Files
TextNLPClassifierApp/graphify-out/cache/ast/v0.9.47-s2/95a7a2d913e284c24849db47815657747893f6be68bef02c86132650a76490b5.json
T
andreferraro 6e3d57619b feat(extractor): add Google News headlines extractor with Foxcape headless and URL resolution
- Add standalone CLI script scripts/extract_google_news.py for Google News RSS scraping
- Integrate foxcape in headless mode as primary stealth anti-bot engine
- Implement parallel article URL resolution using googlenewsdecoder and ThreadPoolExecutor
- Support language and regional locale mapping (-l, --lang, --locale)
- Implement real-time progress logging in stderr and --silent flag
- Add unit, integration, and live E2E tests in tests/test_extract_google_news.py
- Add full SpecKit documentation (specs/002-google-news-extractor/)
- Create comprehensive README.md covering both NLP Classifier and Google News Extractor
2026-08-20 11:50:16 -03:00

1 line
6.1 KiB
JSON

{"nodes": [{"id": "$graphify-root$_specs_002_google_news_extractor_quickstart_md", "label": "quickstart.md", "file_type": "document", "node_kind": "page", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L1"}, {"id": "$graphify-root$_specs_002_google_news_extractor_quickstart_quickstart_google_news_headlines_extractor", "label": "Quickstart: Google News Headlines Extractor", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L1"}, {"id": "$graphify-root$_specs_002_google_news_extractor_quickstart_1_pr\u00e9_requisitos", "label": "1. Pr\u00e9-requisitos", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L7"}, {"id": "$graphify-root$_specs_002_google_news_extractor_quickstart_2_cen\u00e1rios_de_execu\u00e7\u00e3o_e_valida\u00e7\u00e3o", "label": "2. Cen\u00e1rios de Execu\u00e7\u00e3o e Valida\u00e7\u00e3o", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L15"}, {"id": "$graphify-root$_specs_002_google_news_extractor_quickstart_cen\u00e1rio_1_extra\u00e7\u00e3o_b\u00e1sica_portugu\u00eas_brasil", "label": "Cen\u00e1rio 1: Extra\u00e7\u00e3o B\u00e1sica (Portugu\u00eas / Brasil)", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L17"}, {"id": "$graphify-root$_specs_002_google_news_extractor_quickstart_cen\u00e1rio_2_filtragem_regional_espanhol_m\u00e9xico", "label": "Cen\u00e1rio 2: Filtragem Regional (Espanhol / M\u00e9xico)", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L28"}, {"id": "$graphify-root$_specs_002_google_news_extractor_quickstart_cen\u00e1rio_3_pagina\u00e7\u00e3o_ampliada_ingl\u00eas_eua_2_p\u00e1ginas", "label": "Cen\u00e1rio 3: Pagina\u00e7\u00e3o Ampliada (Ingl\u00eas / EUA / 2 P\u00e1ginas)", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L38"}, {"id": "$graphify-root$_specs_002_google_news_extractor_quickstart_cen\u00e1rio_4_valida\u00e7\u00e3o_de_erro_termo_ausente_ou_inv\u00e1lido", "label": "Cen\u00e1rio 4: Valida\u00e7\u00e3o de Erro (Termo Ausente ou Inv\u00e1lido)", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L48"}, {"id": "$graphify-root$_specs_002_google_news_extractor_quickstart_3_execu\u00e7\u00e3o_dos_testes_automatizados", "label": "3. Execu\u00e7\u00e3o dos Testes Automatizados", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L58"}], "edges": [{"source": "$graphify-root$_specs_002_google_news_extractor_quickstart_md", "target": "$graphify-root$_specs_002_google_news_extractor_quickstart_quickstart_google_news_headlines_extractor", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L1", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_quickstart_quickstart_google_news_headlines_extractor", "target": "$graphify-root$_specs_002_google_news_extractor_quickstart_1_pr\u00e9_requisitos", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L7", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_quickstart_quickstart_google_news_headlines_extractor", "target": "$graphify-root$_specs_002_google_news_extractor_quickstart_2_cen\u00e1rios_de_execu\u00e7\u00e3o_e_valida\u00e7\u00e3o", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L15", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_quickstart_2_cen\u00e1rios_de_execu\u00e7\u00e3o_e_valida\u00e7\u00e3o", "target": "$graphify-root$_specs_002_google_news_extractor_quickstart_cen\u00e1rio_1_extra\u00e7\u00e3o_b\u00e1sica_portugu\u00eas_brasil", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L17", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_quickstart_2_cen\u00e1rios_de_execu\u00e7\u00e3o_e_valida\u00e7\u00e3o", "target": "$graphify-root$_specs_002_google_news_extractor_quickstart_cen\u00e1rio_2_filtragem_regional_espanhol_m\u00e9xico", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L28", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_quickstart_2_cen\u00e1rios_de_execu\u00e7\u00e3o_e_valida\u00e7\u00e3o", "target": "$graphify-root$_specs_002_google_news_extractor_quickstart_cen\u00e1rio_3_pagina\u00e7\u00e3o_ampliada_ingl\u00eas_eua_2_p\u00e1ginas", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L38", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_quickstart_2_cen\u00e1rios_de_execu\u00e7\u00e3o_e_valida\u00e7\u00e3o", "target": "$graphify-root$_specs_002_google_news_extractor_quickstart_cen\u00e1rio_4_valida\u00e7\u00e3o_de_erro_termo_ausente_ou_inv\u00e1lido", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L48", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_quickstart_quickstart_google_news_headlines_extractor", "target": "$graphify-root$_specs_002_google_news_extractor_quickstart_3_execu\u00e7\u00e3o_dos_testes_automatizados", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/quickstart.md", "source_location": "L58", "weight": 1.0}], "input_tokens": 0, "output_tokens": 0}