resolve

Author: Mantisus

.github/workflows/build_and_deploy_docs.yaml

@@ -67,6 +67,10 @@ jobs:
         uses: actions/deploy-pages@v4
 
       - name: Invalidate CloudFront cache
-        run: gh workflow run invalidate.yaml --repo apify/apify-docs-private
+        run: |
+          gh workflow run invalidate-cloudfront.yml \
+            --repo apify/apify-docs-private \
+            --field deployment=crawlee-web
+          echo "✅ CloudFront cache invalidation workflow triggered successfully"
         env:
           GITHUB_TOKEN: ${{ secrets.APIFY_SERVICE_ACCOUNT_GITHUB_TOKEN }}

CHANGELOG.md

@@ -3,17 +3,31 @@
 All notable changes to this project will be documented in this file.
 
 <!-- git-cliff-unreleased-start -->
-## 1.1.1 - **not yet released**
+## 1.1.2 - **not yet released**
+
+### 🚀 Features
+
+- Add additional kwargs to Crawler&#x27;s export_data ([#1597](https://github.com/apify/crawlee-python/pull/1597)) ([5977f37](https://github.com/apify/crawlee-python/commit/5977f376b93a7c0d4dd53f0d331a4b04fedba2c6)) by [@vdusek](https://github.com/vdusek), closes [#526](https://github.com/apify/crawlee-python/issues/526)
+- Add `goto_options` for `PlaywrightCrawler` ([#1599](https://github.com/apify/crawlee-python/pull/1599)) ([0b82f3b](https://github.com/apify/crawlee-python/commit/0b82f3b6fb175223ea2aa5b348afcd5fdb767972)) by [@Mantisus](https://github.com/Mantisus), closes [#1576](https://github.com/apify/crawlee-python/issues/1576)
+
+### 🐛 Bug Fixes
+
+- Only apply requestHandlerTimeout to request handler ([#1474](https://github.com/apify/crawlee-python/pull/1474)) ([0dfb6c2](https://github.com/apify/crawlee-python/commit/0dfb6c2a13b6650736245fa39b3fbff397644df7)) by [@janbuchar](https://github.com/janbuchar)
+- Handle the case when `error_handler` returns `Request` ([#1595](https://github.com/apify/crawlee-python/pull/1595)) ([8a961a2](https://github.com/apify/crawlee-python/commit/8a961a2b07d0d33a7302dbb13c17f3d90999d390)) by [@Mantisus](https://github.com/Mantisus)
+
+
+<!-- git-cliff-unreleased-end -->
+## [1.1.1](https://github.com/apify/crawlee-python/releases/tag/v1.1.1) (2025-12-02)
 
 ### 🐛 Bug Fixes
 
 - Unify separators in `unique_key` construction ([#1569](https://github.com/apify/crawlee-python/pull/1569)) ([af46a37](https://github.com/apify/crawlee-python/commit/af46a3733b059a8052489296e172f005def953f7)) by [@vdusek](https://github.com/vdusek), closes [#1512](https://github.com/apify/crawlee-python/issues/1512)
 - Fix `same-domain` strategy ignoring public suffix  ([#1572](https://github.com/apify/crawlee-python/pull/1572)) ([3d018b2](https://github.com/apify/crawlee-python/commit/3d018b21a28a4bee493829783057188d6106a69b)) by [@Pijukatel](https://github.com/Pijukatel), closes [#1571](https://github.com/apify/crawlee-python/issues/1571)
 - Make context helpers work in `FailedRequestHandler` and `ErrorHandler` ([#1570](https://github.com/apify/crawlee-python/pull/1570)) ([b830019](https://github.com/apify/crawlee-python/commit/b830019350830ac33075316061659e2854f7f4a5)) by [@Pijukatel](https://github.com/Pijukatel), closes [#1532](https://github.com/apify/crawlee-python/issues/1532)
 - Fix non-ASCII character corruption in `FileSystemStorageClient` on systems without UTF-8 default encoding ([#1580](https://github.com/apify/crawlee-python/pull/1580)) ([f179f86](https://github.com/apify/crawlee-python/commit/f179f8671b0b6af9264450e4fef7e49d1cecd2bd)) by [@Mantisus](https://github.com/Mantisus), closes [#1579](https://github.com/apify/crawlee-python/issues/1579)
+- Respect `&lt;base&gt;` when enqueuing ([#1590](https://github.com/apify/crawlee-python/pull/1590)) ([de517a1](https://github.com/apify/crawlee-python/commit/de517a1629cc29b20568143eb64018f216d4ba33)) by [@Mantisus](https://github.com/Mantisus), closes [#1589](https://github.com/apify/crawlee-python/issues/1589)
 
 
-<!-- git-cliff-unreleased-end -->
 ## [1.1.0](https://github.com/apify/crawlee-python/releases/tag/v1.1.0) (2025-11-18)
 
 ### 🚀 Features

docs/deployment/code_examples/google/cloud_run_example.py

@@ -9,7 +9,7 @@
 from crawlee.storage_clients import MemoryStorageClient
 
 
-@get('/')
+@get('/')  # type: ignore[untyped-decorator]
 async def main() -> str:
     """The crawler entry point that will be called when the HTTP endpoint is accessed."""
     # highlight-start

docs/deployment/code_examples/google/google_example.py

@@ -6,10 +6,7 @@
 import functions_framework
 from flask import Request, Response
 
-from crawlee.crawlers import (
-    BeautifulSoupCrawler,
-    BeautifulSoupCrawlingContext,
-)
+from crawlee.crawlers import BeautifulSoupCrawler, BeautifulSoupCrawlingContext
 from crawlee.storage_clients import MemoryStorageClient
 
 
@@ -51,7 +48,7 @@ async def request_handler(context: BeautifulSoupCrawlingContext) -> None:
     # highlight-end
 
 
-@functions_framework.http
+@functions_framework.http  # type: ignore[untyped-decorator]
 def crawlee_run(request: Request) -> Response:
     # You can pass data to your crawler using `request`
     function_id = request.headers['Function-Execution-Id']

docs/examples/code_examples/export_entire_dataset_to_file_csv.py

@@ -30,7 +30,8 @@ async def request_handler(context: BeautifulSoupCrawlingContext) -> None:
     await crawler.run(['https://crawlee.dev'])
 
     # Export the entire dataset to a CSV file.
-    await crawler.export_data(path='results.csv')
+    # Use semicolon as delimiter and always quote strings.
+    await crawler.export_data(path='results.csv', delimiter=';', quoting='all')
 
 
 if __name__ == '__main__':

docs/examples/code_examples/export_entire_dataset_to_file_json.py

@@ -30,7 +30,8 @@ async def request_handler(context: BeautifulSoupCrawlingContext) -> None:
     await crawler.run(['https://crawlee.dev'])
 
     # Export the entire dataset to a JSON file.
-    await crawler.export_data(path='results.json')
+    # Set ensure_ascii=False to allow Unicode characters in the output.
+    await crawler.export_data(path='results.json', ensure_ascii=False)
 
 
 if __name__ == '__main__':

docs/examples/export_entire_dataset_to_file.mdx

@@ -11,7 +11,7 @@ import RunnableCodeBlock from '@site/src/components/RunnableCodeBlock';
 import JsonExample from '!!raw-loader!roa-loader!./code_examples/export_entire_dataset_to_file_json.py';
 import CsvExample from '!!raw-loader!roa-loader!./code_examples/export_entire_dataset_to_file_csv.py';
 
-This example demonstrates how to use the <ApiLink to="class/BasicCrawler#export_data">`BasicCrawler.export_data`</ApiLink> method of the crawler to export the entire default dataset to a single file. This method supports exporting data in either CSV or JSON format.
+This example demonstrates how to use the <ApiLink to="class/BasicCrawler#export_data">`BasicCrawler.export_data`</ApiLink> method of the crawler to export the entire default dataset to a single file. This method supports exporting data in either CSV or JSON format and also accepts additional keyword arguments so you can fine-tune the underlying `json.dump` or `csv.writer` behavior.
 
 :::note
 

docs/guides/code_examples/running_in_web_server/server.py

@@ -14,7 +14,7 @@
 app = FastAPI(lifespan=lifespan, title='Crawler app')
 
 
-@app.get('/', response_class=HTMLResponse)
+@app.get('/', response_class=HTMLResponse)  # type: ignore[untyped-decorator]
 def index() -> str:
     return """
 <!DOCTYPE html>
@@ -32,7 +32,7 @@ def index() -> str:
 """
 
 
-@app.get('/scrape')
+@app.get('/scrape')  # type: ignore[untyped-decorator]
 async def scrape_url(request: Request, url: str | None = None) -> dict:
     if not url:
         return {'url': 'missing', 'scrape result': 'no results'}

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "crawlee"
-version = "1.1.1"
+version = "1.1.2"
 description = "Crawlee for Python"
 authors = [{ name = "Apify Technologies s.r.o.", email = "[email protected]" }]
 license = { file = "LICENSE" }
@@ -34,6 +34,7 @@ keywords = [
     "scraping",
 ]
 dependencies = [
+    "async-timeout>=5.0.1",
     "cachetools>=5.5.0",
     "colorama>=0.4.0",
     "impit>=0.8.0",
@@ -74,7 +75,7 @@ otel = [
 ]
 sql_postgres = [
     "sqlalchemy[asyncio]>=2.0.0,<3.0.0",
-    "asyncpg>=0.24.0; python_version < '3.14'" # TODO: https://github.com/apify/crawlee-python/issues/1555
+    "asyncpg>=0.24.0"
 ]
 sql_sqlite = [
     "sqlalchemy[asyncio]>=2.0.0,<3.0.0",
@@ -101,7 +102,7 @@ dev = [
     "build<2.0.0", # For e2e tests.
     "dycw-pytest-only<3.0.0",
     "fakeredis[probabilistic,json,lua]<3.0.0",
-    "mypy~=1.18.0",
+    "mypy~=1.19.0",
     "pre-commit<5.0.0",
     "proxy-py<3.0.0",
     "pydoc-markdown<5.0.0",
@@ -221,6 +222,13 @@ timeout = 300
 markers = [
     "run_alone: marks tests that must run in isolation",
 ]
+# Ignore DeprecationWarnings coming from Uvicorn's internal imports. Uvicorn relies on deprecated
+# modules from `websockets`, which triggers warnings during tests. These are safe to ignore until
+# Uvicorn updates its internals.
+filterwarnings = [
+    "ignore:websockets.legacy is deprecated:DeprecationWarning",
+    "ignore:websockets.server.WebSocketServerProtocol is deprecated:DeprecationWarning",
+]
 
 [tool.mypy]
 python_version = "3.10"

src/crawlee/_utils/context.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-import asyncio
+import inspect
 from collections.abc import Callable
 from functools import wraps
 from typing import Any, TypeVar
@@ -44,4 +44,4 @@ async def async_wrapper(self: Any, *args: Any, **kwargs: Any) -> Any:
 
         return await method(self, *args, **kwargs)
 
-    return async_wrapper if asyncio.iscoroutinefunction(method) else sync_wrapper  # type: ignore[return-value]
+    return async_wrapper if inspect.iscoroutinefunction(method) else sync_wrapper  # type: ignore[return-value]