scraperack 0.1.0a1__tar.gz

scraperack-0.1.0a1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

scraperack-0.1.0a1/PKG-INFO

@@ -0,0 +1,49 @@
+Metadata-Version: 2.4
+Name: scraperack
+Version: 0.1.0a1
+Summary: Python SDK for self-hosted ScrapeRack clusters
+License-Expression: Apache-2.0
+Project-URL: Repository, https://github.com/damadjan/scraperack
+Project-URL: Issues, https://github.com/damadjan/scraperack/issues
+Classifier: Development Status :: 3 - Alpha
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cloudpickle>=3
+Requires-Dist: httpx>=0.27
+Dynamic: license-file
+
+# ScrapeRack SDK
+
+Python client for submitting trusted Python functions to a self-hosted ScrapeRack cluster.
+
+> ScrapeRack is alpha software. Use it on trusted infrastructure and expect breaking changes.
+
+## Install
+
+```sh
+pip install scraperack
+```
+
+## Run a function
+
+The environment must already exist on the cluster.
+
+```python
+from scraperack import Cluster
+
+
+def add(a, b):
+    return a + b
+
+
+cluster = Cluster("http://controller:7070")
+try:
+    execution = cluster.run("python", add, (2, 3))
+    result = cluster.wait(execution["id"])
+    print(result["result"]["value"]["data"])
+finally:
+    cluster.close()
+```
+
+Installation, cluster setup, and source code are available at [github.com/damadjan/scraperack](https://github.com/damadjan/scraperack).

scraperack-0.1.0a1/README.md

@@ -0,0 +1,34 @@
+# ScrapeRack SDK
+
+Python client for submitting trusted Python functions to a self-hosted ScrapeRack cluster.
+
+> ScrapeRack is alpha software. Use it on trusted infrastructure and expect breaking changes.
+
+## Install
+
+```sh
+pip install scraperack
+```
+
+## Run a function
+
+The environment must already exist on the cluster.
+
+```python
+from scraperack import Cluster
+
+
+def add(a, b):
+    return a + b
+
+
+cluster = Cluster("http://controller:7070")
+try:
+    execution = cluster.run("python", add, (2, 3))
+    result = cluster.wait(execution["id"])
+    print(result["result"]["value"]["data"])
+finally:
+    cluster.close()
+```
+
+Installation, cluster setup, and source code are available at [github.com/damadjan/scraperack](https://github.com/damadjan/scraperack).

scraperack-0.1.0a1/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=77"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "scraperack"
+version = "0.1.0a1"
+description = "Python SDK for self-hosted ScrapeRack clusters"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = ["cloudpickle>=3", "httpx>=0.27"]
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+classifiers = ["Development Status :: 3 - Alpha"]
+
+[project.urls]
+Repository = "https://github.com/damadjan/scraperack"
+Issues = "https://github.com/damadjan/scraperack/issues"
+
+[tool.setuptools.package-data]
+scraperack = ["py.typed"]

scraperack-0.1.0a1/scraperack/__init__.py

@@ -0,0 +1,36 @@
+from .client import AsyncCluster, Cluster
+from .types import (
+    EncodedValue,
+    Environment,
+    Execution,
+    ExecutionOutput,
+    ExecutionStatus,
+    Image,
+    ImageView,
+    MicroVM,
+    Node,
+    NodeStatus,
+    Pool,
+    PortProtocol,
+    PortSpec,
+    PublishedPort,
+)
+
+__all__ = [
+    "AsyncCluster",
+    "Cluster",
+    "EncodedValue",
+    "Environment",
+    "Execution",
+    "ExecutionOutput",
+    "ExecutionStatus",
+    "Image",
+    "ImageView",
+    "MicroVM",
+    "Node",
+    "NodeStatus",
+    "Pool",
+    "PortProtocol",
+    "PortSpec",
+    "PublishedPort",
+]

scraperack-0.1.0a1/scraperack/client.py

@@ -0,0 +1,425 @@
+import base64
+import hashlib
+from pathlib import Path
+from typing import Any, Callable, Mapping, Sequence
+
+import cloudpickle
+import httpx
+
+from .types import Environment, Execution, Image, ImageView, MicroVM, Node, Pool, PortSpec
+
+
+def _payload(
+    function: Callable[..., Any], params: Sequence[Any]
+) -> dict[str, Any]:
+    data = cloudpickle.dumps(function)
+    return {
+        "encoding": "python-function",
+        "hash": hashlib.sha256(data).hexdigest(),
+        "function": base64.b64encode(data).decode(),
+        "params": base64.b64encode(cloudpickle.dumps(tuple(params))).decode(),
+    }
+
+
+def _files(files: Mapping[str, str | Path]) -> dict[str, str]:
+    return {
+        name: base64.b64encode(Path(path).read_bytes()).decode()
+        for name, path in files.items()
+    }
+
+
+class Cluster:
+    """Synchronous client for a Scraperack controller."""
+
+    def __init__(self, url: str = "http://127.0.0.1:7070") -> None:
+        """Connect to the controller at ``url``."""
+        self.client = httpx.Client(base_url=url.rstrip("/"))
+
+    def close(self) -> None:
+        """Close the underlying HTTP client."""
+        self.client.close()
+
+    def import_image(
+        self,
+        name: str,
+        reference: str,
+        username: str | None = None,
+        password: str | None = None,
+        kind: str | None = None,
+    ) -> Image:
+        """Import and convert a Docker image from a registry."""
+        return self._post("/v1/images/import", {
+            "name": name,
+            "reference": reference,
+            "username": username,
+            "password": password,
+            "kind": kind,
+        })
+
+    def images(self) -> list[ImageView]:
+        """Return all golden images and their distribution state."""
+        return self._get("/v1/images")
+
+    def delete_image(self, image: str) -> None:
+        """Delete an image by ID."""
+        self._delete(f"/v1/images/{image}")
+
+    def create_pool(
+        self,
+        name: str,
+        image: str,
+        cpu: int | float = 1,
+        memory_mib: int = 512,
+        disk_mib: int = 1024,
+        timeout: int = 300,
+        warm: int = 0,
+        max_instances: int | None = None,
+        idle_timeout: int = 30,
+        reuse: bool = True,
+        network: bool = False,
+        ports: Sequence[PortSpec] = (),
+    ) -> Pool:
+        """Create a pool with execution, concurrency, and idle-VM settings."""
+        return self._post("/v1/pools", {
+            "name": name,
+            "image": image,
+            "warm_instances": warm,
+            "max_instances": max_instances,
+            "cpu_millis": round(cpu * 1000),
+            "memory_mib": memory_mib,
+            "disk_mib": disk_mib,
+            "timeout_secs": timeout,
+            "idle_timeout_secs": idle_timeout,
+            "reuse": reuse,
+            "network": network,
+            "ports": ports,
+        })
+
+    def create_environment(
+        self,
+        name: str,
+        image: str,
+        packages: Sequence[str] = (),
+        cpu: int | float = 1,
+        memory_mib: int = 512,
+        disk_mib: int = 1024,
+        timeout: int = 300,
+        warm: int = 0,
+        max_instances: int | None = None,
+        idle_timeout: int = 30,
+        reuse: bool = True,
+        network: bool = True,
+        preload: Sequence[str] = (),
+    ) -> Environment:
+        """Create a cached Python execution environment."""
+        return self._post("/v1/environments", {
+            "name": name,
+            "image": image,
+            "packages": list(packages),
+            "preload": list(preload),
+            "warm_instances": warm,
+            "max_instances": max_instances,
+            "cpu_millis": round(cpu * 1000),
+            "memory_mib": memory_mib,
+            "disk_mib": disk_mib,
+            "timeout_secs": timeout,
+            "idle_timeout_secs": idle_timeout,
+            "reuse": reuse,
+            "network": network,
+        })
+
+    def environments(self) -> list[Environment]:
+        """Return Python execution environments and cache state."""
+        return self._get("/v1/environments")
+
+    def delete_environment(self, environment: str) -> None:
+        """Delete an inactive execution environment."""
+        self._delete(f"/v1/environments/{environment}")
+
+    def run(
+        self,
+        environment: str,
+        function: Callable[..., Any],
+        params: Sequence[Any] = (),
+        queue: bool = True,
+    ) -> Execution:
+        """Submit a Python function and its positional arguments."""
+        return self.submit(environment, _payload(function, params), queue)
+
+    def delete_pool(self, name: str) -> None:
+        """Delete an inactive pool."""
+        self._delete(f"/v1/pools/{name}")
+
+    def run_json(self, environment: str, payload: Any, queue: bool = True) -> Execution:
+        """Submit a JSON-compatible value as the execution payload."""
+        return self.submit(environment, {"encoding": "json", "data": payload}, queue)
+
+    def run_source(
+        self,
+        environment: str,
+        source: str,
+        params: Sequence[Any] = (),
+        queue: bool = True,
+    ) -> Execution:
+        """Submit Python source that defines ``main(...)``."""
+        return self.submit(environment, {
+            "encoding": "python-source",
+            "source": source,
+            "params": params,
+        }, queue)
+
+    def run_files(
+        self,
+        environment: str,
+        files: Mapping[str, str | Path],
+        command: str | Sequence[str],
+        queue: bool = True,
+    ) -> Execution:
+        """Upload files and run a command inside a temporary directory."""
+        return self.submit(environment, {
+            "encoding": "files",
+            "files": _files(files),
+            "command": command,
+        }, queue)
+
+    def submit(
+        self, environment: str, payload: Mapping[str, Any], queue: bool = True
+    ) -> Execution:
+        """Submit a raw execution payload."""
+        return self._post(
+            "/v1/executions",
+            {"environment": environment, "payload": payload, "queue": queue},
+        )
+
+    def execution(self, execution_id: str) -> Execution:
+        """Return one execution by ID."""
+        return self._get(f"/v1/executions/{execution_id}")
+
+    def wait(self, execution_id: str, interval: float = 0.1) -> Execution:
+        """Wait until an execution succeeds, fails, or times out."""
+        while True:
+            response = self.client.get(f"/v1/executions/{execution_id}/wait", timeout=None)
+            response.raise_for_status()
+            execution = response.json()
+            if execution["status"] in {"succeeded", "failed", "timed_out"}:
+                return execution
+
+    def nodes(self) -> list[Node]:
+        """Return all registered worker nodes."""
+        return self._get("/v1/nodes")
+
+    def vms(self) -> list[MicroVM]:
+        """Return live microVMs and their published ports."""
+        return self._get("/v1/vms")
+
+    def executions(self) -> list[Execution]:
+        """Return all executions."""
+        return self._get("/v1/executions")
+
+    def _get(self, path: str) -> Any:
+        response = self.client.get(path)
+        response.raise_for_status()
+        return response.json()
+
+    def _post(self, path: str, data: Mapping[str, Any]) -> Any:
+        response = self.client.post(path, json=data)
+        response.raise_for_status()
+        return response.json()
+
+    def _delete(self, path: str) -> None:
+        response = self.client.delete(path)
+        response.raise_for_status()
+
+
+class AsyncCluster:
+    """Asynchronous client for a Scraperack controller."""
+
+    def __init__(self, url: str = "http://127.0.0.1:7070") -> None:
+        """Connect to the controller at ``url``."""
+        self.client = httpx.AsyncClient(base_url=url.rstrip("/"))
+
+    async def close(self) -> None:
+        """Close the underlying HTTP client."""
+        await self.client.aclose()
+
+    async def import_image(
+        self,
+        name: str,
+        reference: str,
+        username: str | None = None,
+        password: str | None = None,
+        kind: str | None = None,
+    ) -> Image:
+        """Import and convert a Docker image from a registry."""
+        return await self._post("/v1/images/import", {
+            "name": name,
+            "reference": reference,
+            "username": username,
+            "password": password,
+            "kind": kind,
+        })
+
+    async def create_pool(
+        self,
+        name: str,
+        image: str,
+        cpu: int | float = 1,
+        memory_mib: int = 512,
+        disk_mib: int = 1024,
+        timeout: int = 300,
+        warm: int = 0,
+        max_instances: int | None = None,
+        idle_timeout: int = 30,
+        reuse: bool = True,
+        network: bool = False,
+        ports: Sequence[PortSpec] = (),
+    ) -> Pool:
+        """Create a pool with execution, concurrency, and idle-VM settings."""
+        return await self._post("/v1/pools", {
+            "name": name,
+            "image": image,
+            "warm_instances": warm,
+            "max_instances": max_instances,
+            "cpu_millis": round(cpu * 1000),
+            "memory_mib": memory_mib,
+            "disk_mib": disk_mib,
+            "timeout_secs": timeout,
+            "idle_timeout_secs": idle_timeout,
+            "reuse": reuse,
+            "network": network,
+            "ports": ports,
+        })
+
+    async def create_environment(
+        self,
+        name: str,
+        image: str,
+        packages: Sequence[str] = (),
+        cpu: int | float = 1,
+        memory_mib: int = 512,
+        disk_mib: int = 1024,
+        timeout: int = 300,
+        warm: int = 0,
+        max_instances: int | None = None,
+        idle_timeout: int = 30,
+        reuse: bool = True,
+        network: bool = True,
+        preload: Sequence[str] = (),
+    ) -> Environment:
+        """Create a cached Python execution environment."""
+        return await self._post("/v1/environments", {
+            "name": name,
+            "image": image,
+            "packages": list(packages),
+            "preload": list(preload),
+            "warm_instances": warm,
+            "max_instances": max_instances,
+            "cpu_millis": round(cpu * 1000),
+            "memory_mib": memory_mib,
+            "disk_mib": disk_mib,
+            "timeout_secs": timeout,
+            "idle_timeout_secs": idle_timeout,
+            "reuse": reuse,
+            "network": network,
+        })
+
+    async def environments(self) -> list[Environment]:
+        """Return Python execution environments and cache state."""
+        return await self._get("/v1/environments")
+
+    async def delete_environment(self, environment: str) -> None:
+        """Delete an inactive execution environment."""
+        await self._delete(f"/v1/environments/{environment}")
+
+    async def delete_image(self, image: str) -> None:
+        """Delete an image by ID."""
+        await self._delete(f"/v1/images/{image}")
+
+    async def delete_pool(self, name: str) -> None:
+        """Delete an inactive pool."""
+        await self._delete(f"/v1/pools/{name}")
+
+    async def run(
+        self,
+        environment: str,
+        function: Callable[..., Any],
+        params: Sequence[Any] = (),
+        queue: bool = True,
+    ) -> Execution:
+        """Submit a Python function and its positional arguments."""
+        return await self.submit(environment, _payload(function, params), queue)
+
+    async def run_json(
+        self, environment: str, payload: Any, queue: bool = True
+    ) -> Execution:
+        """Submit a JSON-compatible value as the execution payload."""
+        return await self.submit(environment, {"encoding": "json", "data": payload}, queue)
+
+    async def run_source(
+        self,
+        environment: str,
+        source: str,
+        params: Sequence[Any] = (),
+        queue: bool = True,
+    ) -> Execution:
+        """Submit Python source that defines ``main(...)``."""
+        return await self.submit(environment, {
+            "encoding": "python-source",
+            "source": source,
+            "params": params,
+        }, queue)
+
+    async def run_files(
+        self,
+        environment: str,
+        files: Mapping[str, str | Path],
+        command: str | Sequence[str],
+        queue: bool = True,
+    ) -> Execution:
+        """Upload files and run a command inside a temporary directory."""
+        return await self.submit(environment, {
+            "encoding": "files",
+            "files": _files(files),
+            "command": command,
+        }, queue)
+
+    async def submit(
+        self, environment: str, payload: Mapping[str, Any], queue: bool = True
+    ) -> Execution:
+        """Submit a raw execution payload."""
+        return await self._post("/v1/executions", {
+            "environment": environment,
+            "payload": payload,
+            "queue": queue,
+        })
+
+    async def execution(self, execution_id: str) -> Execution:
+        """Return one execution by ID."""
+        return await self._get(f"/v1/executions/{execution_id}")
+
+    async def wait(self, execution_id: str, interval: float = 0.1) -> Execution:
+        """Wait until an execution succeeds, fails, or times out."""
+        while True:
+            response = await self.client.get(f"/v1/executions/{execution_id}/wait", timeout=None)
+            response.raise_for_status()
+            execution = response.json()
+            if execution["status"] in {"succeeded", "failed", "timed_out"}:
+                return execution
+
+    async def vms(self) -> list[MicroVM]:
+        """Return live microVMs and their published ports."""
+        return await self._get("/v1/vms")
+
+    async def _get(self, path: str) -> Any:
+        response = await self.client.get(path)
+        response.raise_for_status()
+        return response.json()
+
+    async def _post(self, path: str, data: Mapping[str, Any]) -> Any:
+        response = await self.client.post(path, json=data)
+        response.raise_for_status()
+        return response.json()
+
+    async def _delete(self, path: str) -> None:
+        response = await self.client.delete(path)
+        response.raise_for_status()

scraperack-0.1.0a1/scraperack/types.py

@@ -0,0 +1,149 @@
+from typing import Any, Literal, TypedDict
+
+
+NodeStatus = Literal["syncing", "ready"]
+PortProtocol = Literal["tcp", "udp"]
+ExecutionStatus = Literal[
+    "queued", "assigned", "running", "succeeded", "failed", "timed_out"
+]
+
+
+class Image(TypedDict):
+    id: str
+    name: str
+    sha256: str
+    size: int
+    compatible: bool
+    executor: str | None
+    kind: Literal["micro_vm", "runtime"]
+    docker_source: str | None
+
+
+class ImageView(Image):
+    ready: bool
+
+
+class Pool(TypedDict):
+    name: str
+    image: str
+    warm_instances: int
+    max_instances: int | None
+    cpu_millis: int
+    memory_mib: int
+    disk_mib: int
+    timeout_secs: int
+    idle_timeout_secs: int
+    reuse: bool
+    network: bool
+    ports: list["PortSpec"]
+    managed_by: str | None
+    environment: str | None
+    environment_artifact: str | None
+
+
+class Environment(TypedDict):
+    id: str
+    name: str
+    image: str
+    packages: list[str]
+    preload: list[str]
+    artifact: str | None
+    sha256: str | None
+    size: int
+    pool: str
+    warm_instances: int
+    max_instances: int | None
+    cpu_millis: int
+    memory_mib: int
+    disk_mib: int
+    timeout_secs: int
+    idle_timeout_secs: int
+    reuse: bool
+    network: bool
+    ready: bool
+
+
+class PortSpec(TypedDict):
+    name: str
+    guest_port: int
+    host_port: int | None
+    protocol: PortProtocol
+
+
+class PublishedPort(TypedDict):
+    name: str
+    guest_port: int
+    host_port: int
+    protocol: PortProtocol
+
+
+class MicroVM(TypedDict):
+    id: str
+    pool: str
+    status: Literal["idle", "running"]
+    execution: str | None
+    pid: int | None
+    cpu_millis: int
+    memory_mib: int
+    guest_ip: str | None
+    ports: list[PublishedPort]
+    node: str
+    node_name: str
+    node_address: str | None
+    last_seen_ms: int
+    environment: str | None
+
+
+class Node(TypedDict):
+    id: str
+    name: str
+    cpu_millis: int
+    memory_mib: int
+    address: str | None
+    used_cpu_millis: int
+    used_memory_mib: int
+    images: list[str]
+    environments: list[str]
+    idle_instances: dict[str, int]
+    vms: list[MicroVM]
+    status: NodeStatus
+    last_seen_ms: int
+
+
+class EncodedValue(TypedDict):
+    encoding: Literal["json", "cloudpickle"]
+    data: Any
+
+
+class ExecutionOutput(TypedDict, total=False):
+    value: EncodedValue
+    stdout: str
+    stderr: str
+
+
+class ExecutionMetricPoint(TypedDict):
+    elapsed_ms: int
+    cpu_percent: float
+    memory_percent: float
+
+
+class ExecutionMetrics(TypedDict):
+    average_cpu_percent: float
+    average_memory_percent: float
+    peak_memory_percent: float
+    samples: list[ExecutionMetricPoint]
+
+
+class Execution(TypedDict):
+    id: str
+    pool: str
+    node: str | None
+    status: ExecutionStatus
+    payload: Any
+    result: ExecutionOutput | None
+    error: str | None
+    created_at_ms: int
+    started_at_ms: int | None
+    finished_at_ms: int | None
+    environment: str | None
+    metrics: ExecutionMetrics | None

scraperack-0.1.0a1/scraperack.egg-info/PKG-INFO

@@ -0,0 +1,49 @@
+Metadata-Version: 2.4
+Name: scraperack
+Version: 0.1.0a1
+Summary: Python SDK for self-hosted ScrapeRack clusters
+License-Expression: Apache-2.0
+Project-URL: Repository, https://github.com/damadjan/scraperack
+Project-URL: Issues, https://github.com/damadjan/scraperack/issues
+Classifier: Development Status :: 3 - Alpha
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cloudpickle>=3
+Requires-Dist: httpx>=0.27
+Dynamic: license-file
+
+# ScrapeRack SDK
+
+Python client for submitting trusted Python functions to a self-hosted ScrapeRack cluster.
+
+> ScrapeRack is alpha software. Use it on trusted infrastructure and expect breaking changes.
+
+## Install
+
+```sh
+pip install scraperack
+```
+
+## Run a function
+
+The environment must already exist on the cluster.
+
+```python
+from scraperack import Cluster
+
+
+def add(a, b):
+    return a + b
+
+
+cluster = Cluster("http://controller:7070")
+try:
+    execution = cluster.run("python", add, (2, 3))
+    result = cluster.wait(execution["id"])
+    print(result["result"]["value"]["data"])
+finally:
+    cluster.close()
+```
+
+Installation, cluster setup, and source code are available at [github.com/damadjan/scraperack](https://github.com/damadjan/scraperack).

scraperack-0.1.0a1/scraperack.egg-info/SOURCES.txt

@@ -0,0 +1,12 @@
+LICENSE
+README.md
+pyproject.toml
+scraperack/__init__.py
+scraperack/client.py
+scraperack/py.typed
+scraperack/types.py
+scraperack.egg-info/PKG-INFO
+scraperack.egg-info/SOURCES.txt
+scraperack.egg-info/dependency_links.txt
+scraperack.egg-info/requires.txt
+scraperack.egg-info/top_level.txt

scraperack-0.1.0a1/scraperack.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

scraperack-0.1.0a1/scraperack.egg-info/requires.txt

@@ -0,0 +1,2 @@
+cloudpickle>=3
+httpx>=0.27

scraperack-0.1.0a1/scraperack.egg-info/top_level.txt

@@ -0,0 +1 @@
+scraperack

scraperack-0.1.0a1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+