From 7a52c1aad2f51f77cdbf4114b2d5b7f5ae7bc068 Mon Sep 17 00:00:00 2001
From: paraschi <paraschi@adobe.com>
Date: Tue, 20 Aug 2024 22:49:22 +0300
Subject: [PATCH] fix: unexpected close tag issue

---
 src/sitemap/handler.js |  6 +++---
 src/support/utils.js   | 37 ++++++++++++++++++++-----------------
 2 files changed, 23 insertions(+), 20 deletions(-)

diff --git a/src/sitemap/handler.js b/src/sitemap/handler.js
index 7eac7f02..ec9b1c4b 100644
--- a/src/sitemap/handler.js
+++ b/src/sitemap/handler.js
@@ -115,10 +115,10 @@ export async function checkRobotsForSitemap(protocol, domain, log) {
  * @returns {boolean} - True if the sitemap content is valid, otherwise false.
  */
 export function isSitemapContentValid(sitemapContent) {
-  return sitemapContent.payload.trim().startsWith('<?xml')
-      || VALID_MIME_TYPES.some((type) => sitemapContent.type.includes(type));
+  const payload = sitemapContent.payload.trim();
+  return payload.startsWith('<?xml') && payload.endsWith('>')
+      && VALID_MIME_TYPES.some((type) => sitemapContent.type.includes(type));
 }
-
 /**
  * Checks the validity and existence of a sitemap by fetching its content.
  *
diff --git a/src/support/utils.js b/src/support/utils.js
index 5404080f..3edbeea7 100644
--- a/src/support/utils.js
+++ b/src/support/utils.js
@@ -91,23 +91,26 @@ export function extractDomainAndProtocol(inputUrl) {
  * @returns {Array<string>} An array of URLs extracted from the sitemap.
  */
 export function extractUrlsFromSitemap(content, log, tagName = 'url') {
-  const dom = new JSDOM(content.payload, { contentType: 'text/xml' });
-  const { document } = dom.window;
-
-  const elements = document.getElementsByTagName(tagName);
-
-  // Map through the elements, extract the text of the 'loc' tags, and filter out null
-  return Array.from(elements)
-    .map((element) => {
-      const loc = element.getElementsByTagName('loc')[0];
-      // Check if loc exists before trying to access textContent
-      if (loc && loc.textContent) {
-        log.info('Extracted URL:', loc.textContent.trim());
-        return loc.textContent.trim();
-      }
-      return null;
-    })
-    .filter((url) => url !== null);
+  try {
+    const dom = new JSDOM(content.payload, { contentType: 'text/xml' });
+    const { document } = dom.window;
+    const elements = document.getElementsByTagName(tagName);
+
+    return Array.from(elements)
+      .map((element) => {
+        const loc = element.getElementsByTagName('loc')[0];
+        if (loc && loc.textContent) {
+          log.info('Extracted URL:', loc.textContent.trim());
+          return loc.textContent.trim();
+        }
+        return null;
+      })
+      .filter((url) => url !== null);
+  } catch (error) {
+    log.error(`Failed to parse XML content in sitemap: ${error.message}`);
+    log.error(`Content received: ${content.payload}`);
+    return [];
+  }
 }
 
 /**