Metadata-Version: 2.4
Name: apify
Version: 3.4.2b21
Summary: Apify SDK for Python
Project-URL: Apify Homepage, https://apify.com
Project-URL: Changelog, https://docs.apify.com/sdk/python/docs/changelog
Project-URL: Discord, https://discord.com/invite/jyEM2PRvMU
Project-URL: Documentation, https://docs.apify.com/sdk/python/docs/overview
Project-URL: Homepage, https://docs.apify.com/sdk/python/
Project-URL: Issue Tracker, https://github.com/apify/apify-sdk-python/issues
Project-URL: Release Notes, https://docs.apify.com/sdk/python/docs/upgrading/upgrading-to-v4
Project-URL: Source Code, https://github.com/apify/apify-sdk-python
Author-email: "Apify Technologies s.r.o." <support@apify.com>
License:                                  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 2023 Apify Technologies s.r.o.
        
           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.
License-File: LICENSE
Keywords: apify,automation,chrome,crawlee,crawler,headless,scraper,scraping,sdk
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Software Development :: Libraries
Classifier: Typing :: Typed
Requires-Python: >=3.11
Requires-Dist: apify-client<4.0.0,>=3.0.0
Requires-Dist: cachetools>=5.5.0
Requires-Dist: crawlee<2.0.0,>=1.0.4
Requires-Dist: cryptography>=42.0.0
Requires-Dist: impit>=0.8.0
Requires-Dist: lazy-object-proxy>=1.11.0
Requires-Dist: more-itertools>=10.2.0
Requires-Dist: pydantic>=2.11.0
Requires-Dist: typing-extensions>=4.4.0
Requires-Dist: websockets>=14.0
Requires-Dist: yarl>=1.18.0
Provides-Extra: scrapy
Requires-Dist: scrapy>=2.14.0; extra == 'scrapy'
Description-Content-Type: text/markdown

<h1 align="center">Apify SDK for Python</h1>

<p align="center">
  <strong>The official Python SDK for building <a href="https://docs.apify.com/platform/actors">Apify Actors</a>.</strong>
</p>

<p align="center">
  <a href="https://pypi.org/project/apify/"><img src="https://badge.fury.io/py/apify.svg" alt="PyPI version"></a>
  <a href="https://pypi.org/project/apify/"><img src="https://img.shields.io/pypi/dm/apify" alt="PyPI downloads"></a>
  <a href="https://pypi.org/project/apify/"><img src="https://img.shields.io/badge/python-3.11%2B-blue" alt="Python versions"></a>
  <a href="https://github.com/apify/apify-sdk-python/actions/workflows/on_master.yaml"><img src="https://github.com/apify/apify-sdk-python/actions/workflows/on_master.yaml/badge.svg?branch=master" alt="Build status"></a>
  <a href="https://codecov.io/gh/apify/apify-sdk-python"><img src="https://codecov.io/gh/apify/apify-sdk-python/graph/badge.svg?token=Y6JBIZQFT6" alt="Coverage"></a>
  <a href="https://github.com/apify/apify-sdk-python/blob/master/LICENSE"><img src="https://img.shields.io/pypi/l/apify" alt="License"></a>
  <a href="https://discord.gg/jyEM2PRvMU"><img src="https://img.shields.io/discord/801163717915574323?label=discord" alt="Chat on Discord"></a>
</p>

`apify` is the official SDK for building [Apify Actors](https://docs.apify.com/platform/actors) in Python. It handles the Actor lifecycle, [storage](https://docs.apify.com/platform/storage) access, platform events, [Apify Proxy](https://docs.apify.com/platform/proxy), pay-per-event charging, and more.

> If you only need to **consume** the [Apify API](https://docs.apify.com/api/v2) from Python (running Actors, reading datasets, managing storages) rather than building Actors, use the [Apify API client for Python](https://docs.apify.com/api/client/python) instead. It comes bundled with this SDK.

## Table of contents

- [Installation](#installation)
- [Quick start](#quick-start)
- [What are Actors?](#what-are-actors)
- [Features](#features)
- [What you can build](#what-you-can-build)
- [Usage examples](#usage-examples)
- [Documentation](#documentation)
- [Related projects](#related-projects)
- [Support and community](#support-and-community)
- [Contributing](#contributing)
- [License](#license)

## Installation

The Apify SDK for Python requires **Python 3.11 or higher**. It is published on [PyPI](https://pypi.org/project/apify/) as the `apify` package and can be installed with [pip](https://pip.pypa.io/):

```bash
pip install apify
```

or with [uv](https://docs.astral.sh/uv/):

```bash
uv add apify
```

To use the Scrapy integration, install the `scrapy` extra:

```bash
pip install 'apify[scrapy]'
```

## Quick start

An Actor is a Python program that runs inside the `async with Actor:` context. The context initializes the Actor when it starts and tears it down when it finishes. Here's a minimal Actor that reads its input and stores a result:

```python
from apify import Actor


async def main() -> None:
    async with Actor:
        actor_input = await Actor.get_input()
        Actor.log.info('Actor input: %s', actor_input)
        await Actor.set_value('OUTPUT', 'Hello, world!')
```

The quickest way to scaffold a full Actor project, with the `.actor` configuration, input schema, and Dockerfile already in place, is the [Apify CLI](https://docs.apify.com/cli):

1. Install the CLI:

    ```bash
    npm install -g apify-cli
    ```

2. Create a new Actor from the Python "getting started" template:

    ```bash
    apify create my-actor --template python-start
    ```

3. Run it locally:

    ```bash
    cd my-actor
    apify run
    ```

To create, run, and deploy your first Actor step by step, see the [Quick start guide](https://docs.apify.com/sdk/python/docs/quick-start).

## What are Actors?

Actors are serverless cloud programs that can do almost anything a human can do in a web browser. They range from small tasks, such as filling in forms or unsubscribing from online services, all the way up to scraping and processing vast numbers of web pages.

They run either locally or on the [Apify platform](https://docs.apify.com/platform/), where you can run them at scale, monitor them, schedule them, or publish and monetize them. If you're new to Apify, learn [what Apify is](https://docs.apify.com/platform/about) in the platform documentation.

## Features

- Run the full Actor lifecycle inside `async with Actor:`, covering init, exit, failures, status messages, and reboots ([Actor lifecycle](https://docs.apify.com/sdk/python/docs/concepts/actor-lifecycle)).
- Read Actor input validated against your input schema with `Actor.get_input()` ([Actor input](https://docs.apify.com/sdk/python/docs/concepts/actor-input)).
- Read and write datasets, key-value stores, and request queues, locally or on the platform ([Working with storages](https://docs.apify.com/sdk/python/docs/concepts/storages)).
- React to platform events such as system info, migration, and abort ([Actor events](https://docs.apify.com/sdk/python/docs/concepts/actor-events)).
- Route requests through Apify Proxy with group selection, country targeting, and rotation ([Proxy management](https://docs.apify.com/sdk/python/docs/concepts/proxy-management)).
- Start, call, abort, and metamorph other Actors and tasks, and attach webhooks to run events ([Interacting with other Actors](https://docs.apify.com/sdk/python/docs/concepts/interacting-with-other-actors), [Webhooks](https://docs.apify.com/sdk/python/docs/concepts/webhooks)).
- Monetize your Actor with pay-per-event charging ([Pay-per-event](https://docs.apify.com/sdk/python/docs/concepts/pay-per-event)).
- Reach the full [Apify API](https://docs.apify.com/api/v2) through a preconfigured `ApifyClient` ([Accessing the Apify API](https://docs.apify.com/sdk/python/docs/concepts/access-apify-api)).

## What you can build

Almost any Python project can become an Actor, including projects for:

- **Web scraping and crawling** — The SDK is fully compatible with [Crawlee](https://crawlee.dev/python), which makes Apify a natural place to deploy and scale your crawlers (see the [Crawlee guide](https://docs.apify.com/sdk/python/docs/guides/crawlee)). It also works with other popular scraping libraries, such as [Scrapy](https://docs.apify.com/sdk/python/docs/guides/scrapy), [Scrapling](https://docs.apify.com/sdk/python/docs/guides/scrapling), or [Crawl4AI](https://docs.apify.com/sdk/python/docs/guides/crawl4ai).
- **Browser automation** — Drive a real browser with [Playwright](https://docs.apify.com/sdk/python/docs/guides/playwright) or [Selenium](https://docs.apify.com/sdk/python/docs/guides/selenium), or with higher-level tools such as [Browser Use](https://docs.apify.com/sdk/python/docs/guides/browser-use).
- **Web servers and APIs** — Run a [web server](https://docs.apify.com/sdk/python/docs/guides/running-webserver) inside an Actor to serve HTTP requests, for example to expose your scraper as a live API.
- **AI agents** — Host agents built with your framework of choice. Ready-made Actor templates cover [PydanticAI](https://apify.com/templates/python-pydanticai), [CrewAI](https://apify.com/templates/python-crewai), [LangGraph](https://apify.com/templates/python-langgraph), [LlamaIndex](https://apify.com/templates/python-llamaindex-agent), and [Smolagents](https://apify.com/templates/python-smolagents).
- **MCP servers** — Deploy a Python MCP server as an Actor and make its tools available to any MCP client. See [MCP server](https://apify.com/templates/python-mcp-empty) and [MCP proxy](https://apify.com/templates/python-mcp-proxy) templates

Whatever you build, the Apify SDK doesn't lock you into a particular framework. Bring the libraries you already use, and let Apify run your project in the cloud.

## Usage examples

The examples below show two common setups, but the same `async with Actor:` pattern works with any stack. For more, see the [guides](https://docs.apify.com/sdk/python/docs/guides/beautifulsoup-httpx).

### HTTPX with BeautifulSoup

Scrape pages with [HTTPX](https://www.python-httpx.org/) and [BeautifulSoup](https://pypi.org/project/beautifulsoup4/), using the Actor's request queue to track URLs:

```python
from bs4 import BeautifulSoup
from httpx import AsyncClient

from apify import Actor


async def main() -> None:
    async with Actor:
        actor_input = await Actor.get_input() or {}
        start_urls = actor_input.get('start_urls', [{'url': 'https://apify.com'}])

        # Enqueue the start URLs into the default request queue.
        request_queue = await Actor.open_request_queue()
        for start_url in start_urls:
            await request_queue.add_request(start_url['url'])

        # Process the queue until it's empty.
        while request := await request_queue.fetch_next_request():
            Actor.log.info(f'Scraping {request.url} ...')
            async with AsyncClient() as client:
                response = await client.get(request.url)
            soup = BeautifulSoup(response.content, 'html.parser')

            # Push the extracted data to the default dataset.
            await Actor.push_data({
                'url': request.url,
                'title': soup.title.string if soup.title else None,
            })
```

### Crawlee with Playwright

Scrape pages with [Crawlee](https://crawlee.dev/python)'s `PlaywrightCrawler`, which handles queueing, concurrency, and the browser for you:

```python
from crawlee.crawlers import PlaywrightCrawler, PlaywrightCrawlingContext

from apify import Actor


async def main() -> None:
    async with Actor:
        actor_input = await Actor.get_input() or {}
        start_urls = [url['url'] for url in actor_input.get('start_urls', [{'url': 'https://apify.com'}])]

        crawler = PlaywrightCrawler(max_requests_per_crawl=50, headless=True)

        @crawler.router.default_handler
        async def handler(context: PlaywrightCrawlingContext) -> None:
            Actor.log.info(f'Scraping {context.request.url} ...')
            await context.push_data({
                'url': context.request.url,
                'title': await context.page.title(),
            })
            # Follow links found on the page.
            await context.enqueue_links()

        await crawler.run(start_urls)
```

## Documentation

The full SDK documentation lives at **[docs.apify.com/sdk/python](https://docs.apify.com/sdk/python)**. For the Apify platform itself, see the [Apify documentation](https://docs.apify.com/).

| Section | What you'll find |
|---|---|
| [Overview](https://docs.apify.com/sdk/python/docs/overview) | What the SDK is, what Actors are, and how the pieces fit together. |
| [Quick start](https://docs.apify.com/sdk/python/docs/quick-start) | Create, run, and deploy your first Python Actor. |
| [Concepts](https://docs.apify.com/sdk/python/docs/concepts/actor-lifecycle) | Actor lifecycle, input, storages, events, proxy management, interacting with other Actors, webhooks, accessing the Apify API, logging, configuration, and pay-per-event. |
| [Guides](https://docs.apify.com/sdk/python/docs/guides/beautifulsoup-httpx) | Integrations with BeautifulSoup, Parsel, Playwright, Selenium, Crawlee, Scrapy, Crawl4AI, and Browser Use, plus running a web server and using uv. |
| [Upgrading](https://docs.apify.com/sdk/python/docs/upgrading/upgrading-to-v4) | Migrating between major versions. |
| [API reference](https://docs.apify.com/sdk/python/reference) | Generated reference for every class and method. |
| [Changelog](https://docs.apify.com/sdk/python/docs/changelog) | Release history and breaking changes. |

## Related projects

- **[Apify API client for Python](https://docs.apify.com/api/client/python)** — talk to the Apify API directly from Python (bundled with this SDK).
- **[Crawlee for Python](https://crawlee.dev/python)** — web scraping and browser automation framework; fully compatible with this SDK.
- **[Apify SDK for JavaScript / TypeScript](https://docs.apify.com/sdk/js)** — the equivalent SDK for Node.js.
- **[Apify API client for JavaScript / TypeScript](https://docs.apify.com/api/client/js)** — the equivalent API client for Node.js.
- **[Crawlee for JavaScript / TypeScript](https://crawlee.dev)** — the original Node.js implementation of Crawlee.
- **[Apify CLI](https://docs.apify.com/cli)** — command-line tool for creating, running, and deploying Actors locally and on the platform.

## Support and community

- **Discord** — chat with the team and other users on the [Apify Discord server](https://discord.gg/jyEM2PRvMU).
- **GitHub issues** — report a bug or request a feature in the [issue tracker](https://github.com/apify/apify-sdk-python/issues).

## Contributing

Bug reports, fixes, and improvements are welcome! See [CONTRIBUTING.md](./CONTRIBUTING.md) for the development setup, coding standards, testing, and release process. The project uses [uv](https://docs.astral.sh/uv/) for project management and [Poe the Poet](https://poethepoet.natn.io/) as a task runner; the typical loop is:

```bash
uv run poe install-dev   # install dev dependencies and git hooks
uv run poe check-code    # lint, type-check, and unit tests
```

## License

Released under the [Apache License 2.0](./LICENSE).
