Skip to content

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

Remove deprecated code moved to itemloaders

Laerte Pereiraaa0a42582647
diff --git a/scrapy/loader/common.py b/scrapy/loader/common.py
deleted file mode 100644
index 3e8644e0c..000000000
--- a/scrapy/loader/common.py
+++ /dev/null
@@ -1,21 +0,0 @@
-"""Common functions used in Item Loaders code"""
-
-import warnings
-
-from itemloaders import common
-
-from scrapy.utils.deprecate import ScrapyDeprecationWarning
-
-
-def wrap_loader_context(function, context):
- """Wrap functions that receive loader_context to contain the context
- "pre-loaded" and expose a interface that receives only one argument
- """
- warnings.warn(
- "scrapy.loader.common.wrap_loader_context has moved to a new library."
- "Please update your reference to itemloaders.common.wrap_loader_context",
- ScrapyDeprecationWarning,
- stacklevel=2,
- )
-
- return common.wrap_loader_context(function, context)
diff --git a/scrapy/loader/processors.py b/scrapy/loader/processors.py
deleted file mode 100644
index b82c6d5c7..000000000
--- a/scrapy/loader/processors.py
+++ /dev/null
@@ -1,20 +0,0 @@
-"""
-This module provides some commonly used processors for Item Loaders.
-
-See documentation in docs/topics/loaders.rst
-"""
-from itemloaders import processors
-
-from scrapy.utils.deprecate import create_deprecated_class
-
-MapCompose = create_deprecated_class("MapCompose", processors.MapCompose)
-
-Compose = create_deprecated_class("Compose", processors.Compose)
-
-TakeFirst = create_deprecated_class("TakeFirst", processors.TakeFirst)
-
-Identity = create_deprecated_class("Identity", processors.Identity)
-
-SelectJmes = create_deprecated_class("SelectJmes", processors.SelectJmes)
-
-Join = create_deprecated_class("Join", processors.Join)
diff --git a/scrapy/utils/misc.py b/scrapy/utils/misc.py
index b3c28da92..a9364bea2 100644
--- a/scrapy/utils/misc.py
+++ b/scrapy/utils/misc.py
@@ -21,17 +21,12 @@ from typing import (
Iterable,
List,
Optional,
- Pattern,
Union,
cast,
)
-from w3lib.html import replace_entities
-
from scrapy.item import Item
from scrapy.utils.datatypes import LocalWeakReferencedCache
-from scrapy.utils.deprecate import ScrapyDeprecationWarning
-from scrapy.utils.python import flatten, to_unicode
if TYPE_CHECKING:
from scrapy import Spider
@@ -108,39 +103,6 @@ def walk_modules(path: str) -> List[ModuleType]:
return mods
-def extract_regex(
- regex: Union[str, Pattern], text: str, encoding: str = "utf-8"
-) -> List[str]:
- """Extract a list of unicode strings from the given text/encoding using the following policies:
-
- * if the regex contains a named group called "extract" that will be returned
- * if the regex contains multiple numbered groups, all those will be returned (flattened)
- * if the regex doesn't contain any group the entire regex matching is returned
- """
- warnings.warn(
- "scrapy.utils.misc.extract_regex has moved to parsel.utils.extract_regex.",
- ScrapyDeprecationWarning,
- stacklevel=2,
- )
-
- if isinstance(regex, str):
- regex = re.compile(regex, re.UNICODE)
-
- try:
- # named group
- strings = [regex.search(text).group("extract")] # type: ignore[union-attr]
- except Exception:
- # full regex or numbered groups
- strings = regex.findall(text)
- strings = flatten(strings)
-
- if isinstance(text, str):
- return [replace_entities(s, keep=["lt", "amp"]) for s in strings]
- return [
- replace_entities(to_unicode(s, encoding), keep=["lt", "amp"]) for s in strings
- ]
-
-
def md5sum(file: IO) -> str:
"""Calculate the md5 checksum of a file-like object without reading its
whole content in memory.
diff --git a/tests/test_loader_deprecated.py b/tests/test_loader_deprecated.py
index 3eae87599..d7f773d5c 100644
--- a/tests/test_loader_deprecated.py
+++ b/tests/test_loader_deprecated.py
@@ -4,7 +4,6 @@ Once we remove the references from scrapy, we can remove these tests.
"""
import unittest
-import warnings
from functools import partial
from itemloaders.processors import (
@@ -18,9 +17,6 @@ from itemloaders.processors import (
from scrapy.item import Field, Item
from scrapy.loader import ItemLoader
-from scrapy.loader.common import wrap_loader_context
-from scrapy.utils.deprecate import ScrapyDeprecationWarning
-from scrapy.utils.misc import extract_regex
# test items
@@ -722,24 +718,5 @@ class FunctionProcessorTestCase(unittest.TestCase):
self.assertEqual(dict(lo.load_item()), {"foo": ["BAR", "ASDF", "QWERTY"]})
-class DeprecatedUtilityFunctionsTestCase(unittest.TestCase):
- def test_deprecated_wrap_loader_context(self):
- def function(*args):
- return None
-
- with warnings.catch_warnings(record=True) as w:
- wrap_loader_context(function, context={})
-
- assert len(w) == 1
- assert issubclass(w[0].category, ScrapyDeprecationWarning)
-
- def test_deprecated_extract_regex(self):
- with warnings.catch_warnings(record=True) as w:
- extract_regex(r"\w+", "this is a test")
-
- assert len(w) == 1
- assert issubclass(w[0].category, ScrapyDeprecationWarning)
-
-
if __name__ == "__main__":
unittest.main()