apify 2.0.0__py3-none-any.whl → 2.0.0a1__py3-none-any.whl

apify/__init__.py

@@ -1,7 +1,6 @@
 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
@@ -17,7 +16,6 @@ __all__ = [
     'Configuration',
     'ProxyConfiguration',
     'ProxyInfo',
-    'Request',
     'Webhook',
     'WebhookEventType',
     '__version__',

apify/_actor.py

@@ -24,7 +24,7 @@ from apify._platform_event_manager import EventManager, LocalEventManager, Platf
 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.log import logger
 from apify.storages import Dataset, KeyValueStore, RequestQueue
 
 if TYPE_CHECKING:
@@ -46,24 +46,16 @@ 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 +81,6 @@ 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 +111,15 @@ 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."""

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/log.py

@@ -1,12 +1,8 @@
 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
+from crawlee._log_config import CrawleeLogFormatter
 
 # Name of the logger used throughout the library (resolves to 'apify')
 logger_name = __name__.split('.')[0]
@@ -17,27 +13,3 @@ 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)

{apify-2.0.0.dist-info → apify-2.0.0a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: apify
-Version: 2.0.0
+Version: 2.0.0a1
 Summary: Apify SDK for Python
 License: Apache-2.0
 Keywords: apify,sdk,automation,chrome,crawlee,crawler,headless,scraper,scraping
@@ -20,7 +20,7 @@ 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: crawlee (>=0.3.0)
 Requires-Dist: cryptography (>=42.0.0)
 Requires-Dist: httpx (>=0.27.0)
 Requires-Dist: lazy-object-proxy (>=1.10.0)
@@ -64,108 +64,27 @@ 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-2.0.0.dist-info → apify-2.0.0a1.dist-info}/RECORD

@@ -1,5 +1,5 @@
-apify/__init__.py,sha256=ikoi2EpDYl6y-XSVtlU8UsdQdMEyOiIJCRRAaZFDOP8,550
-apify/_actor.py,sha256=oPgQ3rxxIEzVcZ9XtI3lf1a_6gwIMgxihNuYGjJpGww,41816
+apify/__init__.py,sha256=6D62MrlyEsGWRLG5BQXPG5ODGXhBQVjrkJxogVxCT5Y,507
+apify/_actor.py,sha256=0HqsIIdyMGjrUWHoTxuvHb95UMFzvJsMGKqgrqfZVoA,41188
 apify/_configuration.py,sha256=gf7YOun32Whc9DamhoWDLmcUeNwtWVmmBPrl4oq6s4I,8997
 apify/_consts.py,sha256=_Xq4hOfOA1iZ3n1P967YWdyncKivpbX6RTlp_qanUoE,330
 apify/_crypto.py,sha256=b4Czs1NLPkaNzkPjovObjSIbsKnRrgtBkM9JvOysUMA,5612
@@ -13,10 +13,10 @@ apify/apify_storage_client/_dataset_client.py,sha256=j9seF2OKvbSMD9R9XF9fpa1vtr_
 apify/apify_storage_client/_dataset_collection_client.py,sha256=fkYvYGQCigHD2CDzpWk0swNAkfvAinAhMGpYqllle3E,1445
 apify/apify_storage_client/_key_value_store_client.py,sha256=uyeQgb75sGFsqIS4sq4hEZ3QP81COLfS3tmTqHc0tso,3340
 apify/apify_storage_client/_key_value_store_collection_client.py,sha256=vCtMTI-jx89Qp5WHILDNkCthwLuv0MAwm1J_5E4aypU,1519
-apify/apify_storage_client/_request_queue_client.py,sha256=P8ws8jEzi2PWpp-cvYfV7kwuKbgH813BpNQ_wMSVtTA,6278
+apify/apify_storage_client/_request_queue_client.py,sha256=jAiFkaJ38_myHFGTw-Rk21wmpbN0UCR2w2SFoimFGFc,5826
 apify/apify_storage_client/_request_queue_collection_client.py,sha256=NnO73UJ9ZrjV8xoudo30wfaM-SojRkG0guhxDyB-K1g,1527
 apify/apify_storage_client/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-apify/log.py,sha256=pX6ppIvds8OKqjFpIcshqG4zp_5DiOUU31ksyfSExto,1392
+apify/log.py,sha256=Shns441HqiMC9FDdtmftgQmnJWQL3DAKHBRA0E7lbdQ,390
 apify/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 apify/scrapy/__init__.py,sha256=qDPV_zTRFaUqoFOyS5g4uBfz-UCkmWYJ82VXQ_3Cw6k,348
 apify/scrapy/middlewares/__init__.py,sha256=tfW-d3WFWLeNEjL8fTmon6NwgD-OXx1Bw2fBdU-wPy4,114
@@ -31,7 +31,7 @@ apify/scrapy/scheduler.py,sha256=AAIKY5i1QxkC1mtmix6n3M2eQaOw-d1T56Noue9xToc,601
 apify/scrapy/utils.py,sha256=tz_Y8CTqe6KbyMMhLF3m7qqR46jtNH5U7Ty7e19roPU,2814
 apify/storages/__init__.py,sha256=-9tEYJVabVs_eRVhUehxN58GH0UG8OfuGjGwuDieP2M,122
 apify/storages/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-apify-2.0.0.dist-info/LICENSE,sha256=AsFjHssKjj4LGd2ZCqXn6FBzMqcWdjQre1byPPSypVw,11355
-apify-2.0.0.dist-info/METADATA,sha256=DhojQDiiwKEwS7VcAufA7ERVHYHKk5mqHFtddWXL4Qk,8604
-apify-2.0.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-apify-2.0.0.dist-info/RECORD,,
+apify-2.0.0a1.dist-info/LICENSE,sha256=AsFjHssKjj4LGd2ZCqXn6FBzMqcWdjQre1byPPSypVw,11355
+apify-2.0.0a1.dist-info/METADATA,sha256=qmyr_aWFO-X6OPEqikAOlAnbbF1loZMbRAne7kHeDfQ,5231
+apify-2.0.0a1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+apify-2.0.0a1.dist-info/RECORD,,