cernitur-lint 1.0.0__tar.gz

cernitur_lint-1.0.0/PKG-INFO

@@ -0,0 +1,49 @@
+Metadata-Version: 2.4
+Name: cernitur-lint
+Version: 1.0.0
+Summary: Deterministic Answer Engine Optimization (AEO) and JSON-LD schema linter for Google AI Overviews and ChatGPT.
+Author-email: Cernitur Technologies LLC <support@cernitur.com>
+Project-URL: Homepage, https://cernitur.com
+Project-URL: Documentation, https://cernitur.com/guides/json-ld-entity-graph
+Project-URL: Repository, https://github.com/cernitur/aeo-lint
+Project-URL: Issues, https://github.com/cernitur/aeo-lint/issues
+Keywords: aeo,geo,seo,schema,llms-txt,cernitur
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: urllib3>=1.26.0
+
+# cernitur-lint
+
+> **Deterministic Answer Engine Optimization (AEO) and Schema.org Linter.**  
+> Maintained by [Cernitur Technologies LLC](https://cernitur.com).
+
+Inspects web domains for compliance with **Google AI Overviews, OpenAI Search (ChatGPT), Claude, and Perplexity** across robots.txt AI crawlers, `/llms.txt` specifications, and 5-dimension Schema.org `@graph` entity architectures.
+
+---
+
+## ⚡ Installation & Usage
+
+```bash
+pip install cernitur-lint
+cernitur-lint yourdomain.com
+```
+
+Or output raw JSON:
+
+```bash
+cernitur-lint yourdomain.com --json
+```
+
+---
+
+## 🌐 Official Links
+
+- **Hosted Diagnostic Scanner:** [https://cernitur.com/scanner](https://cernitur.com/scanner)
+- **One-Time AEO Architecture Suite:** [https://cernitur.com/pricing](https://cernitur.com/pricing)
+- **AEO vs. Retainers Comparison:** [https://cernitur.com/compare/aeo-platforms](https://cernitur.com/compare/aeo-platforms)
+
+License: Apache-2.0 &copy; 2026 Cernitur Technologies LLC.

cernitur_lint-1.0.0/README.md

@@ -0,0 +1,31 @@
+# cernitur-lint
+
+> **Deterministic Answer Engine Optimization (AEO) and Schema.org Linter.**  
+> Maintained by [Cernitur Technologies LLC](https://cernitur.com).
+
+Inspects web domains for compliance with **Google AI Overviews, OpenAI Search (ChatGPT), Claude, and Perplexity** across robots.txt AI crawlers, `/llms.txt` specifications, and 5-dimension Schema.org `@graph` entity architectures.
+
+---
+
+## ⚡ Installation & Usage
+
+```bash
+pip install cernitur-lint
+cernitur-lint yourdomain.com
+```
+
+Or output raw JSON:
+
+```bash
+cernitur-lint yourdomain.com --json
+```
+
+---
+
+## 🌐 Official Links
+
+- **Hosted Diagnostic Scanner:** [https://cernitur.com/scanner](https://cernitur.com/scanner)
+- **One-Time AEO Architecture Suite:** [https://cernitur.com/pricing](https://cernitur.com/pricing)
+- **AEO vs. Retainers Comparison:** [https://cernitur.com/compare/aeo-platforms](https://cernitur.com/compare/aeo-platforms)
+
+License: Apache-2.0 © 2026 Cernitur Technologies LLC.

cernitur_lint-1.0.0/cernitur_lint/__init__.py

@@ -0,0 +1,6 @@
+"""
+cernitur-lint: Deterministic AEO & Schema Evaluator CLI.
+Copyright (c) 2026 Cernitur Technologies LLC.
+"""
+
+__version__ = "1.0.0"

cernitur_lint-1.0.0/cernitur_lint/cli.py

@@ -0,0 +1,233 @@
+#!/usr/bin/env python3
+"""
+cernitur-lint: AEO & Schema Evaluation CLI
+Copyright (c) 2026 Cernitur Technologies LLC
+https://cernitur.com
+"""
+
+import sys
+import json
+import re
+import urllib.request
+import urllib.error
+import urllib.parse
+
+# Ensure UTF-8 output on Windows consoles
+if sys.platform == "win32" and hasattr(sys.stdout, "reconfigure"):
+    try:
+        sys.stdout.reconfigure(encoding="utf-8")
+    except Exception:
+        pass
+
+def clean_domain(target: str) -> str:
+    target = target.strip()
+    if not target.startswith("http://") and not target.startswith("https://"):
+        target = "https://" + target
+    parsed = urllib.parse.urlparse(target)
+    return (parsed.hostname or target).lower()
+
+def fetch_url(url: str, timeout: int = 8):
+    req = urllib.request.Request(
+        url,
+        headers={"User-Agent": "Cernitur-AEOLint-Py/1.0 (+https://cernitur.com/scanner)"}
+    )
+    try:
+        with urllib.request.urlopen(req, timeout=timeout) as response:
+            return response.getcode(), response.headers.get("Content-Type", ""), response.read().decode("utf-8", errors="replace")
+    except urllib.error.HTTPError as e:
+        return e.code, "", ""
+    except Exception:
+        return 0, "", ""
+
+def evaluate(domain: str):
+    # 1. Robots
+    robots_code, _, robots_txt = fetch_url(f"https://{domain}/robots.txt")
+    robots_score = 0
+    robots_checks = []
+
+    if robots_code == 200:
+        robots_score += 5
+        robots_checks.append({"name": "robots.txt accessible", "pass": True, "note": f"HTTP 200 ({len(robots_txt)} bytes)"})
+        crawlers = ["OAI-SearchBot", "Claude-SearchBot", "PerplexityBot", "Googlebot", "Google-Extended"]
+        found = sum(1 for b in crawlers if re.search(rf"User-agent:\s*{b}", robots_txt, re.IGNORECASE))
+        if found >= 3:
+            robots_score += 10
+            robots_checks.append({"name": "AI search crawlers declared", "pass": True, "note": f"{found}/5 verified bots declared"})
+        elif found > 0:
+            robots_score += 5
+            robots_checks.append({"name": "AI search crawlers declared", "pass": True, "note": f"{found}/5 verified bots declared"})
+        else:
+            robots_checks.append({"name": "AI search crawlers declared", "pass": False, "note": "No explicit AI search crawlers"})
+
+        if re.search(r"Sitemap:\s*https?://", robots_txt, re.IGNORECASE):
+            robots_score += 5
+            robots_checks.append({"name": "Sitemap in robots.txt", "pass": True, "note": "Valid Sitemap URL"})
+        else:
+            robots_checks.append({"name": "Sitemap in robots.txt", "pass": False, "note": "Missing Sitemap directive"})
+
+        if re.search(r"User-agent:\s*\*\s*\n\s*Disallow:\s*/\s*$", robots_txt, re.IGNORECASE | re.MULTILINE):
+            robots_checks.append({"name": "Disallow boundaries", "pass": False, "note": "Blanket Disallow: / blocks AI"})
+        else:
+            robots_score += 5
+            robots_checks.append({"name": "Disallow boundaries", "pass": True, "note": "No blanket Disallow: / blocking bots"})
+    else:
+        robots_checks.append({"name": "robots.txt accessible", "pass": False, "note": f"HTTP {robots_code}"})
+
+    # 2. llms.txt
+    llms_code, llms_mime, llms_txt = fetch_url(f"https://{domain}/llms.txt")
+    llms_score = 0
+    llms_checks = []
+
+    if llms_code == 200:
+        llms_score += 5
+        llms_checks.append({"name": "llms.txt accessible", "pass": True, "note": f"HTTP 200 ({len(llms_txt)} bytes)"})
+        if "text/plain" in llms_mime or "text/markdown" in llms_mime:
+            llms_score += 5
+            llms_checks.append({"name": "llms.txt MIME type", "pass": True, "note": llms_mime.split(";")[0]})
+        else:
+            llms_checks.append({"name": "llms.txt MIME type", "pass": False, "note": f"Non-standard MIME ({llms_mime})"})
+
+        if re.search(r"^#\s+.+", llms_txt, re.MULTILINE):
+            llms_score += 5
+            llms_checks.append({"name": "H1 Title Heading", "pass": True, "note": "Valid top-level heading"})
+        else:
+            llms_checks.append({"name": "H1 Title Heading", "pass": False, "note": "Missing # Title"})
+
+        if re.search(r"^>\s+.+", llms_txt, re.MULTILINE):
+            llms_score += 5
+            llms_checks.append({"name": "Entity summary blockquote", "pass": True, "note": "Found canonical blockquote"})
+        else:
+            llms_checks.append({"name": "Entity summary blockquote", "pass": False, "note": "Missing > summary"})
+
+        links = re.findall(r"\[([^\]]+)\]\(([^)]+)\)", llms_txt)
+        if len(links) >= 3:
+            llms_score += 5
+            llms_checks.append({"name": "Markdown navigation links", "pass": True, "note": f"{len(links)} canonical links"})
+        else:
+            llms_checks.append({"name": "Markdown navigation links", "pass": False, "note": f"{len(links)} links found"})
+    else:
+        llms_checks.append({"name": "llms.txt accessible", "pass": False, "note": f"HTTP {llms_code}"})
+
+    # 3. HTML & Schema
+    html_code, _, html_text = fetch_url(f"https://{domain}/")
+    html_score = 0
+    html_checks = []
+
+    if html_code == 200:
+        if len(html_text) > 2500 and '<div id="__next"></div></body>' not in html_text:
+            html_score += 10
+            html_checks.append({"name": "SSR HTML density", "pass": True, "note": f"{round(len(html_text)/1024)} KB markup"})
+        else:
+            html_checks.append({"name": "SSR HTML density", "pass": False, "note": "Low initial HTML payload"})
+
+        if "<title" in html_text and ('rel="canonical"' in html_text or "rel='canonical'" in html_text):
+            html_score += 5
+            html_checks.append({"name": "SEO metadata", "pass": True, "note": "Title and canonical present"})
+        else:
+            html_checks.append({"name": "SEO metadata", "pass": False, "note": "Missing title or canonical"})
+
+        # Extract JSON-LD
+        blocks = re.findall(r'<script\b[^>]*type=["\']application/ld\+json["\'][^>]*>([\s\S]*?)</script>', html_text, re.IGNORECASE)
+        nodes = []
+        for b in blocks:
+            try:
+                parsed = json.loads(b)
+                if isinstance(parsed, dict) and "@graph" in parsed and isinstance(parsed["@graph"], list):
+                    nodes.extend(parsed["@graph"])
+                elif isinstance(parsed, list):
+                    nodes.extend(parsed)
+                elif isinstance(parsed, dict):
+                    nodes.append(parsed)
+            except Exception:
+                pass
+
+        if nodes:
+            html_score += 5
+            html_checks.append({"name": "JSON-LD structured data", "pass": True, "note": f"{len(nodes)} entity node(s)"})
+
+            has_org = any(n.get("@type") in ["Organization", "LocalBusiness", "Corporation"] for n in nodes)
+            has_same_as = any(isinstance(n.get("sameAs"), list) and len(n.get("sameAs")) > 0 for n in nodes)
+            if has_org and has_same_as:
+                html_score += 8
+                html_checks.append({"name": "Schema: Identity & sameAs", "pass": True, "note": "Organization with sameAs"})
+            elif has_org:
+                html_score += 4
+                html_checks.append({"name": "Schema: Identity & sameAs", "pass": True, "note": "Organization found (sameAs missing)"})
+            else:
+                html_checks.append({"name": "Schema: Identity & sameAs", "pass": False, "note": "Missing Organization node"})
+
+            if any(n.get("knowsAbout") or n.get("disambiguatingDescription") for n in nodes):
+                html_score += 8
+                html_checks.append({"name": "Schema: Ontology Disambiguation", "pass": True, "note": "Declared knowsAbout/disambiguation"})
+            else:
+                html_checks.append({"name": "Schema: Ontology Disambiguation", "pass": False, "note": "Missing topic authority"})
+
+            if any(n.get("address") or n.get("areaServed") or n.get("geo") for n in nodes):
+                html_score += 7
+                html_checks.append({"name": "Schema: Geographic Precision", "pass": True, "note": "PostalAddress or areaServed"})
+            else:
+                html_checks.append({"name": "Schema: Geographic Precision", "pass": False, "note": "No geographic tags"})
+
+            if any(n.get("contactPoint") or n.get("foundingDate") for n in nodes):
+                html_score += 7
+                html_checks.append({"name": "Schema: E-E-A-T Anchoring", "pass": True, "note": "ContactPoint or founding date"})
+            else:
+                html_checks.append({"name": "Schema: E-E-A-T Anchoring", "pass": False, "note": "No ContactPoint found"})
+        else:
+            html_checks.append({"name": "JSON-LD structured data", "pass": False, "note": "No valid JSON-LD parsed"})
+    else:
+        html_checks.append({"name": "Homepage SSR retrieval", "pass": False, "note": f"HTTP {html_code}"})
+
+    total = robots_score + llms_score + html_score
+    return {
+        "domain": domain,
+        "score": total,
+        "max": 100,
+        "grade": "A" if total >= 85 else "B" if total >= 70 else "C" if total >= 50 else "D",
+        "pillars": {
+            "robots": {"score": robots_score, "max": 25, "checks": robots_checks},
+            "llms": {"score": llms_score, "max": 25, "checks": llms_checks},
+            "schema": {"score": html_score, "max": 50, "checks": html_checks},
+        },
+        "reportUrl": f"https://cernitur.com/report/{urllib.parse.quote(domain)}"
+    }
+
+def main():
+    if len(sys.argv) < 2 or sys.argv[1] in ["-h", "--help"]:
+        print("Usage: cernitur-lint <domain-or-url> [--json]")
+        print("Answer Engine Optimization (AEO) diagnostic CLI by Cernitur Technologies LLC")
+        sys.exit(0)
+
+    is_json = "--json" in sys.argv
+    target = [a for a in sys.argv[1:] if not a.startswith("-")][0]
+    domain = clean_domain(target)
+
+    result = evaluate(domain)
+
+    if is_json:
+        print(json.dumps(result, indent=2))
+        return
+
+    print(f"\nCernitur AEO Linter (Python) - Target: https://{domain}")
+    print("=" * 65)
+    print(f"1. AI Crawlers & Robots.txt ({result['pillars']['robots']['score']}/25 pts)")
+    for c in result['pillars']['robots']['checks']:
+        sym = "[PASS]" if c['pass'] else "[FAIL]"
+        print(f"  {sym:<6} {c['name']:<35} {c['note']}")
+
+    print(f"\n2. Machine-Readable Endpoint (/llms.txt) ({result['pillars']['llms']['score']}/25 pts)")
+    for c in result['pillars']['llms']['checks']:
+        sym = "[PASS]" if c['pass'] else "[FAIL]"
+        print(f"  {sym:<6} {c['name']:<35} {c['note']}")
+
+    print(f"\n3. SSR Payload Density & Schema Graph ({result['pillars']['schema']['score']}/50 pts)")
+    for c in result['pillars']['schema']['checks']:
+        sym = "[PASS]" if c['pass'] else "[FAIL]"
+        print(f"  {sym:<6} {c['name']:<35} {c['note']}")
+
+    print("=" * 65)
+    print(f"TOTAL AEO READINESS SCORE: {result['score']}/100 (Grade {result['grade']})")
+    print(f"Full Report: {result['reportUrl']}\n")
+
+if __name__ == "__main__":
+    main()

cernitur_lint-1.0.0/cernitur_lint.egg-info/PKG-INFO

@@ -0,0 +1,49 @@
+Metadata-Version: 2.4
+Name: cernitur-lint
+Version: 1.0.0
+Summary: Deterministic Answer Engine Optimization (AEO) and JSON-LD schema linter for Google AI Overviews and ChatGPT.
+Author-email: Cernitur Technologies LLC <support@cernitur.com>
+Project-URL: Homepage, https://cernitur.com
+Project-URL: Documentation, https://cernitur.com/guides/json-ld-entity-graph
+Project-URL: Repository, https://github.com/cernitur/aeo-lint
+Project-URL: Issues, https://github.com/cernitur/aeo-lint/issues
+Keywords: aeo,geo,seo,schema,llms-txt,cernitur
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: urllib3>=1.26.0
+
+# cernitur-lint
+
+> **Deterministic Answer Engine Optimization (AEO) and Schema.org Linter.**  
+> Maintained by [Cernitur Technologies LLC](https://cernitur.com).
+
+Inspects web domains for compliance with **Google AI Overviews, OpenAI Search (ChatGPT), Claude, and Perplexity** across robots.txt AI crawlers, `/llms.txt` specifications, and 5-dimension Schema.org `@graph` entity architectures.
+
+---
+
+## ⚡ Installation & Usage
+
+```bash
+pip install cernitur-lint
+cernitur-lint yourdomain.com
+```
+
+Or output raw JSON:
+
+```bash
+cernitur-lint yourdomain.com --json
+```
+
+---
+
+## 🌐 Official Links
+
+- **Hosted Diagnostic Scanner:** [https://cernitur.com/scanner](https://cernitur.com/scanner)
+- **One-Time AEO Architecture Suite:** [https://cernitur.com/pricing](https://cernitur.com/pricing)
+- **AEO vs. Retainers Comparison:** [https://cernitur.com/compare/aeo-platforms](https://cernitur.com/compare/aeo-platforms)
+
+License: Apache-2.0 &copy; 2026 Cernitur Technologies LLC.

cernitur_lint-1.0.0/cernitur_lint.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+cernitur_lint/__init__.py
+cernitur_lint/cli.py
+cernitur_lint.egg-info/PKG-INFO
+cernitur_lint.egg-info/SOURCES.txt
+cernitur_lint.egg-info/dependency_links.txt
+cernitur_lint.egg-info/entry_points.txt
+cernitur_lint.egg-info/requires.txt
+cernitur_lint.egg-info/top_level.txt

cernitur_lint-1.0.0/cernitur_lint.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

cernitur_lint-1.0.0/cernitur_lint.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+cernitur-lint = cernitur_lint.cli:main

cernitur_lint-1.0.0/cernitur_lint.egg-info/requires.txt

@@ -0,0 +1 @@
+urllib3>=1.26.0

cernitur_lint-1.0.0/cernitur_lint.egg-info/top_level.txt

@@ -0,0 +1 @@
+cernitur_lint

cernitur_lint-1.0.0/pyproject.toml

@@ -0,0 +1,32 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cernitur-lint"
+version = "1.0.0"
+authors = [
+  { name="Cernitur Technologies LLC", email="support@cernitur.com" },
+]
+description = "Deterministic Answer Engine Optimization (AEO) and JSON-LD schema linter for Google AI Overviews and ChatGPT."
+readme = "README.md"
+requires-python = ">=3.9"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: OS Independent",
+    "Topic :: Internet :: WWW/HTTP :: Indexing/Search",
+]
+keywords = ["aeo", "geo", "seo", "schema", "llms-txt", "cernitur"]
+dependencies = [
+    "urllib3>=1.26.0",
+]
+
+[project.scripts]
+cernitur-lint = "cernitur_lint.cli:main"
+
+[project.urls]
+Homepage = "https://cernitur.com"
+Documentation = "https://cernitur.com/guides/json-ld-entity-graph"
+Repository = "https://github.com/cernitur/aeo-lint"
+Issues = "https://github.com/cernitur/aeo-lint/issues"

cernitur_lint-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+