apify 2.0.0__tar.gz → 2.0.0b1__tar.gz

{apify-2.0.0 → apify-2.0.0b1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: apify
-Version: 2.0.0
+Version: 2.0.0b1
 Summary: Apify SDK for Python
 License: Apache-2.0
 Keywords: apify,sdk,automation,chrome,crawlee,crawler,headless,scraper,scraping
@@ -18,15 +18,21 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Software Development :: Libraries
 Provides-Extra: scrapy
-Requires-Dist: apify-client (>=1.7.1)
-Requires-Dist: apify-shared (>=1.1.2)
-Requires-Dist: crawlee (>=0.3.5)
-Requires-Dist: cryptography (>=42.0.0)
-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)
-Requires-Dist: websockets (>=10.0)
+Requires-Dist: aiofiles (>=22.1.0,<23.0.0)
+Requires-Dist: aioshutil (>=1.0,<2.0)
+Requires-Dist: apify-client (>=1.7.1,<2.0.0)
+Requires-Dist: apify-shared (>=1.1.2,<2.0.0)
+Requires-Dist: colorama (>=0.4.6,<0.5.0)
+Requires-Dist: crawlee (>=0.3.0,<0.4.0)
+Requires-Dist: cryptography (>=39.0.0,<40.0.0)
+Requires-Dist: httpx (>=0.27.0,<0.28.0)
+Requires-Dist: lazy-object-proxy (>=1.10.0,<2.0.0)
+Requires-Dist: psutil (>=6.0.0,<7.0.0)
+Requires-Dist: pyee (>=11.0.0,<12.0.0)
+Requires-Dist: scrapy (>=2.11.0,<3.0.0) ; extra == "scrapy"
+Requires-Dist: sortedcollections (>=2.0.0,<3.0.0)
+Requires-Dist: typing-extensions (>=4.1.0,<5.0.0)
+Requires-Dist: websockets (>=10.1,<11.0)
 Project-URL: Apify Homepage, https://apify.com
 Project-URL: Changelog, https://docs.apify.com/sdk/python/docs/changelog
 Project-URL: Documentation, https://docs.apify.com/sdk/python/
@@ -64,108 +70,27 @@ pip install apify[scrapy]
 
 For usage instructions, check the documentation on [Apify Docs](https://docs.apify.com/sdk/python/).
 
-## Examples
-
-Below are few examples demonstrating how to use the Apify SDK with some web scraping-related libraries.
-
-### Apify SDK with HTTPX and BeautifulSoup
-
-This example illustrates how to integrate the Apify SDK with [HTTPX](https://www.python-httpx.org/) and [BeautifulSoup](https://pypi.org/project/beautifulsoup4/) to scrape data from web pages.
+## Example
 
 ```python
 from apify import Actor
 from bs4 import BeautifulSoup
 from httpx import AsyncClient
 
-
-async def main() -> None:
-    async with Actor:
-        # Retrieve the Actor input, and use default values if not provided.
-        actor_input = await Actor.get_input() or {}
-        start_urls = actor_input.get('start_urls', [{'url': 'https://apify.com'}])
-
-        # Open the default request queue for handling URLs to be processed.
-        request_queue = await Actor.open_request_queue()
-
-        # Enqueue the start URLs.
-        for start_url in start_urls:
-            url = start_url.get('url')
-            await request_queue.add_request(url)
-
-        # Process the URLs from the request queue.
-        while request := await request_queue.fetch_next_request():
-            Actor.log.info(f'Scraping {request.url} ...')
-
-            # Fetch the HTTP response from the specified URL using HTTPX.
-            async with AsyncClient() as client:
-                response = await client.get(request.url)
-
-            # Parse the HTML content using Beautiful Soup.
-            soup = BeautifulSoup(response.content, 'html.parser')
-
-            # Extract the desired data.
-            data = {
-                'url': actor_input['url'],
-                'title': soup.title.string,
-                'h1s': [h1.text for h1 in soup.find_all('h1')],
-                'h2s': [h2.text for h2 in soup.find_all('h2')],
-                'h3s': [h3.text for h3 in soup.find_all('h3')],
-            }
-
-            # Store the extracted data to the default dataset.
-            await Actor.push_data(data)
-```
-
-### Apify SDK with PlaywrightCrawler from Crawlee
-
-This example demonstrates how to use the Apify SDK alongside `PlaywrightCrawler` from [Crawlee](https://crawlee.dev/python) to perform web scraping.
-
-```python
-from apify import Actor, Request
-from crawlee.playwright_crawler import PlaywrightCrawler, PlaywrightCrawlingContext
-
-
 async def main() -> None:
     async with Actor:
-        # Retrieve the Actor input, and use default values if not provided.
-        actor_input = await Actor.get_input() or {}
-        start_urls = [url.get('url') for url in actor_input.get('start_urls', [{'url': 'https://apify.com'}])]
-
-        # Exit if no start URLs are provided.
-        if not start_urls:
-            Actor.log.info('No start URLs specified in Actor input, exiting...')
-            await Actor.exit()
-
-        # Create a crawler.
-        crawler = PlaywrightCrawler(
-            # Limit the crawl to max requests. Remove or increase it for crawling all links.
-            max_requests_per_crawl=50,
-            headless=True,
-        )
-
-        # Define a request handler, which will be called for every request.
-        @crawler.router.default_handler
-        async def request_handler(context: PlaywrightCrawlingContext) -> None:
-            url = context.request.url
-            Actor.log.info(f'Scraping {url}...')
-
-            # Extract the desired data.
-            data = {
-                'url': context.request.url,
-                'title': await context.page.title(),
-                'h1s': [await h1.text_content() for h1 in await context.page.locator('h1').all()],
-                'h2s': [await h2.text_content() for h2 in await context.page.locator('h2').all()],
-                'h3s': [await h3.text_content() for h3 in await context.page.locator('h3').all()],
-            }
-
-            # Store the extracted data to the default dataset.
-            await context.push_data(data)
-
-            # Enqueue additional links found on the current page.
-            await context.enqueue_links()
-
-        # Run the crawler with the starting URLs.
-        await crawler.run(start_urls)
+        # Read the input parameters from the Actor input
+        actor_input = await Actor.get_input()
+        # Fetch the HTTP response from the specified URL
+        async with AsyncClient() as client:
+            response = await client.get(actor_input['url'])
+        # Process the HTML content
+        soup = BeautifulSoup(response.content, 'html.parser')
+        # Push the extracted data
+        await Actor.push_data({
+            'url': actor_input['url'],
+            'title': soup.title.string,
+        })
 ```
 
 ## What are Actors?

apify-2.0.0b1/README.md

@@ -0,0 +1,90 @@
+# Apify SDK for Python
+
+The Apify SDK for Python is the official library to create [Apify Actors](https://docs.apify.com/platform/actors)
+in Python. It provides useful features like Actor lifecycle management, local storage emulation, and Actor
+event handling.
+
+If you just need to access the [Apify API](https://docs.apify.com/api/v2) from your Python applications,
+check out the [Apify Client for Python](https://docs.apify.com/api/client/python) instead.
+
+## Installation
+
+The Apify SDK for Python is available on PyPI as the `apify` package.
+For default installation, using Pip, run the following:
+
+```bash
+pip install apify
+```
+
+For users interested in integrating Apify with Scrapy, we provide a package extra called `scrapy`.
+To install Apify with the `scrapy` extra, use the following command:
+
+```bash
+pip install apify[scrapy]
+```
+
+## Documentation
+
+For usage instructions, check the documentation on [Apify Docs](https://docs.apify.com/sdk/python/).
+
+## Example
+
+```python
+from apify import Actor
+from bs4 import BeautifulSoup
+from httpx import AsyncClient
+
+async def main() -> None:
+    async with Actor:
+        # Read the input parameters from the Actor input
+        actor_input = await Actor.get_input()
+        # Fetch the HTTP response from the specified URL
+        async with AsyncClient() as client:
+            response = await client.get(actor_input['url'])
+        # Process the HTML content
+        soup = BeautifulSoup(response.content, 'html.parser')
+        # Push the extracted data
+        await Actor.push_data({
+            'url': actor_input['url'],
+            'title': soup.title.string,
+        })
+```
+
+## What are Actors?
+
+Actors are serverless cloud programs that can do almost anything a human can do in a web browser.
+They can do anything from small tasks such as filling in forms or unsubscribing from online services,
+all the way up to scraping and processing vast numbers of web pages.
+
+They can be run either locally, or on the [Apify platform](https://docs.apify.com/platform/),
+where you can run them at scale, monitor them, schedule them, or publish and monetize them.
+
+If you're new to Apify, learn [what is Apify](https://docs.apify.com/platform/about)
+in the Apify platform documentation.
+
+## Creating Actors
+
+To create and run Actors through Apify Console,
+see the [Console documentation](https://docs.apify.com/academy/getting-started/creating-actors#choose-your-template).
+
+To create and run Python Actors locally, check the documentation for
+[how to create and run Python Actors locally](https://docs.apify.com/sdk/python/docs/overview/running-locally).
+
+## Guides
+
+To see how you can use the Apify SDK with other popular libraries used for web scraping,
+check out our guides for using
+[Requests and HTTPX](https://docs.apify.com/sdk/python/docs/guides/requests-and-httpx),
+[Beautiful Soup](https://docs.apify.com/sdk/python/docs/guides/beautiful-soup),
+[Playwright](https://docs.apify.com/sdk/python/docs/guides/playwright),
+[Selenium](https://docs.apify.com/sdk/python/docs/guides/selenium),
+or [Scrapy](https://docs.apify.com/sdk/python/docs/guides/scrapy).
+
+## Usage concepts
+
+To learn more about the features of the Apify SDK and how to use them,
+check out the Usage Concepts section in the sidebar,
+particularly the guides for the [Actor lifecycle](https://docs.apify.com/sdk/python/docs/concepts/actor-lifecycle),
+[working with storages](https://docs.apify.com/sdk/python/docs/concepts/storages),
+[handling Actor events](https://docs.apify.com/sdk/python/docs/concepts/actor-events)
+or [how to use proxies](https://docs.apify.com/sdk/python/docs/concepts/proxy-management).

{apify-2.0.0 → apify-2.0.0b1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "apify"
-version = "2.0.0"
+version = "2.0.0b1"
 description = "Apify SDK for Python"
 authors = ["Apify Technologies s.r.o. <support@apify.com>"]
 license = "Apache-2.0"
@@ -46,32 +46,41 @@ keywords = [
 # https://github.com/apify/apify-sdk-python/pull/154.
 [tool.poetry.dependencies]
 python = "^3.9"
-apify-client = ">=1.7.1"
-apify-shared = ">=1.1.2"
-crawlee = ">=0.3.5"
-cryptography = ">=42.0.0"
-httpx = ">=0.27.0"
-lazy-object-proxy = ">=1.10.0"
-scrapy = { version = ">=2.11.0", optional = true }
-typing-extensions = ">=4.1.0"
-websockets = ">=10.0"
+aiofiles = "^22.1.0"
+aioshutil = "^1.0"
+apify-client = "^1.7.1"
+apify-shared = "^1.1.2"
+colorama = "^0.4.6"
+crawlee = "^0.3.0"
+cryptography = "^39.0.0"
+httpx = "^0.27.0"
+lazy-object-proxy = "^1.10.0"
+psutil = "^6.0.0"
+pyee = "^11.0.0"
+scrapy = { version = "^2.11.0", optional = true }
+sortedcollections = "^2.0.0"
+typing-extensions = "^4.1.0"
+websockets = "^10.1"
 
 [tool.poetry.group.dev.dependencies]
-build = "~1.2.0"
-filelock = "~3.16.0"
-griffe = "~1.2.0"
-mypy = "~1.11.0"
-pre-commit = "~3.8.0"
-pydoc-markdown = "~4.8.0"
-pytest = "~8.3.0"
-pytest-asyncio = "~0.24.0"
-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 = "~0.6.0"
-setuptools = "~74.0.0"     # setuptools are used by pytest but not explicitly required
+build = "^1.2.0"
+filelock = "^3.15.0"
+mypy = "^1.11.0"
+pre-commit = "^3.8.0"
+pydoc-markdown = "^4.8.0"
+pytest = "^8.3.0"
+pytest-asyncio = "^0.24.0"
+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 = "^0.6.0"
+setuptools = "^74.0.0"              # setuptools are used by pytest but not explicitly required
+twine = "^5.1.0"
+types-aiofiles = "^24.1.0.20240626"
+types-colorama = "^0.4.15.20240311"
+types-psutil = "^6.0.0.20240621"
 
 [tool.poetry.extras]
 scrapy = ["scrapy"]
@@ -182,7 +191,7 @@ warn_unused_ignores = true
 exclude = []
 
 [[tool.mypy.overrides]]
-module = ['scrapy', 'scrapy.*', 'lazy_object_proxy']
+module = ['scrapy', 'scrapy.*', 'sortedcollections', 'lazy_object_proxy']
 ignore_missing_imports = true
 
 [tool.coverage.report]

apify-2.0.0b1/src/apify/__init__.py

@@ -0,0 +1,11 @@
+from importlib import metadata
+
+from crawlee.events._types import Event
+
+from apify._actor import Actor
+from apify._configuration import Configuration
+from apify._proxy_configuration import ProxyConfiguration, ProxyInfo
+
+__version__ = metadata.version('apify')
+
+__all__ = ['Actor', 'Event', 'Configuration', 'ProxyConfiguration', 'ProxyInfo', '__version__']

{apify-2.0.0 → apify-2.0.0b1}/src/apify/_actor.py

@@ -11,7 +11,7 @@ from pydantic import AliasChoices
 from typing_extensions import Self
 
 from apify_client import ApifyClientAsync
-from apify_shared.consts import ActorEnvVars, ActorExitCodes, ApifyEnvVars
+from apify_shared.consts import ActorEnvVars, ActorExitCodes, ApifyEnvVars, WebhookEventType
 from apify_shared.utils import ignore_docs, maybe_extract_enum_member_value
 from crawlee import service_container
 from crawlee.events._types import Event, EventPersistStateData
@@ -19,12 +19,11 @@ from crawlee.events._types import Event, EventPersistStateData
 from apify._configuration import Configuration
 from apify._consts import EVENT_LISTENERS_TIMEOUT
 from apify._crypto import decrypt_input_secrets, load_private_key
-from apify._models import ActorRun
+from apify._log import logger
 from apify._platform_event_manager import EventManager, LocalEventManager, PlatformEventManager
 from apify._proxy_configuration import ProxyConfiguration
 from apify._utils import get_system_info, is_running_in_ipython
 from apify.apify_storage_client import ApifyStorageClient
-from apify.log import _configure_logging, logger
 from apify.storages import Dataset, KeyValueStore, RequestQueue
 
 if TYPE_CHECKING:
@@ -33,8 +32,6 @@ if TYPE_CHECKING:
 
     from crawlee.proxy_configuration import _NewUrlFunction
 
-    from apify._models import Webhook
-
 
 MainReturnType = TypeVar('MainReturnType')
 
@@ -46,24 +43,16 @@ class _ActorType:
     _configuration: Configuration
     _is_exiting = False
 
-    def __init__(
-        self,
-        configuration: Configuration | None = None,
-        *,
-        configure_logging: bool = True,
-    ) -> None:
+    def __init__(self, config: Configuration | None = None) -> None:
         """Create an Actor instance.
 
         Note that you don't have to do this, all the functionality is accessible using the default instance
         (e.g. `Actor.open_dataset()`).
 
         Args:
-            configuration: The Actor configuration to be used. If not passed, a new Configuration instance will
-                be created.
-            configure_logging: Should the default logging configuration be configured?
+            config: The Actor configuration to be used. If not passed, a new Configuration instance will be created.
         """
-        self._configuration = configuration or Configuration.get_global_configuration()
-        self._configure_logging = configure_logging
+        self._configuration = config or Configuration.get_global_configuration()
         self._apify_client = self.new_client()
 
         self._event_manager: EventManager
@@ -89,9 +78,6 @@ class _ActorType:
         When you exit the `async with` block, the `Actor.exit()` method is called, and if any exception happens while
         executing the block code, the `Actor.fail` method is called.
         """
-        if self._configure_logging:
-            _configure_logging(self._configuration)
-
         await self.init()
         return self
 
@@ -122,20 +108,15 @@ class _ActorType:
 
         return super().__repr__()
 
-    def __call__(self, configuration: Configuration | None = None, *, configure_logging: bool = True) -> Self:
+    def __call__(self, config: Configuration) -> Self:
         """Make a new Actor instance with a non-default configuration."""
-        return self.__class__(configuration=configuration, configure_logging=configure_logging)
+        return self.__class__(config=config)
 
     @property
     def apify_client(self) -> ApifyClientAsync:
         """The ApifyClientAsync instance the Actor instance uses."""
         return self._apify_client
 
-    @property
-    def configuration(self) -> Configuration:
-        """The Configuration instance the Actor instance uses."""
-        return self._configuration
-
     @property
     def config(self) -> Configuration:
         """The Configuration instance the Actor instance uses."""
@@ -552,8 +533,8 @@ class _ActorType:
         memory_mbytes: int | None = None,
         timeout: timedelta | None = None,
         wait_for_finish: int | None = None,
-        webhooks: list[Webhook] | None = None,
-    ) -> ActorRun:
+        webhooks: list[dict] | None = None,
+    ) -> dict:
         """Run an Actor on the Apify platform.
 
         Unlike `Actor.call`, this method just starts the run without waiting for finish.
@@ -574,6 +555,10 @@ class _ActorType:
             webhooks: Optional ad-hoc webhooks (https://docs.apify.com/webhooks/ad-hoc-webhooks) associated with
                 the Actor run which can be used to receive a notification, e.g. when the Actor finished or failed.
                 If you already have a webhook set up for the Actor or task, you do not have to add it again here.
+                Each webhook is represented by a dictionary containing these items:
+                    * `event_types`: list of `WebhookEventType` values which trigger the webhook
+                    * `request_url`: URL to which to send the webhook HTTP request
+                    * `payload_template` (optional): Optional template for the request payload
 
         Returns:
             Info about the started Actor run
@@ -582,25 +567,16 @@ class _ActorType:
 
         client = self.new_client(token=token) if token else self._apify_client
 
-        if webhooks:
-            serialized_webhooks = [
-                hook.model_dump(by_alias=True, exclude_unset=True, exclude_defaults=True) for hook in webhooks
-            ]
-        else:
-            serialized_webhooks = None
-
-        api_result = await client.actor(actor_id).start(
+        return await client.actor(actor_id).start(
             run_input=run_input,
             content_type=content_type,
             build=build,
             memory_mbytes=memory_mbytes,
             timeout_secs=int(timeout.total_seconds()) if timeout is not None else None,
             wait_for_finish=wait_for_finish,
-            webhooks=serialized_webhooks,
+            webhooks=webhooks,
         )
 
-        return ActorRun.model_validate(api_result)
-
     async def abort(
         self,
         run_id: str,
@@ -608,7 +584,7 @@ class _ActorType:
         token: str | None = None,
         status_message: str | None = None,
         gracefully: bool | None = None,
-    ) -> ActorRun:
+    ) -> dict:
         """Abort given Actor run on the Apify platform using the current user account.
 
         The user account is determined by the `APIFY_TOKEN` environment variable.
@@ -631,9 +607,7 @@ class _ActorType:
         if status_message:
             await client.run(run_id).update(status_message=status_message)
 
-        api_result = await client.run(run_id).abort(gracefully=gracefully)
-
-        return ActorRun.model_validate(api_result)
+        return await client.run(run_id).abort(gracefully=gracefully)
 
     async def call(
         self,
@@ -645,9 +619,9 @@ class _ActorType:
         build: str | None = None,
         memory_mbytes: int | None = None,
         timeout: timedelta | None = None,
-        webhooks: list[Webhook] | None = None,
+        webhooks: list[dict] | None = None,
         wait: timedelta | None = None,
-    ) -> ActorRun | None:
+    ) -> dict | None:
         """Start an Actor on the Apify Platform and wait for it to finish before returning.
 
         It waits indefinitely, unless the wait argument is provided.
@@ -676,25 +650,16 @@ class _ActorType:
 
         client = self.new_client(token=token) if token else self._apify_client
 
-        if webhooks:
-            serialized_webhooks = [
-                hook.model_dump(by_alias=True, exclude_unset=True, exclude_defaults=True) for hook in webhooks
-            ]
-        else:
-            serialized_webhooks = None
-
-        api_result = await client.actor(actor_id).call(
+        return await client.actor(actor_id).call(
             run_input=run_input,
             content_type=content_type,
             build=build,
             memory_mbytes=memory_mbytes,
             timeout_secs=int(timeout.total_seconds()) if timeout is not None else None,
-            webhooks=serialized_webhooks,
+            webhooks=webhooks,
             wait_secs=int(wait.total_seconds()) if wait is not None else None,
         )
 
-        return ActorRun.model_validate(api_result)
-
     async def call_task(
         self,
         task_id: str,
@@ -703,10 +668,10 @@ class _ActorType:
         build: str | None = None,
         memory_mbytes: int | None = None,
         timeout: timedelta | None = None,
-        webhooks: list[Webhook] | None = None,
+        webhooks: list[dict] | None = None,
         wait: timedelta | None = None,
         token: str | None = None,
-    ) -> ActorRun | None:
+    ) -> dict | None:
         """Start an Actor task on the Apify Platform and wait for it to finish before returning.
 
         It waits indefinitely, unless the wait argument is provided.
@@ -738,24 +703,15 @@ class _ActorType:
 
         client = self.new_client(token=token) if token else self._apify_client
 
-        if webhooks:
-            serialized_webhooks = [
-                hook.model_dump(by_alias=True, exclude_unset=True, exclude_defaults=True) for hook in webhooks
-            ]
-        else:
-            serialized_webhooks = None
-
-        api_result = await client.task(task_id).call(
+        return await client.task(task_id).call(
             task_input=task_input,
             build=build,
             memory_mbytes=memory_mbytes,
             timeout_secs=int(timeout.total_seconds()) if timeout is not None else None,
-            webhooks=serialized_webhooks,
+            webhooks=webhooks,
             wait_secs=int(wait.total_seconds()) if wait is not None else None,
         )
 
-        return ActorRun.model_validate(api_result)
-
     async def metamorph(
         self,
         target_actor_id: str,
@@ -840,12 +796,14 @@ class _ActorType:
 
     async def add_webhook(
         self,
-        webhook: Webhook,
         *,
+        event_types: list[WebhookEventType],
+        request_url: str,
+        payload_template: str | None = None,
         ignore_ssl_errors: bool | None = None,
         do_not_retry: bool | None = None,
         idempotency_key: str | None = None,
-    ) -> None:
+    ) -> dict | None:
         """Create an ad-hoc webhook for the current Actor run.
 
         This webhook lets you receive a notification when the Actor run finished or failed.
@@ -856,7 +814,9 @@ class _ActorType:
         For more information about Apify Actor webhooks, please see the [documentation](https://docs.apify.com/webhooks).
 
         Args:
-            webhook: The webhook to be added
+            event_types: List of event types that should trigger the webhook. At least one is required.
+            request_url: URL that will be invoked once the webhook is triggered.
+            payload_template: Specification of the payload that will be sent to request_url
             ignore_ssl_errors: Whether the webhook should ignore SSL errors returned by request_url
             do_not_retry: Whether the webhook should retry sending the payload to request_url upon failure.
             idempotency_key: A unique identifier of a webhook. You can use it to ensure that you won't create
@@ -869,17 +829,17 @@ class _ActorType:
 
         if not self.is_at_home():
             self.log.error('Actor.add_webhook() is only supported when running on the Apify platform.')
-            return
+            return None
 
         # If is_at_home() is True, config.actor_run_id is always set
         if not self._configuration.actor_run_id:
             raise RuntimeError('actor_run_id cannot be None when running on the Apify platform.')
 
-        await self._apify_client.webhooks().create(
+        return await self._apify_client.webhooks().create(
             actor_run_id=self._configuration.actor_run_id,
-            event_types=webhook.event_types,
-            request_url=webhook.request_url,
-            payload_template=webhook.payload_template,
+            event_types=event_types,
+            request_url=request_url,
+            payload_template=payload_template,
             ignore_ssl_errors=ignore_ssl_errors,
             do_not_retry=do_not_retry,
             idempotency_key=idempotency_key,
@@ -890,7 +850,7 @@ class _ActorType:
         status_message: str,
         *,
         is_terminal: bool | None = None,
-    ) -> ActorRun | None:
+    ) -> dict | None:
         """Set the status message for the current Actor run.
 
         Args:
@@ -911,12 +871,10 @@ class _ActorType:
         if not self._configuration.actor_run_id:
             raise RuntimeError('actor_run_id cannot be None when running on the Apify platform.')
 
-        api_result = await self._apify_client.run(self._configuration.actor_run_id).update(
+        return await self._apify_client.run(self._configuration.actor_run_id).update(
             status_message=status_message, is_status_message_terminal=is_terminal
         )
 
-        return ActorRun.model_validate(api_result)
-
     async def create_proxy_configuration(
         self,
         *,

apify-2.0.0b1/src/apify/_log.py

@@ -0,0 +1,15 @@
+from __future__ import annotations
+
+import logging
+
+from crawlee._log_config import CrawleeLogFormatter
+
+# Name of the logger used throughout the library (resolves to 'apify')
+logger_name = __name__.split('.')[0]
+
+# Logger used throughout the library
+logger = logging.getLogger(logger_name)
+
+
+class ActorLogFormatter(CrawleeLogFormatter):  # Inherited from parent class
+    pass

{apify-2.0.0 → apify-2.0.0b1}/src/apify/_platform_event_manager.py

@@ -20,7 +20,7 @@ from crawlee.events._types import (
     EventSystemInfoData,
 )
 
-from apify.log import logger
+from apify._log import logger
 
 if TYPE_CHECKING:
     from types import TracebackType
@@ -94,11 +94,6 @@ class EventWithoutData(BaseModel):
     data: Any = None
 
 
-class DeprecatedEvent(BaseModel):
-    name: Literal['cpuInfo']
-    data: Annotated[dict[str, Any], Field(default_factory=dict)]
-
-
 class UnknownEvent(BaseModel):
     name: str
     data: Annotated[dict[str, Any], Field(default_factory=dict)]
@@ -114,13 +109,12 @@ EventMessage = Union[
 ]
 
 
-event_data_adapter: TypeAdapter[EventMessage | DeprecatedEvent | UnknownEvent] = TypeAdapter(
+event_data_adapter: TypeAdapter[EventMessage | UnknownEvent] = TypeAdapter(
     Union[
         Annotated[
             EventMessage,
             Discriminator('name'),
         ],
-        DeprecatedEvent,
         UnknownEvent,
     ]
 )
@@ -195,9 +189,6 @@ class PlatformEventManager(EventManager):
                     try:
                         parsed_message = event_data_adapter.validate_json(message)
 
-                        if isinstance(parsed_message, DeprecatedEvent):
-                            continue
-
                         if isinstance(parsed_message, UnknownEvent):
                             logger.info(
                                 f'Unknown message received: event_name={parsed_message.name}, '

{apify-2.0.0 → apify-2.0.0b1}/src/apify/_proxy_configuration.py

@@ -16,7 +16,7 @@ from crawlee.proxy_configuration import ProxyInfo as CrawleeProxyInfo
 from crawlee.proxy_configuration import _NewUrlFunction
 
 from apify._configuration import Configuration
-from apify.log import logger
+from apify._log import logger
 
 if TYPE_CHECKING:
     from apify_client import ApifyClientAsync

{apify-2.0.0 → apify-2.0.0b1}/src/apify/apify_storage_client/_dataset_client.py

@@ -60,20 +60,18 @@ class DatasetClient(BaseDatasetClient):
         view: str | None = None,
     ) -> DatasetItemsListPage:
         return DatasetItemsListPage.model_validate(
-            vars(
-                await self._client.list_items(
-                    offset=offset,
-                    limit=limit,
-                    clean=clean,
-                    desc=desc,
-                    fields=fields,
-                    omit=omit,
-                    unwind=unwind,
-                    skip_empty=skip_empty,
-                    skip_hidden=skip_hidden,
-                    flatten=flatten,
-                    view=view,
-                )
+            await self._client.list_items(
+                offset=offset,
+                limit=limit,
+                clean=clean,
+                desc=desc,
+                fields=fields,
+                omit=omit,
+                unwind=unwind,
+                skip_empty=skip_empty,
+                skip_hidden=skip_hidden,
+                flatten=flatten,
+                view=view,
             )
         )
 

{apify-2.0.0 → apify-2.0.0b1}/src/apify/apify_storage_client/_request_queue_client.py

@@ -2,7 +2,6 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING
 
-from more_itertools import chunked
 from typing_extensions import override
 
 from crawlee import Request
@@ -158,11 +157,8 @@ class RequestQueueClient(BaseRequestQueueClient):
         *,
         forefront: bool = False,
     ) -> BatchRequestsOperationResponse:
-        processed = []
-        unprocessed = []
-
-        for chunk in chunked(requests, 25):  # The API endpoint won't accept more than 25 requests at once
-            response = await self._client.batch_add_requests(
+        return BatchRequestsOperationResponse.model_validate(
+            await self._client.batch_add_requests(
                 requests=[
                     r.model_dump(
                         by_alias=True,
@@ -174,18 +170,10 @@ class RequestQueueClient(BaseRequestQueueClient):
                             'data',
                         },
                     )
-                    for r in chunk
+                    for r in requests
                 ],
                 forefront=forefront,
             )
-            processed.extend(response['processedRequests'])
-            unprocessed.extend(response['unprocessedRequests'])
-
-        return BatchRequestsOperationResponse.model_validate(
-            {
-                'processedRequests': processed,
-                'unprocessedRequests': unprocessed,
-            }
         )
 
     @override

{apify-2.0.0 → apify-2.0.0b1}/src/apify/scrapy/middlewares/apify_proxy.py

@@ -93,7 +93,7 @@ class ApifyHttpProxyMiddleware:
         request: Request,
         exception: Exception,
         spider: Spider,
-    ) -> None:
+    ) -> None | Request:
         """Process an exception that occurs during request processing.
 
         Args:
@@ -102,9 +102,8 @@ class ApifyHttpProxyMiddleware:
             spider: Scrapy Spider object.
 
         Returns:
-            Returning None, meaning Scrapy will continue processing this exception, executing any other
-            process_exception() methods of installed middleware, until no middleware is left and the default
-            exception handling kicks in.
+            If a TunnelError occurs, return the request object to halt its processing in the middleware pipeline.
+            Return None otherwise to allow the continuation of request processing.
         """
         Actor.log.debug(
             f'ApifyHttpProxyMiddleware.process_exception: request={request}, exception={exception}, spider={spider}',
@@ -115,6 +114,9 @@ class ApifyHttpProxyMiddleware:
                 f'ApifyHttpProxyMiddleware: TunnelError occurred for request="{request}", '
                 'reason="{exception}", skipping...'
             )
+            return request
+
+        return None
 
     async def _get_new_proxy_url(self: ApifyHttpProxyMiddleware) -> ParseResult:
         """Get a new proxy URL.

apify-2.0.0/README.md

@@ -1,171 +0,0 @@
-# Apify SDK for Python
-
-The Apify SDK for Python is the official library to create [Apify Actors](https://docs.apify.com/platform/actors)
-in Python. It provides useful features like Actor lifecycle management, local storage emulation, and Actor
-event handling.
-
-If you just need to access the [Apify API](https://docs.apify.com/api/v2) from your Python applications,
-check out the [Apify Client for Python](https://docs.apify.com/api/client/python) instead.
-
-## Installation
-
-The Apify SDK for Python is available on PyPI as the `apify` package.
-For default installation, using Pip, run the following:
-
-```bash
-pip install apify
-```
-
-For users interested in integrating Apify with Scrapy, we provide a package extra called `scrapy`.
-To install Apify with the `scrapy` extra, use the following command:
-
-```bash
-pip install apify[scrapy]
-```
-
-## Documentation
-
-For usage instructions, check the documentation on [Apify Docs](https://docs.apify.com/sdk/python/).
-
-## Examples
-
-Below are few examples demonstrating how to use the Apify SDK with some web scraping-related libraries.
-
-### Apify SDK with HTTPX and BeautifulSoup
-
-This example illustrates how to integrate the Apify SDK with [HTTPX](https://www.python-httpx.org/) and [BeautifulSoup](https://pypi.org/project/beautifulsoup4/) to scrape data from web pages.
-
-```python
-from apify import Actor
-from bs4 import BeautifulSoup
-from httpx import AsyncClient
-
-
-async def main() -> None:
-    async with Actor:
-        # Retrieve the Actor input, and use default values if not provided.
-        actor_input = await Actor.get_input() or {}
-        start_urls = actor_input.get('start_urls', [{'url': 'https://apify.com'}])
-
-        # Open the default request queue for handling URLs to be processed.
-        request_queue = await Actor.open_request_queue()
-
-        # Enqueue the start URLs.
-        for start_url in start_urls:
-            url = start_url.get('url')
-            await request_queue.add_request(url)
-
-        # Process the URLs from the request queue.
-        while request := await request_queue.fetch_next_request():
-            Actor.log.info(f'Scraping {request.url} ...')
-
-            # Fetch the HTTP response from the specified URL using HTTPX.
-            async with AsyncClient() as client:
-                response = await client.get(request.url)
-
-            # Parse the HTML content using Beautiful Soup.
-            soup = BeautifulSoup(response.content, 'html.parser')
-
-            # Extract the desired data.
-            data = {
-                'url': actor_input['url'],
-                'title': soup.title.string,
-                'h1s': [h1.text for h1 in soup.find_all('h1')],
-                'h2s': [h2.text for h2 in soup.find_all('h2')],
-                'h3s': [h3.text for h3 in soup.find_all('h3')],
-            }
-
-            # Store the extracted data to the default dataset.
-            await Actor.push_data(data)
-```
-
-### Apify SDK with PlaywrightCrawler from Crawlee
-
-This example demonstrates how to use the Apify SDK alongside `PlaywrightCrawler` from [Crawlee](https://crawlee.dev/python) to perform web scraping.
-
-```python
-from apify import Actor, Request
-from crawlee.playwright_crawler import PlaywrightCrawler, PlaywrightCrawlingContext
-
-
-async def main() -> None:
-    async with Actor:
-        # Retrieve the Actor input, and use default values if not provided.
-        actor_input = await Actor.get_input() or {}
-        start_urls = [url.get('url') for url in actor_input.get('start_urls', [{'url': 'https://apify.com'}])]
-
-        # Exit if no start URLs are provided.
-        if not start_urls:
-            Actor.log.info('No start URLs specified in Actor input, exiting...')
-            await Actor.exit()
-
-        # Create a crawler.
-        crawler = PlaywrightCrawler(
-            # Limit the crawl to max requests. Remove or increase it for crawling all links.
-            max_requests_per_crawl=50,
-            headless=True,
-        )
-
-        # Define a request handler, which will be called for every request.
-        @crawler.router.default_handler
-        async def request_handler(context: PlaywrightCrawlingContext) -> None:
-            url = context.request.url
-            Actor.log.info(f'Scraping {url}...')
-
-            # Extract the desired data.
-            data = {
-                'url': context.request.url,
-                'title': await context.page.title(),
-                'h1s': [await h1.text_content() for h1 in await context.page.locator('h1').all()],
-                'h2s': [await h2.text_content() for h2 in await context.page.locator('h2').all()],
-                'h3s': [await h3.text_content() for h3 in await context.page.locator('h3').all()],
-            }
-
-            # Store the extracted data to the default dataset.
-            await context.push_data(data)
-
-            # Enqueue additional links found on the current page.
-            await context.enqueue_links()
-
-        # Run the crawler with the starting URLs.
-        await crawler.run(start_urls)
-```
-
-## What are Actors?
-
-Actors are serverless cloud programs that can do almost anything a human can do in a web browser.
-They can do anything from small tasks such as filling in forms or unsubscribing from online services,
-all the way up to scraping and processing vast numbers of web pages.
-
-They can be run either locally, or on the [Apify platform](https://docs.apify.com/platform/),
-where you can run them at scale, monitor them, schedule them, or publish and monetize them.
-
-If you're new to Apify, learn [what is Apify](https://docs.apify.com/platform/about)
-in the Apify platform documentation.
-
-## Creating Actors
-
-To create and run Actors through Apify Console,
-see the [Console documentation](https://docs.apify.com/academy/getting-started/creating-actors#choose-your-template).
-
-To create and run Python Actors locally, check the documentation for
-[how to create and run Python Actors locally](https://docs.apify.com/sdk/python/docs/overview/running-locally).
-
-## Guides
-
-To see how you can use the Apify SDK with other popular libraries used for web scraping,
-check out our guides for using
-[Requests and HTTPX](https://docs.apify.com/sdk/python/docs/guides/requests-and-httpx),
-[Beautiful Soup](https://docs.apify.com/sdk/python/docs/guides/beautiful-soup),
-[Playwright](https://docs.apify.com/sdk/python/docs/guides/playwright),
-[Selenium](https://docs.apify.com/sdk/python/docs/guides/selenium),
-or [Scrapy](https://docs.apify.com/sdk/python/docs/guides/scrapy).
-
-## Usage concepts
-
-To learn more about the features of the Apify SDK and how to use them,
-check out the Usage Concepts section in the sidebar,
-particularly the guides for the [Actor lifecycle](https://docs.apify.com/sdk/python/docs/concepts/actor-lifecycle),
-[working with storages](https://docs.apify.com/sdk/python/docs/concepts/storages),
-[handling Actor events](https://docs.apify.com/sdk/python/docs/concepts/actor-events)
-or [how to use proxies](https://docs.apify.com/sdk/python/docs/concepts/proxy-management).

apify-2.0.0/src/apify/__init__.py

@@ -1,24 +0,0 @@
-from importlib import metadata
-
-from apify_shared.consts import WebhookEventType
-from crawlee import Request
-from crawlee.events._types import Event
-
-from apify._actor import Actor
-from apify._configuration import Configuration
-from apify._models import Webhook
-from apify._proxy_configuration import ProxyConfiguration, ProxyInfo
-
-__version__ = metadata.version('apify')
-
-__all__ = [
-    'Actor',
-    'Event',
-    'Configuration',
-    'ProxyConfiguration',
-    'ProxyInfo',
-    'Request',
-    'Webhook',
-    'WebhookEventType',
-    '__version__',
-]

apify-2.0.0/src/apify/_models.py

@@ -1,110 +0,0 @@
-# ruff: noqa: TCH001 TCH002 TCH003 (Pydantic)
-from __future__ import annotations
-
-from datetime import datetime, timedelta
-from typing import Annotated
-
-from pydantic import BaseModel, BeforeValidator, ConfigDict, Field
-
-from apify_shared.consts import ActorJobStatus, MetaOrigin, WebhookEventType
-from crawlee._utils.models import timedelta_ms
-from crawlee._utils.urls import validate_http_url
-
-
-class Webhook(BaseModel):
-    __model_config__ = ConfigDict(populate_by_name=True)
-
-    event_types: Annotated[
-        list[WebhookEventType],
-        Field(description='Event types that should trigger the webhook'),
-    ]
-    request_url: Annotated[
-        str,
-        Field(description='URL that the webhook should call'),
-        BeforeValidator(validate_http_url),
-    ]
-    payload_template: Annotated[
-        str | None,
-        Field(description='Template for the payload sent by the webook'),
-    ] = None
-
-
-class ActorRunMeta(BaseModel):
-    __model_config__ = ConfigDict(populate_by_name=True)
-
-    origin: Annotated[MetaOrigin, Field()]
-
-
-class ActorRunStats(BaseModel):
-    __model_config__ = ConfigDict(populate_by_name=True)
-
-    input_body_len: Annotated[int, Field(alias='inputBodyLen')]
-    restart_count: Annotated[int, Field(alias='restartCount')]
-    resurrect_count: Annotated[int, Field(alias='resurrectCount')]
-    mem_avg_bytes: Annotated[float | None, Field(alias='memAvgBytes')] = None
-    mem_max_bytes: Annotated[int | None, Field(alias='memMaxBytes')] = None
-    mem_current_bytes: Annotated[int | None, Field(alias='memCurrentBytes')] = None
-    cpu_avg_usage: Annotated[float | None, Field(alias='cpuAvgUsage')] = None
-    cpu_max_usage: Annotated[float | None, Field(alias='cpuMaxUsage')] = None
-    cpu_current_usage: Annotated[float | None, Field(alias='cpuCurrentUsage')] = None
-    net_rx_bytes: Annotated[int | None, Field(alias='netRxBytes')] = None
-    net_tx_bytes: Annotated[int | None, Field(alias='netTxBytes')] = None
-    duration: Annotated[timedelta_ms | None, Field(alias='durationMillis')] = None
-    run_time: Annotated[timedelta | None, Field(alias='runTimeSecs')] = None
-    metamorph: Annotated[int | None, Field(alias='metamorph')] = None
-    compute_units: Annotated[float, Field(alias='computeUnits')]
-
-
-class ActorRunOptions(BaseModel):
-    __model_config__ = ConfigDict(populate_by_name=True)
-
-    build: str
-    timeout: Annotated[timedelta, Field(alias='timeoutSecs')]
-    memory_mbytes: Annotated[int, Field(alias='memoryMbytes')]
-    disk_mbytes: Annotated[int, Field(alias='diskMbytes')]
-
-
-class ActorRunUsage(BaseModel):
-    __model_config__ = ConfigDict(populate_by_name=True)
-
-    actor_compute_units: Annotated[float | None, Field(alias='ACTOR_COMPUTE_UNITS')] = None
-    dataset_reads: Annotated[float | None, Field(alias='DATASET_READS')] = None
-    dataset_writes: Annotated[float | None, Field(alias='DATASET_WRITES')] = None
-    key_value_store_reads: Annotated[float | None, Field(alias='KEY_VALUE_STORE_READS')] = None
-    key_value_store_writes: Annotated[float | None, Field(alias='KEY_VALUE_STORE_WRITES')] = None
-    key_value_store_lists: Annotated[float | None, Field(alias='KEY_VALUE_STORE_LISTS')] = None
-    request_queue_reads: Annotated[float | None, Field(alias='REQUEST_QUEUE_READS')] = None
-    request_queue_writes: Annotated[float | None, Field(alias='REQUEST_QUEUE_WRITES')] = None
-    data_transfer_internal_gbytes: Annotated[float | None, Field(alias='DATA_TRANSFER_INTERNAL_GBYTES')] = None
-    data_transfer_external_gbytes: Annotated[float | None, Field(alias='DATA_TRANSFER_EXTERNAL_GBYTES')] = None
-    proxy_residential_transfer_gbytes: Annotated[float | None, Field(alias='PROXY_RESIDENTIAL_TRANSFER_GBYTES')] = None
-    proxy_serps: Annotated[float | None, Field(alias='PROXY_SERPS')] = None
-
-
-class ActorRun(BaseModel):
-    __model_config__ = ConfigDict(populate_by_name=True)
-
-    id: Annotated[str, Field(alias='id')]
-    act_id: Annotated[str, Field(alias='actId')]
-    user_id: Annotated[str, Field(alias='userId')]
-    actor_task_id: Annotated[str | None, Field(alias='actorTaskId')] = None
-    started_at: Annotated[datetime, Field(alias='startedAt')]
-    finished_at: Annotated[datetime | None, Field(alias='finishedAt')] = None
-    status: Annotated[ActorJobStatus, Field(alias='status')]
-    status_message: Annotated[str | None, Field(alias='statusMessage')] = None
-    is_status_message_terminal: Annotated[bool | None, Field(alias='isStatusMessageTerminal')] = None
-    meta: Annotated[ActorRunMeta, Field(alias='meta')]
-    stats: Annotated[ActorRunStats, Field(alias='stats')]
-    options: Annotated[ActorRunOptions, Field(alias='options')]
-    build_id: Annotated[str, Field(alias='buildId')]
-    exit_code: Annotated[int | None, Field(alias='exitCode')] = None
-    default_key_value_store_id: Annotated[str, Field(alias='defaultKeyValueStoreId')]
-    default_dataset_id: Annotated[str, Field(alias='defaultDatasetId')]
-    default_request_queue_id: Annotated[str, Field(alias='defaultRequestQueueId')]
-    build_number: Annotated[str | None, Field(alias='buildNumber')] = None
-    container_url: Annotated[str, Field(alias='containerUrl')]
-    is_container_server_ready: Annotated[bool | None, Field(alias='isContainerServerReady')] = None
-    git_branch_name: Annotated[str | None, Field(alias='gitBranchName')] = None
-    usage: Annotated[ActorRunUsage | None, Field(alias='usage')] = None
-    usage_total_usd: Annotated[float | None, Field(alias='usageTotalUsd')] = None
-    usage_usd: Annotated[ActorRunUsage | None, Field(alias='usageUsd')] = None

apify-2.0.0/src/apify/log.py

@@ -1,43 +0,0 @@
-from __future__ import annotations
-
-import logging
-from typing import TYPE_CHECKING
-
-from crawlee._log_config import CrawleeLogFormatter, configure_logger, get_configured_log_level
-
-if TYPE_CHECKING:
-    from apify import Configuration
-
-# Name of the logger used throughout the library (resolves to 'apify')
-logger_name = __name__.split('.')[0]
-
-# Logger used throughout the library
-logger = logging.getLogger(logger_name)
-
-
-class ActorLogFormatter(CrawleeLogFormatter):  # noqa: D101 Inherited from parent class
-    pass
-
-
-def _configure_logging(configuration: Configuration) -> None:
-    apify_client_logger = logging.getLogger('apify_client')
-    configure_logger(apify_client_logger, configuration, remove_old_handlers=True)
-
-    level = get_configured_log_level(configuration)
-
-    # Keep apify_client logger quiet unless debug logging is requested
-    if level > logging.DEBUG:
-        apify_client_logger.setLevel(logging.INFO)
-    else:
-        apify_client_logger.setLevel(level)
-
-    # Silence HTTPX logger unless debug logging is requested
-    httpx_logger = logging.getLogger('httpx')
-    if level > logging.DEBUG:
-        httpx_logger.setLevel(logging.WARNING)
-    else:
-        httpx_logger.setLevel(level)
-
-    # Use configured log level for apify logger
-    apify_logger = logging.getLogger('apify')
-    configure_logger(apify_logger, configuration, remove_old_handlers=True)