From db3fcee0edacd8f11b2a15a95b81f4e6419af2d6 Mon Sep 17 00:00:00 2001
From: anagarwa <anagarwa@adobe.com>
Date: Tue, 10 Jun 2025 17:06:25 +0530
Subject: [PATCH 1/2] fix: scrapping content in api

---
 packages/spacecat-shared-utils/src/index.js | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/packages/spacecat-shared-utils/src/index.js b/packages/spacecat-shared-utils/src/index.js
index 14ba1ca61..2653a6150 100644
--- a/packages/spacecat-shared-utils/src/index.js
+++ b/packages/spacecat-shared-utils/src/index.js
@@ -75,3 +75,10 @@ export {
 } from './formcalc.js';
 
 export { retrievePageAuthentication } from './auth.js';
+
+export {
+  getScrapedContentPath,
+  storeScrapedContent,
+  scrapeUrl,
+  scrapeAndStoreUrls,
+} from './scraper-utils.js';

From 06ffd72366a72d0252a7881d1540eea2bf1daac3 Mon Sep 17 00:00:00 2001
From: anagarwa <anagarwa@adobe.com>
Date: Tue, 10 Jun 2025 17:08:37 +0530
Subject: [PATCH 2/2] fix: scrapping content in api

---
 .../src/scraper-utils.js                      | 120 ++++++++++++++++++
 1 file changed, 120 insertions(+)
 create mode 100644 packages/spacecat-shared-utils/src/scraper-utils.js

diff --git a/packages/spacecat-shared-utils/src/scraper-utils.js b/packages/spacecat-shared-utils/src/scraper-utils.js
new file mode 100644
index 000000000..8a59c1756
--- /dev/null
+++ b/packages/spacecat-shared-utils/src/scraper-utils.js
@@ -0,0 +1,120 @@
+import { PutObjectCommand } from '@aws-sdk/client-s3';
+import { hasText } from './functions.js';
+
+/**
+ * Generates storage path for scraped content that matches run-sqs.js expectations
+ */
+export function getScrapedContentPath(siteId, url, prefix = 'scrapes') {
+    const urlObj = new URL(url);
+    const urlPath = urlObj.pathname.replace(/\/$/, '') || '/';
+    return `${prefix}/${siteId}${urlPath}/scrape.json`;
+}
+
+/**
+ * Stores scraped content in S3 in the format expected by run-sqs.js
+ */
+export async function storeScrapedContent(s3Client, bucketName, siteId, url, content, options = {}) {
+    const { prefix = 'scrapes' } = options;
+
+    const filePath = getScrapedContentPath(siteId, url, prefix);
+
+    const command = new PutObjectCommand({
+        Bucket: bucketName,
+        Key: filePath,
+        Body: JSON.stringify(content),
+        ContentType: 'application/json',
+    });
+
+    await s3Client.send(command);
+    console.log(`Successfully stored scraped content at: ${filePath}`);
+
+    return filePath;
+}
+
+/**
+ * Simple web scraper function
+ */
+export async function scrapeUrl(url, options = {}) {
+    const {
+        customHeaders = {},
+        timeout = 15000,
+        userAgent = 'SpaceCat-Scraper/1.0'
+    } = options;
+
+    try {
+        const response = await fetch(url, {
+            headers: {
+                'User-Agent': userAgent,
+                ...customHeaders,
+            },
+            signal: AbortSignal.timeout(timeout),
+        });
+
+        if (!response.ok) {
+            throw new Error(`HTTP ${response.status}: ${response.statusText}`);
+        }
+
+        const rawBody = await response.text();
+        const finalUrl = response.url;
+
+        return {
+            finalUrl,
+            status: response.status,
+            headers: Object.fromEntries(response.headers.entries()),
+            rawBody,
+            scrapeTime: Date.now(),
+            scrapedAt: new Date().toISOString(),
+        };
+    } catch (error) {
+        throw new Error(`Failed to scrape ${url}: ${error.message}`);
+    }
+}
+
+/**
+ * Batch scrape multiple URLs and store them in S3
+ */
+export async function scrapeAndStoreUrls(s3Client, bucketName, siteId, urls, options = {}) {
+    const results = [];
+
+    for (const url of urls) {
+        try {
+            console.log(`Scraping: ${url}`);
+            const scrapeResult = await scrapeUrl(url, options);
+
+            const contentToStore = {
+                finalUrl: scrapeResult.finalUrl,
+                scrapeResult,
+                userAgent: options.userAgent || 'SpaceCat-Scraper/1.0',
+                scrapeTime: scrapeResult.scrapeTime,
+                scrapedAt: scrapeResult.scrapedAt,
+            };
+
+            const storagePath = await storeScrapedContent(
+                s3Client,
+                bucketName,
+                siteId,
+                url,
+                contentToStore,
+                options
+            );
+
+            results.push({
+                url,
+                finalUrl: scrapeResult.finalUrl,
+                status: 'COMPLETE',
+                location: storagePath,
+                scrapeResult,
+            });
+
+        } catch (error) {
+            console.error(`Failed to scrape ${url}:`, error);
+            results.push({
+                url,
+                status: 'FAILED',
+                error: error.message,
+            });
+        }
+    }
+
+    return results;
+} 
\ No newline at end of file