d31395a166
- Complete browser automation with Playwright integration - High-level API functions: get(), get_many(), discover() - JavaScript execution support with script parameters - Content extraction optimized for LLM workflows - Comprehensive test suite with 18 test files (700+ scenarios) - Local Caddy test server for reproducible testing - Performance benchmarking vs Katana crawler - Complete documentation including JavaScript API guide - PyPI-ready packaging with professional metadata - UNIX philosophy: do web scraping exceptionally well
51 lines
1.1 KiB
Plaintext
51 lines
1.1 KiB
Plaintext
# Include documentation and metadata files
|
|
include README.md
|
|
include LICENSE
|
|
include CHANGELOG.md
|
|
include pyproject.toml
|
|
|
|
# Include documentation directory
|
|
recursive-include docs *.md
|
|
|
|
# Include test configuration (but not tests themselves for distribution)
|
|
include pytest.ini
|
|
include .gitignore
|
|
|
|
# Exclude development and build files
|
|
exclude .env*
|
|
exclude docker-compose*.yml
|
|
exclude Dockerfile*
|
|
exclude .pre-commit-config.yaml
|
|
exclude benchmark_*.py
|
|
exclude demo_*.py
|
|
exclude simple_*.py
|
|
exclude *_COMPLETE.md
|
|
exclude *_SUMMARY.md
|
|
exclude *_ANALYSIS.md
|
|
exclude CLAUDE.md
|
|
|
|
# Exclude test server and temporary files
|
|
recursive-exclude test-server *
|
|
recursive-exclude tests *
|
|
recursive-exclude .git *
|
|
recursive-exclude .pytest_cache *
|
|
recursive-exclude __pycache__ *
|
|
recursive-exclude *.egg-info *
|
|
recursive-exclude .coverage *
|
|
recursive-exclude htmlcov *
|
|
exclude .mypy_cache
|
|
exclude .ruff_cache
|
|
|
|
# Exclude development coordination files
|
|
recursive-exclude coordination *
|
|
recursive-exclude feature *
|
|
|
|
# Include only essential documentation
|
|
prune coordination
|
|
prune feature
|
|
prune test-server
|
|
prune tests
|
|
prune .git
|
|
prune .pytest_cache
|
|
prune __pycache__
|
|
prune *.egg-info |