scrapely-client-python 1.0.0__tar.gz → 1.0.2__tar.gz

scrapely_client_python-1.0.2/CHANGELOG.md

@@ -0,0 +1,14 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+## [1.0.2] - 2026-10-13
+
+- Builds are owner-only: `build_id` on runs and metamorphs and `build` in run options are optional, since runs of someone else's Actor carry no build info. Older versions raise a validation error on those runs.
+- `actor().update(default_non_owner_build=...)` sets the User Build (the build everyone else runs); `''` clears it.
+
+## [1.0.0] - 2026-09-08
+
+Initial release.
+
+- Python client for the Scrapely API: Actors, runs, datasets, key-value stores, request queues, task management, and webhooks

{scrapely_client_python-1.0.0 → scrapely_client_python-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scrapely-client-python
-Version: 1.0.0
+Version: 1.0.2
 Summary: Scrapely API client for Python
 Keywords: scrapely,api,client,automation,crawling,scraping
 Author: Scrapely

{scrapely_client_python-1.0.0 → scrapely_client_python-1.0.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "scrapely-client-python"
-version = "1.0.0"
+version = "1.0.2"
 description = "Scrapely API client for Python"
 license = "Apache-2.0"
 license-files = ["LICENSE"]

{scrapely_client_python-1.0.0 → scrapely_client_python-1.0.2}/pyproject.toml.orig

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "scrapely-client-python"
-version = "1.0.0"
+version = "1.0.2"
 description = "Scrapely API client for Python"
 authors = [{ name = "Scrapely" }]
 license = "Apache-2.0"
@@ -46,7 +46,6 @@ brotli = ["brotli>=1.0.9"]
 dev = [
     # TODO: Remove this constraint once pydoc-markdown updates its dependencies.
     # Package pydoc-markdown is unmaintained and pins old docspec-python with vulnerable black.
-    # See https://github.com/apify/apify-client-python/pull/582/ for more details.
     # We explicitly constrain black>=24.3.0 to override the transitive dependency.
     "black>=24.3.0",
     "datamodel-code-generator[http,ruff]>=0.64.1,<1.0.0",

{scrapely_client_python-1.0.0 → scrapely_client_python-1.0.2}/src/scrapely_client/_models.py

@@ -50,7 +50,7 @@ class ActVersion(BaseModel):
         str | None, Field(examples=['0.0'], pattern='^([0-9]|[1-9][0-9])\\.([0-9]|[1-9][0-9])(\\.[0-9]+)?$')
     ] = None
     git_repo_url: Annotated[
-        str | None, Field(examples=['https://github.com/apifytech/actor-crawler.git#experimental:web-scraper'])
+        str | None, Field(examples=['https://github.com/example/my-actor.git#main:src'])
     ] = None
     """
     URL of the git repository, present when sourceType is GIT_REPO.
@@ -1964,7 +1964,7 @@ class Metamorph(BaseModel):
     """
     ID of the Actor that the run was metamorphed to.
     """
-    build_id: Annotated[str, Field(examples=['ME6oKecqy5kXDS4KQ'])]
+    build_id: Annotated[str | None, Field(examples=['ME6oKecqy5kXDS4KQ'])] = None
     """
     ID of the build used for the metamorphed Actor.
     """
@@ -2915,7 +2915,7 @@ class Run(BaseModel):
     """
     Configuration options for the Actor run.
     """
-    build_id: Annotated[str, Field(examples=['7sT5jcggjjA9fNcxF'])]
+    build_id: Annotated[str | None, Field(examples=['7sT5jcggjjA9fNcxF'])] = None
     """
     ID of the Actor build used for this run.
     """
@@ -3017,7 +3017,7 @@ class RunOptions(BaseModel):
         populate_by_name=True,
         alias_generator=to_camel,
     )
-    build: Annotated[str, Field(examples=['latest'])]
+    build: Annotated[str | None, Field(examples=['latest'])] = None
     timeout_secs: Annotated[int, Field(examples=[300], ge=0)]
     memory_mbytes: Annotated[int, Field(examples=[1024], ge=128, le=32768)]
     disk_mbytes: Annotated[int | None, Field(examples=[2048], ge=0)] = None
@@ -3049,7 +3049,7 @@ class RunShort(BaseModel):
     status: ActorJobStatus
     started_at: Annotated[AwareDatetime, Field(examples=['2019-11-30T07:34:24.202Z'])]
     finished_at: Annotated[AwareDatetime | None, Field(examples=['2019-12-12T09:30:12.202Z'])] = None
-    build_id: Annotated[str, Field(examples=['HG7ML7M8z78YcAPEB'])]
+    build_id: Annotated[str | None, Field(examples=['HG7ML7M8z78YcAPEB'])] = None
     build_number: Annotated[
         str | None, Field(examples=['0.0.2'], pattern='^([0-9]|[1-9][0-9])\\.([0-9]|[1-9][0-9])(\\.[1-9][0-9]{0,4})$')
     ] = None

{scrapely_client_python-1.0.0 → scrapely_client_python-1.0.2}/src/scrapely_client/_resource_clients/actor.py

@@ -124,6 +124,7 @@ class ActorClient(ResourceClient):
         pricing_infos: list[dict[str, Any]] | None = None,
         actor_permission_level: ActorPermissionLevel | None = None,
         tagged_builds: dict[str, dict[str, str] | None] | None = None,
+        default_non_owner_build: str | None = None,
         timeout: Timeout = 'short',
     ) -> Actor:
         """Update the Actor with the specified fields.
@@ -162,6 +163,9 @@ class ActorClient(ResourceClient):
             tagged_builds: A dictionary mapping build tag names to their settings. Use it to create, update,
                 or remove build tags. To assign a tag, provide a dict with 'buildId' key. To remove a tag,
                 set its value to None. Example: {'latest': {'buildId': 'abc'}, 'beta': None}.
+            default_non_owner_build: The User Build: tag or number of the successful build that other users
+                of the public Actor run (they can't pick builds). Editable after publishing. Pass an empty
+                string to fall back to the default build.
             timeout: Timeout for the API HTTP request.
 
         Returns:
@@ -200,7 +204,10 @@ class ActorClient(ResourceClient):
             ),
             tagged_builds=tagged_builds,
         )
-        result = self._update(timeout=timeout, **actor_fields.model_dump(by_alias=True, exclude_none=True))
+        payload = actor_fields.model_dump(by_alias=True, exclude_none=True)
+        if default_non_owner_build is not None:
+            payload['defaultNonOwnerBuild'] = default_non_owner_build
+        result = self._update(timeout=timeout, **payload)
         return ActorResponse.model_validate(result).data
 
     def delete(self, *, timeout: Timeout = 'short') -> None:
@@ -417,7 +424,7 @@ class ActorClient(ResourceClient):
         return BuildResponse.model_validate(result).data
 
     def builds(self) -> BuildCollectionClient:
-        """Retrieve a client for the builds of this Actor."""
+        """Retrieve a client for the builds of this Actor (owner only; other users get 403)."""
         return self._client_registry.build_collection_client(
             resource_path='builds',
             **self._base_client_kwargs,
@@ -436,7 +443,7 @@ class ActorClient(ResourceClient):
         wait_for_finish: int | None = None,
         timeout: Timeout = 'short',
     ) -> BuildClient:
-        """Retrieve Actor's default build.
+        """Retrieve Actor's default build (owner only; other users get 403).
 
 
         Args:
@@ -495,11 +502,11 @@ class ActorClient(ResourceClient):
         )
 
     def versions(self) -> ActorVersionCollectionClient:
-        """Retrieve a client for the versions of this Actor."""
+        """Retrieve a client for the versions of this Actor (owner only; other users get 403)."""
         return self._client_registry.actor_version_collection_client(**self._base_client_kwargs)
 
     def version(self, version_number: str) -> ActorVersionClient:
-        """Retrieve the client for the specified version of this Actor.
+        """Retrieve the client for the specified version of this Actor (owner only).
 
         Args:
             version_number: The version number for which to retrieve the resource client.
@@ -613,6 +620,7 @@ class ActorClientAsync(ResourceClientAsync):
         pricing_infos: list[dict[str, Any]] | None = None,
         actor_permission_level: ActorPermissionLevel | None = None,
         tagged_builds: dict[str, dict[str, str] | None] | None = None,
+        default_non_owner_build: str | None = None,
         timeout: Timeout = 'short',
     ) -> Actor:
         """Update the Actor with the specified fields.
@@ -651,6 +659,9 @@ class ActorClientAsync(ResourceClientAsync):
             tagged_builds: A dictionary mapping build tag names to their settings. Use it to create, update,
                 or remove build tags. To assign a tag, provide a dict with 'buildId' key. To remove a tag,
                 set its value to None. Example: {'latest': {'buildId': 'abc'}, 'beta': None}.
+            default_non_owner_build: The User Build: tag or number of the successful build that other users
+                of the public Actor run (they can't pick builds). Editable after publishing. Pass an empty
+                string to fall back to the default build.
             timeout: Timeout for the API HTTP request.
 
         Returns:
@@ -689,7 +700,10 @@ class ActorClientAsync(ResourceClientAsync):
             ),
             tagged_builds=tagged_builds,
         )
-        result = await self._update(timeout=timeout, **actor_fields.model_dump(by_alias=True, exclude_none=True))
+        payload = actor_fields.model_dump(by_alias=True, exclude_none=True)
+        if default_non_owner_build is not None:
+            payload['defaultNonOwnerBuild'] = default_non_owner_build
+        result = await self._update(timeout=timeout, **payload)
         return ActorResponse.model_validate(result).data
 
     async def delete(self, *, timeout: Timeout = 'short') -> None:
@@ -910,7 +924,7 @@ class ActorClientAsync(ResourceClientAsync):
         return BuildResponse.model_validate(result).data
 
     def builds(self) -> BuildCollectionClientAsync:
-        """Retrieve a client for the builds of this Actor."""
+        """Retrieve a client for the builds of this Actor (owner only; other users get 403)."""
         return self._client_registry.build_collection_client(
             resource_path='builds',
             **self._base_client_kwargs,
@@ -929,7 +943,7 @@ class ActorClientAsync(ResourceClientAsync):
         wait_for_finish: int | None = None,
         timeout: Timeout = 'short',
     ) -> BuildClientAsync:
-        """Retrieve Actor's default build.
+        """Retrieve Actor's default build (owner only; other users get 403).
 
 
         Args:
@@ -988,11 +1002,11 @@ class ActorClientAsync(ResourceClientAsync):
         )
 
     def versions(self) -> ActorVersionCollectionClientAsync:
-        """Retrieve a client for the versions of this Actor."""
+        """Retrieve a client for the versions of this Actor (owner only; other users get 403)."""
         return self._client_registry.actor_version_collection_client(**self._base_client_kwargs)
 
     def version(self, version_number: str) -> ActorVersionClientAsync:
-        """Retrieve the client for the specified version of this Actor.
+        """Retrieve the client for the specified version of this Actor (owner only).
 
         Args:
             version_number: The version number for which to retrieve the resource client.

{scrapely_client_python-1.0.0 → scrapely_client_python-1.0.2}/src/scrapely_client/_resource_clients/dataset.py

@@ -305,7 +305,7 @@ class DatasetClient(ResourceClient):
 
 
         Args:
-            item_format: Format of the results, possible values are: json, jsonl, csv, html, xlsx, xml and rss.
+            item_format: Format of the results, possible values are: json, jsonl, csv, html, xlsx, xml, rss and pdf.
                 The default value is json.
             offset: Number of items that should be skipped at the start. The default value is 0.
             limit: Maximum number of items to return. By default there is no limit.
@@ -402,7 +402,7 @@ class DatasetClient(ResourceClient):
 
 
         Args:
-            item_format: Format of the results, possible values are: json, jsonl, csv, html, xlsx, xml and rss.
+            item_format: Format of the results, possible values are: json, jsonl, csv, html, xlsx, xml, rss and pdf.
                 The default value is json.
             offset: Number of items that should be skipped at the start. The default value is 0.
             limit: Maximum number of items to return. By default there is no limit.
@@ -857,7 +857,7 @@ class DatasetClientAsync(ResourceClientAsync):
 
 
         Args:
-            item_format: Format of the results, possible values are: json, jsonl, csv, html, xlsx, xml and rss.
+            item_format: Format of the results, possible values are: json, jsonl, csv, html, xlsx, xml, rss and pdf.
                 The default value is json.
             offset: Number of items that should be skipped at the start. The default value is 0.
             limit: Maximum number of items to return. By default there is no limit.
@@ -954,7 +954,7 @@ class DatasetClientAsync(ResourceClientAsync):
 
 
         Args:
-            item_format: Format of the results, possible values are: json, jsonl, csv, html, xlsx, xml and rss.
+            item_format: Format of the results, possible values are: json, jsonl, csv, html, xlsx, xml, rss and pdf.
                 The default value is json.
             offset: Number of items that should be skipped at the start. The default value is 0.
             limit: Maximum number of items to return. By default there is no limit.

{scrapely_client_python-1.0.0 → scrapely_client_python-1.0.2}/src/scrapely_client/http_clients/_impit.py

@@ -67,7 +67,7 @@ def _is_retryable_error(exc: Exception) -> bool:
 
 @docs_group('HTTP clients')
 class ImpitHttpClient(HttpClient):
-    """Synchronous HTTP client for the Scrapely API built on top of [Impit](https://github.com/apify/impit).
+    """Synchronous HTTP client for the Scrapely API built on top of Impit.
 
     Impit is a high-performance HTTP client written in Rust that provides browser-like TLS fingerprints,
     automatic header ordering, and HTTP/2 support. This client wraps `impit.Client` and adds automatic retries
@@ -222,7 +222,7 @@ class ImpitHttpClient(HttpClient):
 
             # Impit treats timeout=None as "use client default (30s)", not "no timeout".
             # Use a large value (24 hours) to effectively disable the timeout.
-            # This can be removed once impit updates its behaviour: https://github.com/apify/impit/issues/401
+            # This can be removed once impit updates its behaviour.
             computed_timeout = self._compute_timeout(timeout, attempt=attempt)
             impit_timeout = 86_400 if computed_timeout is None else computed_timeout
 
@@ -327,7 +327,7 @@ class ImpitHttpClient(HttpClient):
 
 @docs_group('HTTP clients')
 class ImpitHttpClientAsync(HttpClientAsync):
-    """Asynchronous HTTP client for the Scrapely API built on top of [Impit](https://github.com/apify/impit).
+    """Asynchronous HTTP client for the Scrapely API built on top of Impit.
 
     Impit is a high-performance HTTP client written in Rust that provides browser-like TLS fingerprints,
     automatic header ordering, and HTTP/2 support. This client wraps `impit.AsyncClient` and adds automatic retries
@@ -495,7 +495,7 @@ class ImpitHttpClientAsync(HttpClientAsync):
 
             # Impit treats timeout=None as "use client default (30s)", not "no timeout".
             # Use a large value (24 hours) to effectively disable the timeout.
-            # This can be removed once impit updates its behaviour: https://github.com/apify/impit/issues/401
+            # This can be removed once impit updates its behaviour.
             computed_timeout = self._compute_timeout(timeout, attempt=attempt)
             impit_timeout = 86_400 if computed_timeout is None else computed_timeout
 

scrapely_client_python-1.0.0/CHANGELOG.md

@@ -1,9 +0,0 @@
-# Changelog
-
-All notable changes to this project will be documented in this file.
-
-## [1.0.0] - 2026-09-08
-
-Initial release.
-
-- Python client for the Scrapely API: Actors, runs, datasets, key-value stores, request queues, task management, and webhooks