feat(extractor): implement multi-engine article content extractor

- Added scripts/extract_article_contents.py for batch scraping with stealth Foxcape and triple extraction (Trafilatura, Newspaper4k, Readability)
- Created unit, integration, and E2E test suite in tests/test_extract_article_contents.py (90/90 passing)
- Updated specs/003-article-content-extractor and README.md with usage documentation and CLI contracts
- Passed ruff linting/formatting and mypy type checking cleanly

graphify-out/2026-08-20/.graphify_labels.json

@@ -4,7 +4,7 @@
   "2": "SpecKit Utilities",
   "3": "Graphify Commands",
   "4": "speckit-analyze/SKILL.md",
-  "5": "POC Readiness & Requirements Quality Checklist: Multilingual NLP Entity Inherence Classifier",
+  "5": "Tasks: Multilingual NLP Entity Inherence Classifier (POC)",
   "6": "Feature Specification Template",
   "7": "Graphify Rules",
   "8": "Implementation Planning",
@@ -44,10 +44,10 @@
   "42": "1. Input Schemas",
   "43": "2. Basic CLI Usage Examples",
   "44": "2. Standard Streams & Exit Codes",
-  "45": "ECPSnapshot",
-  "46": "Tasks: Multilingual NLP Entity Inherence Classifier (POC)",
+  "45": "LocalEmbeddingsAdapter",
+  "46": "InherenceClassifier",
   "47": "detect_language",
-  "48": "test_models.py",
+  "48": "classifier.py",
   "49": "content_northvolt_de.md",
   "50": "content_presal_pt.md",
   "51": "content_tangential_es.md",
@@ -79,7 +79,7 @@
   "77": "pt/tangential.md",
   "78": "tests/__init__.py",
   "79": "text-nlp-classifier",
-  "80": "get_hl_gl_ceid",
+  "80": "test_extract_article_contents.py",
   "81": "Extrator de Notícias do Google News — Guia Completo de Funcionamento",
   "82": "extract_google_news.py",
   "83": "ExtractionResult",
@@ -96,6 +96,22 @@
   "94": "Specification Quality Checklist: Google News Headlines Extractor",
   "95": "CLI Contract: Google News Headlines Extractor",
   "96": "readiness.md",
-  "98": "build_parser",
-  "99": "sample_rss_xml"
+  "97": "🧠 TextNLPClassifierApp",
+  "98": "Extraction Pipeline Checklist: Article Content Multi-Engine Extractor",
+  "99": "sample_rss_xml",
+  "100": "models.py",
+  "101": "ECPSnapshot",
+  "102": "Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)",
+  "103": "4. Requisitos Funcionais (FR)",
+  "104": "Tasks: Article Content Multi-Engine Extractor",
+  "105": "ClassificationResult",
+  "106": "Implementation Plan: Article Content Multi-Engine Extractor",
+  "107": "2. Cenários de Validação",
+  "108": "1. Technical Decisions & Tradeoffs",
+  "109": "Implementation Plan: Multilingual NLP Entity Inherence Classifier (POC)",
+  "110": "POC Readiness & Requirements Quality Checklist: Multilingual NLP Entity Inherence Classifier",
+  "111": "Specification Quality Checklist: Multilingual NLP Entity Inherence Classifier",
+  "112": "CLI Contract: Article Content Multi-Engine Extractor",
+  "113": "001-multilingual-entity-classifier/spec.md",
+  "114": "JSON Schema Contract: Article Content Multi-Engine Extractor"
 }