeline() {
         return ContextPipeline.create()
             .compose({ action: this.checkRobotsTxt.bind(this) })
-            .compose({
-            action: () => this.createBaseContext(),
-            cleanup: async (context) => {
-                await Promise.all(context[deferredCleanupKey].map((fn) => fn()));
-            },
-        })
+            .compose({ action: () => this.createBaseContext() })
             .compose({ action: this.resolveSession.bind(this) })
             .compose({ action: this.createContextHelpers.bind(this) });
     }

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/basic",
-    "version": "4.0.0-beta.74",
+    "version": "4.0.0-beta.76",
     "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"
@@ -42,10 +42,10 @@
         "@apify/datastructures": "^2.0.0",
         "@apify/timeout": "^0.3.2",
         "@apify/utilities": "^2.15.5",
-        "@crawlee/core": "4.0.0-beta.74",
-        "@crawlee/http-client": "4.0.0-beta.74",
-        "@crawlee/types": "4.0.0-beta.74",
-        "@crawlee/utils": "4.0.0-beta.74",
+        "@crawlee/core": "4.0.0-beta.76",
+        "@crawlee/http-client": "4.0.0-beta.76",
+        "@crawlee/types": "4.0.0-beta.76",
+        "@crawlee/utils": "4.0.0-beta.76",
         "csv-stringify": "^6.5.2",
         "fs-extra": "^11.3.0",
         "ow": "^2.0.0",
@@ -54,7 +54,7 @@
         "type-fest": "^4.41.0"
     },
     "optionalDependencies": {
-        "@crawlee/impit-client": "^4.0.0-beta.74"
+        "@crawlee/impit-client": "^4.0.0-beta.76"
     },
     "lerna": {
         "command": {
@@ -63,5 +63,5 @@
             }
         }
     },
-    "gitHead": "4315097d125a7e5f0ff97212bbd66112ab967ea2"
+    "gitHead": "0f76e7dbac40567e81475a6a77c7dedd8a829d12"
 }