ci: add automated SEO & crawl audit workflow for landing page

.github/requirements-audit.txt

@@ -0,0 +1,2 @@
+requests>=2.31.0
+beautifulsoup4>=4.12.0

.github/workflows/seo-audit.yml

@@ -0,0 +1,135 @@
+name: Landing Page Audit Pipeline
+
+on:
+  push:
+    branches: [ main, develop ]
+  pull_request:
+    branches: [ main ]
+  workflow_dispatch:
+
+jobs:
+  seo-and-crawl-audit:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
+        with:
+          persist-credentials: false
+
+      - name: Set up Node.js
+        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+        with:
+          node-version: '20'
+
+      # Decide which URL to audit: local build for PRs, production for push/manual
+      - name: Set audit URL
+        id: set-url
+        run: |
+          if [ "${{ github.event_name }}" == "pull_request" ]; then
+            echo "AUDIT_URL=http://localhost:3000" >> $GITHUB_ENV
+          else
+            echo "AUDIT_URL=https://social-share-button.aossie.org/" >> $GITHUB_ENV
+          fi
+
+      # Build and serve the landing page locally so PR audits test the PR's own code
+      - name: Build and serve landing page (PR only)
+        if: github.event_name == 'pull_request'
+        run: |
+          cd landing-page
+          npm ci
+          npm run build
+          npx serve -s out -l 3000 &
+          sleep 5
+
+      # 1. SCAN FOR BROKEN LINKS & ASSETS
+      # Docker-based actions cannot reach localhost on the runner.
+      # linkchecker runs directly on the runner, so it works for both
+      # localhost (PR builds) and the production URL (push/manual).
+      - name: Install Link Checker
+        run: pip install linkchecker
+
+      - name: Audit Broken Links and Images
+        run: linkchecker "${{ env.AUDIT_URL }}" --check-extern --no-warnings
+
+      # 2. RUN LIGHTHOUSE SEO + PERFORMANCE + ACCESSIBILITY AUDIT (no API key needed)
+      - name: Run Lighthouse Audit
+        uses: treosh/lighthouse-ci-action@0d716cfc9995b090bb89fe8f531fc3c133ec89ef # v11
+        with:
+          urls: |
+            ${{ env.AUDIT_URL }}
+          configPath: ./.lighthouserc.json
+          uploadArtifacts: true
+          temporaryPublicStorage: true
+
+      # 3. ADVANCED VERIFICATIONS (Canonical, Schema, Robots.txt)
+      - name: Set up Python for Advanced Custom Scans
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
+        with:
+          python-version: '3.10'
+
+      - name: Install Advanced Audit Dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -r .github/requirements-audit.txt
+
+      - name: Run Advanced Structural Validation
+        env:
+          TARGET_URL: ${{ env.AUDIT_URL }}
+        run: |
+          python - <<EOF
+          import os
+          import json
+          import requests
+          from bs4 import BeautifulSoup
+
+          url = os.environ["TARGET_URL"]
+          response = requests.get(url, headers={"User-Agent": "Googlebot"}, timeout=(10, 30))
+
+          # Test 1: Server Status and Speed
+          print(f"HTTP Status: {response.status_code}")
+          assert response.status_code == 200, "Landing page is down!"
+          ttfb = response.elapsed.total_seconds()
+          ttfb_budget = 2.5  # TTFB must be under 2.5 seconds
+          print(f"Time to First Byte (TTFB): {ttfb}s (Budget: {ttfb_budget}s)")
+          assert ttfb <= ttfb_budget, f"Performance Error: TTFB of {ttfb}s exceeds budget of {ttfb_budget}s"
+
+          soup = BeautifulSoup(response.text, 'html.parser')
+
+          # Test 2: Canonical Tag Check
+          canonicals = soup.find_all('link', rel='canonical')
+          assert len(canonicals) > 0, "CRITICAL: Missing rel='canonical' tag!"
+          assert len(canonicals) == 1, f"CRITICAL: Duplicate canonical tags found ({len(canonicals)}). Expected exactly 1!"
+
+          canonical_href = canonicals[0].get('href', '').strip()
+          print(f"Canonical URL found: {canonical_href if canonical_href else 'Empty'}")
+
+          assert canonical_href, "CRITICAL: The rel='canonical' tag has an empty or missing 'href' attribute!"
+
+          normalized_href = canonical_href.rstrip('/')
+          normalized_url = "https://social-share-button.aossie.org"
+          assert normalized_href == normalized_url, f"CRITICAL: Canonical URL '{canonical_href}' does not match the expected base URL '{normalized_url}/'!"
+
+          # Test 3: Heading Hierarchy Check
+          h1s = soup.find_all('h1')
+          print(f"Found {len(h1s)} H1 tags.")
+          assert len(h1s) == 1, "SEO Error: Landing page must have exactly ONE <h1> tag."
+
+          # Test 4: Schema Markup Verification (no extruct – uses built-in json)
+          script_tags = soup.find_all('script', type='application/ld+json')
+          json_ld = []
+          for index, tag in enumerate(script_tags, start=1):
+              raw = tag.get_text(strip=True)
+              assert raw, f"CRITICAL: JSON-LD block {index} is empty."
+              try:
+                  data = json.loads(raw)
+                  json_ld.append(data)
+              except json.JSONDecodeError as error:
+                  raise AssertionError(
+                      f"CRITICAL: JSON-LD block {index} is invalid: {error}"
+                  ) from error
+
+          print(f"Structured Data: Found {len(json_ld)} JSON-LD blocks.")
+          assert len(json_ld) > 0, "Warning: No Structured Schema found on page."
+
+          print("✅ All advanced landing page validations passed successfully!")
+          EOF

.lighthouserc.json

@@ -0,0 +1,15 @@
+{
+  "ci": {
+    "assert": {
+      "assertions": {
+        "categories:performance": ["error", { "minScore": 0.8 }],
+        "categories:accessibility": ["error", { "minScore": 0.9 }],
+        "categories:seo": ["error", { "minScore": 0.9 }],
+        "categories:best-practices": ["error", { "minScore": 0.9 }]
+      }
+    },
+    "upload": {
+      "target": "temporary-public-storage"
+    }
+  }
+}