Merge remote-tracking branch 'origin/master' into sessions

.pre-commit-config.yaml

@@ -27,7 +27,7 @@ repos:
   hooks:
     - id: sphinx-lint
 - repo: https://github.com/scrapy/sphinx-scrapy
-  rev: 0.8.10
+  rev: 0.8.11
   hooks:
     - id: sphinx-scrapy
 - repo: https://github.com/zizmorcore/zizmor-pre-commit

docs/_ext/scrapydocs.py

@@ -137,14 +137,6 @@ def source_role(
     return [node], []
 
 
-def issue_role(
-    name, rawtext, text: str, lineno, inliner, options=None, content=None
-) -> tuple[list[Any], list[Any]]:
-    ref = "https://github.com/scrapy/scrapy/issues/" + text
-    node = nodes.reference(rawtext, "issue " + text, refuri=ref)
-    return [node], []
-
-
 def commit_role(
     name, rawtext, text: str, lineno, inliner, options=None, content=None
 ) -> tuple[list[Any], list[Any]]:
@@ -164,7 +156,6 @@ def rev_role(
 def setup(app: Sphinx) -> dict[str, Any]:
     app.add_role("source", source_role)
     app.add_role("commit", commit_role)
-    app.add_role("issue", issue_role)
     app.add_role("rev", rev_role)
 
     app.add_node(

docs/faq.rst

@@ -141,7 +141,7 @@ middleware with a :ref:`custom downloader middleware
 
 -   If you can meet the installation requirements, use pyre2_ instead of
     Python’s re_ to compile your URL-filtering regular expression. See
-    :issue:`1908`.
+    :gh:`1908`.
 
 See also `other suggestions at StackOverflow
 <https://stackoverflow.com/q/36440681>`__.
@@ -419,7 +419,7 @@ Running ``runspider`` I get ``error: No spider found in file: <filename>``
 This may happen if your Scrapy project has a spider module with a name that
 conflicts with the name of one of the `Python standard library modules`_, such
 as ``csv.py`` or ``os.py``, or any `Python package`_ that you have installed.
-See :issue:`2680`.
+See :gh:`2680`.
 
 
 .. _has been reported: https://github.com/scrapy/scrapy/issues/2905

docs/requirements.in

@@ -6,4 +6,4 @@ sphinx-notfound-page
 sphinx-reredirects
 sphinx-rtd-theme
 sphinx-rtd-dark-mode
-sphinx-scrapy @ git+https://github.com/scrapy/sphinx-scrapy.git@0.8.10
+sphinx-scrapy @ git+https://github.com/scrapy/sphinx-scrapy.git@0.8.11

docs/requirements.txt

@@ -156,7 +156,7 @@ sphinx-rtd-theme==3.1.0
     # via
     #   -r docs/requirements.in
     #   sphinx-rtd-dark-mode
-sphinx-scrapy @ git+https://github.com/scrapy/sphinx-scrapy.git@fe176adc1a8577601bc3fa39b590ebed71a7e9b8
+sphinx-scrapy @ git+https://github.com/scrapy/sphinx-scrapy.git@6f8e5e0bbd171a857da480f7188f2a205041cb60
     # via -r docs/requirements.in
 sphinx-sitemap==2.9.0
     # via sphinx-scrapy

scrapy/extensions/periodic_log.py

@@ -1,11 +1,12 @@
 from __future__ import annotations
 
 import logging
+import warnings
 from datetime import datetime, timezone
 from typing import TYPE_CHECKING, Any
 
 from scrapy import Spider, signals
-from scrapy.exceptions import NotConfigured
+from scrapy.exceptions import NotConfigured, ScrapyDeprecationWarning
 from scrapy.utils.asyncio import AsyncioLoopingCall, create_looping_call
 from scrapy.utils.serialize import ScrapyJSONEncoder
 
@@ -38,6 +39,7 @@ class PeriodicLog:
     ):
         self.stats: StatsCollector = stats
         self.interval: float = interval
+        self._multiplier: float = 60.0 / interval
         self.task: AsyncioLoopingCall | LoopingCall | None = None
         self.encoder: JSONEncoder = ScrapyJSONEncoder(sort_keys=True, indent=4)
         self.ext_stats_enabled: bool = bool(ext_stats)
@@ -56,6 +58,24 @@ class PeriodicLog:
         )
         self.ext_timing_enabled: bool = ext_timing_enabled
 
+    @property
+    def multiplier(self) -> float:
+        warnings.warn(
+            "The PeriodicLog.multiplier attribute is deprecated.",
+            ScrapyDeprecationWarning,
+            stacklevel=2,
+        )
+        return self._multiplier
+
+    @multiplier.setter
+    def multiplier(self, value: float) -> None:
+        warnings.warn(
+            "The PeriodicLog.multiplier attribute is deprecated.",
+            ScrapyDeprecationWarning,
+            stacklevel=2,
+        )
+        self._multiplier = value
+
     @classmethod
     def from_crawler(cls, crawler: Crawler) -> Self:
         interval: float = crawler.settings.getfloat("LOGSTATS_INTERVAL")

scrapy/pipelines/files.py

@@ -27,9 +27,7 @@ from twisted.internet.defer import Deferred, maybeDeferred
 from scrapy.exceptions import IgnoreRequest, NotConfigured, ScrapyDeprecationWarning
 from scrapy.http import Request, Response
 from scrapy.http.request import NO_CALLBACK
-from scrapy.pipelines.media import (
-    FileException as FileException,  # noqa: PLC0414  # re-exported for backward compatibility
-)
+from scrapy.pipelines.media import FileException as _FileException
 from scrapy.pipelines.media import (
     FileInfo,
     FileInfoOrError,
@@ -626,7 +624,7 @@ class FilesPipeline(MediaPipeline):
             f"{request} referred in <{referer}>: {failure.value}",
             extra={"spider": info.spider},
         )
-        raise FileException
+        raise _FileException
 
     async def media_downloaded(
         self,
@@ -645,7 +643,7 @@ class FilesPipeline(MediaPipeline):
                 {"status": response.status, "request": request, "referer": referer},
                 extra={"spider": info.spider},
             )
-            raise FileException("download-error")
+            raise _FileException("download-error")
 
         if not response.body:
             logger.warning(
@@ -654,7 +652,7 @@ class FilesPipeline(MediaPipeline):
                 {"request": request, "referer": referer},
                 extra={"spider": info.spider},
             )
-            raise FileException("empty-content")
+            raise _FileException("empty-content")
 
         status = "cached" if "cached" in response.flags else "downloaded"
         logger.debug(
@@ -670,7 +668,7 @@ class FilesPipeline(MediaPipeline):
             checksum: str = await ensure_awaitable(
                 self.file_downloaded(response, request, info, item=item)
             )
-        except FileException as exc:
+        except _FileException as exc:
             logger.warning(
                 "File (error): Error processing file from %(request)s "
                 "referred in <%(referer)s>: %(errormsg)s",
@@ -687,7 +685,7 @@ class FilesPipeline(MediaPipeline):
                 exc_info=True,
                 extra={"spider": info.spider},
             )
-            raise FileException(str(exc)) from exc
+            raise _FileException(str(exc)) from exc
 
         return {
             "url": request.url,
@@ -770,3 +768,15 @@ class FilesPipeline(MediaPipeline):
             if media_type:
                 media_ext = cast("str", mimetypes.guess_extension(media_type))
         return f"full/{media_guid}{media_ext}"
+
+
+def __getattr__(name: str) -> Any:
+    if name == "FileException":
+        warnings.warn(
+            "scrapy.pipelines.files.FileException is deprecated, use "
+            "scrapy.pipelines.media.FileException instead.",
+            ScrapyDeprecationWarning,
+            stacklevel=2,
+        )
+        return _FileException
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")

scrapy/pipelines/images.py

@@ -18,13 +18,8 @@ from itemadapter import ItemAdapter
 from scrapy.exceptions import NotConfigured, ScrapyDeprecationWarning
 from scrapy.http import Request, Response
 from scrapy.http.request import NO_CALLBACK
-from scrapy.pipelines.files import (
-    FileException,
-    FilesPipeline,
-    GCSFilesStore,
-    S3FilesStore,
-    _md5sum,
-)
+from scrapy.pipelines.files import FilesPipeline, GCSFilesStore, S3FilesStore, _md5sum
+from scrapy.pipelines.media import FileException
 from scrapy.utils.defer import ensure_awaitable
 from scrapy.utils.python import to_bytes
 

tests/test_extension_periodic_log.py

@@ -7,7 +7,7 @@ from typing import TYPE_CHECKING, Any
 
 import pytest
 
-from scrapy.exceptions import NotConfigured
+from scrapy.exceptions import NotConfigured, ScrapyDeprecationWarning
 from scrapy.extensions.periodic_log import PeriodicLog
 from scrapy.utils.misc import build_from_crawler
 from scrapy.utils.test import get_crawler
@@ -249,3 +249,17 @@ class TestPeriodicLog:
         assert data["time"]["log_interval_real"] >= 0
         assert data["time"]["elapsed"] >= 0
         assert data["time"]["start_time"] <= data["time"]["utcnow"]
+
+    def test_multiplier_deprecated(self) -> None:
+        crawler = get_crawler(
+            MetaSpider,
+            {"PERIODIC_LOG_TIMING_ENABLED": True, "LOGSTATS_INTERVAL": 30},
+        )
+        crawler._apply_settings()
+        ext = build_from_crawler(PeriodicLog, crawler)
+        with pytest.warns(ScrapyDeprecationWarning):
+            assert ext.multiplier == 2.0
+        with pytest.warns(ScrapyDeprecationWarning):
+            ext.multiplier = 3.0
+        with pytest.warns(ScrapyDeprecationWarning):
+            assert ext.multiplier == 3.0

tests/test_pipeline_files.py

@@ -24,18 +24,18 @@ from twisted.internet.defer import Deferred
 from twisted.python.failure import Failure
 
 from scrapy.crawler import Crawler
-from scrapy.exceptions import IgnoreRequest, NotConfigured
+from scrapy.exceptions import IgnoreRequest, NotConfigured, ScrapyDeprecationWarning
 from scrapy.http import Request, Response
 from scrapy.item import Field, Item
+from scrapy.pipelines import files
 from scrapy.pipelines.files import (
-    FileException,
     FilesPipeline,
     FSFilesStore,
     FTPFilesStore,
     GCSFilesStore,
     S3FilesStore,
 )
-from scrapy.pipelines.media import _MediaRequestFiltered
+from scrapy.pipelines.media import FileException, _MediaRequestFiltered
 from scrapy.settings import Settings
 from scrapy.utils.asyncio import call_later
 from scrapy.utils.defer import maybe_deferred_to_future
@@ -1249,3 +1249,11 @@ def test_files_pipeline_raises_notconfigured_when_files_store_invalid(store):
 
     with pytest.raises(NotConfigured):
         build_from_crawler(FilesPipeline, crawler)
+
+
+def test_file_exception_deprecated_import():
+    with pytest.warns(ScrapyDeprecationWarning, match="FileException"):
+        assert files.FileException is FileException
+
+    with pytest.raises(AttributeError):
+        files.nonexistent

tests/test_pipeline_media.py

@@ -10,8 +10,8 @@ from twisted.python.failure import Failure
 from scrapy import signals
 from scrapy.exceptions import ScrapyDeprecationWarning
 from scrapy.http import Request, Response
-from scrapy.pipelines.files import FileException
 from scrapy.pipelines.media import (
+    FileException,
     FileInfo,
     FileInfoOrError,
     MediaPipeline,

tox.ini

@@ -5,7 +5,7 @@
 
 [tox]
 requires =
-    sphinx-scrapy[tox] @ git+https://github.com/scrapy/sphinx-scrapy.git@0.8.10
+    sphinx-scrapy[tox] @ git+https://github.com/scrapy/sphinx-scrapy.git@0.8.11
     tox-uv
 envlist =
     pre-commit
@@ -124,7 +124,7 @@ commands =
 [testenv:twinecheck]
 basepython = python3
 deps =
-    twine==6.2.0
+    twine==7.0.0
     build==1.5.0
 commands =
     python -m build --sdist