Pricing

Pay per usage

Go to Apify Store

shit-1

Try for free

Pricing

Pay per usage

Rating

0.0

(0)

Developer

Daniel Georgiev

Actor stats

Bookmarked

Total users

Monthly active users

24 days ago

Last modified

.actor/actor.json

{
  "actorSpecification": 1,
  "name": "hello-world",
  "title": "Hello World",
  "version": "0.0",
  "buildTag": "latest"
}

.actor/input_schema.json

.actor/output_schema.json

my_actor/init.py

my_actor/main.py

1import asyncio
2
3from .main import main
4
5if __name__ == '__main__':
6    asyncio.run(main())

my_actor/main.py

1from apify import Actor
2
3
4async def main():
5    async with Actor:
6        print("Hi")
7        await Actor.push_data({"message": "Hi"})
8
9
10if __name__ == "__main__":
11    import asyncio
12    asyncio.run(main())

my_actor/py.typed

my_actor/routes.py

1"""Module defines the router and request handlers for the crawler."""
2
3from __future__ import annotations
4
5from apify import Actor
6from crawlee.crawlers import BeautifulSoupCrawlingContext
7from crawlee.router import Router
8
9router = Router[BeautifulSoupCrawlingContext]()
10
11
12@router.default_handler
13async def default_handler(context: BeautifulSoupCrawlingContext) -> None:
14    """Handle each request by extracting data and enqueueing links."""
15    url = context.request.url
16    Actor.log.info(f'Scraping {url}...')
17
18    # Extract the desired data.
19    data = {
20        'url': context.request.url,
21        'title': context.soup.title.string if context.soup.title else None,
22        'h1s': [h1.text for h1 in context.soup.find_all('h1')],
23        'h2s': [h2.text for h2 in context.soup.find_all('h2')],
24        'h3s': [h3.text for h3 in context.soup.find_all('h3')],
25    }
26
27    # Store the extracted data to the default dataset.
28    await context.push_data(data)
29
30    # Enqueue additional links found on the current page.
31    await context.enqueue_links()

.dockerignore

.git
.mise.toml
.nvim.lua
storage

# The rest is copied from https://github.com/github/gitignore/blob/main/Python.gitignore

# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class

# C extensions
*.so

# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST

# PyInstaller
#  Usually these files are written by a python script from a template
#  before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec

# Installer logs
pip-log.txt
pip-delete-this-directory.txt

# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/

# Translations
*.mo
*.pot

# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal

# Flask stuff:
instance/
.webassets-cache

# Scrapy stuff:
.scrapy

# Sphinx documentation
docs/_build/

# PyBuilder
.pybuilder/
target/

# Jupyter Notebook
.ipynb_checkpoints

# IPython
profile_default/
ipython_config.py

# pyenv
#   For a library or package, you might want to ignore these files since the code is
#   intended to run in multiple environments; otherwise, check them in:
.python-version

# pdm
#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
#   in version control.
#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
.pdm.toml
.pdm-python
.pdm-build/

# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/

# Celery stuff
celerybeat-schedule
celerybeat.pid

# SageMath parsed files
*.sage.py

# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/

# Spyder project settings
.spyderproject
.spyproject

# Rope project settings
.ropeproject

# mkdocs documentation
/site

# mypy
.mypy_cache/
.dmypy.json
dmypy.json

# Pyre type checker
.pyre/

# pytype static type analyzer
.pytype/

# Cython debug symbols
cython_debug/

# PyCharm
#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
#  and can be added to the global gitignore or merged into this file.  For a more nuclear
#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
.idea/

# Visual Studio Code
#  Ignores the folder created by VS Code when changing workspace settings, doing debugger
#  configuration, etc. Can be commented out to share Workspace Settings within a team
.vscode

# Zed editor
#  Ignores the folder created when setting Project Settings in the Zed editor. Can be commented out
#  to share Project Settings within a team
.zed

.gitignore

.mise.toml
.nvim.lua
storage

# The rest is copied from https://github.com/github/gitignore/blob/main/Python.gitignore

# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class

# C extensions
*.so

# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST

# PyInstaller
#  Usually these files are written by a python script from a template
#  before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec

# Installer logs
pip-log.txt
pip-delete-this-directory.txt

# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/

# Translations
*.mo
*.pot

# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal

# Flask stuff:
instance/
.webassets-cache

# Scrapy stuff:
.scrapy

# Sphinx documentation
docs/_build/

# PyBuilder
.pybuilder/
target/

# Jupyter Notebook
.ipynb_checkpoints

# IPython
profile_default/
ipython_config.py

# pyenv
#   For a library or package, you might want to ignore these files since the code is
#   intended to run in multiple environments; otherwise, check them in:
.python-version

# pdm
#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
#   in version control.
#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
.pdm.toml
.pdm-python
.pdm-build/

# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/

# Celery stuff
celerybeat-schedule
celerybeat.pid

# SageMath parsed files
*.sage.py

# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/

# Spyder project settings
.spyderproject
.spyproject

# Rope project settings
.ropeproject

# mkdocs documentation
/site

# mypy
.mypy_cache/
.dmypy.json
dmypy.json

# Pyre type checker
.pyre/

# pytype static type analyzer
.pytype/

# Cython debug symbols
cython_debug/

# PyCharm
#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
#  and can be added to the global gitignore or merged into this file.  For a more nuclear
#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
.idea/

# Zed editor
#  Ignores the folder created when setting Project Settings in the Zed editor. Can be commented out
#  to share Project Settings within a team
.zed

Dockerfile

# 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:3.14

# Install system packages
USER root

RUN apt-get update && \
    apt-get install -y --no-install-recommends \
        ffmpeg && \
    rm -rf /var/lib/apt/lists/*

RUN apt-get update && \
    apt-get install -y curl unzip && \
    curl -fsSL https://deno.land/install.sh | sh && \
    mv /root/.deno/bin/deno /usr/local/bin/deno && \
    chmod +x /usr/local/bin/deno && \
    deno --version

# Switch back to the default user
USER myuser

RUN deno --version || echo "Deno is NOT installed"

# 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 --chown=myuser:myuser 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 --chown=myuser:myuser . ./

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

# Specify how to launch the source code of your Actor.
CMD ["python", "-m", "my_actor"]

requirements.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 >= 3.0.0, < 4.0.0

Actor 1

code_crafter/actor-1

Code Pioneer

Your Actor 1

jupri/your-actor-1

cat

Reviews

hollywood-reporter/reviews

hollywood reporter

Website Scraper

brawny_budget/website-scraper

Lillie Weathers

Website Scraper

precious_budget/website-scraper

Elmira Dibella

Website Scraper

nurtured_mastodon/website-scraper

Jeanne Hughes

Jobs data

neuralhex/jobs-data

NeuralHex

My Actor 3

alice_bob/my-actor-3

APIFY Hunter

Leads Data

neuralhex/leads-data

NeuralHex

Tiktok Scraper

sovanza.inc/tiktok-scraper

Sovanza

5.0

1from apify import Actor 2 3 4async def main(): 5 async with Actor: 6 print("Hi") 7 await Actor.push_data({"message": "Hi"}) 8 9 10if __name__ == "__main__": 11 import asyncio 12 asyncio.run(main())

1"""Module defines the router and request handlers for the crawler.""" 2 3from __future__ import annotations 4 5from apify import Actor 6from crawlee.crawlers import BeautifulSoupCrawlingContext 7from crawlee.router import Router 8 9router = Router[BeautifulSoupCrawlingContext]() 10 11 12@router.default_handler 13async def default_handler(context: BeautifulSoupCrawlingContext) -> None: 14 """Handle each request by extracting data and enqueueing links.""" 15 url = context.request.url 16 Actor.log.info(f'Scraping {url}...') 17 18 # Extract the desired data. 19 data = { 20 'url': context.request.url, 21 'title': context.soup.title.string if context.soup.title else None, 22 'h1s': [h1.text for h1 in context.soup.find_all('h1')], 23 'h2s': [h2.text for h2 in context.soup.find_all('h2')], 24 'h3s': [h3.text for h3 in context.soup.find_all('h3')], 25 } 26 27 # Store the extracted data to the default dataset. 28 await context.push_data(data) 29 30 # Enqueue additional links found on the current page. 31 await context.enqueue_links()

.git .mise.toml .nvim.lua storage # The rest is copied from https://github.com/github/gitignore/blob/main/Python.gitignore # Byte-compiled / optimized / DLL files __pycache__/ *.py[cod] *$py.class # C extensions *.so # Distribution / packaging .Python build/ develop-eggs/ dist/ downloads/ eggs/ .eggs/ lib/ lib64/ parts/ sdist/ var/ wheels/ share/python-wheels/ *.egg-info/ .installed.cfg *.egg MANIFEST # PyInstaller # Usually these files are written by a python script from a template # before PyInstaller builds the exe, so as to inject date/other infos into it. *.manifest *.spec # Installer logs pip-log.txt pip-delete-this-directory.txt # Unit test / coverage reports htmlcov/ .tox/ .nox/ .coverage .coverage.* .cache nosetests.xml coverage.xml *.cover *.py,cover .hypothesis/ .pytest_cache/ cover/ # Translations *.mo *.pot # Django stuff: *.log local_settings.py db.sqlite3 db.sqlite3-journal # Flask stuff: instance/ .webassets-cache # Scrapy stuff: .scrapy # Sphinx documentation docs/_build/ # PyBuilder .pybuilder/ target/ # Jupyter Notebook .ipynb_checkpoints # IPython profile_default/ ipython_config.py # pyenv # For a library or package, you might want to ignore these files since the code is # intended to run in multiple environments; otherwise, check them in: .python-version # pdm # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. #pdm.lock # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it # in version control. # https://pdm.fming.dev/latest/usage/project/#working-with-version-control .pdm.toml .pdm-python .pdm-build/ # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm __pypackages__/ # Celery stuff celerybeat-schedule celerybeat.pid # SageMath parsed files *.sage.py # Environments .env .venv env/ venv/ ENV/ env.bak/ venv.bak/ # Spyder project settings .spyderproject .spyproject # Rope project settings .ropeproject # mkdocs documentation /site # mypy .mypy_cache/ .dmypy.json dmypy.json # Pyre type checker .pyre/ # pytype static type analyzer .pytype/ # Cython debug symbols cython_debug/ # PyCharm # JetBrains specific template is maintained in a separate JetBrains.gitignore that can # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore # and can be added to the global gitignore or merged into this file. For a more nuclear # option (not recommended) you can uncomment the following to ignore the entire idea folder. .idea/ # Visual Studio Code # Ignores the folder created by VS Code when changing workspace settings, doing debugger # configuration, etc. Can be commented out to share Workspace Settings within a team .vscode # Zed editor # Ignores the folder created when setting Project Settings in the Zed editor. Can be commented out # to share Project Settings within a team .zed

.mise.toml .nvim.lua storage # The rest is copied from https://github.com/github/gitignore/blob/main/Python.gitignore # Byte-compiled / optimized / DLL files __pycache__/ *.py[cod] *$py.class # C extensions *.so # Distribution / packaging .Python build/ develop-eggs/ dist/ downloads/ eggs/ .eggs/ lib/ lib64/ parts/ sdist/ var/ wheels/ share/python-wheels/ *.egg-info/ .installed.cfg *.egg MANIFEST # PyInstaller # Usually these files are written by a python script from a template # before PyInstaller builds the exe, so as to inject date/other infos into it. *.manifest *.spec # Installer logs pip-log.txt pip-delete-this-directory.txt # Unit test / coverage reports htmlcov/ .tox/ .nox/ .coverage .coverage.* .cache nosetests.xml coverage.xml *.cover *.py,cover .hypothesis/ .pytest_cache/ cover/ # Translations *.mo *.pot # Django stuff: *.log local_settings.py db.sqlite3 db.sqlite3-journal # Flask stuff: instance/ .webassets-cache # Scrapy stuff: .scrapy # Sphinx documentation docs/_build/ # PyBuilder .pybuilder/ target/ # Jupyter Notebook .ipynb_checkpoints # IPython profile_default/ ipython_config.py # pyenv # For a library or package, you might want to ignore these files since the code is # intended to run in multiple environments; otherwise, check them in: .python-version # pdm # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. #pdm.lock # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it # in version control. # https://pdm.fming.dev/latest/usage/project/#working-with-version-control .pdm.toml .pdm-python .pdm-build/ # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm __pypackages__/ # Celery stuff celerybeat-schedule celerybeat.pid # SageMath parsed files *.sage.py # Environments .env .venv env/ venv/ ENV/ env.bak/ venv.bak/ # Spyder project settings .spyderproject .spyproject # Rope project settings .ropeproject # mkdocs documentation /site # mypy .mypy_cache/ .dmypy.json dmypy.json # Pyre type checker .pyre/ # pytype static type analyzer .pytype/ # Cython debug symbols cython_debug/ # PyCharm # JetBrains specific template is maintained in a separate JetBrains.gitignore that can # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore # and can be added to the global gitignore or merged into this file. For a more nuclear # option (not recommended) you can uncomment the following to ignore the entire idea folder. .idea/ # Zed editor # Ignores the folder created when setting Project Settings in the Zed editor. Can be commented out # to share Project Settings within a team .zed

# 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:3.14 # Install system packages USER root RUN apt-get update && \ apt-get install -y --no-install-recommends \ ffmpeg && \ rm -rf /var/lib/apt/lists/* RUN apt-get update && \ apt-get install -y curl unzip && \ curl -fsSL https://deno.land/install.sh | sh && \ mv /root/.deno/bin/deno /usr/local/bin/deno && \ chmod +x /usr/local/bin/deno && \ deno --version # Switch back to the default user USER myuser RUN deno --version || echo "Deno is NOT installed" # 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 --chown=myuser:myuser 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 --chown=myuser:myuser . ./ # Use compileall to ensure the runnability of the Actor Python code. RUN python -m compileall -q my_actor/ # Specify how to launch the source code of your Actor. CMD ["python", "-m", "my_actor"]

shit-1

.actor/actor.json

.actor/input_schema.json

.actor/output_schema.json

my_actor/__init__.py

my_actor/__main__.py

my_actor/main.py

my_actor/py.typed

my_actor/routes.py

.dockerignore

.gitignore

Dockerfile

requirements.txt

You might also like

Actor 1

Your Actor 1

Reviews

Website Scraper

Website Scraper

Website Scraper

Jobs data

My Actor 3

Leads Data

Tiktok Scraper

.actor/actor.json

.actor/input_schema.json

.actor/output_schema.json

my_actor/__init__.py

my_actor/__main__.py

my_actor/main.py

my_actor/py.typed

my_actor/routes.py

.dockerignore

.gitignore

Dockerfile

requirements.txt

my_actor/init.py

my_actor/main.py

my_actor/init.py

my_actor/main.py