aicodingpricing

#!/usr/bin/env python3
import json, re, subprocess, sys, time
from html.parser import HTMLParser
from urllib.request import Request, urlopen
from urllib.error import HTTPError, URLError

BASE = 'https://aicodingpricing.com'
ROUTES = [
 '/', '/claude-code-pricing', '/claude-code-usage-limits', '/codex-pricing', '/codex-usage',
 '/cursor-pricing', '/claude-code-vs-codex', '/claude-code-vs-cursor', '/pricing-changelog',
 '/claude-code-cost', '/codex-limits', '/codex-vs-cursor', '/api-vs-subscription',
 '/github-copilot-pricing', '/github-copilot-vs-cursor', '/claude-max-vs-pro',
 '/chatgpt-pro-vs-claude-max', '/about', '/contact', '/privacy', '/terms', '/robots.txt', '/sitemap.xml', '/llms.txt'
]
EVENTS = ['cta_click','hero_cta_click','pricing_click','pricing_cta_click','calculator_usage','tool_start','tool_result','newsletter_submit','page_view']

def fetch(path):
    url = BASE + path
    req = Request(url, headers={'User-Agent':'motest-final-reqa/1.0'})
    try:
        with urlopen(req, timeout=25) as r:
            body = r.read().decode('utf-8', 'replace')
            return {'url': url, 'status': r.status, 'headers': dict(r.headers), 'body': body}
    except HTTPError as e:
        return {'url': url, 'status': e.code, 'headers': dict(e.headers), 'body': e.read().decode('utf-8','replace')}
    except Exception as e:
        return {'url': url, 'status': None, 'error': repr(e), 'body': ''}

def extract_json_ld(html):
    blocks = re.findall(r'<script[^>]+type=["\']application/ld\+json["\'][^>]*>(.*?)</script>', html, re.I|re.S)
    out=[]
    for b in blocks:
        try: out.append(json.loads(b.strip()))
        except Exception as e: out.append({'parse_error': str(e), 'raw_prefix': b[:120]})
    return out

def h1_count(html):
    return len(re.findall(r'<h1\b', html, re.I))

def title(html):
    m=re.search(r'<title[^>]*>(.*?)</title>', html, re.I|re.S)
    return re.sub(r'\s+',' ',m.group(1)).strip() if m else ''

def meta_desc(html):
    m=re.search(r'<meta[^>]+name=["\']description["\'][^>]+content=["\']([^"\']*)', html, re.I)
    return m.group(1).strip() if m else ''

def canonical(html):
    m=re.search(r'<link[^>]+rel=["\']canonical["\'][^>]+href=["\']([^"\']*)', html, re.I)
    return m.group(1).strip() if m else ''

def dig(args):
    try:
        return subprocess.check_output(['dig','+short']+args, text=True, timeout=15).strip().splitlines()
    except Exception as e:
        return [f'ERROR: {e}']

pages={p: fetch(p) for p in ROUTES}
home=pages['/']['body']
claude=pages['/claude-code-cost']['body']
llms=pages['/llms.txt']['body']
sitemap=pages['/sitemap.xml']['body']
privacy=pages['/privacy']['body']

route_results={p: {'status': pages[p].get('status'), 'content_type': pages[p].get('headers',{}).get('content-type','')} for p in ROUTES}
html_routes=[p for p in ROUTES if p not in ['/robots.txt','/sitemap.xml','/llms.txt']]
seo={}
for p in html_routes:
    html=pages[p]['body']
    seo[p]={'title': title(html), 'meta_description_len': len(meta_desc(html)), 'canonical': canonical(html), 'h1_count': h1_count(html), 'noindex': bool(re.search(r'<meta[^>]+name=["\']robots["\'][^>]+content=["\'][^"\']*noindex', html, re.I))}

jsonld=extract_json_ld(claude)
schema_types=[]
for b in jsonld:
    if isinstance(b, dict):
        if '@graph' in b:
            schema_types += [x.get('@type') for x in b.get('@graph',[]) if isinstance(x, dict)]
        schema_types.append(b.get('@type'))

result={
 'generated_at_unix': int(time.time()),
 'base': BASE,
 'routes': route_results,
 'routes_ok': all(v['status'] in (200,301,302,307,308) for v in route_results.values()),
 'sitemap_url_count': len(re.findall(r'<loc>', sitemap)),
 'seo_basics': seo,
 'seo_basics_ok': all(v['title'] and v['meta_description_len']>0 and v['canonical'] and v['h1_count']==1 and not v['noindex'] for v in seo.values()),
 'analytics': {
   'plausible_script_present': 'plausible' in home.lower() and 'script.js' in home,
   'events_found_in_home_html_or_bundle_refs': {e: (e in home) for e in EVENTS},
   'analytics_function_refs': sorted(set(re.findall(r'analytics[A-Za-z0-9_]+|track[A-Za-z0-9_]+', home)))[:50],
 },
 'newsletter': {
   'form_refs_present': all(x in home for x in ['newsletter','newsletter_submit']),
   'success_copy_present': ('Launch validation captured locally' in home or 'captured locally' in home),
   'backend_absent_disclosure_present': ('does not subscribe you to a live mailing list' in home or 'live mailing list' in home),
 },
 'claude_code_cost': {
   'status': pages['/claude-code-cost']['status'],
   'json_ld_count': len(jsonld),
   'schema_types': schema_types,
   'has_webapplication': any(t == 'WebApplication' or (isinstance(t, list) and 'WebApplication' in t) for t in schema_types),
 },
 'llms_txt': {
   'status': pages.get('/llms.txt',{}).get('status'),
   'chars': len(llms),
   'mentions_core_routes': all(s in llms for s in ['claude-code-cost','codex-pricing','cursor-pricing']),
 },
 'privacy': {
   'plausible_disclosure': 'Plausible' in privacy,
   'google_clarity_excluded_or_absent': ('Google Analytics' in privacy and 'Microsoft Clarity' in privacy) or ('Plausible' in privacy),
 },
 'dns': {
   'mx_default': dig(['MX','aicodingpricing.com']),
   'mx_1_1_1_1': dig(['MX','aicodingpricing.com','@1.1.1.1']),
   'txt_spf': [x for x in dig(['TXT','aicodingpricing.com']) if 'spf' in x.lower()],
 },
}
print(json.dumps(result, ensure_ascii=False, indent=2))