Apify Project 01

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
.venv

# git folder
.git

root = true

[*]
indent_style = space
indent_size = 4
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
end_of_line = lf

# This file tells Git which files shouldn't be added to source control

.idea
.DS_Store

apify_storage
storage

.venv/
.env/
__pypackages__
dist/
build/
*.egg-info/
*.egg

__pycache__

.mypy_cache
.dmypy.json
dmypy.json
.pytest_cache
.ruff_cache

.scrapy
*.log

# Added by Apify CLI
node_modules
.venv

1# Feel free to add your Python dependencies below. For formatting guidelines, see:
2# https://pip.pypa.io/en/latest/reference/requirements-file-format/
3
4apify ~= 1.7.0
5beautifulsoup4 ~= 4.12.2
6httpx ~= 0.25.2
7types-beautifulsoup4 ~= 4.12.0.7

# First, specify the base Docker image.
# You can see the Docker images from Apify at https://hub.docker.com/r/apify/.
# You can also use any other image from Docker Hub.
FROM apify/actor-python:3.11

# Second, copy just requirements.txt into the Actor image,
# since it should be the only file that affects the dependency install in the next step,
# in order to speed up the build
COPY requirements.txt ./

# Install the packages specified in requirements.txt,
# Print the installed Python version, pip version
# and all installed packages with their versions for debugging
RUN echo "Python version:" \
 && python --version \
 && echo "Pip version:" \
 && pip --version \
 && echo "Installing dependencies:" \
 && pip install -r requirements.txt \
 && echo "All installed Python packages:" \
 && pip freeze

# Next, copy the remaining files and directories with the source code.
# Since we do this after installing the dependencies, quick build will be really fast
# for most source file changes.
COPY . ./

# Use compileall to ensure the runnability of the Actor Python code.
RUN python3 -m compileall -q .

# Specify how to launch the source code of your Actor.
# By default, the "python3 -m src" command is run
CMD ["python3", "-m", "src"]

{
	"actorSpecification": 1,
	"name": "apify-project-01",
	"title": "Getting started with Python and BeautifulSoup",
	"description": "Scrapes titles of websites using BeautifulSoup.",
	"version": "0.0",
	"meta": {
		"templateId": "python-beautifulsoup"
	},
	"input": "./input_schema.json",
	"dockerfile": "./Dockerfile",
	"storages": {
		"dataset": {
			"actorSpecification": 1,
			"title": "URLs and their titles",
			"views": {
				"titles": {
					"title": "URLs and their titles",
					"transformation": {
						"fields": [
							"url",
							"title"
						]
					},
					"display": {
						"component": "table",
						"properties": {
							"url": {
								"label": "URL",
								"format": "text"
							},
							"title": {
								"label": "Title",
								"format": "text"
							}
						}
					}
				}
			}
		}
	}
}

{
    "title": "Python BeautifulSoup Scraper",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "start_urls": {
            "title": "Start URLs",
            "type": "array",
            "description": "URLs to start with",
            "prefill": [
                { "url": "https://apify.com" }
            ],
            "editor": "requestListSources"
        },
        "max_depth": {
            "title": "Maximum depth",
            "type": "integer",
            "description": "Depth to which to scrape to",
            "default": 1
        }
    },
    "required": ["start_urls"]
}

1"""
2This module serves as the entry point for executing the Apify Actor. It handles the configuration of logging
3settings. The `main()` coroutine is then executed using `asyncio.run()`.
4
5Feel free to modify this file to suit your specific needs.
6"""
7
8import asyncio
9import logging
10
11from apify.log import ActorLogFormatter
12
13from .main import main
14
15# Configure loggers
16handler = logging.StreamHandler()
17handler.setFormatter(ActorLogFormatter())
18
19apify_client_logger = logging.getLogger('apify_client')
20apify_client_logger.setLevel(logging.INFO)
21apify_client_logger.addHandler(handler)
22
23apify_logger = logging.getLogger('apify')
24apify_logger.setLevel(logging.DEBUG)
25apify_logger.addHandler(handler)
26
27# Execute the Actor main coroutine
28asyncio.run(main())

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 bs4 import BeautifulSoup
13from httpx import AsyncClient
14
15from apify import Actor
16
17
18async def main() -> None:
19    """
20    The main coroutine is being executed using `asyncio.run()`, so do not attempt to make a normal function
21    out of it, it will not work. Asynchronous execution is required for communication with Apify platform,
22    and it also enhances performance in the field of web scraping significantly.
23    """
24    async with Actor:
25        # Read the Actor input
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        if not start_urls:
31            Actor.log.info('No start URLs specified in actor input, exiting...')
32            await Actor.exit()
33
34        # Enqueue the starting URLs in the default request queue
35        default_queue = await Actor.open_request_queue()
36        for start_url in start_urls:
37            url = start_url.get('url')
38            Actor.log.info(f'Enqueuing {url} ...')
39            await default_queue.add_request({'url': url, 'userData': {'depth': 0}})
40
41        # Process the requests in the queue one by one
42        while request := await default_queue.fetch_next_request():
43            url = request['url']
44            depth = request['userData']['depth']
45            Actor.log.info(f'Scraping {url} ...')
46
47            try:
48                # Fetch the URL using `httpx`
49                async with AsyncClient() as client:
50                    response = await client.get(url, follow_redirects=True)
51
52                # Parse the response using `BeautifulSoup`
53                soup = BeautifulSoup(response.content, 'html.parser')
54
55                # If we haven't reached the max depth,
56                # look for nested links and enqueue their targets
57                if depth < max_depth:
58                    for link in soup.find_all('a'):
59                        link_href = link.get('href')
60                        link_url = urljoin(url, link_href)
61                        if link_url.startswith(('http://', 'https://')):
62                            Actor.log.info(f'Enqueuing {link_url} ...')
63                            await default_queue.add_request({
64                                'url': link_url,
65                                'userData': {'depth': depth + 1},
66                            })
67
68                # Push the title of the page into the default dataset
69                title = soup.title.string if soup.title else None
70                await Actor.push_data({'url': url, 'title': title})
71            except Exception:
72                Actor.log.exception(f'Cannot extract data from {url}.')
73            finally:
74                # Mark the request as handled so it's not processed again
75                await default_queue.mark_request_as_handled(request)