BeautifulSoup

1"""This 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 urllib.parse import urljoin
10
11from bs4 import BeautifulSoup
12from httpx import AsyncClient
13
14from apify import Actor, Request
15
16
17async def main() -> None:
18    """Main entry point for the Apify Actor.
19
20    This coroutine is executed using `asyncio.run()`, so it must remain an asynchronous function for proper execution.
21    Asynchronous execution is required for communication with Apify platform, and it also enhances performance in
22    the field of web scraping significantly.
23    """
24    async with Actor:
25        # Retrieve the Actor input, and use default values if not provided.
26        actor_input = await Actor.get_input() or {}
27        start_urls = actor_input.get('start_urls', [{'url': 'https://apify.com'}])
28        max_depth = actor_input.get('max_depth', 1)
29
30        # Exit if no start URLs are provided.
31        if not start_urls:
32            Actor.log.info('No start URLs specified in Actor input, exiting...')
33            await Actor.exit()
34
35        # Open the default request queue for handling URLs to be processed.
36        request_queue = await Actor.open_request_queue()
37
38        # Enqueue the start URLs with an initial crawl depth of 0.
39        for start_url in start_urls:
40            url = start_url.get('url')
41            Actor.log.info(f'Enqueuing {url} ...')
42            request = Request.from_url(url, user_data={'depth': 0})
43            await request_queue.add_request(request)
44
45        # Process the URLs from the request queue.
46        while request := await request_queue.fetch_next_request():
47            url = request.url
48            depth = request.user_data['depth']
49            Actor.log.info(f'Scraping {url} ...')
50
51            try:
52                # Fetch the HTTP response from the specified URL using HTTPX.
53                async with AsyncClient() as client:
54                    response = await client.get(url, follow_redirects=True)
55
56                # Parse the HTML content using Beautiful Soup.
57                soup = BeautifulSoup(response.content, 'html.parser')
58
59                # If the current depth is less than max_depth, find nested links and enqueue them.
60                if depth < max_depth:
61                    for link in soup.find_all('a'):
62                        link_href = link.get('href')
63                        link_url = urljoin(url, link_href)
64
65                        if link_url.startswith(('http://', 'https://')):
66                            Actor.log.info(f'Enqueuing {link_url} ...')
67                            request = Request.from_url(link_url, user_data={'depth': depth + 1})
68                            await request_queue.add_request(request)
69
70                # Extract the desired data.
71                data = {
72                    'url': url,
73                    'title': soup.title.string if soup.title else None,
74                    'h1s': [h1.text for h1 in soup.find_all('h1')],
75                    'h2s': [h2.text for h2 in soup.find_all('h2')],
76                    'h3s': [h3.text for h3 in soup.find_all('h3')],
77                }
78
79                # Store the extracted data to the default dataset.
80                await Actor.push_data(data)
81
82            except Exception:
83                Actor.log.exception(f'Cannot extract data from {url}.')
84
85            finally:
86                # Mark the request as handled to ensure it is not processed again.
87                await request_queue.mark_request_as_handled(request)