Scrape Number Of Videos Created For A Music In TikTok avatar
Scrape Number Of Videos Created For A Music In TikTok

Pricing

Pay per usage

Go to Store
Scrape Number Of Videos Created For A Music In TikTok

Scrape Number Of Videos Created For A Music In TikTok

Developed by

Zeyad

Zeyad

Maintained by Community

0.0 (0)

Pricing

Pay per usage

0

Total users

3

Monthly users

1

Runs succeeded

>99%

Last modified

2 months ago

.actor/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-playwright:3.13
# 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
# Install Playwright and its dependencies
RUN playwright install-deps && \
playwright install
# 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"]

.actor/actor.json

{
"actorSpecification": 1,
"name": "my-actor-1",
"title": "Getting started with Python and Playwright",
"description": "Scrapes titles of websites using Playwright.",
"version": "0.0",
"buildTag": "latest",
"meta": {
"templateId": "python-playwright"
},
"input": "./input_schema.json",
"dockerfile": "./Dockerfile"
}

.actor/input_schema.json

{
"title": "Python Playwright 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"]
}

src/__init__.py

1

src/__main__.py

1import asyncio
2
3from .main import main
4
5# Execute the Actor entry point.
6asyncio.run(main())

src/main.py

1"""Apify Actor to scrape TikTok video count from sound URLs."""
2
3from apify import Actor
4from playwright.async_api import async_playwright
5
6async def main() -> None:
7 async with Actor:
8 actor_input = await Actor.get_input() or {}
9 start_urls = actor_input.get('start_urls', [])
10
11 if not start_urls:
12 Actor.log.error('No URLs provided in start_urls!')
13 await Actor.exit()
14
15 # Process only the first URL
16 target_url = start_urls[0].get('url') if start_urls else None
17 if not target_url:
18 Actor.log.error('First URL is invalid!')
19 await Actor.exit()
20
21 async with async_playwright() as playwright:
22 browser = await playwright.chromium.launch(
23 headless=Actor.config.headless,
24 args=[
25 '--disable-gpu',
26 '--user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
27 ],
28 )
29 context = await browser.new_context(viewport={'width': 1920, 'height': 1080})
30 page = None
31
32 try:
33 page = await context.new_page()
34 await page.goto(target_url, wait_until='domcontentloaded', timeout=60000)
35
36 # Directly target the video count element
37 video_count_element = await page.wait_for_selector(
38 'h2[data-e2e="music-video-count"] strong',
39 timeout=15000
40 )
41
42 video_count = await video_count_element.text_content()
43 cleaned_count = video_count.replace(' videos', '').strip()
44
45 await Actor.push_data({
46 'url': target_url,
47 'video_count': cleaned_count
48 })
49
50 except Exception as e:
51 await Actor.push_data({
52 'url': target_url,
53 'error': f'Failed to extract video count: {str(e)}'
54 })
55
56 finally:
57 if page:
58 await page.close()
59 await context.close()
60 await browser.close()
61 await Actor.exit()

src/py.typed

.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/

.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/

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
5playwright