Scrapy

1"""This module defines the main entry point for the Apify Actor.
2
3This module defines the main coroutine for the Apify Scrapy Actor, executed from the __main__.py file. The coroutine
4processes the Actor's input and executes the Scrapy spider. Additionally, it updates Scrapy project settings by
5applying Apify-related settings. Which includes adding a custom scheduler, retry middleware, and an item pipeline
6for pushing data to the Apify dataset.
7
8Customization:
9--------------
10
11Feel free to customize this file to add specific functionality to the Actor, such as incorporating your own Scrapy
12components like spiders and handling Actor input. However, make sure you have a clear understanding of your
13modifications. For instance, removing `apply_apify_settings` break the integration between Scrapy and Apify.
14
15Documentation:
16--------------
17
18For an in-depth description of the Apify-Scrapy integration process, our Scrapy components, known limitations and
19other stuff, please refer to the following documentation page: https://docs.apify.com/cli/docs/integrating-scrapy.
20"""
21
22from __future__ import annotations
23
24from scrapy.crawler import CrawlerProcess
25
26from apify import Actor
27from apify.scrapy.utils import apply_apify_settings
28
29# Import your Scrapy spider here.
30from .spiders.title import TitleSpider as Spider
31
32# Default input values for local execution using `apify run`.
33LOCAL_DEFAULT_START_URLS = [{'url': 'https://apify.com'}]
34
35
36async def main() -> None:
37    """Apify Actor main coroutine for executing the Scrapy spider."""
38    async with Actor:
39        Actor.log.info('Actor is being executed...')
40
41        # Retrieve and process Actor input.
42        actor_input = await Actor.get_input() or {}
43        start_urls = actor_input.get('startUrls', LOCAL_DEFAULT_START_URLS)
44        proxy_config = actor_input.get('proxyConfiguration')
45
46        # Open the default request queue for handling URLs to be processed.
47        request_queue = await Actor.open_request_queue()
48
49        # Enqueue the start URLs.
50        for start_url in start_urls:
51            url = start_url.get('url')
52            await request_queue.add_request(url)
53
54        # Apply Apify settings, it will override the Scrapy project settings.
55        settings = apply_apify_settings(proxy_config=proxy_config)
56
57        # Execute the spider using Scrapy `CrawlerProcess`.
58        process = CrawlerProcess(settings, install_root_handler=False)
59        process.crawl(Spider)
60        process.start()