Actor to be moved
Try for free
No credit card required
Go to Store
.actor/Dockerfile
1# First, specify the base Docker image.
2# You can see the Docker images from Apify at https://hub.docker.com/r/apify/.
3# You can also use any other image from Docker Hub.
4FROM apify/actor-python:3.11
5
6# Second, copy just requirements.txt into the Actor image,
7# since it should be the only file that affects the dependency install in the next step,
8# in order to speed up the build
9COPY requirements.txt ./
10
11# Install the packages specified in requirements.txt,
12# Print the installed Python version, pip version
13# and all installed packages with their versions for debugging
14RUN echo "Python version:" \
15 && python --version \
16 && echo "Pip version:" \
17 && pip --version \
18 && echo "Installing dependencies:" \
19 && pip install -r requirements.txt \
20 && echo "All installed Python packages:" \
21 && pip freeze
22
23# Next, copy the remaining files and directories with the source code.
24# Since we do this after installing the dependencies, quick build will be really fast
25# for most source file changes.
26COPY . ./
27
28# Use compileall to ensure the runnability of the Actor Python code.
29RUN python3 -m compileall -q .
30
31# Specify how to launch the source code of your Actor.
32# By default, the "python3 -m src" command is run
33CMD ["python3", "-m", "src"].actor/actor.json
1{
2 "actorSpecification": 1,
3 "name": "my-actor-3",
4 "title": "Scrape single page in Python",
5 "description": "Scrape data from single page with provided URL.",
6 "version": "0.0",
7 "meta": {
8 "templateId": "python-start"
9 },
10 "input": "./input_schema.json",
11 "dockerfile": "./Dockerfile"
12}.actor/input_schema.json
1{
2 "title": "Scrape data from a web page",
3 "type": "object",
4 "schemaVersion": 1,
5 "properties": {
6 "url": {
7 "title": "URL of the page",
8 "type": "string",
9 "description": "The URL of website you want to get the data from.",
10 "editor": "textfield",
11 "prefill": "https://www.apify.com/"
12 }
13 },
14 "required": ["url"]
15}.dockerignore
1# configurations
2.idea
3
4# crawlee and apify storage folders
5apify_storage
6crawlee_storage
7storage
8
9# installed files
10.venv
11
12# git folder
13.git.editorconfig
1root = true
2
3[*]
4indent_style = space
5indent_size = 4
6charset = utf-8
7trim_trailing_whitespace = true
8insert_final_newline = true
9end_of_line = lf.gitignore
1# This file tells Git which files shouldn't be added to source control
2
3.idea
4.DS_Store
5
6apify_storage
7storage/*
8!storage/key_value_stores
9storage/key_value_stores/*
10!storage/key_value_stores/default
11storage/key_value_stores/default/*
12!storage/key_value_stores/default/INPUT.json
13
14.venv/
15.env/
16__pypackages__
17dist/
18build/
19*.egg-info/
20*.egg
21
22__pycache__
23
24.mypy_cache
25.dmypy.json
26dmypy.json
27.pytest_cache
28.ruff_cache
29
30.scrapy
31*.logrequirements.txt
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 ~= 4.12.0.7src/__main__.py
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())src/main.py
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
10# Beautiful Soup - library for pulling data out of HTML and XML files, read more at
11# https://www.crummy.com/software/BeautifulSoup/bs4/doc
12from bs4 import BeautifulSoup
13
14# HTTPX - library for making asynchronous HTTP requests in Python, read more at https://www.python-httpx.org/
15from httpx import AsyncClient
16
17# Apify SDK - toolkit for building Apify Actors, read more at https://docs.apify.com/sdk/python
18from apify import Actor
19
20
21async def main() -> None:
22 """
23 The main coroutine is being executed using `asyncio.run()`, so do not attempt to make a normal function
24 out of it, it will not work. Asynchronous execution is required for communication with Apify platform,
25 and it also enhances performance in the field of web scraping significantly.
26 """
27 async with Actor:
28 # Structure of input is defined in input_schema.json
29 actor_input = await Actor.get_input() or {}
30 url = actor_input.get('url')
31
32 # Create an asynchronous HTTPX client
33 async with AsyncClient() as client:
34 # Fetch the HTML content of the page.
35 response = await client.get(url, follow_redirects=True)
36
37 # Parse the HTML content using Beautiful Soup
38 soup = BeautifulSoup(response.content, 'html.parser')
39
40 # Extract all headings from the page (tag name and text)
41 headings = []
42 for heading in soup.find_all(['h1', 'h2', 'h3', 'h4', 'h5', 'h6']):
43 heading_object = {'level': heading.name, 'text': heading.text}
44 Actor.log.info(f'Extracted heading: {heading_object}')
45 headings.append(heading_object)
46
47 # Save headings to Dataset - a table-like storage
48 await Actor.push_data(headings)
Jan Turoň
