@djangocfg/seo 2.1.109 → 2.1.110

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@djangocfg/seo",
-  "version": "2.1.109",
+  "version": "2.1.110",
   "description": "SEO analytics and indexing diagnostics module with Google Search Console integration and AI-ready reports",
   "keywords": [
     "seo",
@@ -92,7 +92,7 @@
     "google-auth-library": "^9.15.1",
     "chalk": "^5.3.0",
     "consola": "^3.4.2",
-    "cheerio": "^1.0.0",
+    "linkedom": "^0.18.12",
     "linkinator": "^7.5.0",
     "p-limit": "^6.2.0",
     "p-retry": "^7.0.0",
@@ -101,7 +101,7 @@
     "robots-parser": "^3.0.1"
   },
   "devDependencies": {
-    "@djangocfg/typescript-config": "^2.1.109",
+    "@djangocfg/typescript-config": "^2.1.110",
     "@types/node": "^24.7.2",
     "tsup": "^8.5.0",
     "tsx": "^4.19.2",

package/src/crawler/crawler.ts

@@ -3,7 +3,7 @@
  * Internal site crawler for SEO analysis
  */
 
-import { load } from 'cheerio';
+import { parseHTML } from 'linkedom';
 import pLimit from 'p-limit';
 import consola from 'consola';
 import type { CrawlResult, CrawlerConfig, SeoIssue } from '../types/index.js';
@@ -139,10 +139,11 @@ export class SiteCrawler {
    * Parse HTML and extract SEO-relevant data
    */
   private parseHtml(html: string, result: CrawlResult, pageUrl: string, depth: number): void {
-    const $ = load(html);
+    const { document } = parseHTML(html);
 
     // Title
-    result.title = $('title').first().text().trim() || undefined;
+    const titleEl = document.querySelector('title');
+    result.title = titleEl?.textContent?.trim() || undefined;
     if (!result.title) {
       result.warnings.push('Missing title tag');
     } else if (result.title.length > 60) {
@@ -150,8 +151,8 @@ export class SiteCrawler {
     }
 
     // Meta description
-    result.metaDescription =
-      $('meta[name="description"]').attr('content')?.trim() || undefined;
+    const metaDesc = document.querySelector('meta[name="description"]');
+    result.metaDescription = metaDesc?.getAttribute('content')?.trim() || undefined;
     if (!result.metaDescription) {
       result.warnings.push('Missing meta description');
     } else if (result.metaDescription.length > 160) {
@@ -161,25 +162,24 @@ export class SiteCrawler {
     }
 
     // Meta robots
-    result.metaRobots = $('meta[name="robots"]').attr('content')?.trim() || undefined;
-    const xRobots = $('meta[http-equiv="X-Robots-Tag"]').attr('content')?.trim();
-    if (xRobots) {
-      result.metaRobots = result.metaRobots ? `${result.metaRobots}, ${xRobots}` : xRobots;
+    const metaRobots = document.querySelector('meta[name="robots"]');
+    result.metaRobots = metaRobots?.getAttribute('content')?.trim() || undefined;
+    const xRobots = document.querySelector('meta[http-equiv="X-Robots-Tag"]');
+    const xRobotsContent = xRobots?.getAttribute('content')?.trim();
+    if (xRobotsContent) {
+      result.metaRobots = result.metaRobots ? `${result.metaRobots}, ${xRobotsContent}` : xRobotsContent;
     }
 
     // Canonical
-    result.canonicalUrl = $('link[rel="canonical"]').attr('href')?.trim() || undefined;
+    const canonical = document.querySelector('link[rel="canonical"]');
+    result.canonicalUrl = canonical?.getAttribute('href')?.trim() || undefined;
     if (!result.canonicalUrl) {
       result.warnings.push('Missing canonical tag');
     }
 
     // Headings
-    result.h1 = $('h1')
-      .map((_, el) => $(el).text().trim())
-      .get();
-    result.h2 = $('h2')
-      .map((_, el) => $(el).text().trim())
-      .get();
+    result.h1 = Array.from(document.querySelectorAll('h1')).map((el) => (el as { textContent?: string | null }).textContent?.trim() || '');
+    result.h2 = Array.from(document.querySelectorAll('h2')).map((el) => (el as { textContent?: string | null }).textContent?.trim() || '');
 
     if (result.h1.length === 0) {
       result.warnings.push('Missing H1 tag');
@@ -188,9 +188,9 @@ export class SiteCrawler {
     }
 
     // Links
-    $('a[href]').each((_, el) => {
-      const href = $(el).attr('href');
-      if (!href) return;
+    for (const el of document.querySelectorAll('a[href]')) {
+      const href = el.getAttribute('href');
+      if (!href) continue;
 
       try {
         const linkUrl = new URL(href, pageUrl);
@@ -209,21 +209,22 @@ export class SiteCrawler {
       } catch {
         // Invalid URL, skip
       }
-    });
+    }
 
     // Images
-    $('img').each((_, el) => {
-      const src = $(el).attr('src');
-      const alt = $(el).attr('alt');
+    for (const el of document.querySelectorAll('img')) {
+      const src = el.getAttribute('src');
+      const alt = el.getAttribute('alt');
+      const hasAltAttr = alt !== null;
 
       if (src) {
         result.images.push({
           src,
-          alt,
-          hasAlt: alt !== undefined && alt.trim().length > 0,
+          alt: alt ?? undefined,
+          hasAlt: hasAltAttr && alt.trim().length > 0,
         });
       }
-    });
+    }
 
     const imagesWithoutAlt = result.images.filter((img) => !img.hasAlt);
     if (imagesWithoutAlt.length > 0) {

package/src/crawler/sitemap-validator.ts

@@ -3,7 +3,7 @@
  * Validate XML sitemaps
  */
 
-import { load } from 'cheerio';
+import { DOMParser } from 'linkedom';
 import consola from 'consola';
 import type { SeoIssue } from '../types/index.js';
 
@@ -72,34 +72,37 @@ export async function analyzeSitemap(sitemapUrl: string): Promise<SitemapAnalysi
     }
 
     // Parse XML
-    const $ = load(content, { xmlMode: true });
+    const parser = new DOMParser();
+    const doc = parser.parseFromString(content, 'text/xml');
 
     // Check if it's a sitemap index
-    const sitemapIndex = $('sitemapindex');
-    if (sitemapIndex.length > 0) {
+    const sitemapIndex = doc.querySelector('sitemapindex');
+    if (sitemapIndex) {
       analysis.type = 'sitemap-index';
 
-      $('sitemap').each((_, el) => {
-        const loc = $('loc', el).text().trim();
+      for (const sitemap of doc.querySelectorAll('sitemap')) {
+        const loc = sitemap.querySelector('loc')?.textContent?.trim();
         if (loc) {
           analysis.childSitemaps.push(loc);
         }
-      });
+      }
 
       consola.debug(`Sitemap index contains ${analysis.childSitemaps.length} sitemaps`);
     } else {
       analysis.type = 'sitemap';
 
-      $('url').each((_, el) => {
-        const loc = $('loc', el).text().trim();
+      for (const url of doc.querySelectorAll('url')) {
+        const loc = url.querySelector('loc')?.textContent?.trim();
         if (loc) {
           analysis.urls.push(loc);
         }
-      });
-
-      const lastmod = $('url lastmod').first().text().trim();
-      if (lastmod) {
-        analysis.lastmod = lastmod;
+        // Get lastmod from first URL
+        if (!analysis.lastmod) {
+          const lastmod = url.querySelector('lastmod')?.textContent?.trim();
+          if (lastmod) {
+            analysis.lastmod = lastmod;
+          }
+        }
       }
 
       consola.debug(`Sitemap contains ${analysis.urls.length} URLs`);