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

tests/test_models.py

@@ -1,15 +1,15 @@
 """Unit tests for ECP models, schema validation, and structured error handling."""
 
 import pytest
+
 from src.models import (
-    ECPSnapshot,
-    RelatedEntity,
-    ClassificationResult,
     ClassificationError,
+    ClassificationResult,
     DecisionCategory,
+    ECPSnapshot,
     ErrorCode,
 )
-from src.parser import strip_markdown, extract_sentences, extract_evidence_snippets
+from src.parser import extract_evidence_snippets, strip_markdown
 
 
 def test_ecp_snapshot_valid():
@@ -29,9 +29,9 @@ def test_ecp_snapshot_valid():
                 "weight": 0.9,
                 "aliases": ["Transpetro Logística"],
                 "scope": "logistics",
-                "confidence": 0.95
+                "confidence": 0.95,
             }
-        ]
+        ],
     }
     snapshot = ECPSnapshot.from_dict(data)
     assert snapshot.target_entity_id == "ent_123"
@@ -48,7 +48,7 @@ def test_ecp_snapshot_defaults():
         "target_name": "Petrobras",
         "aliases": ["Petrobras"],
         "domain": "Oil & Gas",
-        "anchors": ["energia"]
+        "anchors": ["energia"],
     }
     snapshot = ECPSnapshot.from_dict(data)
     assert snapshot.negative_anchors == []
@@ -61,7 +61,7 @@ def test_ecp_snapshot_missing_required():
         "target_entity_id": "ent_123",
         "aliases": ["Petrobras"],
         "domain": "Oil & Gas",
-        "anchors": ["energia"]
+        "anchors": ["energia"],
     }
     with pytest.raises(ValueError, match="Missing required field"):
         ECPSnapshot.from_dict(data)
@@ -89,7 +89,7 @@ def test_classification_error_serialization():
     err = ClassificationError(
         error_code=ErrorCode.INVALID_ECP_JSON,
         message="Malformed JSON syntax",
-        details={"path": "snapshot.json"}
+        details={"path": "snapshot.json"},
     )
     d = err.to_dict()
     assert d["error_code"] == "invalid_ecp_json"