Release v2.2.0

CHANGELOG.md

@@ -1,5 +1,20 @@
 # check-http-status changelog
 
+## 2.2.0 - Unreleased
+
+### New
+
+- Crawled pages record the first `h1`, the number of H1s (`h1Count`) and the `metaDescription`
+- Assets record where they came from (`assetType`: `image`, `script`, `stylesheet`, `icon`, `media` or `iframe`)
+- Images record their `alt` texts and `title` attributes, per page and in total, and `missingAlt` when an `<img>` has no `alt` attribute
+- Excel and CSV reports have Asset Type, H1, # H1, Meta Description, Alt Text, Image Title and Missing Alt columns
+- HTML report: filters for images, scripts, stylesheets, missing title, missing or multiple H1, missing meta description and missing alt text
+
+### Fixed
+
+- HTML report: search only looked inside the selected filter (*All issues* by default), so a URL without an issue was never found. Filter counts now follow the search, and a search with no matches in the selected filter offers to show all matches
+- HTML report: search no longer matches every link on a page whose URL contains the search text; it looks in the URL, redirect, title, H1, link text and alt text
+
 ## 2.1.0 - Oct 2, 2026
 
 ### New

README.md

@@ -238,8 +238,10 @@ await writeReport(report, 'report.xlsx', 'xlsx');
 | `error` | Connection error (timeout, DNS, TLS…) if the request failed. |
 | `type`, `linkType`, `scope` | `internal`/`external`, `page`/`asset`, and whether it was crawled, excluded, checked or skipped. |
 | `redirectTo`, `redirectChain`, `finalUrl`, `finalStatus`, `redirectCount` | Redirect details. `note` is set for loops or too many redirects. |
-| `foundOn` | `[{ page, anchors, count, kind }]`, where `kind` is `link`, `redirect` or `sitemap`. |
-| `title`, `contentType`, `responseTime`, `depth`, `inSitemap`, `orphan` | Page details. |
+| `foundOn` | `[{ page, anchors, count, kind }]`, where `kind` is `link`, `redirect` or `sitemap`. Images also have `alt`, `imageTitle` and `missingAlt` for that page. |
+| `title`, `h1`, `h1Count`, `metaDescription` | Crawled pages: `<title>`, the first `<h1>` and how many there are, and the meta description. |
+| `assetType`, `alt`, `imageTitle`, `missingAlt` | Assets: `image`, `script`, `stylesheet`, `icon`, `media` or `iframe`. Images: every alt text and `title` used for it, and whether an `<img>` has no `alt` attribute (`alt=""` counts as set). |
+| `contentType`, `responseTime`, `depth`, `inSitemap`, `orphan` | Page details. |
 
 ## Config file
 

index.d.ts

@@ -151,6 +151,12 @@ declare namespace checkHttpStatus {
     /** Times the link appears on that page. */
     count: number;
     kind: 'link' | 'redirect' | 'sitemap' | 'seed';
+    /** Images only: `alt` texts used on that page. */
+    alt?: string[];
+    /** Images only: `title` attributes used on that page. */
+    imageTitle?: string[];
+    /** Images only: `<img>` tags on that page without an `alt` attribute. */
+    missingAlt?: number;
   }
 
   interface RedirectHop {
@@ -167,6 +173,8 @@ declare namespace checkHttpStatus {
     error: string;
     type: 'internal' | 'external';
     linkType: 'page' | 'asset';
+    /** Assets only: the tag it was found in. */
+    assetType: '' | 'image' | 'script' | 'stylesheet' | 'icon' | 'media' | 'iframe';
     scope: Scope;
     redirectTo: string;
     redirectChain: RedirectHop[];
@@ -179,6 +187,15 @@ declare namespace checkHttpStatus {
     note: string;
     foundOn: FoundOn[];
     title: string;
+    /** Crawled pages: first `<h1>` and how many there are. */
+    h1: string;
+    h1Count: number;
+    metaDescription: string;
+    /** Images: every `alt` text and `title` attribute used for it. */
+    alt: string[];
+    imageTitle: string[];
+    /** Images: some `<img>` has no `alt` attribute (`alt=""` is fine). */
+    missingAlt: boolean;
     contentType: string;
     responseTime: number | null;
     depth: number;

lib/checker.js

@@ -190,7 +190,8 @@ class Checker {
     return { depth, 'scope': 'crawl' };
   }
 
-  discover(raw, { from = null, fromUrl = null, kind = 'link', anchor = '', base, isAsset = false, seed = null } = {}) {
+  discover(raw, { from = null, fromUrl = null, kind = 'link', anchor = '', base, assetType = '', image = null, seed = null } = {}) {
+    const isAsset = !!assetType;
     const url = this.normalize(raw, base || (from && from.url) || undefined);
     if (!url) {
       return;
@@ -206,13 +207,17 @@ class Checker {
       }
 
       record = {
+        'assetType': assetType,
         'contentType': '',
         'crawled': false,
         'depth': depth,
         'error': '',
+        'h1': '',
+        'h1Count': 0,
         'internal': this.isInternal(url),
         'isStart': seed === 'crawl',
         'linkType': isAsset ? 'asset' : 'page',
+        'metaDescription': '',
         'note': '',
         'queued': false,
         'redirectHops': kind === 'redirect' ? from.redirectHops + 1 : 0,
@@ -249,6 +254,18 @@ class Checker {
       if (anchor) {
         source.anchors.add(anchor);
       }
+
+      if (image) {
+        source.alt = source.alt || new Set();
+        source.imageTitle = source.imageTitle || new Set();
+        source.missingAlt = (source.missingAlt || 0) + (image.alt === null ? 1 : 0);
+        if (image.alt) {
+          source.alt.add(image.alt);
+        }
+        if (image.title) {
+          source.imageTitle.add(image.title);
+        }
+      }
     }
   }
 
@@ -434,8 +451,8 @@ class Checker {
 
       this.discover(target.href, {
         'anchor': '(redirect)',
+        'assetType': record.assetType,
         'from': record,
-        'isAsset': record.linkType === 'asset',
         'kind': 'redirect'
       });
       return;
@@ -450,7 +467,12 @@ class Checker {
 
   extractLinks(record, html) {
     const $ = cheerio.load(html);
-    record.title = $('title').first().text().replace(/\s+/g, ' ').trim().slice(0, 300);
+    const text = (node) => node.text().replace(/\s+/g, ' ').trim().slice(0, 300);
+    record.title = text($('title').first());
+    record.h1 = text($('h1').first());
+    record.h1Count = $('h1').length;
+    record.metaDescription = ($('meta[name]').filter((_, el) => $(el).attr('name').toLowerCase() === 'description').first().attr('content') || '')
+      .replace(/\s+/g, ' ').trim().slice(0, 500);
 
     let base = record.url;
     const baseHref = $('base[href]').attr('href');
@@ -489,11 +511,19 @@ class Checker {
 
       for (const [selector, attr, label] of assets) {
         $(selector).each((_, el) => {
-          this.discover($(el).attr(attr), {
+          const $el = $(el);
+          // `alt=""` marks a decorative image; only a missing attribute counts as missing.
+          const image = label === 'image' ? {
+            'alt': $el.attr('alt') === undefined ? null : $el.attr('alt').replace(/\s+/g, ' ').trim().slice(0, 300),
+            'title': ($el.attr('title') || '').replace(/\s+/g, ' ').trim().slice(0, 300)
+          } : null;
+
+          this.discover($el.attr(attr), {
             'anchor': `(${label})`,
+            'assetType': label,
             'base': base,
             'from': record,
-            'isAsset': true
+            image
           });
         });
       }
@@ -573,15 +603,27 @@ class Checker {
   toResult(record) {
     const { chain, loop } = record.redirectTo ? this.redirectChain(record) : { 'chain': [], 'loop': false };
     const final = chain[chain.length - 1];
-    const foundOn = [...record.sources].map(([page, source]) => ({
-      'anchors': [...source.anchors],
-      'count': source.count,
-      'kind': source.kind,
-      'page': page
-    }));
+    const foundOn = [...record.sources].map(([page, source]) => {
+      const entry = {
+        'anchors': [...source.anchors],
+        'count': source.count,
+        'kind': source.kind,
+        'page': page
+      };
+      if (source.alt) {
+        entry.alt = [...source.alt];
+        entry.imageTitle = [...source.imageTitle];
+        entry.missingAlt = source.missingAlt;
+      }
+
+      return entry;
+    });
+    const unique = (key) => [...new Set(foundOn.flatMap((source) => source[key] || []))];
     const inSitemap = foundOn.some((source) => source.kind === 'sitemap');
 
     return {
+      'alt': unique('alt'),
+      'assetType': record.assetType,
       'botProtection': record.botProtection || '',
       'category': categorize(record),
       'contentType': record.contentType,
@@ -591,8 +633,13 @@ class Checker {
       'finalStatus': final ? final.status : null,
       'finalUrl': final ? final.url : '',
       'foundOn': foundOn,
+      'h1': record.h1,
+      'h1Count': record.h1Count,
+      'imageTitle': unique('imageTitle'),
       'inSitemap': inSitemap,
       'linkType': record.linkType,
+      'metaDescription': record.metaDescription,
+      'missingAlt': foundOn.some((source) => source.missingAlt > 0),
       'note': loop ? 'Redirect loop' : record.note,
       'orphan': this.crawlMode && inSitemap && !record.isStart && !this.isLinked(record),
       'redirectChain': chain,

lib/report/csv.js

@@ -11,11 +11,18 @@ const COLUMNS = [
   ['category', 'Category'],
   ['type', 'Type'],
   ['linkType', 'Link Type'],
+  ['assetType', 'Asset Type'],
   ['scope', 'Crawl'],
   ['redirectCount', '# Redirects'],
   ['finalUrl', 'Final URL'],
   ['finalStatus', 'Final Status'],
   ['title', 'Title'],
+  ['h1', 'H1'],
+  ['h1Count', '# H1'],
+  ['metaDescription', 'Meta Description'],
+  ['alt', 'Alt Text'],
+  ['imageTitle', 'Image Title'],
+  ['missingAlt', 'Missing Alt'],
   ['contentType', 'Content Type'],
   ['depth', 'Depth'],
   ['responseTime', 'Response (ms)'],

lib/report/excel.js

@@ -31,11 +31,18 @@ const URL_COLUMNS = [
   CATEGORY,
   { 'header': 'Type', 'key': 'type', 'width': 10 },
   { 'header': 'Link Type', 'key': 'linkType', 'width': 10 },
+  { 'header': 'Asset Type', 'key': 'assetType', 'width': 11 },
   { 'header': 'Crawl', 'key': 'scope', 'width': 22 },
   { 'header': '# Redirects', 'key': 'redirectCount', 'width': 11 },
   FINAL_URL,
   FINAL_STATUS,
   { 'header': 'Title', 'key': 'title', 'width': 40 },
+  { 'header': 'H1', 'key': 'h1', 'width': 40 },
+  { 'header': '# H1', 'key': 'h1Count', 'width': 6 },
+  { 'header': 'Meta Description', 'key': 'metaDescription', 'width': 60 },
+  { 'header': 'Alt Text', 'key': 'alt', 'width': 40 },
+  { 'header': 'Image Title', 'key': 'imageTitle', 'width': 30 },
+  { 'header': 'Missing Alt', 'key': 'missingAlt', 'width': 11 },
   { 'header': 'Content Type', 'key': 'contentType', 'width': 20 },
   { 'header': 'Depth', 'key': 'depth', 'width': 7 },
   { 'header': 'Response (ms)', 'key': 'responseTime', 'width': 13 },

lib/report/rows.js

@@ -44,17 +44,27 @@ function finalUrlLabel(result) {
 const byTypeThenUrl = (a, b) => (a.type === b.type ? 0 : a.type === 'internal' ? -1 : 1) || a.url.localeCompare(b.url);
 const byIssueThenUrl = (a, b) => ISSUE_ORDER.indexOf(a.category) - ISSUE_ORDER.indexOf(b.category) || a.url.localeCompare(b.url);
 
+// Older reports have no SEO fields.
+const list = (values) => (values || []).join(' | ');
+
 function toRow(result) {
   return {
+    'alt': list(result.alt),
+    'assetType': result.assetType || '',
     'category': result.category,
     'contentType': result.contentType,
     'depth': result.depth,
     'finalStatus': result.finalStatus === null ? '' : result.finalStatus,
     'finalUrl': finalUrlLabel(result),
     'foundOn': foundOnLabel(result),
     'foundOnCount': result.foundOn.length,
+    'h1': result.h1 || '',
+    'h1Count': result.crawled ? result.h1Count || 0 : '',
+    'imageTitle': list(result.imageTitle),
     'inSitemap': result.inSitemap ? 'Yes' : '',
     'linkType': result.linkType,
+    'metaDescription': result.metaDescription || '',
+    'missingAlt': result.missingAlt ? 'Yes' : '',
     'orphan': result.orphan ? 'Yes' : '',
     'redirectCount': result.redirectCount || '',
     'redirectTo': result.redirectTo,