chore!: drop Python 3.10 support

.github/workflows/_checks.yaml

@@ -41,13 +41,13 @@ jobs:
     name: Lint check
     uses: apify/workflows/.github/workflows/python_lint_check.yaml@main
     with:
-      python_versions: '["3.10", "3.11", "3.12", "3.13", "3.14"]'
+      python_versions: '["3.11", "3.12", "3.13", "3.14"]'
 
   type_check:
     name: Type check
     uses: apify/workflows/.github/workflows/python_type_check.yaml@main
     with:
-      python_versions: '["3.10", "3.11", "3.12", "3.13", "3.14"]'
+      python_versions: '["3.11", "3.12", "3.13", "3.14"]'
 
   markdown_lint_check:
     name: Markdown lint check
@@ -135,7 +135,7 @@ jobs:
     uses: apify/workflows/.github/workflows/python_unit_tests.yaml@main
     secrets: inherit
     with:
-      python_versions: '["3.10", "3.11", "3.12", "3.13", "3.14"]'
+      python_versions: '["3.11", "3.12", "3.13", "3.14"]'
       operating_systems: '["ubuntu-latest", "windows-latest", "macos-latest"]'
       python_version_for_codecov: "3.14"
       operating_system_for_codecov: ubuntu-latest

.rules.md

@@ -49,7 +49,7 @@ Note: `uv run poe unit-tests` first runs tests marked `@pytest.mark.run_alone` i
 - **Line length**: 120 characters
 - **Quotes**: Single quotes (double for docstrings)
 - **Docstrings**: Google format (enforced by Ruff)
-- **Type checker**: ty (Astral's type checker), target Python 3.10
+- **Type checker**: ty (Astral's type checker), target Python 3.11
 - **Async mode**: pytest-asyncio in `auto` mode (no need for `@pytest.mark.asyncio`)
 - **Commits**: [Conventional Commits](https://www.conventionalcommits.org/) format. Choose the type based on *what* changed, not just *why*:
     - `feat:` / `fix:` / `perf:` / `refactor:` / `style:` — **source code only**; these trigger a release and appear in the changelog

CONTRIBUTING.md

@@ -4,7 +4,7 @@ Here you'll find a contributing guide to get started with development.
 
 ## Environment
 
-For local development, it is required to have Python 3.10 (or a later version) installed.
+For local development, it is required to have Python 3.11 (or a later version) installed.
 
 We use [uv](https://docs.astral.sh/uv/) for project management. Install it and set up your IDE accordingly.
 

README.md

@@ -16,7 +16,7 @@
 <p align="center">
   <a href="https://badge.fury.io/py/crawlee" rel="nofollow"><img src="https://badge.fury.io/py/crawlee.svg" alt="PyPI package version"></a>
   <a href="https://pypi.org/project/crawlee/" rel="nofollow"><img src="https://img.shields.io/pypi/dm/crawlee" alt="PyPI package downloads"></a>
-  <a href="https://pypi.org/project/crawlee/" rel="nofollow"><img src="https://img.shields.io/badge/python-3.10%2B-blue" alt="PyPI Python version"></a>
+  <a href="https://pypi.org/project/crawlee/" rel="nofollow"><img src="https://img.shields.io/badge/python-3.11%2B-blue" alt="PyPI Python version"></a>
   <a href="https://github.com/apify/crawlee-python/actions/workflows/on_master.yaml"><img src="https://github.com/apify/crawlee-python/actions/workflows/on_master.yaml/badge.svg?branch=master" alt="Build status"></a>
   <a href="https://codecov.io/gh/apify/crawlee-python"><img src="https://codecov.io/gh/apify/crawlee-python/graph/badge.svg?token=cCju61iPQG" alt="Codecov report"></a>
   <a href="https://github.com/apify/crawlee-python/blob/master/LICENSE"><img src="https://img.shields.io/pypi/l/crawlee" alt="License"></a>

docs/guides/code_examples/http_crawlers/selectolax_context.py

@@ -1,7 +1,7 @@
 from dataclasses import dataclass, fields
+from typing import Self
 
 from selectolax.lexbor import LexborHTMLParser
-from typing_extensions import Self
 
 from crawlee.crawlers._abstract_http import ParsedHttpCrawlingContext
 

docs/introduction/01_setting_up.mdx

@@ -14,7 +14,7 @@ This guide will help you get started with Crawlee by setting it up on your compu
 
 Before installing Crawlee itself, make sure that your system meets the following requirements:
 
-- **Python 3.10 or higher**: Crawlee requires Python 3.10 or a newer version. You can download Python from the [official website](https://python.org/downloads/).
+- **Python 3.11 or higher**: Crawlee requires Python 3.11 or a newer version. You can download Python from the [official website](https://python.org/downloads/).
 - **Python package manager**: While this guide uses [pip](https://pip.pypa.io/) (the most common package manager), you can also use any package manager you want. You can download pip from the [official website](https://pip.pypa.io/en/stable/installation/).
 
 ### Verifying prerequisites

docs/quick-start/index.mdx

@@ -23,7 +23,7 @@ Crawlee offers the following main crawler classes: <ApiLink to="class/BeautifulS
 
 :::caution Minimum Python version
 
-Crawlee requires Python 3.10 or higher.
+Crawlee requires Python 3.11 or higher.
 
 :::
 

docs/upgrading/upgrading_to_v2.md

@@ -0,0 +1,14 @@
+---
+id: upgrading-to-v2
+title: Upgrading to v2
+---
+
+This page summarizes the breaking changes between Crawlee for Python v1 and v2.
+
+## Python version support
+
+We drop support for Python 3.10, which reached its end of life in October 2026. The minimum supported version is now Python 3.11.
+
+## `Event` is a `StrEnum`
+
+`Event` now subclasses `enum.StrEnum`. Calling `str()` on a member or formatting it in an f-string returns its value, for example `'systemInfo'`, where v1 returned `'Event.SYSTEM_INFO'`. Comparisons with plain strings work the same way as in v1.

pyproject.toml

@@ -10,13 +10,12 @@ authors = [{ name = "Apify Technologies s.r.o.", email = "support@apify.com" }]
 license = "Apache-2.0"
 license-files = ["LICENSE"]
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 classifiers = [
     "Development Status :: 5 - Production/Stable",
     "Environment :: Console",
     "Intended Audience :: Developers",
     "Operating System :: OS Independent",
-    "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
@@ -279,7 +278,7 @@ filterwarnings = [
 ]
 
 [tool.ty.environment]
-python-version = "3.10"
+python-version = "3.11"
 
 [tool.ty.src]
 include = ["src", "tests", "scripts", "docs", "website"]

src/crawlee/_autoscaling/_types.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from dataclasses import dataclass, field
-from datetime import datetime, timedelta, timezone
+from datetime import UTC, datetime, timedelta
 from typing import TYPE_CHECKING, Annotated
 
 from pydantic import Field
@@ -46,7 +46,7 @@ class SystemInfo:
     client_info: LoadRatioInfo
     """The client load ratio."""
 
-    created_at: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
+    created_at: datetime = field(default_factory=lambda: datetime.now(UTC))
     """The time at which the system load information was measured."""
 
     @property
@@ -80,7 +80,7 @@ class CpuSnapshot:
     max_used_ratio: float
     """The maximum ratio of CPU that is considered acceptable."""
 
-    created_at: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
+    created_at: datetime = field(default_factory=lambda: datetime.now(UTC))
     """The time at which the system load information was measured."""
 
     @property
@@ -108,7 +108,7 @@ class MemorySnapshot:
     max_used_memory_ratio: float
     """The maximum acceptable ratio of `current_size` to `max_memory_size`."""
 
-    created_at: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
+    created_at: datetime = field(default_factory=lambda: datetime.now(UTC))
     """The time at which the system load information was measured."""
 
     @property
@@ -132,7 +132,7 @@ class EventLoopSnapshot:
     max_delay: timedelta
     """The maximum delay that is considered acceptable."""
 
-    created_at: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
+    created_at: datetime = field(default_factory=lambda: datetime.now(UTC))
     """The time at which the system load information was measured."""
 
     @property
@@ -159,7 +159,7 @@ class ClientSnapshot:
     max_error_count: int
     """The maximum number of errors that is considered acceptable."""
 
-    created_at: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
+    created_at: datetime = field(default_factory=lambda: datetime.now(UTC))
     """The time at which the system load information was measured."""
 
     @property

src/crawlee/_autoscaling/autoscaled_pool.py

@@ -243,7 +243,7 @@ async def _worker_task_orchestrator(self, run: _AutoscaledPoolRun) -> None:
 
                     continue
 
-                with suppress(asyncio.TimeoutError):
+                with suppress(TimeoutError):
                     await asyncio.wait_for(run.worker_tasks_updated.wait(), timeout=0.5)
         except Exception as exc:
             # Surface the error through `run.result` only once the cleanup below has awaited the worker tasks,
@@ -290,7 +290,7 @@ async def _worker_task(self) -> None:
                 self._run_task_function(),
                 timeout=self._TASK_TIMEOUT.total_seconds() if self._TASK_TIMEOUT is not None else None,
             )
-        except asyncio.TimeoutError:
+        except TimeoutError:
             if self._TASK_TIMEOUT is None:
                 # Without a timeout, `wait_for` cannot time out - the error comes from the task function itself.
                 raise

src/crawlee/_autoscaling/snapshotter.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 from bisect import insort
-from datetime import datetime, timedelta, timezone
+from datetime import UTC, datetime, timedelta
 from logging import WARNING, getLogger
 from typing import TYPE_CHECKING, TypeVar, cast
 
@@ -107,7 +107,7 @@ def __init__(
         self._snapshot_event_loop_task = RecurringTask(self._snapshot_event_loop, self._EVENT_LOOP_SNAPSHOT_INTERVAL)
         self._snapshot_client_task = RecurringTask(self._snapshot_client, self._CLIENT_SNAPSHOT_INTERVAL)
 
-        self._timestamp_of_last_memory_warning: datetime = datetime.now(timezone.utc) - timedelta(hours=1)
+        self._timestamp_of_last_memory_warning: datetime = datetime.now(UTC) - timedelta(hours=1)
 
         # Flag to indicate the context state.
         self._active = False

src/crawlee/_log_config.py

@@ -4,10 +4,9 @@
 import logging
 import sys
 import textwrap
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING, Any, assert_never
 
 from colorama import Fore, Style, just_fix_windows_console
-from typing_extensions import assert_never
 
 from crawlee import service_locator
 

src/crawlee/_request.py

@@ -15,7 +15,7 @@
 from crawlee._utils.urls import validate_http_url
 
 if TYPE_CHECKING:
-    from typing_extensions import NotRequired, Required, Self
+    from typing import NotRequired, Required, Self
 
 
 class RequestState(IntEnum):

src/crawlee/_types.py

@@ -15,8 +15,9 @@
     import re
     from collections.abc import Awaitable, Coroutine, MutableMapping, Sequence
     from datetime import timedelta
+    from typing import NotRequired, Required, Self
 
-    from typing_extensions import NotRequired, Required, Self, Unpack
+    from typing_extensions import Unpack
 
     from crawlee import Glob, Request
     from crawlee._request import RequestOptions

src/crawlee/_utils/html.py

@@ -17,9 +17,10 @@
 
 if TYPE_CHECKING:
     from collections.abc import Mapping, Sequence
+    from typing import NotRequired
 
     from lxml.html import HtmlElement
-    from typing_extensions import NotRequired, Unpack
+    from typing_extensions import Unpack
 
     from crawlee._types import JsonSerializable
 

src/crawlee/_utils/http.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 import re
-from datetime import datetime, timedelta, timezone
+from datetime import UTC, datetime, timedelta
 from email.utils import parsedate_to_datetime
 from logging import getLogger
 
@@ -56,9 +56,9 @@ def parse_retry_after_header(value: str | None) -> timedelta | None:
         # `parsedate_to_datetime` may return a naive datetime when the input has no timezone info.
         # Treat such values as UTC — HTTP-dates are GMT per RFC 7231.
         if retry_date.tzinfo is None:
-            retry_date = retry_date.replace(tzinfo=timezone.utc)
+            retry_date = retry_date.replace(tzinfo=UTC)
 
-        delay = retry_date - datetime.now(timezone.utc)
+        delay = retry_date - datetime.now(UTC)
         if delay.total_seconds() > 0:
             return delay
         logger.debug(f'Retry-After HTTP-date {value!r} is in the past; ignoring.')

src/crawlee/_utils/recurring_task.py

@@ -9,8 +9,7 @@
     from collections.abc import Callable
     from datetime import timedelta
     from types import TracebackType
-
-    from typing_extensions import Self
+    from typing import Self
 
 logger = getLogger(__name__)
 

src/crawlee/_utils/retry.py

@@ -46,7 +46,7 @@ async def wrapper(*args: P.args, **kwargs: P.kwargs) -> T:
             for attempt in range(max_attempts):
                 try:
                     return await func(*args, **kwargs)
-                except exception_types as exc:  # noqa: PERF203
+                except exception_types as exc:
                     if attempt >= max_attempts - 1:
                         raise
 

src/crawlee/_utils/robots.py

@@ -11,7 +11,7 @@
 from crawlee._utils.web import is_status_code_client_error, is_status_code_server_error
 
 if TYPE_CHECKING:
-    from typing_extensions import Self
+    from typing import Self
 
     from crawlee._types import EnqueueStrategy
     from crawlee.http_clients import HttpClient

src/crawlee/_utils/sitemap.py

@@ -11,12 +11,12 @@
 from hashlib import sha256
 from http import HTTPStatus
 from logging import getLogger
-from typing import TYPE_CHECKING, Literal, TypedDict
+from typing import TYPE_CHECKING, Literal, NotRequired, TypedDict
 from xml.sax import SAXParseException
 from xml.sax.expatreader import ExpatParser
 from xml.sax.handler import ContentHandler
 
-from typing_extensions import NotRequired, override
+from typing_extensions import override
 from yarl import URL
 
 from crawlee._utils.urls import filter_url
@@ -151,7 +151,7 @@ def endElement(self, name: str) -> None:
 
             elif name == 'lastmod' and text:
                 with suppress(ValueError):
-                    self._current_url['lastmod'] = datetime.fromisoformat(text.replace('Z', '+00:00'))
+                    self._current_url['lastmod'] = datetime.fromisoformat(text)
 
             elif name == 'priority' and text:
                 with suppress(ValueError):
@@ -228,7 +228,7 @@ async def flush(self) -> AsyncGenerator[_SitemapItem, None]:
         """Process any remaining data in the buffer, yielding items one by one."""
         try:
             # `ExpatParser.flush` isn't part of the `IncrementalParser` interface and is missing before CPython
-            # 3.10.14, 3.11.9 and 3.12.3, whose bundled expat predates reparse deferral, so nothing stays buffered.
+            # 3.11.9 and 3.12.3, whose bundled expat predates reparse deferral, so nothing stays buffered.
             if (flush := getattr(self._parser, 'flush', None)) is not None:
                 flush()
 
@@ -744,7 +744,7 @@ def _check_and_add(url: str) -> bool:
                     yield candidate
             except ProxyError:
                 logger.warning(f'Proxy error when checking {candidate} with sitemap discovery for {hostname}')
-            except asyncio.TimeoutError:
+            except TimeoutError:
                 logger.warning(f'Timeout when checking {candidate} with sitemap discovery for {hostname}')
             except Exception:
                 logger.warning(f'Error when checking {candidate} with sitemap discovery for {hostname}', exc_info=True)

src/crawlee/_utils/system.py

@@ -2,7 +2,7 @@
 
 import os
 import sys
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from logging import WARNING, getLogger
 from typing import TYPE_CHECKING, Annotated
 
@@ -135,14 +135,14 @@ class CpuInfo(BaseModel):
 
     # Workaround for Pydantic and type checkers when using Annotated with default_factory
     if TYPE_CHECKING:
-        created_at: datetime = datetime.now(timezone.utc)
+        created_at: datetime = datetime.now(UTC)
         """The time at which the measurement was taken."""
     else:
         created_at: Annotated[
             datetime,
             Field(
                 alias='createdAt',
-                default_factory=lambda: datetime.now(timezone.utc),
+                default_factory=lambda: datetime.now(UTC),
             ),
         ]
         """The time at which the measurement was taken."""
@@ -168,14 +168,14 @@ class MemoryUsageInfo(BaseModel):
 
     # Workaround for Pydantic and type checkers when using Annotated with default_factory
     if TYPE_CHECKING:
-        created_at: datetime = datetime.now(timezone.utc)
+        created_at: datetime = datetime.now(UTC)
         """The time at which the measurement was taken."""
     else:
         created_at: Annotated[
             datetime,
             Field(
                 alias='createdAt',
-                default_factory=lambda: datetime.now(timezone.utc),
+                default_factory=lambda: datetime.now(UTC),
             ),
         ]
         """The time at which the measurement was taken."""

src/crawlee/_utils/urls.py

@@ -2,11 +2,10 @@
 
 import tempfile
 from functools import lru_cache
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, assert_never
 
 from pydantic import AnyHttpUrl, TypeAdapter
 from tldextract import TLDExtract
-from typing_extensions import assert_never
 from yarl import URL
 
 if TYPE_CHECKING: