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
107 lines
3.4 KiB
JSON
107 lines
3.4 KiB
JSON
{
|
|
"0": "Task Planning",
|
|
"1": "Convergence Workflow",
|
|
"2": "SpecKit Utilities",
|
|
"3": "Graphify Commands",
|
|
"4": "speckit-analyze/SKILL.md",
|
|
"5": "Tasks: Multilingual NLP Entity Inherence Classifier (POC)",
|
|
"6": "Feature Specification Template",
|
|
"7": "Graphify Rules",
|
|
"8": "Implementation Planning",
|
|
"9": "Feature Specification",
|
|
"10": "Task Generation",
|
|
"11": "Project Constitution",
|
|
"12": "Constitution Template",
|
|
"13": "Graphify Exports",
|
|
"14": "Ponytail Configuration",
|
|
"15": "Implementation Planning Template",
|
|
"16": "Ponytail Help",
|
|
"17": "Checklist Generation",
|
|
"18": "Clarification Workflow",
|
|
"19": "Implementation Workflow",
|
|
"20": "Graph Query",
|
|
"21": "Constitution Workflow",
|
|
"22": "Feature Branch Creation",
|
|
"23": "Ponytail Audit",
|
|
"24": "Ponytail Metrics",
|
|
"25": "Ponytail Review",
|
|
"26": "Task Issue Conversion",
|
|
"27": "Checklist Template",
|
|
"28": "Graphify Watch Mode",
|
|
"29": "Graphify Hooks",
|
|
"30": "Graphify Updates",
|
|
"31": "Ponytail Debt",
|
|
"32": "Repository Merge",
|
|
"33": "Media Transcription",
|
|
"34": "Extraction Specification",
|
|
"35": "Prerequisite Checks",
|
|
"36": "Template Resolution",
|
|
"37": "Plan Setup",
|
|
"38": "Task Setup",
|
|
"39": "Graphify Workflows",
|
|
"40": "main",
|
|
"41": "1. Technical Decisions & Tradeoffs",
|
|
"42": "1. Input Schemas",
|
|
"43": "2. Basic CLI Usage Examples",
|
|
"44": "2. Standard Streams & Exit Codes",
|
|
"45": "ClassificationResult",
|
|
"46": "InherenceClassifier",
|
|
"47": "detect_language",
|
|
"48": "test_models.py",
|
|
"49": "content_northvolt_de.md",
|
|
"50": "content_presal_pt.md",
|
|
"51": "content_tangential_es.md",
|
|
"52": "adapters/__init__.py",
|
|
"53": "src/__init__.py",
|
|
"54": "de/contextual.md",
|
|
"55": "de/direct.md",
|
|
"56": "de/not_related.md",
|
|
"57": "de/tangential.md",
|
|
"58": "en/contextual.md",
|
|
"59": "en/direct.md",
|
|
"60": "en/not_related.md",
|
|
"61": "en/tangential.md",
|
|
"62": "es/contextual.md",
|
|
"63": "es/direct.md",
|
|
"64": "es/not_related.md",
|
|
"65": "es/tangential.md",
|
|
"66": "fr/contextual.md",
|
|
"67": "fr/direct.md",
|
|
"68": "fr/not_related.md",
|
|
"69": "fr/tangential.md",
|
|
"70": "it/contextual.md",
|
|
"71": "it/direct.md",
|
|
"72": "it/not_related.md",
|
|
"73": "it/tangential.md",
|
|
"74": "pt/contextual.md",
|
|
"75": "pt/direct.md",
|
|
"76": "pt/not_related.md",
|
|
"77": "pt/tangential.md",
|
|
"78": "tests/__init__.py",
|
|
"79": "text-nlp-classifier",
|
|
"80": "get_hl_gl_ceid",
|
|
"81": "Extrator de Notícias do Google News — Guia Completo de Funcionamento",
|
|
"82": "extract_google_news.py",
|
|
"83": "ExtractionResult",
|
|
"84": "test_extract_google_news.py",
|
|
"85": "Implementation Tasks: Google News Headlines Extractor",
|
|
"86": "Feature Specification: Google News Headlines Extractor",
|
|
"87": "2. Cenários Práticos de Uso",
|
|
"88": "Implementation Plan: Google News Headlines Extractor",
|
|
"89": "scripts/__init__.py",
|
|
"90": "SearchQuery",
|
|
"91": "1. Technical Decisions & Tradeoffs",
|
|
"92": "General Readiness Checklist: Google News Headlines Extractor",
|
|
"93": "1. Entidades de Domínio & DTOs",
|
|
"94": "Specification Quality Checklist: Google News Headlines Extractor",
|
|
"95": "CLI Contract: Google News Headlines Extractor",
|
|
"96": "readiness.md",
|
|
"97": "🧠 TextNLPClassifierApp",
|
|
"98": "build_parser",
|
|
"99": "sample_rss_xml",
|
|
"100": "classifier.py",
|
|
"101": "ECPSnapshot",
|
|
"102": "Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)",
|
|
"103": "main"
|
|
}
|