apify 2.7.1b10__tar.gz → 2.7.1b12__tar.gz

{apify-2.7.1b10 → apify-2.7.1b12}/.github/workflows/build_and_deploy_docs.yaml

@@ -27,7 +27,7 @@ jobs:
           token: ${{ secrets.APIFY_SERVICE_ACCOUNT_GITHUB_TOKEN }}
 
       - name: Set up Node
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v5
         with:
           node-version: ${{ env.NODE_VERSION }}
           cache: npm
@@ -50,7 +50,7 @@ jobs:
           git push
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 

{apify-2.7.1b10 → apify-2.7.1b12}/CHANGELOG.md

@@ -8,6 +8,7 @@ All notable changes to this project will be documented in this file.
 ### 🚀 Features
 
 - Add deduplication to `add_batch_of_requests` ([#534](https://github.com/apify/apify-sdk-python/pull/534)) ([dd03c4d](https://github.com/apify/apify-sdk-python/commit/dd03c4d446f611492adf35f1b5738648ee5a66f7)) by [@Pijukatel](https://github.com/Pijukatel), closes [#514](https://github.com/apify/apify-sdk-python/issues/514)
+- Add new methods to ChargingManager ([#580](https://github.com/apify/apify-sdk-python/pull/580)) ([54f7f8b](https://github.com/apify/apify-sdk-python/commit/54f7f8b29c5982be98b595dac11eceff915035c9)) by [@vdusek](https://github.com/vdusek)
 
 ### 🐛 Bug Fixes
 
@@ -52,6 +53,30 @@ All notable changes to this project will be documented in this file.
 - Tagline overlap ([#501](https://github.com/apify/apify-sdk-python/pull/501)) ([bae8340](https://github.com/apify/apify-sdk-python/commit/bae8340c46fea756ea35ea4d591da84c09d478e2)) by [@katzino](https://github.com/katzino)
 
 
+## [2.7.0](https://github.com/apify/apify-sdk-python/releases/tag/v2.7.0) (2025-07-14)
+
+### 🚀 Features
+
+- **crypto:** Decrypt secret objects ([#482](https://github.com/apify/apify-sdk-python/pull/482)) ([ce9daf7](https://github.com/apify/apify-sdk-python/commit/ce9daf7381212b8dc194e8a643e5ca0dedbc0078)) by [@MFori](https://github.com/MFori)
+
+### 🐛 Bug Fixes
+
+- Sync `@docusaurus` theme version [internal] ([#500](https://github.com/apify/apify-sdk-python/pull/500)) ([a7485e7](https://github.com/apify/apify-sdk-python/commit/a7485e7d2276fde464ce862573d5b95e7d4d836a)) by [@katzino](https://github.com/katzino)
+- Tagline overlap ([#501](https://github.com/apify/apify-sdk-python/pull/501)) ([bae8340](https://github.com/apify/apify-sdk-python/commit/bae8340c46fea756ea35ea4d591da84c09d478e2)) by [@katzino](https://github.com/katzino)
+
+
+## [2.7.0](https://github.com/apify/apify-sdk-python/releases/tag/v2.7.0) (2025-07-14)
+
+### 🚀 Features
+
+- **crypto:** Decrypt secret objects ([#482](https://github.com/apify/apify-sdk-python/pull/482)) ([ce9daf7](https://github.com/apify/apify-sdk-python/commit/ce9daf7381212b8dc194e8a643e5ca0dedbc0078)) by [@MFori](https://github.com/MFori)
+
+### 🐛 Bug Fixes
+
+- Sync `@docusaurus` theme version [internal] ([#500](https://github.com/apify/apify-sdk-python/pull/500)) ([a7485e7](https://github.com/apify/apify-sdk-python/commit/a7485e7d2276fde464ce862573d5b95e7d4d836a)) by [@katzino](https://github.com/katzino)
+- Tagline overlap ([#501](https://github.com/apify/apify-sdk-python/pull/501)) ([bae8340](https://github.com/apify/apify-sdk-python/commit/bae8340c46fea756ea35ea4d591da84c09d478e2)) by [@katzino](https://github.com/katzino)
+
+
 
 ## [2.7.3](https://github.com/apify/apify-sdk-python/releases/tag/v2.7.3) (2025-08-11)
 

{apify-2.7.1b10 → apify-2.7.1b12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: apify
-Version: 2.7.1b10
+Version: 2.7.1b12
 Summary: Apify SDK for Python
 Project-URL: Apify Homepage, https://apify.com
 Project-URL: Changelog, https://docs.apify.com/sdk/python/docs/changelog
@@ -240,7 +240,22 @@ Provides-Extra: scrapy
 Requires-Dist: scrapy>=2.11.0; extra == 'scrapy'
 Description-Content-Type: text/markdown
 
-# Apify SDK for Python
+<h1 align=center>Apify SDK for Python</h1>
+
+<p align=center>
+    <a href="https://badge.fury.io/py/apify" rel="nofollow">
+        <img src="https://badge.fury.io/py/apify.svg" alt="PyPI version" style="max-width: 100%;">
+    </a>
+    <a href="https://pypi.org/project/apify/" rel="nofollow">
+        <img src="https://img.shields.io/pypi/dm/apify" alt="PyPI - Downloads" style="max-width: 100%;">
+    </a>
+    <a href="https://pypi.org/project/apify/" rel="nofollow">
+        <img src="https://img.shields.io/pypi/pyversions/apify" alt="PyPI - Python Version" style="max-width: 100%;">
+    </a>
+    <a href="https://discord.gg/jyEM2PRvMU" rel="nofollow">
+        <img src="https://img.shields.io/discord/801163717915574323?label=discord" alt="Chat on discord" style="max-width: 100%;">
+    </a>
+</p>
 
 The Apify SDK for Python is the official library to create [Apify Actors](https://docs.apify.com/platform/actors)
 in Python. It provides useful features like Actor lifecycle management, local storage emulation, and Actor

{apify-2.7.1b10 → apify-2.7.1b12}/README.md

@@ -1,4 +1,19 @@
-# Apify SDK for Python
+<h1 align=center>Apify SDK for Python</h1>
+
+<p align=center>
+    <a href="https://badge.fury.io/py/apify" rel="nofollow">
+        <img src="https://badge.fury.io/py/apify.svg" alt="PyPI version" style="max-width: 100%;">
+    </a>
+    <a href="https://pypi.org/project/apify/" rel="nofollow">
+        <img src="https://img.shields.io/pypi/dm/apify" alt="PyPI - Downloads" style="max-width: 100%;">
+    </a>
+    <a href="https://pypi.org/project/apify/" rel="nofollow">
+        <img src="https://img.shields.io/pypi/pyversions/apify" alt="PyPI - Python Version" style="max-width: 100%;">
+    </a>
+    <a href="https://discord.gg/jyEM2PRvMU" rel="nofollow">
+        <img src="https://img.shields.io/discord/801163717915574323?label=discord" alt="Chat on discord" style="max-width: 100%;">
+    </a>
+</p>
 
 The Apify SDK for Python is the official library to create [Apify Actors](https://docs.apify.com/platform/actors)
 in Python. It provides useful features like Actor lifecycle management, local storage emulation, and Actor

apify-2.7.1b12/docs/03_guides/01_beautifulsoup_httpx.mdx

@@ -0,0 +1,30 @@
+---
+id: beautifulsoup-httpx
+title: Using BeautifulSoup with HTTPX
+---
+
+import CodeBlock from '@theme/CodeBlock';
+
+import BeautifulSoupHttpxExample from '!!raw-loader!./code/01_beautifulsoup_httpx.py';
+
+In this guide, you'll learn how to use the [BeautifulSoup](https://www.crummy.com/software/BeautifulSoup/) library with the [HTTPX](https://www.python-httpx.org/) library in your Apify Actors.
+
+## Introduction
+
+[BeautifulSoup](https://www.crummy.com/software/BeautifulSoup/) is a Python library for extracting data from HTML and XML files. It provides simple methods and Pythonic idioms for navigating, searching, and modifying a website's element tree, enabling efficient data extraction.
+
+[HTTPX](https://www.python-httpx.org/) is a modern, high-level HTTP client library for Python. It provides a simple interface for making HTTP requests and supports both synchronous and asynchronous requests.
+
+To create an Actor which uses those libraries, start from the [BeautifulSoup & Python](https://apify.com/templates/categories/python) Actor template. This template includes the [BeautifulSoup](https://www.crummy.com/software/BeautifulSoup/) and [HTTPX](https://www.python-httpx.org/) libraries preinstalled, allowing you to begin development immediately.
+
+## Example Actor
+
+Below is a simple Actor that recursively scrapes titles from all linked websites, up to a specified maximum depth, starting from URLs provided in the Actor input. It uses [HTTPX](https://www.python-httpx.org/) for fetching pages and [BeautifulSoup](https://www.crummy.com/software/BeautifulSoup/) for parsing their content to extract titles and links to other pages.
+
+<CodeBlock className="language-python">
+    {BeautifulSoupHttpxExample}
+</CodeBlock>
+
+## Conclusion
+
+In this guide, you learned how to use the [BeautifulSoup](https://www.crummy.com/software/BeautifulSoup/) with the [HTTPX](https://www.python-httpx.org/) in your Apify Actors. By combining these libraries, you can efficiently extract data from HTML or XML files, making it easy to build web scraping tasks in Python. See the [Actor templates](https://apify.com/templates/categories/python) to get started with your own scraping tasks. If you have questions or need assistance, feel free to reach out on our [GitHub](https://github.com/apify/apify-sdk-python) or join our [Discord community](https://discord.com/invite/jyEM2PRvMU). Happy scraping!

apify-2.7.1b12/docs/03_guides/02_parsel_impit.mdx

@@ -0,0 +1,28 @@
+---
+id: parsel-impit
+title: Using Parsel with Impit
+---
+
+import CodeBlock from '@theme/CodeBlock';
+
+import ParselImpitExample from '!!raw-loader!./code/02_parsel_impit.py';
+
+In this guide, you'll learn how to combine the [Parsel](https://github.com/scrapy/parsel) and [Impit](https://github.com/apify/impit) libraries when building Apify Actors.
+
+## Introduction
+
+[Parsel](https://github.com/scrapy/parsel) is a Python library for extracting data from HTML and XML documents using CSS selectors and [XPath](https://en.wikipedia.org/wiki/XPath) expressions. It offers an intuitive API for navigating and extracting structured data, making it a popular choice for web scraping. Compared to [BeautifulSoup](https://www.crummy.com/software/BeautifulSoup/), it also delivers better performance.
+
+[Impit](https://github.com/apify/impit) is Apify's high-performance HTTP client for Python. It supports both synchronous and asynchronous workflows and is built for large-scale web scraping, where making thousands of requests efficiently is essential. With built-in browser impersonation and anti-blocking features, it simplifies handling modern websites.
+
+## Example Actor
+
+The following example shows a simple Actor that recursively scrapes titles from linked pages, up to a user-defined maximum depth. It uses [Impit](https://github.com/apify/impit) to fetch pages and [Parsel](https://github.com/scrapy/parsel) to extract titles and discover new links.
+
+<CodeBlock className="language-python">
+    {ParselImpitExample}
+</CodeBlock>
+
+## Conclusion
+
+In this guide, you learned how to use [Parsel](https://github.com/scrapy/parsel) with [Impit](https://github.com/apify/impit) in your Apify Actors. By combining these libraries, you get a powerful and efficient solution for web scraping: [Parsel](https://github.com/scrapy/parsel) provides excellent CSS selector and XPath support for data extraction, while [Impit](https://github.com/apify/impit) offers a fast and simple HTTP client built by Apify. This combination makes it easy to build scalable web scraping tasks in Python. See the [Actor templates](https://apify.com/templates/categories/python) to get started with your own scraping tasks. If you have questions or need assistance, feel free to reach out on our [GitHub](https://github.com/apify/apify-sdk-python) or join our [Discord community](https://discord.com/invite/jyEM2PRvMU). Happy scraping!

apify-2.7.1b12/docs/03_guides/05_crawlee.mdx

@@ -0,0 +1,46 @@
+---
+id: crawlee
+title: Using Crawlee
+---
+
+import CodeBlock from '@theme/CodeBlock';
+
+import CrawleeBeautifulSoupExample from '!!raw-loader!./code/05_crawlee_beautifulsoup.py';
+import CrawleeParselExample from '!!raw-loader!./code/05_crawlee_parsel.py';
+import CrawleePlaywrightExample from '!!raw-loader!./code/05_crawlee_playwright.py';
+
+In this guide you'll learn how to use the [Crawlee](https://crawlee.dev/python) library in your Apify Actors.
+
+## Introduction
+
+[Crawlee](https://crawlee.dev/python) is a Python library for web scraping and browser automation that provides a robust and flexible framework for building web scraping tasks. It seamlessly integrates with the Apify platform and supports a variety of scraping techniques, from static HTML parsing to dynamic JavaScript-rendered content handling. Crawlee offers a range of crawlers, including HTTP-based crawlers like [`HttpCrawler`](https://crawlee.dev/python/api/class/HttpCrawler), [`BeautifulSoupCrawler`](https://crawlee.dev/python/api/class/BeautifulSoupCrawler) and [`ParselCrawler`](https://crawlee.dev/python/api/class/ParselCrawler), and browser-based crawlers like [`PlaywrightCrawler`](https://crawlee.dev/python/api/class/PlaywrightCrawler), to suit different scraping needs.
+
+In this guide, you'll learn how to use Crawlee with [`BeautifulSoupCrawler`](https://crawlee.dev/python/api/class/BeautifulSoupCrawler), [`ParselCrawler`](https://crawlee.dev/python/api/class/ParselCrawler), and [`PlaywrightCrawler`](https://crawlee.dev/python/api/class/PlaywrightCrawler) to build Apify Actors for web scraping.
+
+## Actor with BeautifulSoupCrawler
+
+The [`BeautifulSoupCrawler`](https://crawlee.dev/python/api/class/BeautifulSoupCrawler) is ideal for extracting data from static HTML pages. It uses [BeautifulSoup](https://www.crummy.com/software/BeautifulSoup/bs4/doc/) for parsing and [`ImpitHttpClient`](https://crawlee.dev/python/api/class/ImpitHttpClient) for HTTP communication, ensuring efficient and lightweight scraping. If you do not need to execute JavaScript on the page, [`BeautifulSoupCrawler`](https://crawlee.dev/python/api/class/BeautifulSoupCrawler) is a great choice for your scraping tasks. Below is an example of how to use it` in an Apify Actor.
+
+<CodeBlock className="language-python">
+    {CrawleeBeautifulSoupExample}
+</CodeBlock>
+
+## Actor with ParselCrawler
+
+The [`ParselCrawler`](https://crawlee.dev/python/api/class/ParselCrawler) works in the same way as [`BeautifulSoupCrawler`](https://crawlee.dev/python/api/class/BeautifulSoupCrawler), but it uses the [Parsel](https://parsel.readthedocs.io/en/latest/) library for HTML parsing. This allows for more powerful and flexible data extraction using [XPath](https://en.wikipedia.org/wiki/XPath) selectors. It should be faster than [`BeautifulSoupCrawler`](https://crawlee.dev/python/api/class/BeautifulSoupCrawler). Below is an example of how to use [`ParselCrawler`](https://crawlee.dev/python/api/class/ParselCrawler) in an Apify Actor.
+
+<CodeBlock className="language-python">
+    {CrawleeParselExample}
+</CodeBlock>
+
+## Actor with PlaywrightCrawler
+
+The [`PlaywrightCrawler`](https://crawlee.dev/python/api/class/PlaywrightCrawler) is built for handling dynamic web pages that rely on JavaScript for content rendering. Using the [Playwright](https://playwright.dev/) library, it provides a browser-based automation environment to interact with complex websites. Below is an example of how to use [`PlaywrightCrawler`](https://crawlee.dev/python/api/class/PlaywrightCrawler) in an Apify Actor.
+
+<CodeBlock className="language-python">
+    {CrawleePlaywrightExample}
+</CodeBlock>
+
+## Conclusion
+
+In this guide, you learned how to use the [Crawlee](https://crawlee.dev/python) library in your Apify Actors. By using the [`BeautifulSoupCrawler`](https://crawlee.dev/python/api/class/BeautifulSoupCrawler), [`ParselCrawler`](https://crawlee.dev/python/api/class/ParselCrawler), and [`PlaywrightCrawler`](https://crawlee.dev/python/api/class/PlaywrightCrawler) crawlers, you can efficiently scrape static or dynamic web pages, making it easy to build web scraping tasks in Python. See the [Actor templates](https://apify.com/templates/categories/python) to get started with your own scraping tasks. If you have questions or need assistance, feel free to reach out on our [GitHub](https://github.com/apify/apify-sdk-python) or join our [Discord community](https://discord.com/invite/jyEM2PRvMU). Happy scraping!

{apify-2.7.1b10/docs/02_guides → apify-2.7.1b12/docs/03_guides}/code/01_beautifulsoup_httpx.py

@@ -1,9 +1,8 @@
-from __future__ import annotations
-
+import asyncio
 from urllib.parse import urljoin
 
+import httpx
 from bs4 import BeautifulSoup
-from httpx import AsyncClient
 
 from apify import Actor, Request
 
@@ -32,7 +31,7 @@ async def main() -> None:
             await request_queue.add_request(new_request)
 
         # Create an HTTPX client to fetch the HTML content of the URLs.
-        async with AsyncClient() as client:
+        async with httpx.AsyncClient() as client:
             # Process the URLs from the request queue.
             while request := await request_queue.fetch_next_request():
                 url = request.url
@@ -83,3 +82,7 @@ async def main() -> None:
                 finally:
                     # Mark the request as handled to ensure it is not processed again.
                     await request_queue.mark_request_as_handled(new_request)
+
+
+if __name__ == '__main__':
+    asyncio.run(main())

apify-2.7.1b12/docs/03_guides/code/02_parsel_impit.py

@@ -0,0 +1,94 @@
+import asyncio
+from urllib.parse import urljoin
+
+import impit
+import parsel
+
+from apify import Actor, Request
+
+
+async def main() -> None:
+    # Enter the context of the Actor.
+    async with Actor:
+        # Retrieve the Actor input, and use default values if not provided.
+        actor_input = await Actor.get_input() or {}
+        start_urls = actor_input.get('start_urls', [{'url': 'https://apify.com'}])
+        max_depth = actor_input.get('max_depth', 1)
+
+        # Exit if no start URLs are provided.
+        if not start_urls:
+            Actor.log.info('No start URLs specified in Actor input, exiting...')
+            await Actor.exit()
+
+        # Open the default request queue for handling URLs to be processed.
+        request_queue = await Actor.open_request_queue()
+
+        # Enqueue the start URLs with an initial crawl depth of 0.
+        for start_url in start_urls:
+            url = start_url.get('url')
+            Actor.log.info(f'Enqueuing {url} ...')
+            new_request = Request.from_url(url, user_data={'depth': 0})
+            await request_queue.add_request(new_request)
+
+        # Create an Impit client to fetch the HTML content of the URLs.
+        async with impit.AsyncClient() as client:
+            # Process the URLs from the request queue.
+            while request := await request_queue.fetch_next_request():
+                url = request.url
+
+                if not isinstance(request.user_data['depth'], (str, int)):
+                    raise TypeError('Request.depth is an unexpected type.')
+
+                depth = int(request.user_data['depth'])
+                Actor.log.info(f'Scraping {url} (depth={depth}) ...')
+
+                try:
+                    # Fetch the HTTP response from the specified URL using Impit.
+                    response = await client.get(url)
+
+                    # Parse the HTML content using Parsel Selector.
+                    selector = parsel.Selector(text=response.text)
+
+                    # If the current depth is less than max_depth, find nested links
+                    # and enqueue them.
+                    if depth < max_depth:
+                        # Extract all links using CSS selector
+                        links = selector.css('a::attr(href)').getall()
+                        for link_href in links:
+                            link_url = urljoin(url, link_href)
+
+                            if link_url.startswith(('http://', 'https://')):
+                                Actor.log.info(f'Enqueuing {link_url} ...')
+                                new_request = Request.from_url(
+                                    link_url,
+                                    user_data={'depth': depth + 1},
+                                )
+                                await request_queue.add_request(new_request)
+
+                    # Extract the desired data using Parsel selectors.
+                    title = selector.css('title::text').get()
+                    h1s = selector.css('h1::text').getall()
+                    h2s = selector.css('h2::text').getall()
+                    h3s = selector.css('h3::text').getall()
+
+                    data = {
+                        'url': url,
+                        'title': title,
+                        'h1s': h1s,
+                        'h2s': h2s,
+                        'h3s': h3s,
+                    }
+
+                    # Store the extracted data to the default dataset.
+                    await Actor.push_data(data)
+
+                except Exception:
+                    Actor.log.exception(f'Cannot extract data from {url}.')
+
+                finally:
+                    # Mark the request as handled to ensure it is not processed again.
+                    await request_queue.mark_request_as_handled(request)
+
+
+if __name__ == '__main__':
+    asyncio.run(main())

{apify-2.7.1b10/docs/02_guides → apify-2.7.1b12/docs/03_guides}/code/03_playwright.py

@@ -1,5 +1,4 @@
-from __future__ import annotations
-
+import asyncio
 from urllib.parse import urljoin
 
 from playwright.async_api import async_playwright
@@ -92,3 +91,7 @@ async def main() -> None:
                     await page.close()
                     # Mark the request as handled to ensure it is not processed again.
                     await request_queue.mark_request_as_handled(request)
+
+
+if __name__ == '__main__':
+    asyncio.run(main())

{apify-2.7.1b10/docs/02_guides → apify-2.7.1b12/docs/03_guides}/code/04_selenium.py

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 import asyncio
 from urllib.parse import urljoin
 
@@ -102,3 +100,7 @@ async def main() -> None:
                 await request_queue.mark_request_as_handled(request)
 
         driver.quit()
+
+
+if __name__ == '__main__':
+    asyncio.run(main())

apify-2.7.1b12/docs/03_guides/code/05_crawlee_beautifulsoup.py

@@ -0,0 +1,55 @@
+import asyncio
+
+from crawlee.crawlers import BeautifulSoupCrawler, BeautifulSoupCrawlingContext
+
+from apify import Actor
+
+# Create a crawler.
+crawler = BeautifulSoupCrawler(
+    # Limit the crawl to max requests. Remove or increase it for crawling all links.
+    max_requests_per_crawl=50,
+)
+
+
+# Define a request handler, which will be called for every request.
+@crawler.router.default_handler
+async def request_handler(context: BeautifulSoupCrawlingContext) -> None:
+    Actor.log.info(f'Scraping {context.request.url}...')
+
+    # Extract the desired data.
+    data = {
+        'url': context.request.url,
+        'title': context.soup.title.string if context.soup.title else None,
+        'h1s': [h1.text for h1 in context.soup.find_all('h1')],
+        'h2s': [h2.text for h2 in context.soup.find_all('h2')],
+        'h3s': [h3.text for h3 in context.soup.find_all('h3')],
+    }
+
+    # Store the extracted data to the default dataset.
+    await context.push_data(data)
+
+    # Enqueue additional links found on the current page.
+    await context.enqueue_links(strategy='same-domain')
+
+
+async def main() -> None:
+    # Enter the context of the Actor.
+    async with Actor:
+        # Retrieve the Actor input, and use default values if not provided.
+        actor_input = await Actor.get_input() or {}
+        start_urls = [
+            url.get('url')
+            for url in actor_input.get('start_urls', [{'url': 'https://apify.com'}])
+        ]
+
+        # Exit if no start URLs are provided.
+        if not start_urls:
+            Actor.log.info('No start URLs specified in Actor input, exiting...')
+            await Actor.exit()
+
+        # Run the crawler with the starting requests.
+        await crawler.run(start_urls)
+
+
+if __name__ == '__main__':
+    asyncio.run(main())

apify-2.7.1b12/docs/03_guides/code/05_crawlee_parsel.py

@@ -0,0 +1,55 @@
+import asyncio
+
+from crawlee.crawlers import ParselCrawler, ParselCrawlingContext
+
+from apify import Actor
+
+# Create a crawler.
+crawler = ParselCrawler(
+    # Limit the crawl to max requests. Remove or increase it for crawling all links.
+    max_requests_per_crawl=50,
+)
+
+
+# Define a request handler, which will be called for every request.
+@crawler.router.default_handler
+async def request_handler(context: ParselCrawlingContext) -> None:
+    Actor.log.info(f'Scraping {context.request.url}...')
+
+    # Extract the desired data.
+    data = {
+        'url': context.request.url,
+        'title': context.selector.xpath('//title/text()').get(),
+        'h1s': context.selector.xpath('//h1/text()').getall(),
+        'h2s': context.selector.xpath('//h2/text()').getall(),
+        'h3s': context.selector.xpath('//h3/text()').getall(),
+    }
+
+    # Store the extracted data to the default dataset.
+    await context.push_data(data)
+
+    # Enqueue additional links found on the current page.
+    await context.enqueue_links(strategy='same-domain')
+
+
+async def main() -> None:
+    # Enter the context of the Actor.
+    async with Actor:
+        # Retrieve the Actor input, and use default values if not provided.
+        actor_input = await Actor.get_input() or {}
+        start_urls = [
+            url.get('url')
+            for url in actor_input.get('start_urls', [{'url': 'https://apify.com'}])
+        ]
+
+        # Exit if no start URLs are provided.
+        if not start_urls:
+            Actor.log.info('No start URLs specified in Actor input, exiting...')
+            await Actor.exit()
+
+        # Run the crawler with the starting requests.
+        await crawler.run(start_urls)
+
+
+if __name__ == '__main__':
+    asyncio.run(main())

apify-2.7.1b12/docs/03_guides/code/05_crawlee_playwright.py

@@ -0,0 +1,58 @@
+import asyncio
+
+from crawlee.crawlers import PlaywrightCrawler, PlaywrightCrawlingContext
+
+from apify import Actor
+
+# Create a crawler.
+crawler = PlaywrightCrawler(
+    # Limit the crawl to max requests. Remove or increase it for crawling all links.
+    max_requests_per_crawl=50,
+    # Run the browser in a headless mode.
+    headless=True,
+    browser_launch_options={'args': ['--disable-gpu']},
+)
+
+
+# Define a request handler, which will be called for every request.
+@crawler.router.default_handler
+async def request_handler(context: PlaywrightCrawlingContext) -> None:
+    Actor.log.info(f'Scraping {context.request.url}...')
+
+    # Extract the desired data.
+    data = {
+        'url': context.request.url,
+        'title': await context.page.title(),
+        'h1s': [await h1.text_content() for h1 in await context.page.locator('h1').all()],
+        'h2s': [await h2.text_content() for h2 in await context.page.locator('h2').all()],
+        'h3s': [await h3.text_content() for h3 in await context.page.locator('h3').all()],
+    }
+
+    # Store the extracted data to the default dataset.
+    await context.push_data(data)
+
+    # Enqueue additional links found on the current page.
+    await context.enqueue_links(strategy='same-domain')
+
+
+async def main() -> None:
+    # Enter the context of the Actor.
+    async with Actor:
+        # Retrieve the Actor input, and use default values if not provided.
+        actor_input = await Actor.get_input() or {}
+        start_urls = [
+            url.get('url')
+            for url in actor_input.get('start_urls', [{'url': 'https://apify.com'}])
+        ]
+
+        # Exit if no start URLs are provided.
+        if not start_urls:
+            Actor.log.info('No start URLs specified in Actor input, exiting...')
+            await Actor.exit()
+
+        # Run the crawler with the starting requests.
+        await crawler.run(start_urls)
+
+
+if __name__ == '__main__':
+    asyncio.run(main())

{apify-2.7.1b10 → apify-2.7.1b12}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "apify"
-version = "2.7.1b10"
+version = "2.7.1b12"
 description = "Apify SDK for Python"
 authors = [{ name = "Apify Technologies s.r.o.", email = "support@apify.com" }]
 license = { file = "LICENSE" }

{apify-2.7.1b10 → apify-2.7.1b12}/src/apify/_charging.py

@@ -64,6 +64,16 @@ class ChargingManager(Protocol):
         This can be used for instance when your code needs to support multiple pricing models in transition periods.
         """
 
+    def get_charged_event_count(self, event_name: str) -> int:
+        """Get the number of events with the given name that were charged so far.
+
+        Args:
+            event_name: Name of the inspected event.
+        """
+
+    def get_max_total_charge_usd(self) -> Decimal:
+        """Get the configured maximum total charge for this Actor run."""
+
 
 @docs_group('Charging')
 @dataclass(frozen=True)
@@ -309,6 +319,15 @@ class ChargingManagerImplementation(ChargingManager):
             },
         )
 
+    @ensure_context
+    def get_charged_event_count(self, event_name: str) -> int:
+        item = self._charging_state.get(event_name)
+        return item.charge_count if item is not None else 0
+
+    @ensure_context
+    def get_max_total_charge_usd(self) -> Decimal:
+        return self._max_total_charge_usd
+
 
 @dataclass
 class ChargingStateItem:

{apify-2.7.1b10 → apify-2.7.1b12}/tests/integration/test_actor_scrapy.py

@@ -11,7 +11,7 @@ async def test_actor_scrapy_title_spider(
     make_actor: MakeActorFunction,
     run_actor: RunActorFunction,
 ) -> None:
-    base_path = Path('docs/02_guides/code/scrapy_project')
+    base_path = Path('docs/03_guides/code/scrapy_project')
 
     actor_source_files = {
         'src/__init__.py': (base_path / 'src/__init__.py').read_text(),

{apify-2.7.1b10 → apify-2.7.1b12}/uv.lock

@@ -28,7 +28,7 @@ wheels = [
 
 [[package]]
 name = "apify"
-version = "2.7.1b10"
+version = "2.7.1b12"
 source = { editable = "." }
 dependencies = [
     { name = "apify-client" },

{apify-2.7.1b10 → apify-2.7.1b12}/website/package-lock.json

@@ -7,7 +7,7 @@
             "name": "apify-sdk-python",
             "dependencies": {
                 "@apify/docs-theme": "^1.0.203",
-                "@apify/docusaurus-plugin-typedoc-api": "^4.4.6",
+                "@apify/docusaurus-plugin-typedoc-api": "^4.4.8",
                 "@docusaurus/core": "^3.8.1",
                 "@docusaurus/faster": "^3.8.1",
                 "@docusaurus/plugin-client-redirects": "^3.8.1",
@@ -1614,9 +1614,9 @@
             }
         },
         "node_modules/@apify/docs-theme": {
-            "version": "1.0.203",
-            "resolved": "https://registry.npmjs.org/@apify/docs-theme/-/docs-theme-1.0.203.tgz",
-            "integrity": "sha512-vvFoyS/d/7dLrTJDBB+qpZYzH+mxhWt45C3iLfZaUW4P/oUAfEVKksxv5iLHCBfuxKQ6JIMmuzGnT4OeZ/O+VQ==",
+            "version": "1.0.209",
+            "resolved": "https://registry.npmjs.org/@apify/docs-theme/-/docs-theme-1.0.209.tgz",
+            "integrity": "sha512-1IJpcITFgZ6rx/c23Rii5RC8OVRe7bmdhERuRhj6llMbn5WSl8B0z/BoqoTXNkNFrtQfyL3jvbzCZ3H7e7jDxA==",
             "license": "ISC",
             "dependencies": {
                 "@apify/docs-search-modal": "^1.2.2",
@@ -1642,9 +1642,9 @@
             }
         },
         "node_modules/@apify/docusaurus-plugin-typedoc-api": {
-            "version": "4.4.7",
-            "resolved": "https://registry.npmjs.org/@apify/docusaurus-plugin-typedoc-api/-/docusaurus-plugin-typedoc-api-4.4.7.tgz",
-            "integrity": "sha512-xJMcRARQHYECg8xDOkJfCX6EZb4++doWCU2eWEHxtc4d4m38xMdRkh3RU78ovWgRwjkkAu/mfV7DY7aNaQebGA==",
+            "version": "4.4.8",
+            "resolved": "https://registry.npmjs.org/@apify/docusaurus-plugin-typedoc-api/-/docusaurus-plugin-typedoc-api-4.4.8.tgz",
+            "integrity": "sha512-iAGPaFKXz5SBzhf+611bk41b2sBRXPPINQOegxd0tOXwGOopnkKfr0LAvJp1Hd1jZFrVJhjyDsVZ6HM7Wwh9zg==",
             "license": "MIT",
             "dependencies": {
                 "@vscode/codicons": "^0.0.35",