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
27 lines
546 B
TOML
27 lines
546 B
TOML
[build-system]
|
|
requires = ["setuptools>=61.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "text-nlp-classifier"
|
|
version = "0.1.0"
|
|
description = "Multilingual NLP Entity Inherence Classifier (POC)"
|
|
readme = "README.md"
|
|
requires-python = ">=3.10"
|
|
dependencies = []
|
|
|
|
[project.optional-dependencies]
|
|
test = [
|
|
"pytest>=7.0.0",
|
|
]
|
|
|
|
[tool.pytest.ini_options]
|
|
pythonpath = [".", "src"]
|
|
testpaths = ["tests"]
|
|
python_files = ["test_*.py"]
|
|
python_classes = ["Test*"]
|
|
python_functions = ["test_*"]
|
|
|
|
[tool.pyright]
|
|
extraPaths = [".", "src"]
|