scrapely-client-python 3.1.3__py3-none-any.whl

scrapely_client/_resource_clients/schedule_collection.py

@@ -0,0 +1,260 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
+
+from scrapely_client._docs import docs_group
+from scrapely_client._models import (
+    ListOfSchedules,
+    ListOfSchedulesResponse,
+    Schedule,
+    ScheduleCreate,
+    ScheduleResponse,
+)
+from scrapely_client._pagination import get_items_iterator, get_items_iterator_async
+from scrapely_client._resource_clients._resource_client import ResourceClient, ResourceClientAsync
+
+if TYPE_CHECKING:
+    from collections.abc import AsyncIterator, Iterator
+
+    from scrapely_client._models import ScheduleShort
+    from scrapely_client.types import Timeout
+
+
+@docs_group('Resource clients')
+class ScheduleCollectionClient(ResourceClient):
+    """Sub-client for the schedule collection.
+
+    Provides methods to manage the schedule collection, e.g. list or create schedules. Obtain an instance via an
+    appropriate method on the `ApifyClient` class.
+    """
+
+    def __init__(
+        self,
+        *,
+        resource_path: str = 'schedules',
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            resource_path=resource_path,
+            **kwargs,
+        )
+
+    def list(
+        self,
+        *,
+        limit: int | None = None,
+        offset: int | None = None,
+        desc: bool | None = None,
+        timeout: Timeout = 'medium',
+    ) -> ListOfSchedules:
+        """List the available schedules.
+
+
+        Args:
+            limit: How many schedules to retrieve.
+            offset: What schedules to include as first when retrieving the list.
+            desc: Whether to sort the schedules in descending order based on their modification date.
+            timeout: Timeout for the API HTTP request.
+
+        Returns:
+            The list of available schedules matching the specified filters.
+        """
+        result = self._list(timeout=timeout, limit=limit, offset=offset, desc=desc)
+        return ListOfSchedulesResponse.model_validate(result).data
+
+    def iterate(
+        self,
+        *,
+        limit: int | None = None,
+        offset: int | None = None,
+        desc: bool | None = None,
+        timeout: Timeout = 'medium',
+    ) -> Iterator[ScheduleShort]:
+        """Iterate over the available schedules.
+
+        Simple `list` does only one API call, possibly not listing all items matching the criteria. This method
+        returns an iterator that is capable of making multiple API calls to retrieve all items matching the criteria.
+
+
+        Args:
+            limit: How many schedules to retrieve.
+            offset: What schedules to include as first when retrieving the list.
+            desc: Whether to sort the schedules in descending order based on their modification date.
+            timeout: Timeout for the API HTTP request.
+
+        Yields:
+            The available schedules matching the specified filters.
+        """
+
+        def _callback(*, limit: int | None = None, offset: int | None = None) -> ListOfSchedules:
+            return self.list(limit=limit, offset=offset, desc=desc, timeout=timeout)
+
+        return get_items_iterator(_callback, limit=limit, offset=offset)
+
+    def create(
+        self,
+        *,
+        cron_expression: str,
+        is_enabled: bool,
+        is_exclusive: bool,
+        name: str | None = None,
+        actions: list[dict[str, Any]] | None = None,  # ty: ignore[invalid-type-form]
+        description: str | None = None,
+        timezone: str | None = None,
+        title: str | None = None,
+        timeout: Timeout = 'short',
+    ) -> Schedule:
+        """Create a new schedule.
+
+
+        Args:
+            cron_expression: The cron expression used by this schedule.
+            is_enabled: True if the schedule should be enabled.
+            is_exclusive: When set to true, don't start Actor or Actor task if it's still running from the previous
+                schedule.
+            name: The name of the schedule to create.
+            actions: Actors or tasks that should be run on this schedule. See the API documentation for exact structure.
+            description: Description of this schedule.
+            timezone: Timezone in which your cron expression runs (TZ database name from
+                https://en.wikipedia.org/wiki/List_of_tz_database_time_zones).
+            title: Title of this schedule.
+            timeout: Timeout for the API HTTP request.
+
+        Returns:
+            The created schedule.
+        """
+        if not actions:
+            actions = []
+
+        schedule_fields = ScheduleCreate(
+            cron_expression=cron_expression,
+            is_enabled=is_enabled,
+            is_exclusive=is_exclusive,
+            name=name,
+            actions=actions or None,
+            description=description,
+            timezone=timezone,
+            title=title,
+        )
+        result = self._create(timeout=timeout, **schedule_fields.model_dump(by_alias=True, exclude_none=True))
+        return ScheduleResponse.model_validate(result).data
+
+
+@docs_group('Resource clients')
+class ScheduleCollectionClientAsync(ResourceClientAsync):
+    """Sub-client for the schedule collection.
+
+    Provides methods to manage the schedule collection, e.g. list or create schedules. Obtain an instance via an
+    appropriate method on the `ApifyClientAsync` class.
+    """
+
+    def __init__(
+        self,
+        *,
+        resource_path: str = 'schedules',
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            resource_path=resource_path,
+            **kwargs,
+        )
+
+    async def list(
+        self,
+        *,
+        limit: int | None = None,
+        offset: int | None = None,
+        desc: bool | None = None,
+        timeout: Timeout = 'medium',
+    ) -> ListOfSchedules:
+        """List the available schedules.
+
+
+        Args:
+            limit: How many schedules to retrieve.
+            offset: What schedules to include as first when retrieving the list.
+            desc: Whether to sort the schedules in descending order based on their modification date.
+            timeout: Timeout for the API HTTP request.
+
+        Returns:
+            The list of available schedules matching the specified filters.
+        """
+        result = await self._list(timeout=timeout, limit=limit, offset=offset, desc=desc)
+        return ListOfSchedulesResponse.model_validate(result).data
+
+    def iterate(
+        self,
+        *,
+        limit: int | None = None,
+        offset: int | None = None,
+        desc: bool | None = None,
+        timeout: Timeout = 'medium',
+    ) -> AsyncIterator[ScheduleShort]:
+        """Iterate over the available schedules.
+
+        Simple `list` does only one API call, possibly not listing all items matching the criteria. This method
+        returns an iterator that is capable of making multiple API calls to retrieve all items matching the criteria.
+
+
+        Args:
+            limit: How many schedules to retrieve.
+            offset: What schedules to include as first when retrieving the list.
+            desc: Whether to sort the schedules in descending order based on their modification date.
+            timeout: Timeout for the API HTTP request.
+
+        Yields:
+            The available schedules matching the specified filters.
+        """
+
+        async def _callback(*, limit: int | None = None, offset: int | None = None) -> ListOfSchedules:
+            return await self.list(limit=limit, offset=offset, desc=desc, timeout=timeout)
+
+        return get_items_iterator_async(_callback, limit=limit, offset=offset)
+
+    async def create(
+        self,
+        *,
+        cron_expression: str,
+        is_enabled: bool,
+        is_exclusive: bool,
+        name: str | None = None,
+        actions: list[dict[str, Any]] | None = None,  # ty: ignore[invalid-type-form]
+        description: str | None = None,
+        timezone: str | None = None,
+        title: str | None = None,
+        timeout: Timeout = 'short',
+    ) -> Schedule:
+        """Create a new schedule.
+
+
+        Args:
+            cron_expression: The cron expression used by this schedule.
+            is_enabled: True if the schedule should be enabled.
+            is_exclusive: When set to true, don't start Actor or Actor task if it's still running from the previous
+                schedule.
+            name: The name of the schedule to create.
+            actions: Actors or tasks that should be run on this schedule. See the API documentation for exact structure.
+            description: Description of this schedule.
+            timezone: Timezone in which your cron expression runs (TZ database name from
+                https://en.wikipedia.org/wiki/List_of_tz_database_time_zones).
+            title: Title of this schedule.
+            timeout: Timeout for the API HTTP request.
+
+        Returns:
+            The created schedule.
+        """
+        if not actions:
+            actions = []
+
+        schedule_fields = ScheduleCreate(
+            cron_expression=cron_expression,
+            is_enabled=is_enabled,
+            is_exclusive=is_exclusive,
+            name=name,
+            actions=actions or None,
+            description=description,
+            timezone=timezone,
+            title=title,
+        )
+        result = await self._create(timeout=timeout, **schedule_fields.model_dump(by_alias=True, exclude_none=True))
+        return ScheduleResponse.model_validate(result).data

scrapely_client/_resource_clients/store_collection.py

@@ -0,0 +1,242 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
+
+from scrapely_client._docs import docs_group
+from scrapely_client._models import ListOfActorsInStoreResponse, ListOfStoreActors
+from scrapely_client._pagination import get_items_iterator, get_items_iterator_async
+from scrapely_client._resource_clients._resource_client import ResourceClient, ResourceClientAsync
+
+if TYPE_CHECKING:
+    from collections.abc import AsyncIterator, Iterator
+
+    from scrapely_client._models import StoreListActor
+    from scrapely_client.types import Timeout
+
+
+@docs_group('Resource clients')
+class StoreCollectionClient(ResourceClient):
+    """Sub-client for the Scrapely store collection.
+
+    Provides methods to browse the Scrapely store, e.g. list available Actors. Obtain an instance via an appropriate
+    method on the `ApifyClient` class.
+    """
+
+    def __init__(
+        self,
+        *,
+        resource_path: str = 'store/actors',  # Scrapely mounts the store listing at /v2/store/actors
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            resource_path=resource_path,
+            **kwargs,
+        )
+
+    def list(
+        self,
+        *,
+        limit: int | None = None,
+        offset: int | None = None,
+        search: str | None = None,
+        sort_by: str | None = None,
+        category: str | None = None,
+        username: str | None = None,
+        pricing_model: str | None = None,
+        include_unrunnable_actors: bool | None = None,
+        timeout: Timeout = 'medium',
+    ) -> ListOfStoreActors:
+        """List Actors in Scrapely store.
+
+
+        Args:
+            limit: How many Actors to list.
+            offset: What Actor to include as first when retrieving the list.
+            search: String to search by. The search runs on the following fields: title, name, description, username,
+                readme.
+            sort_by: Specifies the field by which to sort the results.
+            category: Filter by this category.
+            username: Filter by this username.
+            pricing_model: Filter by this pricing model.
+            include_unrunnable_actors: If True, the response will include Actors that cannot be run.
+            timeout: Timeout for the API HTTP request.
+
+        Returns:
+            The list of available Actors matching the specified filters.
+        """
+        result = self._list(
+            timeout=timeout,
+            limit=limit,
+            offset=offset,
+            search=search,
+            sortBy=sort_by,
+            category=category,
+            username=username,
+            pricingModel=pricing_model,
+            includeUnrunnableActors=include_unrunnable_actors,
+        )
+        return ListOfActorsInStoreResponse.model_validate(result).data
+
+    def iterate(
+        self,
+        *,
+        limit: int | None = None,
+        offset: int | None = None,
+        search: str | None = None,
+        sort_by: str | None = None,
+        category: str | None = None,
+        username: str | None = None,
+        pricing_model: str | None = None,
+        include_unrunnable_actors: bool | None = None,
+        timeout: Timeout = 'medium',
+    ) -> Iterator[StoreListActor]:
+        """Iterate over Actors in Scrapely store.
+
+        Simple `list` does only one API call, possibly not listing all items matching the criteria. This method
+        returns an iterator that is capable of making multiple API calls to retrieve all items matching the criteria.
+
+
+        Args:
+            limit: How many Actors to list.
+            offset: What Actor to include as first when retrieving the list.
+            search: String to search by. The search runs on the following fields: title, name, description, username,
+                readme.
+            sort_by: Specifies the field by which to sort the results.
+            category: Filter by this category.
+            username: Filter by this username.
+            pricing_model: Filter by this pricing model.
+            include_unrunnable_actors: If True, the response will include Actors that cannot be run.
+            timeout: Timeout for the API HTTP request.
+
+        Yields:
+            The Actors in the store matching the specified filters.
+        """
+
+        def _callback(*, limit: int | None = None, offset: int | None = None) -> ListOfStoreActors:
+            return self.list(
+                limit=limit,
+                offset=offset,
+                search=search,
+                sort_by=sort_by,
+                category=category,
+                username=username,
+                pricing_model=pricing_model,
+                include_unrunnable_actors=include_unrunnable_actors,
+                timeout=timeout,
+            )
+
+        return get_items_iterator(_callback, limit=limit, offset=offset)
+
+
+@docs_group('Resource clients')
+class StoreCollectionClientAsync(ResourceClientAsync):
+    """Sub-client for the Scrapely store collection.
+
+    Provides methods to browse the Scrapely store, e.g. list available Actors. Obtain an instance via an appropriate
+    method on the `ApifyClientAsync` class.
+    """
+
+    def __init__(
+        self,
+        *,
+        resource_path: str = 'store/actors',  # Scrapely mounts the store listing at /v2/store/actors
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            resource_path=resource_path,
+            **kwargs,
+        )
+
+    async def list(
+        self,
+        *,
+        limit: int | None = None,
+        offset: int | None = None,
+        search: str | None = None,
+        sort_by: str | None = None,
+        category: str | None = None,
+        username: str | None = None,
+        pricing_model: str | None = None,
+        include_unrunnable_actors: bool | None = None,
+        timeout: Timeout = 'medium',
+    ) -> ListOfStoreActors:
+        """List Actors in Scrapely store.
+
+
+        Args:
+            limit: How many Actors to list.
+            offset: What Actor to include as first when retrieving the list.
+            search: String to search by. The search runs on the following fields: title, name, description, username,
+                readme.
+            sort_by: Specifies the field by which to sort the results.
+            category: Filter by this category.
+            username: Filter by this username.
+            pricing_model: Filter by this pricing model.
+            include_unrunnable_actors: If True, the response will include Actors that cannot be run.
+            timeout: Timeout for the API HTTP request.
+
+        Returns:
+            The list of available Actors matching the specified filters.
+        """
+        result = await self._list(
+            timeout=timeout,
+            limit=limit,
+            offset=offset,
+            search=search,
+            sortBy=sort_by,
+            category=category,
+            username=username,
+            pricingModel=pricing_model,
+            includeUnrunnableActors=include_unrunnable_actors,
+        )
+        return ListOfActorsInStoreResponse.model_validate(result).data
+
+    def iterate(
+        self,
+        *,
+        limit: int | None = None,
+        offset: int | None = None,
+        search: str | None = None,
+        sort_by: str | None = None,
+        category: str | None = None,
+        username: str | None = None,
+        pricing_model: str | None = None,
+        include_unrunnable_actors: bool | None = None,
+        timeout: Timeout = 'medium',
+    ) -> AsyncIterator[StoreListActor]:
+        """Iterate over Actors in Scrapely store.
+
+        Simple `list` does only one API call, possibly not listing all items matching the criteria. This method
+        returns an iterator that is capable of making multiple API calls to retrieve all items matching the criteria.
+
+
+        Args:
+            limit: How many Actors to list.
+            offset: What Actor to include as first when retrieving the list.
+            search: String to search by. The search runs on the following fields: title, name, description, username,
+                readme.
+            sort_by: Specifies the field by which to sort the results.
+            category: Filter by this category.
+            username: Filter by this username.
+            pricing_model: Filter by this pricing model.
+            include_unrunnable_actors: If True, the response will include Actors that cannot be run.
+            timeout: Timeout for the API HTTP request.
+
+        Yields:
+            The Actors in the store matching the specified filters.
+        """
+
+        async def _callback(*, limit: int | None = None, offset: int | None = None) -> ListOfStoreActors:
+            return await self.list(
+                limit=limit,
+                offset=offset,
+                search=search,
+                sort_by=sort_by,
+                category=category,
+                username=username,
+                pricing_model=pricing_model,
+                include_unrunnable_actors=include_unrunnable_actors,
+                timeout=timeout,
+            )
+
+        return get_items_iterator_async(_callback, limit=limit, offset=offset)