apify 2.0.1b6__tar.gz → 2.0.1b7__tar.gz

{apify-2.0.1b6 → apify-2.0.1b7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: apify
-Version: 2.0.1b6
+Version: 2.0.1b7
 Summary: Apify SDK for Python
 License: Apache-2.0
 Keywords: apify,sdk,automation,chrome,crawlee,crawler,headless,scraper,scraping
@@ -16,11 +16,12 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Software Development :: Libraries
 Provides-Extra: scrapy
 Requires-Dist: apify-client (>=1.8.1)
 Requires-Dist: apify-shared (>=1.1.2)
-Requires-Dist: crawlee (>=0.3.5)
+Requires-Dist: crawlee (>=0.3.8)
 Requires-Dist: cryptography (>=42.0.0)
 Requires-Dist: httpx (>=0.27.0)
 Requires-Dist: lazy-object-proxy (>=1.10.0)

{apify-2.0.1b6 → apify-2.0.1b7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "apify"
-version = "2.0.1b6"
+version = "2.0.1b7"
 description = "Apify SDK for Python"
 authors = ["Apify Technologies s.r.o. <support@apify.com>"]
 license = "Apache-2.0"
@@ -48,7 +48,7 @@ keywords = [
 python = "^3.9"
 apify-client = ">=1.8.1"
 apify-shared = ">=1.1.2"
-crawlee = ">=0.3.5"
+crawlee = ">=0.3.8"
 cryptography = ">=42.0.0"
 httpx = ">=0.27.0"
 lazy-object-proxy = ">=1.10.0"
@@ -162,6 +162,7 @@ max-branches = 18
 
 [tool.pytest.ini_options]
 addopts = "-ra"
+asyncio_default_fixture_loop_scope = "function"
 asyncio_mode = "auto"
 timeout = 1200
 

{apify-2.0.1b6 → apify-2.0.1b7}/src/apify/_configuration.py

@@ -5,8 +5,10 @@ from datetime import datetime, timedelta
 from typing import Annotated
 
 from pydantic import AliasChoices, BeforeValidator, Field
+from typing_extensions import deprecated
 
 from crawlee._utils.models import timedelta_ms
+from crawlee._utils.urls import validate_http_url
 from crawlee.configuration import Configuration as CrawleeConfiguration
 
 
@@ -160,15 +162,16 @@ class Configuration(CrawleeConfiguration):
         str | None,
         Field(
             alias='apify_sdk_latest_version',
-            deprecated=True,
             description='Specifies the most recent release version of the Apify SDK for Javascript. Used for '
             'checking for updates.',
         ),
+        deprecated('SDK version checking is not supported for the Python SDK'),
     ] = None
 
     log_format: Annotated[
         str | None,
-        Field(alias='apify_log_format', deprecated=True),
+        Field(alias='apify_log_format'),
+        deprecated('Adjust the log format in code instead'),
     ] = None
 
     max_paid_dataset_items: Annotated[
@@ -256,7 +259,17 @@ class Configuration(CrawleeConfiguration):
             alias='actor_standby_port',
             description='TCP port for the Actor to start an HTTP server to receive messages in the Actor Standby mode',
         ),
-    ] = 4322
+        deprecated('Use `web_server_port` instead'),
+    ] = 4321
+
+    standby_url: Annotated[
+        str,
+        BeforeValidator(validate_http_url),
+        Field(
+            alias='actor_standby_url',
+            description='URL for accessing web servers of Actor runs in Standby mode',
+        ),
+    ] = 'http://localhost'
 
     token: Annotated[
         str | None,
@@ -293,7 +306,7 @@ class Configuration(CrawleeConfiguration):
                 'actor_web_server_url',
                 'apify_container_url',
             ),
-            description='Unique public URL for accessing the Actor run web server from the outside world',
+            description='Unique public URL for accessing a specific Actor run web server from the outside world',
         ),
     ] = 'http://localhost:4321'
 

{apify-2.0.1b6 → apify-2.0.1b7}/src/apify/scrapy/requests.py

@@ -16,6 +16,7 @@ except ImportError as exc:
     ) from exc
 
 from crawlee import Request as CrawleeRequest
+from crawlee._types import HttpHeaders
 from crawlee._utils.crypto import crypto_random_object_id
 from crawlee._utils.requests import compute_unique_key, unique_key_to_request_id
 
@@ -77,9 +78,9 @@ def to_apify_request(scrapy_request: Request, spider: Spider) -> CrawleeRequest
             id=request_id,
         )
 
-        # Convert Scrapy's headers to a dictionary and store them in the apify_request
+        # Convert Scrapy's headers to a HttpHeaders and store them in the apify_request
         if isinstance(scrapy_request.headers, Headers):
-            apify_request.headers = dict(scrapy_request.headers.to_unicode_dict())
+            apify_request.headers = HttpHeaders(scrapy_request.headers.to_unicode_dict())
         else:
             Actor.log.warning(
                 f'Invalid scrapy_request.headers type, not scrapy.http.headers.Headers: {scrapy_request.headers}'
@@ -164,13 +165,7 @@ def to_scrapy_request(apify_request: CrawleeRequest, spider: Spider) -> Request:
 
     # Add optional 'headers' field
     if apify_request.headers:
-        if isinstance(cast(Any, apify_request.headers), dict):
-            scrapy_request.headers = Headers(apify_request.headers)
-        else:
-            Actor.log.warning(
-                'apify_request[headers] is not an instance of the dict class, '
-                f'apify_request[headers] = {apify_request.headers}',
-            )
+        scrapy_request.headers |= Headers(apify_request.headers)
 
     # Add optional 'userData' field
     if apify_request.user_data: