Simple SEO Testing

from locust import task, HttpUser
import re
import random

class SEOTestUser(HttpUser):
    def on_start(self):
        # Pages to test for SEO
        self.test_pages = [
            "/",
            "/about",
            "/products",
            "/contact",
            "/blog"
        ]

    @task(4)
    def test_page_titles(self):
        """Test that pages have proper titles"""
        page = random.choice(self.test_pages)
        
        with self.client.get(page, name="SEO Title Test") as response:
            if response.status_code == 200:
                html = response.text
                
                # Check for title tag
                title_match = re.search(r'<title[^>]*>(.*?)</title>', html, re.IGNORECASE | re.DOTALL)
                
                if title_match:
                    title = title_match.group(1).strip()
                    title_length = len(title)
                    
                    print(f"Page {page}: Title '{title}' ({title_length} chars)")
                    
                    # Check title length (SEO best practice: 50-60 chars)
                    if title_length == 0:
                        response.failure(f"Empty title on {page}")
                    elif title_length > 60:
                        print(f"WARNING: Title too long on {page} ({title_length} chars)")
                    elif title_length < 30:
                        print(f"WARNING: Title too short on {page} ({title_length} chars)")
                    else:
                        print(f"Title length OK on {page}")
                else:
                    print(f"ERROR: No title tag found on {page}")
                    response.failure(f"Missing title tag on {page}")
            else:
                response.failure(f"Page {page} failed to load: {response.status_code}")

    @task(3)
    def test_meta_descriptions(self):
        """Test that pages have meta descriptions"""
        page = random.choice(self.test_pages)
        
        with self.client.get(page, name="SEO Meta Description Test") as response:
            if response.status_code == 200:
                html = response.text
                
                # Check for meta description
                desc_pattern = r'<meta[^>]*name=["\']description["\'][^>]*content=["\']([^"\']*)["\'][^>]*>'
                desc_match = re.search(desc_pattern, html, re.IGNORECASE)
                
                if desc_match:
                    description = desc_match.group(1).strip()
                    desc_length = len(description)
                    
                    print(f"Page {page}: Meta description ({desc_length} chars)")
                    
                    # Check description length (SEO best practice: 150-160 chars)
                    if desc_length == 0:
                        response.failure(f"Empty meta description on {page}")
                    elif desc_length > 160:
                        print(f"WARNING: Meta description too long on {page} ({desc_length} chars)")
                    elif desc_length < 120:
                        print(f"WARNING: Meta description too short on {page} ({desc_length} chars)")
                    else:
                        print(f"Meta description length OK on {page}")
                else:
                    print(f"ERROR: No meta description found on {page}")
                    response.failure(f"Missing meta description on {page}")
            else:
                response.failure(f"Page {page} failed to load: {response.status_code}")

    @task(2)
    def test_heading_structure(self):
        """Test page heading structure (H1, H2, etc.)"""
        page = random.choice(self.test_pages)
        
        with self.client.get(page, name="SEO Heading Test") as response:
            if response.status_code == 200:
                html = response.text
                
                # Check for H1 tags
                h1_matches = re.findall(r'<h1[^>]*>(.*?)</h1>', html, re.IGNORECASE | re.DOTALL)
                h1_count = len(h1_matches)
                
                print(f"Page {page}: Found {h1_count} H1 tags")
                
                if h1_count == 0:
                    print(f"WARNING: No H1 tag found on {page}")
                elif h1_count > 1:
                    print(f"WARNING: Multiple H1 tags on {page} ({h1_count})")
                else:
                    h1_text = h1_matches[0].strip()
                    print(f"H1 on {page}: '{h1_text}'")
                
                # Check for H2 tags
                h2_matches = re.findall(r'<h2[^>]*>', html, re.IGNORECASE)
                h2_count = len(h2_matches)
                print(f"Page {page}: Found {h2_count} H2 tags")
                
            else:
                response.failure(f"Page {page} failed to load: {response.status_code}")

    @task(2)
    def test_meta_viewport(self):
        """Test for mobile viewport meta tag"""
        page = random.choice(self.test_pages)
        
        with self.client.get(page, name="SEO Viewport Test") as response:
            if response.status_code == 200:
                html = response.text
                
                # Check for viewport meta tag
                viewport_pattern = r'<meta[^>]*name=["\']viewport["\'][^>]*>'
                viewport_match = re.search(viewport_pattern, html, re.IGNORECASE)
                
                if viewport_match:
                    print(f"Page {page}: Viewport meta tag found")
                    
                    # Check if it includes width=device-width
                    if 'width=device-width' in viewport_match.group(0).lower():
                        print(f"Viewport includes device-width on {page}")
                    else:
                        print(f"WARNING: Viewport missing device-width on {page}")
                else:
                    print(f"WARNING: No viewport meta tag on {page}")
                    response.failure(f"Missing viewport meta tag on {page}")
            else:
                response.failure(f"Page {page} failed to load: {response.status_code}")

    @task(1)
    def test_canonical_urls(self):
        """Test for canonical URL tags"""
        page = random.choice(self.test_pages)
        
        with self.client.get(page, name="SEO Canonical Test") as response:
            if response.status_code == 200:
                html = response.text
                
                # Check for canonical link
                canonical_pattern = r'<link[^>]*rel=["\']canonical["\'][^>]*href=["\']([^"\']*)["\'][^>]*>'
                canonical_match = re.search(canonical_pattern, html, re.IGNORECASE)
                
                if canonical_match:
                    canonical_url = canonical_match.group(1)
                    print(f"Page {page}: Canonical URL found - {canonical_url}")
                else:
                    print(f"INFO: No canonical URL on {page} (may be optional)")
            else:
                response.failure(f"Page {page} failed to load: {response.status_code}")

    @task(1)
    def test_open_graph_tags(self):
        """Test for basic Open Graph tags"""
        page = random.choice(self.test_pages)
        
        with self.client.get(page, name="SEO Open Graph Test") as response:
            if response.status_code == 200:
                html = response.text
                
                # Check for og:title
                og_title_pattern = r'<meta[^>]*property=["\']og:title["\'][^>]*content=["\']([^"\']*)["\'][^>]*>'
                og_title_match = re.search(og_title_pattern, html, re.IGNORECASE)
                
                # Check for og:description
                og_desc_pattern = r'<meta[^>]*property=["\']og:description["\'][^>]*content=["\']([^"\']*)["\'][^>]*>'
                og_desc_match = re.search(og_desc_pattern, html, re.IGNORECASE)
                
                og_tags_found = 0
                if og_title_match:
                    og_tags_found += 1
                    print(f"Page {page}: og:title found")
                
                if og_desc_match:
                    og_tags_found += 1
                    print(f"Page {page}: og:description found")
                
                if og_tags_found == 0:
                    print(f"INFO: No Open Graph tags on {page}")
                else:
                    print(f"Page {page}: {og_tags_found} Open Graph tags found")
            else:
                response.failure(f"Page {page} failed to load: {response.status_code}")

    @task(1)
    def test_robots_meta(self):
        """Test for robots meta tags"""
        page = random.choice(self.test_pages)
        
        with self.client.get(page, name="SEO Robots Test") as response:
            if response.status_code == 200:
                html = response.text
                
                # Check for robots meta tag
                robots_pattern = r'<meta[^>]*name=["\']robots["\'][^>]*content=["\']([^"\']*)["\'][^>]*>'
                robots_match = re.search(robots_pattern, html, re.IGNORECASE)
                
                if robots_match:
                    robots_content = robots_match.group(1).lower()
                    print(f"Page {page}: Robots directive - {robots_content}")
                    
                    # Check for noindex (might be intentional)
                    if 'noindex' in robots_content:
                        print(f"WARNING: Page {page} has noindex directive")
                else:
                    print(f"INFO: No robots meta tag on {page} (using defaults)")
            else:
                response.failure(f"Page {page} failed to load: {response.status_code}")

    @task(1)
    def test_page_load_speed(self):
        """Test page load speed (basic SEO factor)"""
        page = random.choice(self.test_pages)
        
        import time
        start_time = time.time()
        
        with self.client.get(page, name="SEO Speed Test") as response:
            load_time = time.time() - start_time
            
            if response.status_code == 200:
                print(f"Page {page}: Load time {load_time:.2f}s")
                
                # Basic speed thresholds
                if load_time > 3.0:
                    print(f"WARNING: Slow page load on {page} ({load_time:.2f}s)")
                elif load_time > 1.5:
                    print(f"MODERATE: Page load time on {page} ({load_time:.2f}s)")
                else:
                    print(f"GOOD: Fast page load on {page} ({load_time:.2f}s)")
            else:
                response.failure(f"Page {page} failed to load: {response.status_code}")