Selenium + Chrome

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
11import asyncio
12from urllib.parse import urljoin
13
14from apify import Actor, Request
15from selenium import webdriver
16from selenium.webdriver.chrome.options import Options as ChromeOptions
17from selenium.webdriver.common.by import By
18
19# To run this Actor locally, you need to have the Selenium Chromedriver installed.
20# Follow the installation guide at:
21# https://www.selenium.dev/documentation/webdriver/getting_started/install_drivers/
22# When running on the Apify platform, the Chromedriver is already included
23# in the Actor's Docker image.
24
25
26async def main() -> None:
27    """Define a main entry point for the Apify Actor.
28
29    This coroutine is executed using `asyncio.run()`, so it must remain an asynchronous function for proper execution.
30    Asynchronous execution is required for communication with Apify platform, and it also enhances performance in
31    the field of web scraping significantly.
32    """
33    # Enter the context of the Actor.
34    async with Actor:
35        # Retrieve the Actor input, and use default values if not provided.
36        actor_input = await Actor.get_input() or {}
37        start_urls = actor_input.get('start_urls', [{'url': 'https://apify.com'}])
38        max_depth = actor_input.get('max_depth', 1)
39
40        # Exit if no start URLs are provided.
41        if not start_urls:
42            Actor.log.info('No start URLs specified in actor input, exiting...')
43            await Actor.exit()
44
45        # Open the default request queue for handling URLs to be processed.
46        request_queue = await Actor.open_request_queue()
47
48        # Enqueue the start URLs with an initial crawl depth of 0.
49        for start_url in start_urls:
50            url = start_url.get('url')
51            Actor.log.info(f'Enqueuing {url} ...')
52            new_request = Request.from_url(url, user_data={'depth': 0})
53            await request_queue.add_request(new_request)
54
55        # Launch a new Selenium Chrome WebDriver and configure it.
56        Actor.log.info('Launching Chrome WebDriver...')
57        chrome_options = ChromeOptions()
58
59        if Actor.config.headless:
60            chrome_options.add_argument('--headless')
61
62        chrome_options.add_argument('--no-sandbox')
63        chrome_options.add_argument('--disable-dev-shm-usage')
64        driver = webdriver.Chrome(options=chrome_options)
65
66        # Test WebDriver setup by navigating to an example page.
67        driver.get('http://www.example.com')
68        if driver.title != 'Example Domain':
69            raise ValueError('Failed to open example page.')
70
71        # Process the URLs from the request queue.
72        while request := await request_queue.fetch_next_request():
73            url = request.url
74
75            if not isinstance(request.user_data['depth'], (str, int)):
76                raise TypeError('Request.depth is an enexpected type.')
77
78            depth = int(request.user_data['depth'])
79            Actor.log.info(f'Scraping {url} (depth={depth}) ...')
80
81            try:
82                # Navigate to the URL using Selenium WebDriver. Use asyncio.to_thread
83                # for non-blocking execution.
84                await asyncio.to_thread(driver.get, url)
85
86                # If the current depth is less than max_depth, find nested links
87                # and enqueue them.
88                if depth < max_depth:
89                    for link in driver.find_elements(By.TAG_NAME, 'a'):
90                        link_href = link.get_attribute('href')
91                        link_url = urljoin(url, link_href)
92
93                        if link_url.startswith(('http://', 'https://')):
94                            Actor.log.info(f'Enqueuing {link_url} ...')
95                            new_request = Request.from_url(
96                                link_url,
97                                user_data={'depth': depth + 1},
98                            )
99                            await request_queue.add_request(new_request)
100
101                # Extract the desired data.
102                data = {
103                    'url': url,
104                    'title': driver.title,
105                }
106
107                # Store the extracted data to the default dataset.
108                await Actor.push_data(data)
109
110            except Exception:
111                Actor.log.exception(f'Cannot extract data from {url}.')
112
113            finally:
114                # Mark the request as handled to ensure it is not processed again.
115                await request_queue.mark_request_as_handled(request)
116
117        driver.quit()