1#!/usr/bin/env python3
2"""
3SEO audit script (no API required)
4Usage: python3 scripts/seo_audit.py "https://example.com"
5"""
6import argparse
7import urllib.request
8import urllib.parse
9import re
10import time
11import sys
12 
13 
14def fetch_url(url: str, timeout: int = 30) -> tuple:
15    """Fetch URL and return (content, headers, load_time)"""
16    try:
17        start = time.time()
18        req = urllib.request.Request(url, headers={"User-Agent": "SEO-Audit/1.0"})
19        with urllib.request.urlopen(req, timeout=timeout) as resp:
20            content = resp.read().decode("utf-8", errors="ignore")
21            headers = dict(resp.headers)
22            load_time = time.time() - start
23            return content, headers, load_time
24    except Exception as e:
25        return None, None, None
26 
27 
28def extract_meta(html: str) -> dict:
29    """Extract meta tags from HTML"""
30    result = {}
31    
32    # Title
33    title_match = re.search(r"<title[^>]*>([^<]+)</title>", html, re.I)
34    result["title"] = title_match.group(1).strip() if title_match else None
35    
36    # Meta description
37    desc_match = re.search(r'<meta[^>]+name=["\']description["\'][^>]+content=["\']([^"\']+)["\']', html, re.I)
38    if not desc_match:
39        desc_match = re.search(r'<meta[^>]+content=["\']([^"\']+)["\'][^>]+name=["\']description["\']', html, re.I)
40    result["description"] = desc_match.group(1).strip() if desc_match else None
41    
42    # OG tags
43    og_match = re.search(r'<meta[^>]+property=["\']og:title["\']', html, re.I)
44    result["og_tags"] = bool(og_match)
45    
46    # JSON-LD
47    jsonld_count = len(re.findall(r'application/ld\+json', html, re.I))
48    result["jsonld_count"] = jsonld_count
49    
50    # H1 (handle inline tags like <br>)
51    h1_match = re.search(r"<h1[^>]*>(.*?)</h1>", html, re.I | re.DOTALL)
52    if h1_match:
53        h1_text = re.sub(r"<[^>]+>", " ", h1_match.group(1))  # Remove inner tags
54        h1_text = re.sub(r"\s+", " ", h1_text).strip()  # Normalize whitespace
55        result["h1"] = h1_text[:100]
56    else:
57        result["h1"] = None
58    
59    return result
60 
61 
62def check_robots(url: str) -> dict:
63    """Check robots.txt"""
64    parsed = urllib.parse.urlparse(url)
65    robots_url = f"{parsed.scheme}://{parsed.netloc}/robots.txt"
66    content, _, _ = fetch_url(robots_url)
67    
68    result = {"exists": False, "ai_bots": []}
69    if content:
70        result["exists"] = True
71        ai_bots = ["GPTBot", "PerplexityBot", "ClaudeBot", "anthropic-ai", "ChatGPT-User"]
72        for bot in ai_bots:
73            if bot.lower() in content.lower():
74                result["ai_bots"].append(bot)
75    return result
76 
77 
78def check_sitemap(url: str) -> bool:
79    """Check if sitemap.xml exists"""
80    parsed = urllib.parse.urlparse(url)
81    sitemap_url = f"{parsed.scheme}://{parsed.netloc}/sitemap.xml"
82    content, _, _ = fetch_url(sitemap_url)
83    if not content:
84        return False
85    # Check for common sitemap indicators
86    return "<urlset" in content.lower() or "<sitemapindex" in content.lower() or "<?xml" in content.lower()
87 
88 
89def main():
90    parser = argparse.ArgumentParser(description="SEO audit")
91    parser.add_argument("url", help="URL to audit")
92    args = parser.parse_args()
93    
94    url = args.url
95    if not url.startswith("http"):
96        url = f"https://{url}"
97    
98    print(f"=== SEO Audit: {url} ===")
99    print()
100    
101    # Fetch page
102    content, headers, load_time = fetch_url(url)
103    if not content:
104        print("error: Could not fetch URL")
105        sys.exit(1)
106    
107    # Meta tags
108    print("## Meta Tags")
109    meta = extract_meta(content)
110    title = meta["title"]
111    print(f"title: {title[:60] if title else 'MISSING'}{'...' if title and len(title) > 60 else ''}")
112    print(f"title_length: {len(title) if title else 0} chars")
113    desc = meta["description"]
114    print(f"description: {desc[:80] if desc else 'MISSING'}{'...' if desc and len(desc) > 80 else ''}")
115    print(f"description_length: {len(desc) if desc else 0} chars")
116    print(f"og_tags: {'yes' if meta['og_tags'] else 'no'}")
117    print(f"h1: {meta['h1'] if meta['h1'] else 'MISSING'}")
118    print()
119    
120    # Schema
121    print("## Schema Markup")
122    print(f"json_ld_blocks: {meta['jsonld_count']}")
123    print()
124    
125    # Performance
126    print("## Performance")
127    print(f"load_time: {load_time:.2f}s")
128    print(f"status: {'good' if load_time < 3 else 'slow'}")
129    print()
130    
131    # robots.txt
132    print("## robots.txt")
133    robots = check_robots(url)
134    print(f"exists: {'yes' if robots['exists'] else 'no'}")
135    if robots["ai_bots"]:
136        print(f"ai_bots_mentioned: {', '.join(robots['ai_bots'])}")
137    else:
138        print("ai_bots_mentioned: none")
139    print()
140    
141    # Sitemap
142    print("## Sitemap")
143    has_sitemap = check_sitemap(url)
144    print(f"sitemap_xml: {'yes' if has_sitemap else 'no'}")
145    print()
146    
147    print("=== Audit Complete ===")
148 
149 
150if __name__ == "__main__":
151    main()
152