@crawlee/core 3.17.1-beta.67 → 3.17.1-beta.69

package/enqueue_links/enqueue_links.d.ts

@@ -194,7 +194,7 @@ export declare function enqueueLinks(options: SetRequired<Omit<EnqueueLinksOptio
  *   request domain, or a redirected one
  * - In all other cases, we return the domain of the original request as that's the one we need to use for filtering
  */
-export declare function resolveBaseUrlForEnqueueLinksFiltering({ enqueueStrategy, finalRequestUrl, originalRequestUrl, userProvidedBaseUrl, }: ResolveBaseUrl): string | undefined;
+export declare function resolveBaseUrlForEnqueueLinksFiltering({ enqueueStrategy, finalRequestUrl, originalRequestUrl, userProvidedBaseUrl, }: ResolveBaseUrl): string;
 /**
  * @internal
  */

package/enqueue_links/enqueue_links.js

@@ -203,15 +203,15 @@ function resolveBaseUrlForEnqueueLinksFiltering({ enqueueStrategy, finalRequestU
         return finalUrlOrigin;
     }
     // If the user wants to ensure the same domain is accessed, regardless of subdomains, we check to ensure the domains match
-    // Returning undefined here is intentional! If the domains don't match, having no baseUrl in enqueueLinks will cause it to not enqueue anything
-    // which is the intended behavior (since we went off domain)
+    // If they don't (we went off domain via a redirect), we keep filtering against the original domain - returning
+    // undefined here would disable the filtering entirely and enqueue every link on the redirected page
     if (enqueueStrategy === utils_1.EnqueueStrategy.SameDomain) {
         const originalHostname = (0, tldts_1.getDomain)(originalUrlOrigin, { mixedInputs: false });
         const finalHostname = (0, tldts_1.getDomain)(finalUrlOrigin, { mixedInputs: false });
         if (originalHostname === finalHostname) {
             return finalUrlOrigin;
         }
-        return undefined;
+        return originalUrlOrigin;
     }
     // Always enqueue urls that are from the same origin in all other cases, as the filtering happens on the original request url, even if there was a redirect
     // before actually finding the urls

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/core",
-    "version": "3.17.1-beta.67",
+    "version": "3.17.1-beta.69",
     "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"
@@ -59,9 +59,9 @@
         "@apify/pseudo_url": "^2.0.30",
         "@apify/timeout": "^0.4.0",
         "@apify/utilities": "^2.7.10",
-        "@crawlee/memory-storage": "3.17.1-beta.67",
-        "@crawlee/types": "3.17.1-beta.67",
-        "@crawlee/utils": "3.17.1-beta.67",
+        "@crawlee/memory-storage": "3.17.1-beta.69",
+        "@crawlee/types": "3.17.1-beta.69",
+        "@crawlee/utils": "3.17.1-beta.69",
         "@sapphire/async-queue": "^1.5.1",
         "@standard-schema/spec": "^1.0.0",
         "@vladfrangu/async_event_emitter": "^2.2.2",
@@ -84,5 +84,5 @@
             }
         }
     },
-    "gitHead": "f4621717f7e09ef21e1730bb0a817fa869f4a8f9"
+    "gitHead": "4cd950f1eb99bca5176ab20c8d88f6c3d6901e24"
 }