Python Playwright scraper

1"""Module defines the main entry point for the Apify Actor.
2
3Feel free to modify this file to suit your specific needs.
4
5To build Apify Actors, utilize the Apify SDK toolkit, read more at the official documentation:
6https://docs.apify.com/sdk/python
7"""
8
9from __future__ import annotations
10
11from urllib.parse import urljoin
12
13from apify import Actor, Request
14from playwright.async_api import async_playwright
15
16# Note: To run this Actor locally, ensure that Playwright browsers are installed.
17# Run `playwright install --with-deps` in the Actor's virtual environment to install them.
18# When running on the Apify platform, these dependencies are already included
19# in the Actor's Docker image.
20
21# Limit the crawl to max requests. Increase it to crawl more links.
22MAX_REQUESTS_PER_CRAWL = 10
23
24
25async def main() -> None:
26    """Define a main entry point for the Apify Actor.
27
28    This coroutine is executed using `asyncio.run()`, so it must remain an asynchronous function for proper execution.
29    Asynchronous execution is required for communication with Apify platform, and it also enhances performance in
30    the field of web scraping significantly.
31    """
32    # Enter the context of the Actor.
33    async with Actor:
34        # Retrieve the Actor input, and use default values if not provided.
35        actor_input = await Actor.get_input() or {}
36        start_urls = actor_input.get('start_urls', [{'url': 'https://apify.com'}])
37        max_depth = actor_input.get('max_depth', 1)
38
39        # Exit if no start URLs are provided.
40        if not start_urls:
41            Actor.log.info('No start URLs specified in Actor input, exiting...')
42            await Actor.exit()
43
44        # Open the default request queue for handling URLs to be processed.
45        request_queue = await Actor.open_request_queue()
46
47        # Enqueue the start URLs with an initial crawl depth of 0.
48        for start_url in start_urls:
49            url = start_url.get('url')
50            Actor.log.info(f'Enqueuing {url} ...')
51            new_request = Request.from_url(url, user_data={'depth': 0})
52            await request_queue.add_request(new_request)
53
54        Actor.log.info('Launching Playwright...')
55
56        # Launch Playwright and open a new browser context.
57        async with async_playwright() as playwright:
58            # Configure the browser to launch in headless mode as per Actor configuration.
59            browser = await playwright.chromium.launch(
60                headless=Actor.configuration.headless,
61                args=['--disable-gpu'],
62            )
63            context = await browser.new_context()
64
65            handled_requests = 0
66
67            # Process the URLs from the request queue.
68            while handled_requests < MAX_REQUESTS_PER_CRAWL and (request := await request_queue.fetch_next_request()):
69                url = request.url
70
71                if not isinstance(request.user_data['depth'], (str, int)):
72                    raise TypeError('Request.depth is an unexpected type.')
73
74                depth = int(request.user_data['depth'])
75                Actor.log.info(f'Scraping {url} (depth={depth}) ...')
76
77                try:
78                    # Open a new page in the browser context and navigate to the URL.
79                    page = await context.new_page()
80                    await page.goto(url)
81
82                    # If the current depth is less than max_depth, find nested links
83                    # and enqueue them.
84                    if depth < max_depth:
85                        for link in await page.locator('a').all():
86                            link_href = await link.get_attribute('href')
87                            link_url = urljoin(url, link_href)
88
89                            if link_url.startswith(('http://', 'https://')):
90                                Actor.log.info(f'Enqueuing {link_url} ...')
91                                new_request = Request.from_url(
92                                    link_url,
93                                    user_data={'depth': depth + 1},
94                                )
95                                await request_queue.add_request(new_request)
96
97                    # Extract the desired data.
98                    data = {
99                        'url': url,
100                        'title': await page.title(),
101                    }
102
103                    # Store the extracted data to the default dataset.
104                    await Actor.push_data(data)
105
106                except Exception:
107                    Actor.log.exception(f'Cannot extract data from {url}.')
108
109                finally:
110                    await page.close()
111                    # Mark the request as handled to ensure it is not processed again.
112                    await request_queue.mark_request_as_handled(request)
113                    handled_requests += 1