pyproject.toml

[tool.poetry]
name = "webarticlecurator"
version = "1.10.1"
description = "A crawler program to download content from portals (news, forums, blogs) and convert it to the desired output format according to the configuration."
readme = "README.md"
repository = "https://github.com/ELTE-DH/WebArticleCurator"
authors = ["dlazesz"]
license = "LGPLv3"
# License and required Python version is automatically added
classifiers = [
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Operating System :: OS Independent",
    "Development Status :: 5 - Production/Stable",
]
include = ["webarticlecurator/crawl_schema.yaml", "webarticlecurator/site_schema.yaml"]

[tool.poetry.scripts]
webarticlecurator = "webarticlecurator.__main__:main"

[tool.poetry.dependencies]
python = "^3.8"
beautifulsoup4 = "^4.9.0"
lxml = "^4.5.0"
pyyaml = "^6.0.0"
warcio = "^1.7.0"
chardet = "^4.0.0"
requests = "^2.26.0"
urllib3 = "^1.26.7"
ratelimit = "^2.2.1"
yamale = "^4.0.2"
mplogger = "^1.0.0"
# A list of all of the optional dependencies, some of which are included in the
# below `extras`. They can be opted into by apps.
newspaper3k = { version = "^0.2.8", optional = true }

[tool.poetry.extras]
newspaper3k = ["newspaper3k"]
full = ["newspaper3k"]

[tool.poetry.dev-dependencies]
pytest = "^6"

[build-system]
requires = ["poetry-core>=1.0.0"]
build-backend = "poetry.core.masonry.api"