- 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
6.0 KiB
JSON
1 line
6.0 KiB
JSON
{"nodes": [{"id": "$graphify-root$_specs_003_article_content_extractor_quickstart_md", "label": "quickstart.md", "file_type": "document", "node_kind": "page", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L1"}, {"id": "$graphify-root$_specs_003_article_content_extractor_quickstart_quickstart_validation_guide_article_content_multi_engine_extractor", "label": "Quickstart & Validation Guide: Article Content Multi-Engine Extractor", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L1"}, {"id": "$graphify-root$_specs_003_article_content_extractor_quickstart_1_pr\u00e9_requisitos", "label": "1. Pr\u00e9-requisitos", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L7"}, {"id": "$graphify-root$_specs_003_article_content_extractor_quickstart_2_cen\u00e1rios_de_valida\u00e7\u00e3o", "label": "2. Cen\u00e1rios de Valida\u00e7\u00e3o", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L17"}, {"id": "$graphify-root$_specs_003_article_content_extractor_quickstart_cen\u00e1rio_1_extra\u00e7\u00e3o_com_amostragem_r\u00e1pida_limit_2", "label": "Cen\u00e1rio 1: Extra\u00e7\u00e3o com Amostragem R\u00e1pida (Limit 2)", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L19"}, {"id": "$graphify-root$_specs_003_article_content_extractor_quickstart_cen\u00e1rio_2_caminho_customizado_de_sa\u00edda", "label": "Cen\u00e1rio 2: Caminho Customizado de Sa\u00edda", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L33"}, {"id": "$graphify-root$_specs_003_article_content_extractor_quickstart_cen\u00e1rio_3_modo_silencioso_silent", "label": "Cen\u00e1rio 3: Modo Silencioso (`--silent`)", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L45"}, {"id": "$graphify-root$_specs_003_article_content_extractor_quickstart_cen\u00e1rio_4_resili\u00eancia_contra_urls_inv\u00e1lidas", "label": "Cen\u00e1rio 4: Resili\u00eancia contra URLs Inv\u00e1lidas", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L58"}, {"id": "$graphify-root$_specs_003_article_content_extractor_quickstart_3_valida\u00e7\u00e3o_automatizada_de_testes", "label": "3. Valida\u00e7\u00e3o Automatizada de Testes", "file_type": "document", "node_kind": "heading", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L71"}], "edges": [{"source": "$graphify-root$_specs_003_article_content_extractor_quickstart_md", "target": "$graphify-root$_specs_003_article_content_extractor_quickstart_quickstart_validation_guide_article_content_multi_engine_extractor", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L1", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_quickstart_quickstart_validation_guide_article_content_multi_engine_extractor", "target": "$graphify-root$_specs_003_article_content_extractor_quickstart_1_pr\u00e9_requisitos", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L7", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_quickstart_quickstart_validation_guide_article_content_multi_engine_extractor", "target": "$graphify-root$_specs_003_article_content_extractor_quickstart_2_cen\u00e1rios_de_valida\u00e7\u00e3o", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L17", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_quickstart_2_cen\u00e1rios_de_valida\u00e7\u00e3o", "target": "$graphify-root$_specs_003_article_content_extractor_quickstart_cen\u00e1rio_1_extra\u00e7\u00e3o_com_amostragem_r\u00e1pida_limit_2", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L19", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_quickstart_2_cen\u00e1rios_de_valida\u00e7\u00e3o", "target": "$graphify-root$_specs_003_article_content_extractor_quickstart_cen\u00e1rio_2_caminho_customizado_de_sa\u00edda", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L33", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_quickstart_2_cen\u00e1rios_de_valida\u00e7\u00e3o", "target": "$graphify-root$_specs_003_article_content_extractor_quickstart_cen\u00e1rio_3_modo_silencioso_silent", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L45", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_quickstart_2_cen\u00e1rios_de_valida\u00e7\u00e3o", "target": "$graphify-root$_specs_003_article_content_extractor_quickstart_cen\u00e1rio_4_resili\u00eancia_contra_urls_inv\u00e1lidas", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L58", "weight": 1.0}, {"source": "$graphify-root$_specs_003_article_content_extractor_quickstart_quickstart_validation_guide_article_content_multi_engine_extractor", "target": "$graphify-root$_specs_003_article_content_extractor_quickstart_3_valida\u00e7\u00e3o_automatizada_de_testes", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/003-article-content-extractor/quickstart.md", "source_location": "L71", "weight": 1.0}], "input_tokens": 0, "output_tokens": 0} |