Selenium + Chrome

1"""
2This module defines the `main()` coroutine for the Apify Actor, executed from the `__main__.py` file.
3
4Feel free to modify this file to suit your specific needs.
5
6To build Apify Actors, utilize the Apify SDK toolkit, read more at the official documentation:
7https://docs.apify.com/sdk/python
8"""
9
10from urllib.parse import urljoin
11
12from selenium import webdriver
13from selenium.webdriver.chrome.options import Options as ChromeOptions
14from selenium.webdriver.common.by import By
15
16from apify import Actor
17
18# To run this Actor locally, you need to have the Selenium Chromedriver installed.
19# https://www.selenium.dev/documentation/webdriver/getting_started/install_drivers/
20# When running on the Apify platform, it is already included in the Actor's Docker image.
21
22
23async def main() -> None:
24    """
25    The main coroutine is being executed using `asyncio.run()`, so do not attempt to make a normal function
26    out of it, it will not work. Asynchronous execution is required for communication with Apify platform,
27    and it also enhances performance in the field of web scraping significantly.
28    """
29    async with Actor:
30        # Read the Actor input
31        actor_input = await Actor.get_input() or {}
32        start_urls = actor_input.get('start_urls', [{'url': 'https://apify.com'}])
33        max_depth = actor_input.get('max_depth', 1)
34
35        if not start_urls:
36            Actor.log.info('No start URLs specified in actor input, exiting...')
37            await Actor.exit()
38
39        # Enqueue the starting URLs in the default request queue
40        default_queue = await Actor.open_request_queue()
41        for start_url in start_urls:
42            url = start_url.get('url')
43            Actor.log.info(f'Enqueuing {url} ...')
44            await default_queue.add_request({'url': url, 'userData': {'depth': 0}})
45
46        # Launch a new Selenium Chrome WebDriver
47        Actor.log.info('Launching Chrome WebDriver...')
48        chrome_options = ChromeOptions()
49        if Actor.config.headless:
50            chrome_options.add_argument('--headless')
51        chrome_options.add_argument('--no-sandbox')
52        chrome_options.add_argument('--disable-dev-shm-usage')
53        driver = webdriver.Chrome(options=chrome_options)
54
55        driver.get('http://www.example.com')
56        assert driver.title == 'Example Domain'
57
58        # Process the requests in the queue one by one
59        while request := await default_queue.fetch_next_request():
60            url = request['url']
61            depth = request['userData']['depth']
62            Actor.log.info(f'Scraping {url} ...')
63
64            try:
65                # Open the URL in the Selenium WebDriver
66                driver.get(url)
67
68                # If we haven't reached the max depth,
69                # look for nested links and enqueue their targets
70                if depth < max_depth:
71                    for link in driver.find_elements(By.TAG_NAME, 'a'):
72                        link_href = link.get_attribute('href')
73                        link_url = urljoin(url, link_href)
74                        if link_url.startswith(('http://', 'https://')):
75                            Actor.log.info(f'Enqueuing {link_url} ...')
76                            await default_queue.add_request({
77                                'url': link_url,
78                                'userData': {'depth': depth + 1},
79                            })
80
81                # Push the title of the page into the default dataset
82                title = driver.title
83                await Actor.push_data({'url': url, 'title': title})
84            except Exception:
85                Actor.log.exception(f'Cannot extract data from {url}.')
86            finally:
87                await default_queue.mark_request_as_handled(request)
88
89        driver.quit()