Skip to content

Scrapy, a fast high-level web crawling & scraping framework for Python.

Add ruff with basic rules. (#6565)

Andrey Rakhmatullincc146b9df7c6
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index b411f4927..ec8693c00 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -1,4 +1,8 @@
repos:
+- repo: https://github.com/astral-sh/ruff-pre-commit
+ rev: v0.8.1
+ hooks:
+ - id: ruff
- repo: https://github.com/PyCQA/bandit
rev: 1.7.9
hooks:
diff --git a/pyproject.toml b/pyproject.toml
index f25715e76..b6c02472d 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -232,4 +232,25 @@ markers = [
"requires_botocore: marks tests that need botocore (but not boto3)",
"requires_boto3: marks tests that need botocore and boto3",
]
-filterwarnings = []
\ No newline at end of file
+filterwarnings = []
+
+[tool.ruff.lint]
+extend-select = [
+]
+ignore = [
+]
+
+[tool.ruff.lint.per-file-ignores]
+# Exclude files that are meant to provide top-level imports
+"scrapy/__init__.py" = ["E402"]
+"scrapy/core/downloader/handlers/http.py" = ["F401"]
+"scrapy/http/__init__.py" = ["F401"]
+"scrapy/linkextractors/__init__.py" = ["E402", "F401"]
+"scrapy/selector/__init__.py" = ["F401"]
+"scrapy/spiders/__init__.py" = ["E402", "F401"]
+
+# Issues pending a review:
+"docs/conf.py" = ["E402"]
+"scrapy/utils/url.py" = ["F403", "F405"]
+"tests/CrawlerRunner/change_reactor.py" = ["E402"]
+"tests/test_loader.py" = ["E741"]
diff --git a/scrapy/http/request/form.py b/scrapy/http/request/form.py
index 10ad1305e..b3c3d7c7a 100644
--- a/scrapy/http/request/form.py
+++ b/scrapy/http/request/form.py
@@ -186,7 +186,7 @@ def _get_inputs(
if not dont_click:
clickable = _get_clickable(clickdata, form)
- if clickable and clickable[0] not in formdata and not clickable[0] is None:
+ if clickable and clickable[0] not in formdata and clickable[0] is not None:
values.append(clickable)
formdata_items = formdata.items() if isinstance(formdata, dict) else formdata
diff --git a/tests/test_pipeline_crawl.py b/tests/test_pipeline_crawl.py
index 7add27aa7..9e1b1ab5b 100644
--- a/tests/test_pipeline_crawl.py
+++ b/tests/test_pipeline_crawl.py
@@ -218,7 +218,7 @@ class FileDownloadCrawlTestCase(TestCase):
skip_pillow: str | None
try:
- from PIL import Image # noqa: imported just to check for the import error
+ from PIL import Image # noqa: F401
except ImportError:
skip_pillow = "Missing Python Imaging Library, install https://pypi.org/pypi/Pillow"
else:
diff --git a/tests/test_pipeline_media.py b/tests/test_pipeline_media.py
index cb1e2f9a1..dd8f1084a 100644
--- a/tests/test_pipeline_media.py
+++ b/tests/test_pipeline_media.py
@@ -19,7 +19,7 @@ from scrapy.utils.signal import disconnect_all
from scrapy.utils.test import get_crawler
try:
- from PIL import Image # noqa: imported just to check for the import error
+ from PIL import Image # noqa: F401
except ImportError:
skip_pillow: str | None = (
"Missing Python Imaging Library, install https://pypi.org/pypi/Pillow"