Merge pull request #238 from apify/feat/output-and-dataset-schema

chore: output schema

Author: nikitachapovskii-dev

packages/actor-scraper/sitemap-scraper/.actor/actor.json

@@ -3,6 +3,7 @@
     "name": "sitemap-extractor",
     "version": "0.1",
     "buildTag": "latest",
+    "output": "./output_schema.json",
     "defaultMemoryMbytes": 1024,
     "minMemoryMbytes": 256,
     "maxMemoryMbytes": 4096,

packages/actor-scraper/sitemap-scraper/.actor/output_schema.json

@@ -0,0 +1,13 @@
+{
+    "actorOutputSchemaVersion": 1,
+    "title": "Sitemap Extractor Output",
+    "description": "Links to the default dataset containing extracted sitemap URLs and request metadata.",
+    "properties": {
+        "results": {
+            "type": "string",
+            "title": "Results",
+            "description": "Dataset items with discovered URLs and crawl status.",
+            "template": "{{links.apiDefaultDatasetUrl}}/items"
+        }
+    }
+}

packages/actor-scraper/sitemap-scraper/OUTPUT_SCHEMA.json

@@ -55,7 +55,7 @@ const REQUEST_QUEUE_INIT_FLAG_KEY = 'REQUEST_QUEUE_INITIALIZED';
  * instance and creating a context for a pageFunction invocation.
  */
 export class CrawlerSetup {
-    name = 'Sitemap Scraper';
+    name = 'Sitemap Extractor';
     rawInput: string;
     env: ApifyEnv;
     /**