GitHub Stars
Try for free
No credit card required
Go to Store
GitHub Stars
sauain/github-stars
Try for free
No credit card required
Input will be the URL of any GitHub repository, and output will be GitHub Stars.
.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-selenium: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-1",
4 "title": "Getting started with Python and Selenium",
5 "description": "Scrapes titles of websites using Selenium.",
6 "version": "0.0",
7 "meta": {
8 "templateId": "python-selenium"
9 },
10 "input": "./input_schema.json",
11 "dockerfile": "./Dockerfile",
12 "storages": {
13 "dataset": {
14 "actorSpecification": 1,
15 "title": "Name of repo and stars",
16 "views": {
17 "titles": {
18 "title": "Name of repo and stars",
19 "transformation": {
20 "fields": [
21 "repo_name",
22 "stars_count"
23 ]
24 },
25 "display": {
26 "component": "table",
27 "properties": {
28 "repo_name": {
29 "label": "Name",
30 "format": "text"
31 },
32 "star_count": {
33 "label": "Stars",
34 "format": "text"
35 }
36 }
37 }
38 }
39 }
40 }
41 }
42}
.actor/input_schema.json
1{
2 "title": "Python Selenium Scraper",
3 "type": "object",
4 "schemaVersion": 1,
5 "properties": {
6 "start_urls": {
7 "title": "Start URLs",
8 "type": "array",
9 "description": "URLs to start with",
10 "prefill": [
11 { "url": "https://github.com/apify/crawlee" }
12 ],
13 "editor": "requestListSources"
14 },
15 "max_depth": {
16 "title": "Maximum depth",
17 "type": "integer",
18 "description": "Depth to which to scrape to",
19 "default": 1
20 }
21 },
22 "required": ["start_urls"]
23}
src/__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
1from selenium import webdriver
2from selenium.webdriver.chrome.options import Options as ChromeOptions
3from selenium.webdriver.common.by import By
4from selenium.webdriver.support.ui import WebDriverWait
5from selenium.webdriver.support import expected_conditions as EC
6from apify import Actor
7
8async def main() -> None:
9 async with Actor() as actor:
10 repo_url = 'https://github.com/apify/crawlee' # Example repository URL
11
12 chrome_options = ChromeOptions()
13 if actor.config.headless:
14 chrome_options.add_argument('--headless')
15 chrome_options.add_argument('--no-sandbox')
16 chrome_options.add_argument('--disable-dev-shm-usage')
17 driver = webdriver.Chrome(options=chrome_options)
18
19 try:
20 driver.get(repo_url)
21
22 wait = WebDriverWait(driver, 10)
23 repo_name_element = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "strong a[href*='/apify/crawlee']")))
24 repo_name = repo_name_element.text.strip() if repo_name_element else 'Repo name not found'
25
26 stars_element = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "a.Link--muted[href*='/stargazers'] strong")))
27 stars_count = stars_element.text.strip() if stars_element else '0'
28
29
30
31 print(f"Repository: {repo_name}, Stars: {stars_count}")
32 await actor.push_data({
33 'repo_url': repo_url,
34 'repo_name': repo_name,
35 'stars_count': stars_count
36 })
37
38 except Exception as e:
39 actor.log.exception(f'Cannot extract data from {repo_url}. Exception: {e}')
40 finally:
41 driver.quit()
.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
9.venv/
10.env/
11__pypackages__
12dist/
13build/
14*.egg-info/
15*.egg
16
17__pycache__
18
19.mypy_cache
20.dmypy.json
21dmypy.json
22.pytest_cache
23.ruff_cache
24
25.scrapy
26*.log
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 ~= 1.5.1
5selenium ~= 4.14.0
Developer
Maintained by Community
Actor Metrics
1 monthly user
-
1 star
>99% runs succeeded
Created in Jan 2024
Modified 10 months ago
Categories