# 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 . ./

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

.actor/actor.json

{
    "actorSpecification": 1,
    "name": "my-actor-3",
    "title": "Scrape single page in Python",
    "description": "Scrape data from single page with provided URL.",
    "version": "0.0",
    "meta": {
        "templateId": "python-start"
    },
    "input": "./input_schema.json",
    "dockerfile": "./Dockerfile"
}

.actor/input_schema.json

{
    "title": "Scrape data from a web page",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "url": {
            "title": "URL of the page",
            "type": "string",
            "description": "The URL of website you want to get the data from.",
            "editor": "textfield",
            "prefill": "https://www.apify.com/"
        }
    }
}

src/init.py

src/main.py

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())

src/main.py

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            pass

.dockerignore

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
.venv

# git folder
.git

.editorconfig

root = true

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

.gitignore

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

.idea
.DS_Store

apify_storage
storage/*
!storage/key_value_stores
storage/key_value_stores/*
!storage/key_value_stores/default
storage/key_value_stores/default/*
!storage/key_value_stores/default/INPUT.json

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

__pycache__

.mypy_cache
.dmypy.json
dmypy.json
.pytest_cache

.scrapy
*.log

requirements.txt

1# 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

Test public

honzakirchner43/my-actor-12

Jan Kirchner

Public Test

jancurn/public-test

Jan Curn

My public actor

effervescent_iguana/my-public-actor

testing

My public Actor

dogmatic_olive/my-public-actor

testing actor

Jan Novotny

Test actor

apentest_citadelo100/test-actor

Test actor

testers

4.0

Test Public With Env Vars

someuser/test-public-with-env-vars

fwef wefwef

Simple sample public actor

fuchsia_porcupine/simple-sample-public-actor

Kateřina Hroníková

Test

jnnv/yr-no

Jan Novotný

Test Actor 1

jk1/test-actor-1

Honza

My second public actor

dogmatic_olive/my-second-public-actor

this is second testing actor

Jan Novotny

# 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 . ./ # 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": "my-actor-3", "title": "Scrape single page in Python", "description": "Scrape data from single page with provided URL.", "version": "0.0", "meta": { "templateId": "python-start" }, "input": "./input_schema.json", "dockerfile": "./Dockerfile" }

{ "title": "Scrape data from a web page", "type": "object", "schemaVersion": 1, "properties": { "url": { "title": "URL of the page", "type": "string", "description": "The URL of website you want to get the data from.", "editor": "textfield", "prefill": "https://www.apify.com/" } } }

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 pass

# This file tells Git which files shouldn't be added to source control .idea .DS_Store apify_storage storage/* !storage/key_value_stores storage/key_value_stores/* !storage/key_value_stores/default storage/key_value_stores/default/* !storage/key_value_stores/default/INPUT.json .venv/ .env/ __pypackages__ dist/ build/ *.egg-info/ *.egg __pycache__ .mypy_cache .dmypy.json dmypy.json .pytest_cache .scrapy *.log

API features test public actor

API features test public actor

.actor/Dockerfile

.actor/actor.json

.actor/input_schema.json

src/__init__.py

src/__main__.py

src/main.py

.dockerignore

.editorconfig

.gitignore

requirements.txt

You might also like

Test public

Public Test

My public actor

My public Actor

Test actor

Test Public With Env Vars

Simple sample public actor

Test

Test Actor 1

My second public actor

.actor/Dockerfile

.actor/actor.json

.actor/input_schema.json

src/__init__.py

src/__main__.py

src/main.py

.dockerignore

.editorconfig

.gitignore

requirements.txt

src/init.py

src/main.py

src/init.py

src/main.py