Geo Fundamentals

#!/usr/bin/env python3
"""
GEO Checker - Generative Engine Optimization Audit
Checks PUBLIC WEB CONTENT for AI citation readiness.

PURPOSE:
    - Analyze pages that will be INDEXED by AI engines (ChatGPT, Perplexity, etc.)
    - Check for structured data, author info, dates, FAQ sections
    - Help content rank in AI-generated answers

WHAT IT CHECKS:
    - HTML files (actual web pages)
    - JSX/TSX files (React page components)
    - NOT markdown files (those are developer docs, not public content)

Usage:
    python geo_checker.py <project_path>
"""
import sys
import re
import json
from pathlib import Path

# Fix Windows console encoding
try:
    sys.stdout.reconfigure(encoding='utf-8', errors='replace')
    sys.stderr.reconfigure(encoding='utf-8', errors='replace')
except AttributeError:
    pass


# Directories to skip (not public content)
SKIP_DIRS = {
    'node_modules', '.next', 'dist', 'build', '.git', '.github',
    '__pycache__', '.vscode', '.idea', 'coverage', 'test', 'tests',
    '__tests__', 'spec', 'docs', 'documentation'
}

# Files to skip (not public pages)
SKIP_FILES = {
    'jest.config', 'webpack.config', 'vite.config', 'tsconfig',
    'package.json', 'package-lock', 'yarn.lock', '.eslintrc',
    'tailwind.config', 'postcss.config', 'next.config'
}


def is_page_file(file_path: Path) -> bool:
    """Check if this file is likely a public-facing page."""
    name = file_path.stem.lower()
    
    # Skip config/utility files
    if any(skip in name for skip in SKIP_FILES):
        return False
    
    # Skip test files
    if name.endswith('.test') or name.endswith('.spec'):
        return False
    if name.startswith('test_') or name.startswith('spec_'):
        return False
    
    # Likely page indicators
    page_indicators = ['page', 'index', 'home', 'about', 'contact', 'blog', 
                       'post', 'article', 'product', 'service', 'landing']
    
    # Check if it's in a pages/app directory (Next.js, etc.)
    parts = [p.lower() for p in file_path.parts]
    if 'pages' in parts or 'app' in parts or 'routes' in parts:
        return True
    
    # Check filename indicators
    if any(ind in name for ind in page_indicators):
        return True
    
    # HTML files are usually pages
    if file_path.suffix.lower() == '.html':
        return True
    
    return False


def find_web_pages(project_path: Path) -> list:
    """Find public-facing web pages only."""
    patterns = ['**/*.html', '**/*.htm', '**/*.jsx', '**/*.tsx']
    
    files = []
    for pattern in patterns:
        for f in project_path.glob(pattern):
            # Skip excluded directories
            if any(skip in f.parts for skip in SKIP_DIRS):
                continue
            
            # Check if it's likely a page
            if is_page_file(f):
                files.append(f)
    
    return files[:30]  # Limit to 30 pages


def check_page(file_path: Path) -> dict:
    """Check a single web page for GEO elements."""
    try:
        content = file_path.read_text(encoding='utf-8', errors='ignore')
    except Exception as e:
        return {'file': str(file_path.name), 'passed': [], 'issues': [f"Error: {e}"], 'score': 0}
    
    issues = []
    passed = []
    
    # 1. JSON-LD Structured Data (Critical for AI)
    if 'application/ld+json' in content:
        passed.append("JSON-LD structured data found")
        if '"@type"' in content:
            if 'Article' in content:
                passed.append("Article schema present")
            if 'FAQPage' in content:
                passed.append("FAQ schema present")
            if 'Organization' in content or 'Person' in content:
                passed.append("Entity schema present")
    else:
        issues.append("No JSON-LD structured data (AI engines prefer structured content)")
    
    # 2. Heading Structure
    h1_count = len(re.findall(r'<h1[^>]*>', content, re.I))
    h2_count = len(re.findall(r'<h2[^>]*>', content, re.I))
    
    if h1_count == 1: