andreferraro
6e3d57619b
- 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
1 line
7.3 KiB
JSON
1 line
7.3 KiB
JSON
{"nodes": [{"id": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_md", "label": "readiness.md", "file_type": "document", "node_kind": "page", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L1"}, {"id": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_general_readiness_checklist_google_news_headlines_extractor", "label": "General Readiness Checklist: Google News Headlines Extractor", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L1"}, {"id": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_cli_interface_parameter_contracts", "label": "CLI Interface & Parameter Contracts", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L12"}, {"id": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_scraping_engine_feed_mapping", "label": "Scraping Engine & Feed Mapping", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L20"}, {"id": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_data_sanitization_article_extraction", "label": "Data Sanitization & Article Extraction", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L27"}, {"id": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_error_handling_edge_cases", "label": "Error Handling & Edge Cases", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L35"}, {"id": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_non_functional_operational_readiness", "label": "Non-Functional & Operational Readiness", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L42"}, {"id": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_notes", "label": "Notes", "file_type": "document", "node_kind": "heading", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L48"}], "edges": [{"source": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_md", "target": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_general_readiness_checklist_google_news_headlines_extractor", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L1", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_md", "target": "$graphify-root$_specs_002_google_news_extractor_spec_md", "relation": "references", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L6", "weight": 1.0, "target_file": "$graphify-root$/specs/002-google-news-extractor/spec.md"}, {"source": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_md", "target": "$graphify-root$_specs_002_google_news_extractor_plan_md", "relation": "references", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L6", "weight": 1.0, "target_file": "$graphify-root$/specs/002-google-news-extractor/plan.md"}, {"source": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_md", "target": "$graphify-root$_specs_002_google_news_extractor_contracts_cli_contract_md", "relation": "references", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L6", "weight": 1.0, "target_file": "$graphify-root$/specs/002-google-news-extractor/contracts/cli_contract.md"}, {"source": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_md", "target": "$graphify-root$_specs_002_google_news_extractor_data_model_md", "relation": "references", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L6", "weight": 1.0, "target_file": "$graphify-root$/specs/002-google-news-extractor/data-model.md"}, {"source": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_md", "target": "$graphify-root$_specs_002_google_news_extractor_research_md", "relation": "references", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L6", "weight": 1.0, "target_file": "$graphify-root$/specs/002-google-news-extractor/research.md"}, {"source": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_general_readiness_checklist_google_news_headlines_extractor", "target": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_cli_interface_parameter_contracts", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L12", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_general_readiness_checklist_google_news_headlines_extractor", "target": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_scraping_engine_feed_mapping", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L20", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_general_readiness_checklist_google_news_headlines_extractor", "target": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_data_sanitization_article_extraction", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L27", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_general_readiness_checklist_google_news_headlines_extractor", "target": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_error_handling_edge_cases", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L35", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_general_readiness_checklist_google_news_headlines_extractor", "target": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_non_functional_operational_readiness", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L42", "weight": 1.0}, {"source": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_general_readiness_checklist_google_news_headlines_extractor", "target": "$graphify-root$_specs_002_google_news_extractor_checklists_readiness_notes", "relation": "contains", "confidence": "EXTRACTED", "source_file": "specs/002-google-news-extractor/checklists/readiness.md", "source_location": "L48", "weight": 1.0}], "input_tokens": 0, "output_tokens": 0} |