pyproject.toml

[build-system]
requires = ["setuptools >= 61.0"]
build-backend = "setuptools.build_meta"

[project]
name = "Scrapy"
dynamic = ["version"]
description = "A high-level Web Crawling and Web Scraping framework"
dependencies = [
    "Twisted>=21.7.0",
    "cryptography>=37.0.0",
    "cssselect>=0.9.1",
    "itemloaders>=1.0.1",
    "parsel>=1.5.0",
    "pyOpenSSL>=22.0.0",
    "queuelib>=1.4.2",
    "service_identity>=18.1.0",
    "w3lib>=1.17.0",
    "zope.interface>=5.1.0",
    "protego>=0.1.15",
    "itemadapter>=0.1.0",
    "packaging",
    "tldextract",
    "lxml>=4.6.0",
    "defusedxml>=0.7.1",
    # Platform-specific dependencies
    'PyDispatcher>=2.0.5; platform_python_implementation == "CPython"',
    'PyPyDispatcher>=2.1.0; platform_python_implementation == "PyPy"',
]
classifiers = [
    "Framework :: Scrapy",
    "Development Status :: 5 - Production/Stable",
    "Environment :: Console",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: BSD License",
    "Operating System :: OS Independent",
    "Programming Language :: Python",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Programming Language :: Python :: Implementation :: CPython",
    "Programming Language :: Python :: Implementation :: PyPy",
    "Topic :: Internet :: WWW/HTTP",
    "Topic :: Software Development :: Libraries :: Application Frameworks",
    "Topic :: Software Development :: Libraries :: Python Modules",
]
readme = "README.rst"
requires-python = ">=3.9"
authors = [{ name = "Scrapy developers", email = "pablo@pablohoffman.com" }]
maintainers = [{ name = "Pablo Hoffman", email = "pablo@pablohoffman.com" }]

[project.urls]
Homepage = "https://scrapy.org/"
Documentation = "https://docs.scrapy.org/"
Source = "https://github.com/scrapy/scrapy"
Tracker = "https://github.com/scrapy/scrapy/issues"
Changelog = "https://github.com/scrapy/scrapy/commits/master/"
releasenotes = "https://docs.scrapy.org/en/latest/news.html"

[project.scripts]
scrapy = "scrapy.cmdline:execute"

[tool.setuptools.packages.find]
where = ["."]
include = ["scrapy", "scrapy.*",]

[tool.setuptools.dynamic]
version = {file = "./scrapy/VERSION"}

[tool.mypy]
ignore_missing_imports = true
implicit_reexport = false

# Interface classes are hard to support
[[tool.mypy.overrides]]
module = "twisted.internet.interfaces"
follow_imports = "skip"

[[tool.mypy.overrides]]
module = "scrapy.interfaces"
ignore_errors = true

[[tool.mypy.overrides]]
module = "twisted.internet.reactor"
follow_imports = "skip"

# FIXME: remove the following section once the issues are solved
[[tool.mypy.overrides]]
module = "scrapy.settings.default_settings"
ignore_errors = true

[[tool.mypy.overrides]]
module = "itemadapter"
implicit_reexport = true

[[tool.mypy.overrides]]
module = "twisted"
implicit_reexport = true

[tool.bumpversion]
current_version = "2.12.0"
commit = true
tag = true
tag_name = "{new_version}"

[[tool.bumpversion.files]]
filename = "scrapy/VERSION"

[[tool.bumpversion.files]]
filename = "SECURITY.md"
parse = """(?P<major>0|[1-9]\\d*)\\.(?P<minor>0|[1-9]\\d*)"""
serialize = ["{major}.{minor}"]

[tool.coverage.run]
branch = true
include = ["scrapy/*"]
omit = ["tests/*"]
disable_warnings = ["include-ignored"]

[tool.coverage.paths]
source = [
    "scrapy",
    ".tox/**/site-packages/scrapy"
]

[tool.coverage.report]
# https://github.com/nedbat/coveragepy/issues/831#issuecomment-517778185
exclude_lines = ["pragma: no cover", "if TYPE_CHECKING:"]

[tool.pylint.MASTER]
persistent = "no"
jobs = 1          # >1 hides results
extension-pkg-allow-list=[
    "lxml",
]

[tool.pylint."MESSAGES CONTROL"]
enable = [
    "useless-suppression",
]
disable = [
    # Ones we want to ignore
    "attribute-defined-outside-init",
    "broad-exception-caught",
    "consider-using-with",
    "cyclic-import",
    "disallowed-name",
    "duplicate-code",  # https://github.com/pylint-dev/pylint/issues/214
    "fixme",
    "import-outside-toplevel",
    "inherit-non-class",  # false positives with create_deprecated_class()
    "invalid-name",
    "invalid-overridden-method",
    "isinstance-second-argument-not-valid-type",  # false positives with create_deprecated_class()
    "line-too-long",
    "logging-format-interpolation",
    "logging-fstring-interpolation",
    "logging-not-lazy",
    "missing-docstring",
    "no-member",
    "no-value-for-parameter",  # https://github.com/pylint-dev/pylint/issues/3268
    "not-callable",
    "protected-access",
    "redefined-builtin",
    "redefined-outer-name",
    "too-few-public-methods",
    "too-many-ancestors",
    "too-many-arguments",
    "too-many-branches",
    "too-many-function-args",
    "too-many-instance-attributes",
    "too-many-lines",
    "too-many-locals",
    "too-many-positional-arguments",
    "too-many-public-methods",
    "too-many-return-statements",
    "unused-argument",
    "unused-import",
    "unused-variable",
    "useless-return",  # https://github.com/pylint-dev/pylint/issues/6530
    "wrong-import-position",

    # Ones that we may want to address (fix, ignore per-line or move to "don't want to fix")
    "abstract-method",
    "arguments-differ",
    "arguments-renamed",
    "dangerous-default-value",
    "keyword-arg-before-vararg",
    "pointless-statement",
    "raise-missing-from",
    "unbalanced-tuple-unpacking",
    "unnecessary-dunder-call",
    "used-before-assignment",
]

[tool.pytest.ini_options]
xfail_strict = true
usefixtures = "chdir"
python_files = ["test_*.py", "__init__.py"]
python_classes = []
addopts = [
    "--assert=plain",
    "--ignore=docs/_ext",
    "--ignore=docs/conf.py",
    "--ignore=docs/news.rst",
    "--ignore=docs/topics/dynamic-content.rst",
    "--ignore=docs/topics/items.rst",
    "--ignore=docs/topics/leaks.rst",
    "--ignore=docs/topics/loaders.rst",
    "--ignore=docs/topics/selectors.rst",
    "--ignore=docs/topics/shell.rst",
    "--ignore=docs/topics/stats.rst",
    "--ignore=docs/topics/telnetconsole.rst",
    "--ignore=docs/utils",
]
markers = [
    "only_asyncio: marks tests as only enabled when --reactor=asyncio is passed",
    "only_not_asyncio: marks tests as only enabled when --reactor=asyncio is not passed",
    "requires_uvloop: marks tests as only enabled when uvloop is known to be working",
    "requires_botocore: marks tests that need botocore (but not boto3)",
    "requires_boto3: marks tests that need botocore and boto3",
]
filterwarnings = []

[tool.ruff.lint]
extend-select = [
    # flake8-bugbear
    "B",
    # flake8-comprehensions
    "C4",
    # pydocstyle
    "D",
    # flake8-future-annotations
    "FA",
    # flynt
    "FLY",
    # refurb
    "FURB",
    # isort
    "I",
    # flake8-implicit-str-concat
    "ISC",
    # flake8-logging
    "LOG",
    # Perflint
    "PERF",
    # pygrep-hooks
    "PGH",
    # flake8-pie
    "PIE",
    # pylint
    "PL",
    # flake8-use-pathlib
    "PTH",
    # flake8-pyi
    "PYI",
    # flake8-quotes
    "Q",
    # flake8-return
    "RET",
    # flake8-raise
    "RSE",
    # Ruff-specific rules
    "RUF",
    # flake8-bandit
    "S",
    # flake8-simplify
    "SIM",
    # flake8-slots
    "SLOT",
    # flake8-debugger
    "T10",
    # flake8-type-checking
    "TC",
    # pyupgrade
    "UP",
    # pycodestyle warnings
    "W",
    # flake8-2020
    "YTT",
]
ignore = [
    # Ones we want to ignore

    # Missing docstring in public module
    "D100",
    # Missing docstring in public class
    "D101",
    # Missing docstring in public method
    "D102",
    # Missing docstring in public function
    "D103",
    # Missing docstring in public package
    "D104",
    # Missing docstring in magic method
    "D105",
    # Missing docstring in public nested class
    "D106",
    # Missing docstring in __init__
    "D107",
    # One-line docstring should fit on one line with quotes
    "D200",
    # No blank lines allowed after function docstring
    "D202",
    # 1 blank line required between summary line and description
    "D205",
    # Multi-line docstring closing quotes should be on a separate line
    "D209",
    # First line should end with a period
    "D400",
    # First line should be in imperative mood; try rephrasing
    "D401",
    # First line should not be the function's "signature"
    "D402",
    # First word of the first line should be properly capitalized
    "D403",
    # `try`-`except` within a loop incurs performance overhead
    "PERF203",
    # Too many return statements
    "PLR0911",
    # Too many branches
    "PLR0912",
    # Too many arguments in function definition
    "PLR0913",
    # Too many statements
    "PLR0915",
    # Magic value used in comparison
    "PLR2004",
    # `for` loop variable overwritten by assignment target
    "PLW2901",
    # String contains ambiguous {}.
    "RUF001",
    # Docstring contains ambiguous {}.
    "RUF002",
    # Comment contains ambiguous {}.
    "RUF003",
    # Mutable class attributes should be annotated with `typing.ClassVar`
    "RUF012",
    # Use of `assert` detected; needed for mypy
    "S101",
    # FTP-related functions are being called; https://github.com/scrapy/scrapy/issues/4180
    "S321",
    # Argument default set to insecure SSL protocol
    "S503",
    # Use a context manager for opening files
    "SIM115",
    # Yoda condition detected
    "SIM300",

    # Ones that we may want to address (fix, ignore per-line or move to "don't want to fix")

    # Assigning to `os.environ` doesn't clear the environment.
    "B003",
    # Do not use mutable data structures for argument defaults.
    "B006",
    # Loop control variable not used within the loop body.
    "B007",
    # Do not perform function calls in argument defaults.
    "B008",
    # Found useless expression.
    "B018",
    # Star-arg unpacking after a keyword argument is strongly discouraged.
    "B026",
    # No explicit stacklevel argument found.
    "B028",
    # Within an `except` clause, raise exceptions with `raise ... from`
    "B904",
    # Use capitalized environment variable
    "SIM112",
]

[tool.ruff.lint.per-file-ignores]
# Circular import workarounds
"scrapy/linkextractors/__init__.py" = ["E402"]
"scrapy/spiders/__init__.py" = ["E402"]

# Skip bandit in tests
"tests/**" = ["S"]

# Issues pending a review:
"docs/conf.py" = ["E402"]
"scrapy/utils/url.py" = ["F403", "F405"]
"tests/test_loader.py" = ["E741"]

[tool.ruff.lint.pydocstyle]
convention = "pep257"