auditor.py

import requests
from bs4 import BeautifulSoup
from transformers import pipeline
import time
import socket
import ssl
from urllib.parse import urlparse
import sys
import json
import os
from datetime import datetime

class SiteAuditor:
    def __init__(self, url):
        # Ensure URL has schema
        if not url.startswith(('http://', 'https://')):
            url = 'https://' + url
        self.url = url
        self.domain = urlparse(url).netloc
        self.soup = None
        self.response = None
        self.report = {}

    def fetch_site(self):
        """Basic setup: Gets the HTML and measures response time."""
        try:
            start_time = time.time()
            headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
            self.response = requests.get(self.url, headers=headers, timeout=10)
            self.load_time = round(time.time() - start_time, 2)
            self.soup = BeautifulSoup(self.response.text, 'html.parser')
            return True
        except Exception as e:
            self.report['error'] = str(e)
            return False
        
    def extract_visible_text(self):
        """Extracts and returns visible text from the HTML."""
        if not self.soup:
            return ""
        for tag in self.soup(["script", "style", "noscript"]):
            tag.decompose()
        text = self.soup.get_text(separator="\n")
        lines = [line.strip() for line in text.splitlines()]
        visible_text = "\n".join(line for line in lines if line)
        return visible_text

    def summarize_content(self):
        """Uses a transfermer model to summarize the visible text."""
        text = self.extract_visible_text()
        if not text:
            return "No visible text found."
        # Limit input size to avoid model overload

        short_text = text[:2000]

        try:
            summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
            summary = summarizer(short_text, max_length=200, min_length=50, do_sample=False)
            return summary[0]['summary_text']
        except Exception as e:
            return f"Summarization failed: {e}"


    # --- MODULE 1: SPEED & BASICS ---
    def fetch_site(self):
        print(f"Attempting to connect to: {self.url}...") # Feedback so you know it's working
        try:
            start_time = time.time()
            # Added a shorter timeout (5 seconds) so it doesn't hang forever
            headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
            self.response = requests.get(self.url, headers=headers, timeout=5)
            self.load_time = round(time.time() - start_time, 2)
            self.soup = BeautifulSoup(self.response.text, 'html.parser')
            print("✅ Connection Established!")
            return True
        except Exception as e:
            print(f"❌ ERROR: Could not connect to {self.url}")
            print(f"Reason: {e}")
            self.report['error'] = str(e)
            return False

    def check_health(self):
        # SECURITY CHECK: Stop if the site didn't load
        if not self.response and not self.fetch_site():
            return 
        
        print(f"Analyzing Health...")
        
        # 1. Load Speed
        self.report['load_time'] = f"{self.load_time} seconds"
        self.report['speed_rating'] = "GOOD" if self.load_time < 1.5 else "CRITICAL WARNING"
        
        # 2. Mobile Viewport
        viewport = self.soup.find('meta', attrs={'name': 'viewport'})
        self.report['mobile_optimized'] = bool(viewport)
    # --- MODULE 2: SECURITY ---
    def check_security(self):
        print("Checking Security...")
        # 1. SSL Check
        if self.url.startswith('https'):
            self.report['ssl'] = True
        else:
            self.report['ssl'] = False
            
    # --- MODULE 3: THE MONEY (Ad Tech) ---
    def check_ad_pixels(self):
        print("Checking Ad Tech...")
        html_text = str(self.soup)
        
        # Check for Facebook Pixel
        has_fb_pixel = "fbq('init'" in html_text or "fbevents.js" in html_text
        
        # Check for Google Analytics/Ads (G-Tag)
        has_google_tag = "gtag(" in html_text or "googletagmanager" in html_text
        
        self.report['facebook_pixel'] = has_fb_pixel
        self.report['google_tag'] = has_google_tag

    def generate_report(self):
        """Outputs the data in a readable format for the client."""
        print("\n" + "="*40)
        print(f"AUDIT REPORT FOR: {self.domain}")
        print("="*40)
        
        # FIRST PAUSE
        print("\n📊 First, let's look at Performance...")
        input("   [Press Enter to see Speed & Mobile results]")
        print("\n--- SITE HEALTH CHECK ---")

        print("Reporting Speed, Mobile, and Security Status:\n\n")
        # Speed Section
        print(f"⏱️  Load Speed: {self.report['load_time']} [{self.report['speed_rating']}]")
        if self.report['speed_rating'] == "CRITICAL WARNING":
            print("   -> PITCH: 'Amazon found that every 0.1s delay costs 1% in sales.'")

        # Mobile Section
        mobile_status = "✅ Optimized" if self.report['mobile_optimized'] else "❌ NOT OPTIMIZED"
        print(f"📱 Mobile Ready: {mobile_status}")
        if not self.report['mobile_optimized']:
            print("   -> PITCH: '50% of traffic is mobile. You are blocking half your customers.'")


        # SECOND PAUSE
        print("\n🔒 Next, let's look at Security and SEO...")
        input("   [Press Enter to see Security  and SEO results]")

        # Security Section
        ssl_status = "✅ Secure" if self.report['ssl'] else "❌ NOT SECURE"
        print(f"🔒 Security: {ssl_status}")


        print("\n--- DIGITAL MARKETING CHECK ---")
        print("Analyzing Ad Tech, SEO, and Contact Options:\n\n")
        # Money Section (The Closer)
        print("-" * 20)
        print("💰 MISSED REVENUE DETECTOR")
        
        fb_status = "✅ Installed" if self.report['facebook_pixel'] else "❌ MISSING (Losing Money)"
        print(f"   - Facebook Pixel: {fb_status}")
        
        google_status = "✅ Installed" if self.report['google_tag'] else "❌ MISSING (Flying Blind)"
        print(f"   - Google Tag: {google_status}")
        
        #SEO Section
        print("-" * 20)
        print("🔍 Checking SEO Health (Google visibility)")
        print(f"   - Title Tag: {self.report.get('seo_title', 0)}")
        
        # Logic: Titles should be between 30-60 characters
        t_len = self.report.get('seo_title_len', 0)
        if t_len < 25 or t_len > 70:
            print("    ⚠️ Title length is suboptimal. Aim for 30-60 characters. ⚠️")
            print(f"      (Current Length: {t_len} characters)")
        
        print(f"   - Meta Description: {self.report.get('seo__desc')}")
        if self.report.get('seo_desc') == "❌ MISSING":
            print("    ⚠️ Meta Description is missing. This hurts SEO and CTR. ⚠️")
            print("    ⚠️ YOU ARE INVISIBLE ON GOOGLE WITHOUT PROPER METADATA! ⚠️")


        # THIRD PAUSE
        print("\n  Next, lets check Socials and Contact Options results....")
        input("   [Press Enter to see Socials and Contact Options results]")


        # CONTACT OPTIONS Section
        print("-" * 20)
        print("📞 CONVERSION CHECK")
        P_COUNT = self.report.get('phone_links', 0)
        E_COUNT = self.report.get('email_links', 0)

        print(f"   - Click-to-Call: {'✅ Active' if P_COUNT > 0 else '❌ NO CLICK-TO-CALLS'} (Found: {P_COUNT})")
        print(f"   - Click-to-Email: {'✅ Active' if E_COUNT > 0 else '❌ NO CLICK-TO-EMAILS'} (Found: {E_COUNT})")

        

        if not self.report['facebook_pixel'] or not self.report['google_tag']:
             print("\n   -> CLOSING LINE: 'You are paying for ads but not tracking them. We need to fix this today.'")
        # Social Section
        print("-" * 20)
        print("🌐 SOCIAL MEDIA LINKS")
        socials = self.report.get('social_links', [])

        if socials:
            for link in socials:
                print(f"   - {link}")
        else:
            print(" ⚠️ No social media links found. ⚠️")

    def save_report(self, directory='reports', filename=None, fmt='json'):
        """Save the audit report in the requested format (json, md, txt).
        Returns the saved file path or None on failure."""
        try:
            os.makedirs(directory, exist_ok=True)
            ts = datetime.now().strftime('%Y%m%d_%H%M%S')
            safe_domain = self.domain.replace(':', '_')

            fmt = (fmt or 'json').lower()
            if fmt not in ('json', 'md', 'txt'):
                fmt = 'json'

            ext = fmt
            if not filename:
                filename = f"{safe_domain}_{ts}.{ext}"
            path = os.path.join(directory, filename)

            payload = {
                'url': self.url,
                'domain': self.domain,
                'timestamp': ts,
                'report': self.report
            }

            if fmt == 'json':
                with open(path, 'w', encoding='utf-8') as f:
                    json.dump(payload, f, ensure_ascii=False, indent=2)

            else:
                # Build a readable markdown/plain-text report
                lines = []
                lines.append(f"# Audit Report for {self.domain}")
                lines.append(f"- URL: {self.url}")
                lines.append(f"- Timestamp: {ts}")
                lines.append("")
                # Summary (if exists)
                summary = self.report.get('summary') or self.report.get('summary', '')
                if summary:
                    lines.append("## Summary")
                    lines.append(summary)
                    lines.append("")

                lines.append("## Details")
                for key in sorted(self.report.keys()):
                    if key == 'summary':
                        continue
                    val = self.report.get(key)
                    lines.append(f"### {key}")
                    if isinstance(val, list):
                        if val:
                            for item in val:
                                lines.append(f"- {item}")
                        else:
                            lines.append("- (none)")
                    else:
                        lines.append(str(val))
                    lines.append("")

                content = '\n'.join(lines)
                # For .txt, we can strip markdown headings
                if fmt == 'txt':
                    content = content.replace('#', '')

                with open(path, 'w', encoding='utf-8') as f:
                    f.write(content)

            return path
        except Exception as e:
            print(f"Failed to save report: {e}")
            return None


    def check_social_links(self):
            print("Checking Social Media Links...")
            #The sites we are looking for
            target = ['facebook', 'twitter', 'instagram', 'linkedin']
            results = []

            # Find links
            links = self.soup.find_all('a', href=True)

            for link in links:
                href = link.get('href')
                # Check if link contains a target name
                if any(t in href for t in target):
                    try:
                        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
                        res = requests.head(href, headers=headers, timeout=5)

                        # Test if the links actually work
                        # Linkedin throws 999 or 403 to bots. We count those as "Found".
                        if res.status_code == 200:
                            status = "✅ Active"
                        elif res.status_code in [403, 429, 999]:
                            status = f"⚠️ Restricted, Please confirm link manually. (Status: {res.status_code})"
                        else:
                            status = f"❌ Broken (Status: {res.status_code})"
                        
                        results.append(f"{href} - {status}")
                    except:
                        results.append(f"{href} - ❌ Could not reach link. Connection Failed.")
    
            self.report['social_links'] = results


    # --- Module 5: SEO CHECK ---
    def check_seo(self):
        print("Checking SEO Basics...")
        # 1. Title Tag
        if self.soup.title and self.soup.title.string:
            title = self.soup.title.string.strip()
            self.report['seo_title'] = title
            self.report['seo_title_len'] = len(title)
        else:
            self.report['seo_title'] = "❌ MISSING"
            self.report['seo_title_len'] = 0                

    # 2. Meta Description
        meta_desc = self.soup.find('meta', attrs={'name': 'description'})
        if meta_desc and meta_desc.get('content'):
            description = meta_desc['content'].strip()
            self.report['seo_meta_desc'] = description
            self.report['seo_meta_desc_len'] = len(description)
        else:
            self.report['seo_meta_desc'] = "❌ MISSING"
            self.report['seo_meta_desc_len'] = 0
    # 3. H1 Tag
        h1_tag = self.soup.find('h1')
        if h1_tag:
            h1_text = h1_tag.get_text(strip=True)
            self.report['seo_h1'] = h1_text
        else:
            self.report['seo_h1'] = "❌ MISSING"
        

        # 4. Image Alt Tags
        images = self.soup.find_all('img')
        alt_tags_count = sum(1 for img in images if img.get('alt'))
        total_images = len(images)
        self.report['seo_images_with_alt'] = alt_tags_count
        self.report['seo_total_images'] = total_images

    # ---Module 6: CONTACT OPTIONS & IMAGE ALT TAGS ---
    def check_contact_options(self):
        print("Checking Contact Options...")
        # Check for clickable phone numbers
        phone_links = self.soup.find_all('a', href=True)
        tel_links = [link for link in phone_links if link['href'].startswith('tel:')]
        self.report['phone_links'] = len(tel_links)

        # Check for clickable emails
        mail_links = [link for link in phone_links if link['href'].startswith('mailto:')]
        self.report['email_links'] = len(mail_links)
    

    # --- Module 7: Platform Check ---
    def check_platform(self):
        print("Detecting Web Platform being used...")
        # Convert soup to string for easier pattern matching
        soup_str = str(self.soup)

        # Default to "Unknown"

        



# --- EXECUTION ---
if __name__ == "__main__":
    while True:
        print("\n")
        print("\n" *3)
        print("    🕵️ Eternal Kosmos Auditor v0.9 🕵️    ")
        print("="*50 + "\n")

    # 1. Interactive Prompt
        print("Type 'exit', 'quit' or 'q' to close the program.\n")
        target = input("Enter the website URL to audit (e.g., example.com): ").strip()


        if target.lower() in ['exit', 'quit', 'q']:
            print("Exiting the program. Goodbye!")
            sys.exit()

        # Smart URL Handling: Add www/https if missing
        if not target.startswith(('http://', 'https://')):
            target = 'https://' + target

        print(f"\n Initializing scanner for: {target}...\n")

        audit = SiteAuditor(target)

        connected = audit.fetch_site()

        # retry logic: If the first try fails, we ask the user if they want to try 'www'
        if not connected:
            print("⚠️  Direct connection failed.")
            if "www" not in target:
                retry = input(f"   Do you want to try adding 'www.'? (y/n): ")
                if retry.lower() == 'y':
                    target = target.replace("https://", "https://www.")
                    audit = SiteAuditor(target)
                    connected = audit.fetch_site()

        if connected:
            audit.check_health()
            audit.check_security()
            audit.check_seo()
            audit.check_contact_options()
            audit.check_ad_pixels()
            audit.check_social_links()
            audit.report['summary'] = audit.summarize_content()

            print("\n 🔍 AI Summary of Page Content:")
            print(audit.report['summary'])

            audit.generate_report()

            # Prompt to save the audit report
            try:
                save_choice = input("\nSave audit report to file? (y/n): ").strip().lower()
                if save_choice == 'y':
                    fmt_choice = input("Save format - json/md/txt (default json): ").strip().lower()
                    if not fmt_choice:
                        fmt_choice = 'json'
                    if fmt_choice not in ('json', 'md', 'txt'):
                        print("Unknown format, defaulting to JSON.")
                        fmt_choice = 'json'

                    saved_path = audit.save_report(fmt=fmt_choice)
                    if saved_path:
                        print(f"Report saved to: {saved_path}")
                    else:
                        print("Report could not be saved.")
            except Exception:
                print("Skipping save prompt due to input error.")
        else:
            print("Could not analyze site.")

        print("\nAudit Complete. Thank you for using Eternal Kosmos Auditor!\n")
        read = input("Press Enter to either search another site or quit the application...")