Update app.py

app.py

@@ -0,0 +1,455 @@
+"""
+Web Testing Suite for Hugging Face Spaces
+Interactive UI with Gradio for Performance, SEO, Security, Accessibility Testing
+"""
+
+import gradio as gr
+import time
+import ssl
+import socket
+import json
+import requests
+from urllib.parse import urljoin, urlparse
+from bs4 import BeautifulSoup
+from datetime import datetime
+import re
+from typing import Dict, List, Tuple
+
+# ============================================================================
+# PERFORMANCE TESTING
+# ============================================================================
+
+class PerformanceTester:
+    def __init__(self, url: str):
+        self.url = url
+    
+    def measure_ttfb(self) -> float:
+        try:
+            start = time.time()
+            response = requests.get(self.url, stream=True, timeout=10)
+            ttfb = time.time() - start
+            return round(ttfb * 1000, 2)
+        except Exception as e:
+            return f"Error: {e}"
+    
+    def get_payload_size(self) -> Dict:
+        try:
+            response = requests.get(self.url, timeout=10)
+            html_size = len(response.content)
+            
+            soup = BeautifulSoup(response.content, 'html.parser')
+            
+            scripts = len(soup.find_all('script', src=True))
+            stylesheets = len(soup.find_all('link', rel='stylesheet'))
+            images = len(soup.find_all('img'))
+            
+            return {
+                'html_size_kb': round(html_size / 1024, 2),
+                'script_count': scripts,
+                'stylesheet_count': stylesheets,
+                'image_count': images,
+                'compression': response.headers.get('Content-Encoding', 'none')
+            }
+        except Exception as e:
+            return {'error': str(e)}
+    
+    def test_all(self) -> str:
+        result = f"⚡ **PERFORMANCE TEST RESULTS**\n\n"
+        result += f"🌐 URL: {self.url}\n\n"
+        
+        # TTFB
+        ttfb = self.measure_ttfb()
+        if isinstance(ttfb, float):
+            status = "✅ Excellent" if ttfb < 200 else "⚠️ Needs Improvement" if ttfb < 500 else "❌ Poor"
+            result += f"⏱️ **Time To First Byte:** {ttfb} ms {status}\n"
+        else:
+            result += f"⏱️ **Time To First Byte:** {ttfb}\n"
+        
+        # Payload
+        payload = self.get_payload_size()
+        if 'error' not in payload:
+            result += f"\n📦 **Page Size:** {payload['html_size_kb']} KB\n"
+            result += f"📜 **Scripts:** {payload['script_count']}\n"
+            result += f"🎨 **Stylesheets:** {payload['stylesheet_count']}\n"
+            result += f"🖼️ **Images:** {payload['image_count']}\n"
+            result += f"🗜️ **Compression:** {payload['compression']}\n"
+        
+        return result
+
+
+# ============================================================================
+# SEO AUDITOR
+# ============================================================================
+
+class SEOAuditor:
+    def __init__(self, url: str):
+        self.url = url
+        self.soup = None
+    
+    def fetch_page(self):
+        try:
+            response = requests.get(self.url, timeout=10)
+            self.soup = BeautifulSoup(response.content, 'html.parser')
+        except Exception as e:
+            return False
+        return True
+    
+    def check_meta_tags(self) -> Dict:
+        title = self.soup.find('title')
+        description = self.soup.find('meta', attrs={'name': 'description'})
+        og_title = self.soup.find('meta', property='og:title')
+        og_description = self.soup.find('meta', property='og:description')
+        og_image = self.soup.find('meta', property='og:image')
+        canonical = self.soup.find('link', rel='canonical')
+        
+        return {
+            'title': title.text if title else '❌ Missing',
+            'title_length': len(title.text) if title else 0,
+            'description': description.get('content')[:100] + '...' if description else '❌ Missing',
+            'og_title': '✅ Present' if og_title else '❌ Missing',
+            'og_description': '✅ Present' if og_description else '❌ Missing',
+            'og_image': '✅ Present' if og_image else '❌ Missing',
+            'canonical': '✅ Present' if canonical else '❌ Missing'
+        }
+    
+    def check_headers(self) -> Dict:
+        h1 = self.soup.find_all('h1')
+        h2 = self.soup.find_all('h2')
+        h3 = self.soup.find_all('h3')
+        
+        return {
+            'h1_count': len(h1),
+            'h1_text': [h.text.strip()[:50] for h in h1][:3],
+            'h2_count': len(h2),
+            'h3_count': len(h3),
+            'valid': len(h1) == 1
+        }
+    
+    def check_sitemap(self) -> Dict:
+        sitemap_url = urljoin(self.url, '/sitemap.xml')
+        try:
+            resp = requests.get(sitemap_url, timeout=5)
+            return {'exists': resp.status_code == 200}
+        except:
+            return {'exists': False}
+    
+    def audit(self) -> str:
+        result = f"🔍 **SEO AUDIT RESULTS**\n\n"
+        result += f"🌐 URL: {self.url}\n\n"
+        
+        if not self.fetch_page():
+            return result + "❌ Failed to fetch page"
+        
+        # Meta Tags
+        meta = self.check_meta_tags()
+        result += f"📝 **Meta Tags**\n"
+        result += f"• Title: {meta['title']}\n"
+        result += f"• Title Length: {meta['title_length']} chars "
+        result += f"{'✅' if 50 <= meta['title_length'] <= 60 else '⚠️'}\n"
+        result += f"• Description: {meta['description']}\n"
+        result += f"• OG Title: {meta['og_title']}\n"
+        result += f"• OG Description: {meta['og_description']}\n"
+        result += f"• OG Image: {meta['og_image']}\n"
+        result += f"• Canonical: {meta['canonical']}\n\n"
+        
+        # Headers
+        headers = self.check_headers()
+        result += f"📋 **Header Structure**\n"
+        result += f"• H1 Count: {headers['h1_count']} {'✅' if headers['valid'] else '❌'}\n"
+        if headers['h1_text']:
+            result += f"• H1 Text: {headers['h1_text'][0]}\n"
+        result += f"• H2 Count: {headers['h2_count']}\n"
+        result += f"• H3 Count: {headers['h3_count']}\n\n"
+        
+        # Sitemap
+        sitemap = self.check_sitemap()
+        result += f"🗺️ **Sitemap:** {'✅ Found' if sitemap['exists'] else '❌ Not Found'}\n"
+        
+        return result
+
+
+# ============================================================================
+# SECURITY TESTER
+# ============================================================================
+
+class SecurityTester:
+    def __init__(self, url: str):
+        self.url = url
+        self.domain = urlparse(url).netloc
+    
+    def check_ssl(self) -> Dict:
+        try:
+            context = ssl.create_default_context()
+            with socket.create_connection((self.domain, 443), timeout=5) as sock:
+                with context.wrap_socket(sock, server_hostname=self.domain) as ssock:
+                    cert = ssock.getpeercert()
+                    return {
+                        'valid': True,
+                        'expires': cert['notAfter']
+                    }
+        except Exception as e:
+            return {'valid': False, 'error': str(e)}
+    
+    def check_security_headers(self) -> Dict:
+        try:
+            response = requests.get(self.url, timeout=10)
+            headers = response.headers
+            
+            return {
+                'hsts': headers.get('Strict-Transport-Security', '❌'),
+                'x_content_type': headers.get('X-Content-Type-Options', '❌'),
+                'x_frame': headers.get('X-Frame-Options', '❌'),
+                'csp': headers.get('Content-Security-Policy', '❌'),
+                'referrer': headers.get('Referrer-Policy', '❌')
+            }
+        except Exception as e:
+            return {'error': str(e)}
+    
+    def check_mixed_content(self) -> List[str]:
+        if not self.url.startswith('https'):
+            return ['⚠️ Page is not HTTPS']
+        
+        try:
+            response = requests.get(self.url, timeout=10)
+            soup = BeautifulSoup(response.content, 'html.parser')
+            mixed = []
+            
+            for tag in soup.find_all(['img', 'script', 'link']):
+                src = tag.get('src') or tag.get('href', '')
+                if src.startswith('http://'):
+                    mixed.append(src[:50])
+            
+            return mixed[:5] if mixed else ['✅ No mixed content']
+        except:
+            return ['Error checking']
+    
+    def test_all(self) -> str:
+        result = f"🔒 **SECURITY TEST RESULTS**\n\n"
+        result += f"🌐 URL: {self.url}\n\n"
+        
+        # SSL
+        ssl_info = self.check_ssl()
+        if ssl_info['valid']:
+            result += f"🔐 **SSL Certificate:** ✅ Valid\n"
+            result += f"• Expires: {ssl_info['expires']}\n\n"
+        else:
+            result += f"🔐 **SSL Certificate:** ❌ Invalid\n\n"
+        
+        # Security Headers
+        headers = self.check_security_headers()
+        if 'error' not in headers:
+            result += f"🛡️ **Security Headers**\n"
+            result += f"• HSTS: {'✅' if headers['hsts'] != '❌' else '❌'}\n"
+            result += f"• X-Content-Type-Options: {'✅' if headers['x_content_type'] != '❌' else '❌'}\n"
+            result += f"• X-Frame-Options: {'✅' if headers['x_frame'] != '❌' else '❌'}\n"
+            result += f"• Content-Security-Policy: {'✅' if headers['csp'] != '❌' else '❌'}\n"
+            result += f"• Referrer-Policy: {'✅' if headers['referrer'] != '❌' else '❌'}\n\n"
+        
+        # Mixed Content
+        mixed = self.check_mixed_content()
+        result += f"📦 **Mixed Content Check**\n"
+        for item in mixed:
+            result += f"• {item}\n"
+        
+        return result
+
+
+# ============================================================================
+# ACCESSIBILITY TESTER
+# ============================================================================
+
+class AccessibilityTester:
+    def __init__(self, url: str):
+        self.url = url
+        self.soup = None
+    
+    def fetch_page(self):
+        try:
+            response = requests.get(self.url, timeout=10)
+            self.soup = BeautifulSoup(response.content, 'html.parser')
+            return True
+        except:
+            return False
+    
+    def check_alt_attributes(self) -> Dict:
+        images = self.soup.find_all('img')
+        missing_alt = []
+        
+        for img in images:
+            if not img.get('alt'):
+                src = img.get('src', 'No src')[:50]
+                missing_alt.append(src)
+        
+        return {
+            'total': len(images),
+            'missing': len(missing_alt),
+            'samples': missing_alt[:5]
+        }
+    
+    def check_form_labels(self) -> Dict:
+        inputs = self.soup.find_all(['input', 'textarea', 'select'])
+        missing_labels = 0
+        
+        for inp in inputs:
+            input_id = inp.get('id')
+            aria_label = inp.get('aria-label')
+            
+            if input_id:
+                label = self.soup.find('label', attrs={'for': input_id})
+                if not label and not aria_label:
+                    missing_labels += 1
+            elif not aria_label:
+                missing_labels += 1
+        
+        return {
+            'total': len(inputs),
+            'missing': missing_labels
+        }
+    
+    def test_all(self) -> str:
+        result = f"♿ **ACCESSIBILITY TEST RESULTS**\n\n"
+        result += f"🌐 URL: {self.url}\n\n"
+        
+        if not self.fetch_page():
+            return result + "❌ Failed to fetch page"
+        
+        # Alt Attributes
+        alt_check = self.check_alt_attributes()
+        result += f"🖼️ **Image Alt Attributes**\n"
+        result += f"• Total Images: {alt_check['total']}\n"
+        result += f"• Missing Alt: {alt_check['missing']} "
+        result += f"{'✅' if alt_check['missing'] == 0 else '❌'}\n"
+        if alt_check['samples']:
+            result += f"• Samples: {', '.join(alt_check['samples'][:2])}\n"
+        result += f"\n"
+        
+        # Form Labels
+        label_check = self.check_form_labels()
+        result += f"📝 **Form Labels**\n"
+        result += f"• Total Inputs: {label_check['total']}\n"
+        result += f"• Missing Labels: {label_check['missing']} "
+        result += f"{'✅' if label_check['missing'] == 0 else '❌'}\n"
+        
+        return result
+
+
+# ============================================================================
+# GRADIO INTERFACE
+# ============================================================================
+
+def run_performance_test(url):
+    if not url:
+        return "⚠️ Please enter a URL"
+    if not url.startswith(('http://', 'https://')):
+        url = 'https://' + url
+    try:
+        tester = PerformanceTester(url)
+        return tester.test_all()
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
+
+def run_seo_audit(url):
+    if not url:
+        return "⚠️ Please enter a URL"
+    if not url.startswith(('http://', 'https://')):
+        url = 'https://' + url
+    try:
+        auditor = SEOAuditor(url)
+        return auditor.audit()
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
+
+def run_security_test(url):
+    if not url:
+        return "⚠️ Please enter a URL"
+    if not url.startswith(('http://', 'https://')):
+        url = 'https://' + url
+    try:
+        tester = SecurityTester(url)
+        return tester.test_all()
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
+
+def run_accessibility_test(url):
+    if not url:
+        return "⚠️ Please enter a URL"
+    if not url.startswith(('http://', 'https://')):
+        url = 'https://' + url
+    try:
+        tester = AccessibilityTester(url)
+        return tester.test_all()
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
+
+def run_all_tests(url):
+    if not url:
+        return "⚠️ Please enter a URL", "", "", ""
+    if not url.startswith(('http://', 'https://')):
+        url = 'https://' + url
+    
+    perf = run_performance_test(url)
+    seo = run_seo_audit(url)
+    sec = run_security_test(url)
+    a11y = run_accessibility_test(url)
+    
+    return perf, seo, sec, a11y
+
+# Create Gradio Interface
+with gr.Blocks(title="Web Testing Suite", theme=gr.themes.Soft()) as demo:
+    gr.Markdown("""
+    # 🚀 Comprehensive Web Testing Suite
+    Test any website for **Performance**, **SEO**, **Security**, and **Accessibility**
+    """)
+    
+    with gr.Row():
+        url_input = gr.Textbox(
+            label="🌐 Website URL",
+            placeholder="https://example.com",
+            scale=3
+        )
+    
+    with gr.Row():
+        test_all_btn = gr.Button("🔍 Run All Tests", variant="primary", scale=1)
+    
+    with gr.Row():
+        perf_btn = gr.Button("⚡ Performance", scale=1)
+        seo_btn = gr.Button("🔍 SEO", scale=1)
+        sec_btn = gr.Button("🔒 Security", scale=1)
+        a11y_btn = gr.Button("♿ Accessibility", scale=1)
+    
+    with gr.Tabs():
+        with gr.Tab("⚡ Performance"):
+            perf_output = gr.Textbox(label="Results", lines=15)
+        
+        with gr.Tab("🔍 SEO"):
+            seo_output = gr.Textbox(label="Results", lines=15)
+        
+        with gr.Tab("🔒 Security"):
+            sec_output = gr.Textbox(label="Results", lines=15)
+        
+        with gr.Tab("♿ Accessibility"):
+            a11y_output = gr.Textbox(label="Results", lines=15)
+    
+    # Button actions
+    test_all_btn.click(
+        run_all_tests,
+        inputs=[url_input],
+        outputs=[perf_output, seo_output, sec_output, a11y_output]
+    )
+    
+    perf_btn.click(run_performance_test, inputs=[url_input], outputs=[perf_output])
+    seo_btn.click(run_seo_audit, inputs=[url_input], outputs=[seo_output])
+    sec_btn.click(run_security_test, inputs=[url_input], outputs=[sec_output])
+    a11y_btn.click(run_accessibility_test, inputs=[url_input], outputs=[a11y_output])
+    
+    gr.Markdown("""
+    ---
+    ### 📋 What Each Test Checks:
+    - **⚡ Performance**: TTFB, Page Size, Resource Count, Compression
+    - **🔍 SEO**: Meta Tags, Headers, Sitemap, Title/Description Length
+    - **🔒 Security**: SSL, Security Headers, Mixed Content
+    - **♿ Accessibility**: Alt Text, Form Labels, ARIA Roles
+    """)
+
+if __name__ == "__main__":
+    demo.launch()