Merge pull request #6113 from Laerte/master

Remove some deprecated code

scrapy/crawler.py

@@ -12,7 +12,6 @@
     inlineCallbacks,
     maybeDeferred,
 )
-from zope.interface.exceptions import DoesNotImplement
 
 try:
     # zope >= 5.0 only supports MultipleInvalid
@@ -205,19 +204,7 @@ def _get_spider_loader(settings: BaseSettings):
         """Get SpiderLoader instance from settings"""
         cls_path = settings.get("SPIDER_LOADER_CLASS")
         loader_cls = load_object(cls_path)
-        excs = (
-            (DoesNotImplement, MultipleInvalid) if MultipleInvalid else DoesNotImplement
-        )
-        try:
-            verifyClass(ISpiderLoader, loader_cls)
-        except excs:
-            warnings.warn(
-                "SPIDER_LOADER_CLASS (previously named SPIDER_MANAGER_CLASS) does "
-                "not fully implement scrapy.interfaces.ISpiderLoader interface. "
-                "Please add all missing methods to avoid unexpected runtime errors.",
-                category=ScrapyDeprecationWarning,
-                stacklevel=2,
-            )
+        verifyClass(ISpiderLoader, loader_cls)
         return loader_cls.from_settings(settings.frozencopy())
 
     def __init__(self, settings: Union[Dict[str, Any], Settings, None] = None):

scrapy/downloadermiddlewares/httpauth.py

@@ -3,13 +3,10 @@
 
 See documentation in docs/topics/downloader-middleware.rst
 """
-import warnings
 
 from w3lib.http import basic_auth_header
 
 from scrapy import signals
-from scrapy.exceptions import ScrapyDeprecationWarning
-from scrapy.utils.httpobj import urlparse_cached
 from scrapy.utils.url import url_is_from_any_domain
 
 
@@ -28,25 +25,10 @@ def spider_opened(self, spider):
         pwd = getattr(spider, "http_pass", "")
         if usr or pwd:
             self.auth = basic_auth_header(usr, pwd)
-            if not hasattr(spider, "http_auth_domain"):
-                warnings.warn(
-                    "Using HttpAuthMiddleware without http_auth_domain is deprecated and can cause security "
-                    "problems if the spider makes requests to several different domains. http_auth_domain "
-                    "will be set to the domain of the first request, please set it to the correct value "
-                    "explicitly.",
-                    category=ScrapyDeprecationWarning,
-                )
-                self.domain_unset = True
-            else:
-                self.domain = spider.http_auth_domain
-                self.domain_unset = False
+            self.domain = spider.http_auth_domain
 
     def process_request(self, request, spider):
         auth = getattr(self, "auth", None)
         if auth and b"Authorization" not in request.headers:
-            domain = urlparse_cached(request).hostname
-            if self.domain_unset:
-                self.domain = domain
-                self.domain_unset = False
             if not self.domain or url_is_from_any_domain(request.url, [self.domain]):
                 request.headers[b"Authorization"] = auth

scrapy/downloadermiddlewares/httpcompression.py

@@ -1,11 +1,9 @@
 import io
-import warnings
 import zlib
 
 from scrapy.exceptions import NotConfigured
 from scrapy.http import Response, TextResponse
 from scrapy.responsetypes import responsetypes
-from scrapy.utils.deprecate import ScrapyDeprecationWarning
 from scrapy.utils.gz import gunzip
 
 ACCEPTED_ENCODINGS = [b"gzip", b"deflate"]
@@ -36,18 +34,7 @@ def __init__(self, stats=None):
     def from_crawler(cls, crawler):
         if not crawler.settings.getbool("COMPRESSION_ENABLED"):
             raise NotConfigured
-        try:
-            return cls(stats=crawler.stats)
-        except TypeError:
-            warnings.warn(
-                "HttpCompressionMiddleware subclasses must either modify "
-                "their '__init__' method to support a 'stats' parameter or "
-                "reimplement the 'from_crawler' method.",
-                ScrapyDeprecationWarning,
-            )
-            result = cls()
-            result.stats = crawler.stats
-            return result
+        return cls(stats=crawler.stats)
 
     def process_request(self, request, spider):
         request.headers.setdefault("Accept-Encoding", b", ".join(ACCEPTED_ENCODINGS))

scrapy/dupefilters.py

@@ -3,14 +3,12 @@
 import logging
 from pathlib import Path
 from typing import TYPE_CHECKING, Optional, Set
-from warnings import warn
 
 from twisted.internet.defer import Deferred
 
 from scrapy.http.request import Request
 from scrapy.settings import BaseSettings
 from scrapy.spiders import Spider
-from scrapy.utils.deprecate import ScrapyDeprecationWarning
 from scrapy.utils.job import job_dir
 from scrapy.utils.request import (
     RequestFingerprinter,
@@ -75,38 +73,15 @@ def from_settings(
         fingerprinter: Optional[RequestFingerprinterProtocol] = None,
     ) -> Self:
         debug = settings.getbool("DUPEFILTER_DEBUG")
-        try:
-            return cls(job_dir(settings), debug, fingerprinter=fingerprinter)
-        except TypeError:
-            warn(
-                "RFPDupeFilter subclasses must either modify their '__init__' "
-                "method to support a 'fingerprinter' parameter or reimplement "
-                "the 'from_settings' class method.",
-                ScrapyDeprecationWarning,
-            )
-            result = cls(job_dir(settings), debug)
-            result.fingerprinter = fingerprinter or RequestFingerprinter()
-            return result
+        return cls(job_dir(settings), debug, fingerprinter=fingerprinter)
 
     @classmethod
     def from_crawler(cls, crawler: Crawler) -> Self:
         assert crawler.request_fingerprinter
-        try:
-            return cls.from_settings(
-                crawler.settings,
-                fingerprinter=crawler.request_fingerprinter,
-            )
-        except TypeError:
-            warn(
-                "RFPDupeFilter subclasses must either modify their overridden "
-                "'__init__' method and 'from_settings' class method to "
-                "support a 'fingerprinter' parameter, or reimplement the "
-                "'from_crawler' class method.",
-                ScrapyDeprecationWarning,
-            )
-            result = cls.from_settings(crawler.settings)
-            result.fingerprinter = crawler.request_fingerprinter
-            return result
+        return cls.from_settings(
+            crawler.settings,
+            fingerprinter=crawler.request_fingerprinter,
+        )
 
     def request_seen(self, request: Request) -> bool:
         fp = self.request_fingerprint(request)

scrapy/extensions/feedexport.py

@@ -29,7 +29,7 @@
 from scrapy.utils.ftp import ftp_store_file
 from scrapy.utils.log import failure_to_exc_info
 from scrapy.utils.misc import create_instance, load_object
-from scrapy.utils.python import get_func_args, without_none_values
+from scrapy.utils.python import without_none_values
 
 logger = logging.getLogger(__name__)
 
@@ -42,17 +42,7 @@
 
 
 def build_storage(builder, uri, *args, feed_options=None, preargs=(), **kwargs):
-    argument_names = get_func_args(builder)
-    if "feed_options" in argument_names:
-        kwargs["feed_options"] = feed_options
-    else:
-        warnings.warn(
-            f"{builder.__qualname__} does not support the 'feed_options' keyword argument. Add a "
-            "'feed_options' parameter to its signature to remove this "
-            "warning. This parameter will become mandatory in a future "
-            "version of Scrapy.",
-            category=ScrapyDeprecationWarning,
-        )
+    kwargs["feed_options"] = feed_options
     return builder(*preargs, uri, *args, **kwargs)
 
 

scrapy/http/request/__init__.py

@@ -200,7 +200,7 @@ def from_curl(
         ``ignore_unknown_options=False``.
 
         .. caution:: Using :meth:`from_curl` from :class:`~scrapy.http.Request`
-                     subclasses, such as :class:`~scrapy.http.JSONRequest`, or
+                     subclasses, such as :class:`~scrapy.http.JsonRequest`, or
                      :class:`~scrapy.http.XmlRpcRequest`, as well as having
                      :ref:`downloader middlewares <topics-downloader-middleware>`
                      and

scrapy/http/request/json_request.py

@@ -11,7 +11,6 @@
 from typing import Optional, Tuple
 
 from scrapy.http.request import Request
-from scrapy.utils.deprecate import create_deprecated_class
 
 
 class JsonRequest(Request):
@@ -58,6 +57,3 @@ def replace(self, *args, **kwargs) -> Request:
     def _dumps(self, data: dict) -> str:
         """Convert to JSON"""
         return json.dumps(data, **self._dumps_kwargs)
-
-
-JSONRequest = create_deprecated_class("JSONRequest", JsonRequest)