andreferraro
6a45368cb0
- 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
1 line
2.6 KiB
JSON
1 line
2.6 KiB
JSON
{"nodes": [{"id": "$graphify-root$_specs_003_article_content_extractor_contracts_json_schema_md", "label": "json-schema.md", "file_type": "document", "node_kind": "page", "source_file": "specs/003-article-content-extractor/contracts/json-schema.md", "source_location": "L1"}, {"id": "$graphify-root$_specs_003_article_content_extractor_contracts_json_schema_json_schema_contract_article_content_multi_engine_extractor", "label": "JSON Schema Contract: Article Content Multi-Engine Extractor", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/contracts/json-schema.md", "source_location": "L1"}, {"id": "$graphify-root$_specs_003_article_content_extractor_contracts_json_schema_1_schema_de_entrada_input_json", "label": "1. Schema de Entrada (Input JSON)", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/contracts/json-schema.md", "source_location": "L3"}, {"id": "$graphify-root$_specs_003_article_content_extractor_contracts_json_schema_2_schema_de_sa\u00edda_output_json", "label": "2. Schema de Sa\u00edda (Output JSON)", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/contracts/json-schema.md", "source_location": "L27"}], "edges": [{"source": "$graphify-root$_specs_003_article_content_extractor_contracts_json_schema_md", "target": "$graphify-root$_specs_003_article_content_extractor_contracts_json_schema_json_schema_contract_article_content_multi_engine_extractor", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/contracts/json-schema.md", "source_location": "L1", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_contracts_json_schema_json_schema_contract_article_content_multi_engine_extractor", "target": "$graphify-root$_specs_003_article_content_extractor_contracts_json_schema_1_schema_de_entrada_input_json", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/contracts/json-schema.md", "source_location": "L3", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_contracts_json_schema_json_schema_contract_article_content_multi_engine_extractor", "target": "$graphify-root$_specs_003_article_content_extractor_contracts_json_schema_2_schema_de_sa\u00edda_output_json", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/contracts/json-schema.md", "source_location": "L27", "weight": 1.0}], "input_tokens": 0, "output_tokens": 0} |