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
16 KiB
JSON
1 line
16 KiB
JSON
{"nodes": [{"id": "$graphify-root$_readme_md", "label": "README.md", "file_type": "document", "node_kind": "page", "source_file": "README.md", "source_location": "L1"}, {"id": "$graphify-root$_readme_textnlpclassifierapp", "label": "\ud83e\udde0 TextNLPClassifierApp", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L1"}, {"id": "$graphify-root$_readme_tabela_de_conte\u00fados", "label": "\ud83d\udcd1 Tabela de Conte\u00fados", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L13"}, {"id": "$graphify-root$_readme_vis\u00e3o_geral", "label": "\ud83c\udf1f Vis\u00e3o Geral", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L38"}, {"id": "$graphify-root$_readme_instala\u00e7\u00e3o_e_setup", "label": "\u2699\ufe0f Instala\u00e7\u00e3o e Setup", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L47"}, {"id": "$graphify-root$_readme_1_clonar_o_reposit\u00f3rio_e_criar_ambiente_virtual", "label": "1. Clonar o Reposit\u00f3rio e Criar Ambiente Virtual", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L49"}, {"id": "$graphify-root$_readme_2_instalar_depend\u00eancias", "label": "2. Instalar Depend\u00eancias", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L62"}, {"id": "$graphify-root$_readme_3_baixar_bin\u00e1rios_do_navegador_stealth_camoufox", "label": "3. Baixar Bin\u00e1rios do Navegador Stealth (Camoufox)", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L68"}, {"id": "$graphify-root$_readme_1_classificador_de_conte\u00fado_e_iner\u00eancia_nlp_llm_ecp", "label": "1. \ud83e\udde0 Classificador de Conte\u00fado e Iner\u00eancia (NLP / LLM / ECP)", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L78"}, {"id": "$graphify-root$_readme_o_que_\u00e9_e_como_funciona", "label": "O que \u00e9 e Como Funciona", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L80"}, {"id": "$graphify-root$_readme_arquitetura_de_classifica\u00e7\u00e3o_em_3_tiers", "label": "Arquitetura de Classifica\u00e7\u00e3o em 3 Tiers", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L86"}, {"id": "$graphify-root$_readme_categorias_de_decis\u00e3o", "label": "Categorias de Decis\u00e3o", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L107"}, {"id": "$graphify-root$_readme_formato_do_ecp_snapshot_e_markdown", "label": "Formato do ECP Snapshot e Markdown", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L116"}, {"id": "$graphify-root$_readme_exemplo_de_ecp_snapshot_ecp_sample_json", "label": "Exemplo de ECP Snapshot (`ecp_sample.json`):", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L118"}, {"id": "$graphify-root$_readme_exemplos_de_uso_cli", "label": "Exemplos de Uso CLI", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L140"}, {"id": "$graphify-root$_readme_2_extrator_de_manchetes_do_google_news", "label": "2. \ud83d\udcf0 Extrator de Manchetes do Google News", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L155"}, {"id": "$graphify-root$_readme_o_que_\u00e9_e_como_funciona_157", "label": "O que \u00e9 e Como Funciona", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L157"}, {"id": "$graphify-root$_readme_diferenciais_t\u00e9cnicos", "label": "Diferenciais T\u00e9cnicos", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L161"}, {"id": "$graphify-root$_readme_argumentos_e_flags_de_linha_de_comando", "label": "Argumentos e Flags de Linha de Comando", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L169"}, {"id": "$graphify-root$_readme_exemplos_pr\u00e1ticos_de_uso", "label": "Exemplos Pr\u00e1ticos de Uso", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L182"}, {"id": "$graphify-root$_readme_1_river_plate_argentina_espanhol_2_p\u00e1ginas_salvar_em_arquivo", "label": "1. River Plate (Argentina / Espanhol / 2 P\u00e1ginas / Salvar em Arquivo)", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L184"}, {"id": "$graphify-root$_readme_2_cruzeiro_brasil_portugu\u00eas_formatado_no_terminal", "label": "2. Cruzeiro (Brasil / Portugu\u00eas / Formatado no Terminal)", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L198"}, {"id": "$graphify-root$_readme_3_f\u00f3rmula_1_inglaterra_ingl\u00eas", "label": "3. F\u00f3rmula 1 (Inglaterra / Ingl\u00eas)", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L203"}, {"id": "$graphify-root$_readme_4_filtragem_com_jq_em_modo_silencioso", "label": "4. Filtragem com `jq` em Modo Silencioso", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L208"}, {"id": "$graphify-root$_readme_3_extrator_e_parser_multimotor_de_artigos", "label": "3. \ud83d\udcf0 Extrator e Parser Multimotor de Artigos", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L215"}, {"id": "$graphify-root$_readme_vis\u00e3o_geral_e_tr\u00edplice_extra\u00e7\u00e3o", "label": "Vis\u00e3o Geral e Tr\u00edplice Extra\u00e7\u00e3o", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L217"}, {"id": "$graphify-root$_readme_argumentos_e_flags_cli", "label": "Argumentos e Flags CLI", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L227"}, {"id": "$graphify-root$_readme_exemplos_de_uso", "label": "Exemplos de Uso", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L238"}, {"id": "$graphify-root$_readme_1_extra\u00e7\u00e3o_completa_autom\u00e1tica", "label": "1. Extra\u00e7\u00e3o Completa Autom\u00e1tica", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L240"}, {"id": "$graphify-root$_readme_2_amostragem_r\u00e1pida_limit_2_not\u00edcias", "label": "2. Amostragem R\u00e1pida (Limit 2 Not\u00edcias)", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L246"}, {"id": "$graphify-root$_readme_3_destino_customizado_e_timeout_ajustado", "label": "3. Destino Customizado e Timeout Ajustado", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L251"}, {"id": "$graphify-root$_readme_estrutura_do_projeto", "label": "\ud83d\udcc1 Estrutura do Projeto", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L258"}, {"id": "$graphify-root$_readme_testes_e_qualidade_de_c\u00f3digo", "label": "\ud83e\uddea Testes e Qualidade de C\u00f3digo", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L287"}, {"id": "$graphify-root$_readme_licen\u00e7a", "label": "\ud83d\udcc4 Licen\u00e7a", "file_type": "document", "node_kind": "heading", "source_file": "README.md", "source_location": "L308"}], "edges": [{"source": "$graphify-root$_readme_md", "target": "$graphify-root$_readme_textnlpclassifierapp", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L1", "weight": 1.0}, {"source": "$graphify-root$_readme_textnlpclassifierapp", "target": "$graphify-root$_readme_tabela_de_conte\u00fados", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L13", "weight": 1.0}, {"source": "$graphify-root$_readme_textnlpclassifierapp", "target": "$graphify-root$_readme_vis\u00e3o_geral", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L38", "weight": 1.0}, {"source": "$graphify-root$_readme_textnlpclassifierapp", "target": "$graphify-root$_readme_instala\u00e7\u00e3o_e_setup", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L47", "weight": 1.0}, {"source": "$graphify-root$_readme_instala\u00e7\u00e3o_e_setup", "target": "$graphify-root$_readme_1_clonar_o_reposit\u00f3rio_e_criar_ambiente_virtual", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L49", "weight": 1.0}, {"source": "$graphify-root$_readme_instala\u00e7\u00e3o_e_setup", "target": "$graphify-root$_readme_2_instalar_depend\u00eancias", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L62", "weight": 1.0}, {"source": "$graphify-root$_readme_instala\u00e7\u00e3o_e_setup", "target": "$graphify-root$_readme_3_baixar_bin\u00e1rios_do_navegador_stealth_camoufox", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L68", "weight": 1.0}, {"source": "$graphify-root$_readme_textnlpclassifierapp", "target": "$graphify-root$_readme_1_classificador_de_conte\u00fado_e_iner\u00eancia_nlp_llm_ecp", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L78", "weight": 1.0}, {"source": "$graphify-root$_readme_1_classificador_de_conte\u00fado_e_iner\u00eancia_nlp_llm_ecp", "target": "$graphify-root$_readme_o_que_\u00e9_e_como_funciona", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L80", "weight": 1.0}, {"source": "$graphify-root$_readme_1_classificador_de_conte\u00fado_e_iner\u00eancia_nlp_llm_ecp", "target": "$graphify-root$_readme_arquitetura_de_classifica\u00e7\u00e3o_em_3_tiers", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L86", "weight": 1.0}, {"source": "$graphify-root$_readme_1_classificador_de_conte\u00fado_e_iner\u00eancia_nlp_llm_ecp", "target": "$graphify-root$_readme_categorias_de_decis\u00e3o", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L107", "weight": 1.0}, {"source": "$graphify-root$_readme_1_classificador_de_conte\u00fado_e_iner\u00eancia_nlp_llm_ecp", "target": "$graphify-root$_readme_formato_do_ecp_snapshot_e_markdown", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L116", "weight": 1.0}, {"source": "$graphify-root$_readme_formato_do_ecp_snapshot_e_markdown", "target": "$graphify-root$_readme_exemplo_de_ecp_snapshot_ecp_sample_json", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L118", "weight": 1.0}, {"source": "$graphify-root$_readme_1_classificador_de_conte\u00fado_e_iner\u00eancia_nlp_llm_ecp", "target": "$graphify-root$_readme_exemplos_de_uso_cli", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L140", "weight": 1.0}, {"source": "$graphify-root$_readme_textnlpclassifierapp", "target": "$graphify-root$_readme_2_extrator_de_manchetes_do_google_news", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L155", "weight": 1.0}, {"source": "$graphify-root$_readme_2_extrator_de_manchetes_do_google_news", "target": "$graphify-root$_readme_o_que_\u00e9_e_como_funciona_157", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L157", "weight": 1.0}, {"source": "$graphify-root$_readme_2_extrator_de_manchetes_do_google_news", "target": "$graphify-root$_readme_diferenciais_t\u00e9cnicos", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L161", "weight": 1.0}, {"source": "$graphify-root$_readme_2_extrator_de_manchetes_do_google_news", "target": "$graphify-root$_readme_argumentos_e_flags_de_linha_de_comando", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L169", "weight": 1.0}, {"source": "$graphify-root$_readme_2_extrator_de_manchetes_do_google_news", "target": "$graphify-root$_readme_exemplos_pr\u00e1ticos_de_uso", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L182", "weight": 1.0}, {"source": "$graphify-root$_readme_exemplos_pr\u00e1ticos_de_uso", "target": "$graphify-root$_readme_1_river_plate_argentina_espanhol_2_p\u00e1ginas_salvar_em_arquivo", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L184", "weight": 1.0}, {"source": "$graphify-root$_readme_exemplos_pr\u00e1ticos_de_uso", "target": "$graphify-root$_readme_2_cruzeiro_brasil_portugu\u00eas_formatado_no_terminal", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L198", "weight": 1.0}, {"source": "$graphify-root$_readme_exemplos_pr\u00e1ticos_de_uso", "target": "$graphify-root$_readme_3_f\u00f3rmula_1_inglaterra_ingl\u00eas", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L203", "weight": 1.0}, {"source": "$graphify-root$_readme_exemplos_pr\u00e1ticos_de_uso", "target": "$graphify-root$_readme_4_filtragem_com_jq_em_modo_silencioso", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L208", "weight": 1.0}, {"source": "$graphify-root$_readme_textnlpclassifierapp", "target": "$graphify-root$_readme_3_extrator_e_parser_multimotor_de_artigos", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L215", "weight": 1.0}, {"source": "$graphify-root$_readme_3_extrator_e_parser_multimotor_de_artigos", "target": "$graphify-root$_readme_vis\u00e3o_geral_e_tr\u00edplice_extra\u00e7\u00e3o", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L217", "weight": 1.0}, {"source": "$graphify-root$_readme_3_extrator_e_parser_multimotor_de_artigos", "target": "$graphify-root$_readme_argumentos_e_flags_cli", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L227", "weight": 1.0}, {"source": "$graphify-root$_readme_3_extrator_e_parser_multimotor_de_artigos", "target": "$graphify-root$_readme_exemplos_de_uso", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L238", "weight": 1.0}, {"source": "$graphify-root$_readme_exemplos_de_uso", "target": "$graphify-root$_readme_1_extra\u00e7\u00e3o_completa_autom\u00e1tica", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L240", "weight": 1.0}, {"source": "$graphify-root$_readme_exemplos_de_uso", "target": "$graphify-root$_readme_2_amostragem_r\u00e1pida_limit_2_not\u00edcias", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L246", "weight": 1.0}, {"source": "$graphify-root$_readme_exemplos_de_uso", "target": "$graphify-root$_readme_3_destino_customizado_e_timeout_ajustado", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L251", "weight": 1.0}, {"source": "$graphify-root$_readme_textnlpclassifierapp", "target": "$graphify-root$_readme_estrutura_do_projeto", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L258", "weight": 1.0}, {"source": "$graphify-root$_readme_textnlpclassifierapp", "target": "$graphify-root$_readme_testes_e_qualidade_de_c\u00f3digo", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L287", "weight": 1.0}, {"source": "$graphify-root$_readme_textnlpclassifierapp", "target": "$graphify-root$_readme_licen\u00e7a", "relation": "contains", "confidence": "EXTRACTED", "source_file": "README.md", "source_location": "L308", "weight": 1.0}], "input_tokens": 0, "output_tokens": 0} |