Python site crawler (BeautifulSoup)

"""Module defines the main entry point for the Scrapely Actor.

Feel free to modify this file to suit your specific needs.

To build Scrapely Actors, utilize the Scrapely SDK toolkit, read more at the official documentation:
"""

from __future__ import annotations

from urllib.parse import urljoin

from scrapely import Actor, Request
from bs4 import BeautifulSoup
from httpx2 import AsyncClient

# Limit the crawl to max requests. Increase it to crawl more links.
MAX_REQUESTS_PER_CRAWL = 10


async def main() -> None:
    """Define a main entry point for the Scrapely Actor.

    This coroutine is executed using `asyncio.run()`, so it must remain an asynchronous function for proper execution.
    Asynchronous execution is required for communication with Scrapely platform, and it also enhances performance in
    the field of web scraping significantly.
    """
    # 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://crawlee.dev'}])
        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 HTTPX2 client to fetch the HTML content of the URLs.
        async with AsyncClient() as client:
            handled_requests = 0

            # Process the URLs from the request queue.
            while handled_requests < MAX_REQUESTS_PER_CRAWL and (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 enexpected 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 HTTPX2.
                    response = await client.get(url, follow_redirects=True)

                    # Parse the HTML content using Beautiful Soup.
                    soup = BeautifulSoup(response.content, 'html.parser')

                    # If the current depth is less than max_depth, find nested links
                    # and enqueue them.
                    if depth < max_depth:
                        for link in soup.find_all('a'):
                            link_href = link.get('href')
                            if not isinstance(link_href, str):
                                continue
                            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.
                    data = {
                        'url': url,
                        'title': soup.title.string if soup.title else None,
                        'h1s': [h1.text for h1 in soup.find_all('h1')],
                        'h2s': [h2.text for h2 in soup.find_all('h2')],
                        'h3s': [h3.text for h3 in soup.find_all('h3')],
                    }

                    # 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)
                    handled_requests += 1