API features test public actor
No credit card required
No credit card required
API features test public actor
Actor Metrics
1 monthly user
2 stars
>99% runs succeeded
Created in Aug 2023
Modified a year ago
Jiri Moravcik
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# Specify how to launch the source code of your actor.
29# By default, the "python3 -m src" command is run
30CMD ["python3", "-m", "src"]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}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}1import asyncio
2import logging
3
4from apify.log import ActorLogFormatter
5
6from .main import main
7
8# Set up logging of messages from the Apify SDK
9handler = logging.StreamHandler()
10handler.setFormatter(ActorLogFormatter())
11
12apify_client_logger = logging.getLogger('apify_client')
13apify_client_logger.setLevel(logging.INFO)
14apify_client_logger.addHandler(handler)
15
16apify_logger = logging.getLogger('apify')
17apify_logger.setLevel(logging.DEBUG)
18apify_logger.addHandler(handler)
19
20asyncio.run(main())1# Apify SDK - toolkit for building Apify Actors (Read more at https://docs.apify.com/sdk/python).
2from apify import Actor
3
4async def main():
5 async with Actor:
6 # Structure of input is defined in input_schema.json
7 actor_input = await Actor.get_input() or {}
8
9 actor_env = Actor.get_env()
10 actor_id = actor_env['actor_id']
11 actor_build_id = actor_env['actor_build_id']
12 actor_run_id = actor_env['actor_run_id']
13 actor_task_id = actor_env['actor_task_id']
14 user_id = actor_env['user_id']
15
16 client = Actor.new_client()
17 await client.actor(actor_id).get()
18 await client.build(actor_build_id).get()
19 await client.run(actor_run_id).get()
20 await client.log(actor_run_id).get()
21 if actor_task_id:
22 await client.task(actor_task_id).get()
23
24 await client.user(user_id).get()
25
26 rq = await Actor.open_request_queue()
27 await rq.add_request({'uniqueKey': 'https://apify.com', 'url': 'https://apify.com'})
28 await rq.fetch_next_request()
29 await Actor.set_value('test', {'test': 123})
30 await Actor.push_data({'abc': 456})
31 dataset = await Actor.open_dataset()
32 async for item in dataset.iterate_items():
33 pass1# 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.git1root = true
2
3[*]
4indent_style = space
5indent_size = 4
6charset = utf-8
7trim_trailing_whitespace = true
8insert_final_newline = true
9end_of_line = lf1# 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
29.scrapy
30*.log1# Add your dependencies here.
2# See https://pip.pypa.io/en/latest/reference/requirements-file-format/
3# for how to format them
4apify ~= 1.1.1
5beautifulsoup4 ~= 4.12.0
6requests ~= 2.31.0