@adobe/spacecat-shared-scrape-client 2.1.6 → 2.2.0

package/CHANGELOG.md

@@ -1,3 +1,17 @@
+# [@adobe/spacecat-shared-scrape-client-v2.2.0](https://github.com/adobe/spacecat-shared/compare/@adobe/spacecat-shared-scrape-client-v2.1.7...@adobe/spacecat-shared-scrape-client-v2.2.0) (2025-10-29)
+
+
+### Features
+
+* scrape url access pattern ([#1059](https://github.com/adobe/spacecat-shared/issues/1059)) ([26facf6](https://github.com/adobe/spacecat-shared/commit/26facf63dfae4908ed88221f16266910205e2473))
+
+# [@adobe/spacecat-shared-scrape-client-v2.1.7](https://github.com/adobe/spacecat-shared/compare/@adobe/spacecat-shared-scrape-client-v2.1.6...@adobe/spacecat-shared-scrape-client-v2.1.7) (2025-10-28)
+
+
+### Bug Fixes
+
+* remove cyclic deps in shared ([#1053](https://github.com/adobe/spacecat-shared/issues/1053)) ([acbbc93](https://github.com/adobe/spacecat-shared/commit/acbbc93f8c961fdef55edb5e7947958456538586))
+
 # [@adobe/spacecat-shared-scrape-client-v2.1.6](https://github.com/adobe/spacecat-shared/compare/@adobe/spacecat-shared-scrape-client-v2.1.5...@adobe/spacecat-shared-scrape-client-v2.1.6) (2025-10-28)
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@adobe/spacecat-shared-scrape-client",
-  "version": "2.1.6",
+  "version": "2.2.0",
   "description": "Shared modules of the Spacecat Services - Scrape Client",
   "type": "module",
   "engines": {
@@ -37,7 +37,7 @@
   "dependencies": {
     "@adobe/helix-universal": "5.2.3",
     "@adobe/spacecat-shared-data-access": "2.45.0",
-    "@adobe/spacecat-shared-utils": "1.31.0"
+    "@adobe/spacecat-shared-utils": "1.66.0"
   },
   "devDependencies": {
     "chai": "6.2.0",

package/src/clients/scrape-client.js

@@ -16,6 +16,7 @@ import {
 import { ScrapeJob as ScrapeJobModel } from '@adobe/spacecat-shared-data-access';
 import { ScrapeJobDto } from './scrapeJobDto.js';
 import ScrapeJobSupervisor from './scrape-job-supervisor.js';
+import { ScrapeUrlDto } from './scrapeUrlDto.js';
 
 export default class ScrapeClient {
   config = null;
@@ -343,4 +344,30 @@ export default class ScrapeClient {
       throw new Error(msgError);
     }
   }
+
+  async getScrapeUrlsByProcessingType(url, processingType, maxScrapeAge = 168) {
+    let decodedUrl;
+    try {
+      decodedUrl = decodeURIComponent(url);
+      if (!isValidUrl(decodedUrl)) {
+        throw new Error(`Invalid request: ${decodedUrl} must be a valid URL`);
+      }
+
+      const scrapeUrls = await this.scrapeSupervisor.getScrapeUrlsByProcessingType(
+        decodedUrl,
+        processingType,
+        maxScrapeAge,
+      );
+
+      if (!isNonEmptyArray(scrapeUrls)) {
+        return null;
+      }
+
+      return scrapeUrls.map((scrapeUrl) => ScrapeUrlDto.toJSON(scrapeUrl));
+    } catch (error) {
+      const msgError = `Failed to fetch scrape URL by URL: ${decodedUrl} and processing type: ${processingType}, ${error.message}`;
+      this.config.log.error(msgError);
+      throw new Error(msgError);
+    }
+  }
 }

package/src/clients/scrape-job-supervisor.js

@@ -11,7 +11,7 @@
  */
 
 import { ScrapeJob as ScrapeJobModel } from '@adobe/spacecat-shared-data-access';
-import { isValidUUID } from '@adobe/spacecat-shared-utils';
+import { isValidUrl, isValidUUID } from '@adobe/spacecat-shared-utils';
 
 /**
  * Scrape Supervisor provides functionality to start and manage scrape jobs.
@@ -30,7 +30,7 @@ function ScrapeJobSupervisor(services, config) {
     dataAccess, sqs, log,
   } = services;
 
-  const { ScrapeJob } = dataAccess;
+  const { ScrapeJob, ScrapeUrl } = dataAccess;
 
   const {
     scrapeWorkerQueue, // URL of the scrape worker queue
@@ -227,12 +227,27 @@ function ScrapeJobSupervisor(services, config) {
     }
   }
 
+  async function getScrapeUrlsByProcessingType(url, processingType, maxScrapeAge) {
+    if (!isValidUrl(url)) {
+      throw new Error(`${url} must be a valid URL`);
+    }
+    try {
+      return ScrapeUrl.allRecentByUrlAndProcessingType(url, processingType, maxScrapeAge);
+    } catch (error) {
+      if (error.message.includes('Not found')) {
+        return null;
+      }
+      throw error;
+    }
+  }
+
   return {
     startNewJob,
     getScrapeJob,
     getScrapeJobsByDateRange,
     getScrapeJobsByBaseURL,
     getScrapeJobsByBaseURLAndProcessingType,
+    getScrapeUrlsByProcessingType,
   };
 }
 

package/src/clients/scrapeUrlDto.js

@@ -0,0 +1,30 @@
+/*
+ * Copyright 2024 Adobe. All rights reserved.
+ * This file is licensed to you under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License. You may obtain a copy
+ * of the License at http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software distributed under
+ * the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR REPRESENTATIONS
+ * OF ANY KIND, either express or implied. See the License for the specific language
+ * governing permissions and limitations under the License.
+ */
+
+/**
+ * Data transfer object for Import Job.
+ */
+export const ScrapeUrlDto = {
+  /**
+     * Converts an Import Job object into a JSON object.
+     */
+  toJSON: (scrapeUrl) => ({
+    id: scrapeUrl.getId(),
+    URL: scrapeUrl.getUrl(),
+    processingType: scrapeUrl.getProcessingType(),
+    options: scrapeUrl.getOptions(),
+    status: scrapeUrl.getStatus(),
+    path: scrapeUrl.getPath(),
+    scrapeJobId: scrapeUrl.getScrapeJobId(),
+    createdAt: scrapeUrl.getCreatedAt(),
+  }),
+};