apify 2.1.0__tar.gz → 2.1.0b2__tar.gz

{apify-2.1.0 → apify-2.1.0b2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: apify
-Version: 2.1.0
+Version: 2.1.0b2
 Summary: Apify SDK for Python
 License: Apache-2.0
 Keywords: apify,sdk,automation,chrome,crawlee,crawler,headless,scraper,scraping
@@ -21,9 +21,9 @@ 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 (>=0.4.0,<0.5.0)
+Requires-Dist: crawlee (>=0.3.9)
 Requires-Dist: cryptography (>=42.0.0)
-Requires-Dist: httpx (>=0.27.0,<0.28.0)
+Requires-Dist: httpx (>=0.27.0)
 Requires-Dist: lazy-object-proxy (>=1.10.0)
 Requires-Dist: scrapy (>=2.11.0) ; extra == "scrapy"
 Requires-Dist: typing-extensions (>=4.1.0)

{apify-2.1.0 → apify-2.1.0b2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "apify"
-version = "2.1.0"
+version = "2.1.0b2"
 description = "Apify SDK for Python"
 authors = ["Apify Technologies s.r.o. <support@apify.com>"]
 license = "Apache-2.0"
@@ -41,15 +41,16 @@ keywords = [
 "Issue Tracker" = "https://github.com/apify/apify-sdk-python/issues"
 "Repository" = "https://github.com/apify/apify-sdk-python"
 
+# We use inclusive ordered comparison clauses for external packages intentionally in order to enhance SDK's
+# compatibility with external packages. This decision was discussed in detail in the following PR:
+# https://github.com/apify/apify-sdk-python/pull/154.
 [tool.poetry.dependencies]
 python = "^3.9"
 apify-client = ">=1.8.1"
 apify-shared = ">=1.1.2"
-crawlee = "~0.4.0"
+crawlee = ">=0.3.9"
 cryptography = ">=42.0.0"
-# TODO: relax the upper bound once the issue is resolved:
-# https://github.com/apify/apify-sdk-python/issues/348
-httpx = "~0.27.0"
+httpx = ">=0.27.0"
 lazy-object-proxy = ">=1.10.0"
 scrapy = { version = ">=2.11.0", optional = true }
 typing-extensions = ">=4.1.0"
@@ -64,13 +65,13 @@ pre-commit = "~4.0.0"
 pydoc-markdown = "~4.8.0"
 pytest = "~8.3.0"
 pytest-asyncio = "~0.24.0"
-pytest-cov = "~6.0.0"
+pytest-cov = "~5.0.0"
 pytest-only = "~2.1.0"
 pytest-timeout = "~2.3.0"
 pytest-xdist = "~3.6.0"
 respx = "~0.21.0"
-ruff = "~0.8.0"
-setuptools = "~75.6.0"     # setuptools are used by pytest but not explicitly required
+ruff = "~0.7.0"
+setuptools = "~75.0.0"     # setuptools are used by pytest but not explicitly required
 
 [tool.poetry.extras]
 scrapy = ["scrapy"]
@@ -81,6 +82,8 @@ line-length = 120
 [tool.ruff.lint]
 select = ["ALL"]
 ignore = [
+    "ANN101",   # Missing type annotation for `self` in method
+    "ANN102",   # Missing type annotation for `{name}` in classmethod
     "ANN401",   # Dynamically typed expressions (typing.Any) are disallowed in {filename}
     "ASYNC109", # Async function definition with a `timeout` parameter
     "BLE001",   # Do not catch blind exception
@@ -93,6 +96,7 @@ ignore = [
     "G004",     # Logging statement uses f-string
     "ISC001",   # This rule may cause conflicts when used with the formatter
     "FIX",      # flake8-fixme
+    "PGH003",   # Use specific rule codes when ignoring type issues
     "PLR0911",  # Too many return statements
     "PLR0913",  # Too many arguments in function definition
     "PLR0915",  # Too many statements
@@ -138,10 +142,7 @@ docstring-quotes = "double"
 inline-quotes = "single"
 
 [tool.ruff.lint.flake8-type-checking]
-runtime-evaluated-base-classes = [
-    "pydantic.BaseModel",
-    "crawlee.configuration.Configuration",
-]
+runtime-evaluated-base-classes = ["pydantic.BaseModel", "crawlee.configuration.Configuration"]
 
 [tool.ruff.lint.flake8-builtins]
 builtins-ignorelist = ["id"]
@@ -182,17 +183,15 @@ exclude = []
 module = ['scrapy', 'scrapy.*', 'lazy_object_proxy']
 ignore_missing_imports = true
 
-[tool.basedpyright]
-pythonVersion = "3.9"
-typeCheckingMode = "standard"
-include = ["src", "tests"]
-
 [tool.coverage.report]
 exclude_lines = [
     "pragma: no cover",
     "if TYPE_CHECKING:",
-    "assert_never()",
+    "assert_never()"
 ]
 
+[tool.basedpyright]
+typeCheckingMode = "standard"
+
 [tool.ipdb]
 context = 7

{apify-2.1.0 → apify-2.1.0b2}/src/apify/_configuration.py

@@ -323,4 +323,4 @@ class Configuration(CrawleeConfiguration):
 
 
 # Monkey-patch the base class so that it works with the extended configuration
-CrawleeConfiguration.get_global_configuration = Configuration.get_global_configuration  # type: ignore[method-assign]
+CrawleeConfiguration.get_global_configuration = Configuration.get_global_configuration  # type: ignore

{apify-2.1.0 → apify-2.1.0b2}/src/apify/_proxy_configuration.py

@@ -280,7 +280,7 @@ class ProxyConfiguration(CrawleeProxyConfiguration):
             return
 
         status = None
-        async with httpx.AsyncClient(proxy=proxy_info.url, timeout=10) as client:
+        async with httpx.AsyncClient(proxies=proxy_info.url, timeout=10) as client:
             for _ in range(2):
                 try:
                     response = await client.get(proxy_status_url)

{apify-2.1.0 → apify-2.1.0b2}/src/apify/scrapy/requests.py

@@ -42,10 +42,8 @@ def to_apify_request(scrapy_request: Request, spider: Spider) -> CrawleeRequest
     Returns:
         The converted Apify request if the conversion was successful, otherwise None.
     """
-    if not isinstance(scrapy_request, Request):
-        Actor.log.warning(  # type: ignore[unreachable]
-            'Failed to convert to Apify request: Scrapy request must be a Request instance.'
-        )
+    if not isinstance(cast(Any, scrapy_request), Request):
+        Actor.log.warning('Failed to convert to Apify request: Scrapy request must be a Request instance.')
         return None
 
     call_id = crypto_random_object_id(8)
@@ -55,7 +53,7 @@ def to_apify_request(scrapy_request: Request, spider: Spider) -> CrawleeRequest
         if _is_request_produced_by_middleware(scrapy_request):
             unique_key = compute_unique_key(
                 url=scrapy_request.url,
-                method=scrapy_request.method,  # type: ignore[arg-type]  # str vs literal
+                method=scrapy_request.method,
                 payload=scrapy_request.body,
                 use_extended_unique_key=True,
             )
@@ -82,9 +80,9 @@ def to_apify_request(scrapy_request: Request, spider: Spider) -> CrawleeRequest
 
         # Convert Scrapy's headers to a HttpHeaders and store them in the apify_request
         if isinstance(scrapy_request.headers, Headers):
-            apify_request.headers = HttpHeaders(dict(scrapy_request.headers.to_unicode_dict()))
+            apify_request.headers = HttpHeaders(scrapy_request.headers.to_unicode_dict())
         else:
-            Actor.log.warning(  # type: ignore[unreachable]
+            Actor.log.warning(
                 f'Invalid scrapy_request.headers type, not scrapy.http.headers.Headers: {scrapy_request.headers}'
             )
 

{apify-2.1.0 → apify-2.1.0b2}/src/apify/storages/__init__.py

@@ -2,4 +2,4 @@ from crawlee.storages import Dataset, KeyValueStore, RequestQueue
 
 from ._request_list import RequestList
 
-__all__ = ['Dataset', 'KeyValueStore', 'RequestList', 'RequestQueue']
+__all__ = ['Dataset', 'KeyValueStore', 'RequestQueue', 'RequestList']

{apify-2.1.0 → apify-2.1.0b2}/src/apify/__init__.py

@@ -13,8 +13,8 @@ __version__ = metadata.version('apify')
 
 __all__ = [
     'Actor',
-    'Configuration',
     'Event',
+    'Configuration',
     'ProxyConfiguration',
     'ProxyInfo',
     'Request',

{apify-2.1.0 → apify-2.1.0b2}/src/apify/scrapy/__init__.py

@@ -3,9 +3,9 @@ from apify.scrapy.scheduler import ApifyScheduler
 from apify.scrapy.utils import get_basic_auth_header, get_running_event_loop_id
 
 __all__ = [
+    'to_apify_request',
+    'to_scrapy_request',
     'ApifyScheduler',
     'get_basic_auth_header',
     'get_running_event_loop_id',
-    'to_apify_request',
-    'to_scrapy_request',
 ]