refactor!: Preparation for v2 release (#210)

- **Update pyproject.toml**
- **Use storage code from crawlee, add ApifyStorageClient**

- [x] make sure we use `APIFY_IS_AT_HOME` instead of token for all
platform vs. local decisions
- [x] port over `warnedAboutMissingInitCall` from JS SDK (this is not
exactly ported over, but we expect this won't happen frequently, so we
just throw an exception)

### Issues

- Closes: #135
- Closes: #137
- Closes: #138
- Closes: #147
- Closes: #149
- Closes: #237

Author: janbuchar

CONTRIBUTING.md

@@ -50,7 +50,7 @@ tests with HTML coverage report execute `make unit-tests-cov`.
 
 ## Integration tests
 
-We have integration tests which build and run actors using the Python SDK on the Apify Platform. To run these tests,
+We have integration tests which build and run Actors using the Python SDK on the Apify Platform. To run these tests,
 you need to set the `APIFY_TEST_USER_API_TOKEN` environment variable to the API token of the Apify user you want to
 use for the tests, and then start them with `make integration-tests`.
 

docs/02-guides/02-beautiful-soup.mdx

@@ -36,7 +36,7 @@ async def main():
         max_depth = actor_input.get('max_depth', 1)
 
         if not start_urls:
-            Actor.log.info('No start URLs specified in actor input, exiting...')
+            Actor.log.info('No start URLs specified in Actor input, exiting...')
             await Actor.exit()
 
         # Enqueue the starting URLs in the default request queue

docs/02-guides/03-playwright.mdx

@@ -29,7 +29,7 @@ To create Actors which use Playwright, start from the [Playwright & Python](http
 On the Apify platform, the Actor will already have Playwright and the necessary browsers preinstalled in its Docker image,
 including the tools and setup necessary to run browsers in headful mode.
 
-When running the Actor locally, you'll need to finish the Playwright setup yourself before you can run the actor.
+When running the Actor locally, you'll need to finish the Playwright setup yourself before you can run the Actor.
 
 <Tabs groupId="operating-systems">
     <TabItem value="unix" label="Linux / macOS" default>
@@ -69,7 +69,7 @@ async def main():
         max_depth = actor_input.get('max_depth', 1)
 
         if not start_urls:
-            Actor.log.info('No start URLs specified in actor input, exiting...')
+            Actor.log.info('No start URLs specified in Actor input, exiting...')
             await Actor.exit()
 
         # Enqueue the starting URLs in the default request queue

docs/02-guides/04-selenium.mdx

@@ -53,7 +53,7 @@ async def main():
         max_depth = actor_input.get('max_depth', 1)
 
         if not start_urls:
-            Actor.log.info('No start URLs specified in actor input, exiting...')
+            Actor.log.info('No start URLs specified in Actor input, exiting...')
             await Actor.exit()
 
         # Enqueue the starting URLs in the default request queue

docs/02-guides/05-scrapy.mdx

@@ -87,7 +87,7 @@ class TitleSpider(scrapy.Spider):
             if link_url.startswith(('http://', 'https://')):
                 yield scrapy.Request(link_url)
 
-# Pushes the scraped items into the actor's default dataset
+# Pushes the scraped items into the Actor's default dataset
 class ActorDatasetPushPipeline:
     async def process_item(self, item, spider):
         item_dict = ItemAdapter(item).asdict()

docs/03-concepts/04-actor-events.mdx

@@ -91,7 +91,7 @@ async def main():
         # Save the state when the `PERSIST_STATE` event happens
         async def save_state(event_data):
             nonlocal processed_items
-            Actor.log.info('Saving actor state', extra=event_data)
+            Actor.log.info('Saving Actor state', extra=event_data)
             await Actor.set_value('STATE', processed_items)
 
         Actor.on(ActorEventTypes.PERSIST_STATE, save_state)

mypy.ini

@@ -1,6 +1,6 @@
 [project]
 name = "apify"
-version = "1.7.3"
+version = "2.0.0"
 description = "Apify SDK for Python"
 readme = "README.md"
 license = { text = "Apache Software License" }
@@ -20,7 +20,7 @@ classifiers = [
     "Topic :: Software Development :: Libraries",
 ]
 
-requires-python = ">=3.8"
+requires-python = ">=3.9"
 
 # We use inclusive ordered comparison clause for non-Apify packages intentionally in order to enhance the Apify SDK's
 # compatibility with a wide range of external packages. This decision was discussed in detail in the following PR:
@@ -31,8 +31,10 @@ dependencies = [
     "aiofiles >= 22.1.0",
     "aioshutil >= 1.0",
     "colorama >= 0.4.6",
+    "crawlee >= 0.3.0",
     "cryptography >= 39.0.0",
     "httpx >= 0.24.0",
+    "lazy-object-proxy >= 1.10.0",
     "psutil >= 5.9.0",
     "pyee >= 11.0.0",
     "sortedcollections >= 2.0.0",
@@ -90,12 +92,16 @@ line-length = 150
 [tool.ruff.lint]
 select = ["ALL"]
 ignore = [
+    "A002",    # Argument is shadowing a Python builtin
+    "ANN101",  # Missing type annotation for `self` in method
+    "ANN102",  # Missing type annotation for `cls` in method
     "ANN401",  # Dynamically typed expressions (typing.Any) are disallowed in {filename}
     "BLE001",  # Do not catch blind exception
     "C901",    # `{name}` is too complex
     "COM812",  # This rule may cause conflicts when used with the formatter
     "D100",    # Missing docstring in public module
     "D104",    # Missing docstring in public package
+    "D107",    # Missing docstring in `__init__`
     "EM",      # flake8-errmsg
     "G004",    # Logging statement uses f-string
     "ISC001",  # This rule may cause conflicts when used with the formatter
@@ -152,6 +158,33 @@ inline-quotes = "single"
 
 [tool.ruff.lint.isort]
 known-local-folder = ["apify"]
+known-first-party = ["apify_client", "apify_shared", "crawlee"]
 
 [tool.ruff.lint.pydocstyle]
 convention = "google"
+
+[tool.basedpyright]
+typeCheckingMode = "standard"
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+timeout = 1200
+
+[tool.mypy]
+python_version = "3.9"
+plugins = ["pydantic.mypy"]
+files = ["scripts", "src", "tests"]
+check_untyped_defs = true
+disallow_incomplete_defs = true
+disallow_untyped_calls = true
+disallow_untyped_decorators = true
+disallow_untyped_defs = true
+no_implicit_optional = true
+warn_redundant_casts = true
+warn_return_any = true
+warn_unreachable = true
+warn_unused_ignores = true
+
+[[tool.mypy.overrides]]
+module = ['scrapy', 'scrapy.*', 'sortedcollections', 'lazy_object_proxy']
+ignore_missing_imports = true

pyproject.toml

@@ -1,9 +1,11 @@
 from importlib import metadata
 
-from .actor import Actor
-from .config import Configuration
-from .proxy_configuration import ProxyConfiguration, ProxyInfo
+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', 'Configuration', 'ProxyConfiguration', 'ProxyInfo', '__version__']
+__all__ = ['Actor', 'Event', 'Configuration', 'ProxyConfiguration', 'ProxyInfo', '__version__']