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
4.4 KiB
JSON
1 line
4.4 KiB
JSON
{"nodes": [{"id": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_md", "label": "requirements.md", "file_type": "document", "node_kind": "page", "source_file": "specs/003-article-content-extractor/checklists/requirements.md", "source_location": "L1"}, {"id": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_specification_quality_checklist_article_content_multi_engine_extractor", "label": "Specification Quality Checklist: Article Content Multi-Engine Extractor", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/checklists/requirements.md", "source_location": "L1"}, {"id": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_content_quality", "label": "Content Quality", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/checklists/requirements.md", "source_location": "L7"}, {"id": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_requirement_completeness", "label": "Requirement Completeness", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/checklists/requirements.md", "source_location": "L14"}, {"id": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_feature_readiness", "label": "Feature Readiness", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/checklists/requirements.md", "source_location": "L25"}, {"id": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_notes", "label": "Notes", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/checklists/requirements.md", "source_location": "L32"}], "edges": [{"source": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_md", "target": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_specification_quality_checklist_article_content_multi_engine_extractor", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/checklists/requirements.md", "source_location": "L1", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_md", "target": "$graphify-root$_specs_003_article_content_extractor_spec_md", "relation": "references", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/checklists/requirements.md", "source_location": "L5", "weight": 1.0, "target_file": "$graphify-root$/specs/003-article-content-extractor/spec.md"}, {"source": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_specification_quality_checklist_article_content_multi_engine_extractor", "target": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_content_quality", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/checklists/requirements.md", "source_location": "L7", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_specification_quality_checklist_article_content_multi_engine_extractor", "target": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_requirement_completeness", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/checklists/requirements.md", "source_location": "L14", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_specification_quality_checklist_article_content_multi_engine_extractor", "target": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_feature_readiness", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/checklists/requirements.md", "source_location": "L25", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_specification_quality_checklist_article_content_multi_engine_extractor", "target": "$graphify-root$_specs_003_article_content_extractor_checklists_requirements_notes", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/checklists/requirements.md", "source_location": "L32", "weight": 1.0}], "input_tokens": 0, "output_tokens": 0} |