FROM ruby:alpine
#FROM ruby:slim-bullseye

WORKDIR /app

#RUN apt-get update \
#&& apt-get -y install git \ 
#&& git clone https://github.com/JupriGH/apify-ruby-sdk.git \
#&& gem install async-websocket

RUN apk add git --no-cache \
&& git clone https://github.com/JupriGH/apify-ruby-sdk.git \
&& apk add build-base --no-cache \
&& gem install async-websocket sys-proctable mime-types awesome_print colorize  \
&& apk del build-base \
&& rm -rf /var/cache/apk/* \
&& df

COPY . .

CMD ruby -W0 src/main.rb

.actor/actor.json

{
    "actorSpecification": 1,
    "name": "my-actor-4",
    "title": "Empty Python project",
    "description": "Empty project in Python.",
    "version": "0.0",
    "buildTag": "latest",
    "meta": {
        "templateId": "python-empty"
    },
    "dockerfile": "./Dockerfile"
}

.actor/input_schema.json

{
    "title": "Ruby SDK",
    "description": "Testing Ruby inputs.",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "secret_message": { "title": "Secret",  "type": "string",  "editor": "textfield", "isSecret": true, "description": "" },
        "proxy_input": { "title": "Proxy", "type": "object", "editor": "proxy", "description": ""}
    }
}

src/main.rb

### LESSON 0: line starting with "#" is comment
"""
This is also (multiline)comments
"""
### LESSON 1: QUICK LEARN RUBY SYNTAX

# import from relative folder location (.rb file)
require_relative '../apify-ruby-sdk/lib/apify_sdk'
require_relative 'stackexchange'

# import from installed library, eg: gem install json
require 'json'
require 'awesome_print'

# multiline print
puts "if you love PHP, JavaScript and Python", "then you'll love Ruby more!"

# when variable first letter is UPPERCASE, its automatically become constant (really ?)
GREEN = "🟩"
# spread assignment
RED, YELLOW = "🟥",  "🟧"
# illegal, this is supposed to be constants! (nevermind, assign it anyway, will just show ugly warnings ...)
YELLOW = "🟨"
# string formatting
TRAFFIC_LIGHTS = "#{GREEN}#{RED}#{YELLOW}"

# lambda
def pretty(node) = JSON.pretty_generate(node)
def echo(title, *args) = puts "#{TRAFFIC_LIGHTS} #{title}", *args

### LESSON 2: USING SDK

def on_abort data
	puts "ON_aborting".red, data
end
def on_persistState data
	puts "ON_persistState".red, data
end 
def on_systemInfo data
	puts "ON_systemInfo".red, data
end
def on_dummy data
	## testing if event manager catch the errors
	p undefined_variable
end

def main(actor)
	### get_env()
	#echo "ENV :", pretty(actor.get_env)
	
	### get_config() awesome_print
	echo "CONFIG :"
	ap actor.config.to_h

	### get_input()
	input = actor.get_input
	echo "INPUT :", pretty(input)

	### create_proxy_configuration()
	proxy_input = input['proxy_input'] 
	if proxy_input
		proxy_config = actor.create_proxy_configuration proxy_input
		new_proxy = proxy_config.new_url
		echo "PROXYURL :", new_proxy
	end

	### scraping ...
	echo "Scraping data ..."
	data = stackexchange(page: 1)["items"]

	### push_data() 
	if data
		actor.push_data data
		echo "PUSHDATA : #{data.length} rows."
	end

	### open_dataset()
	dataset = actor.open_dataset
	info = dataset.get_info
	echo "DATASET :", pretty(info)
	
	### get_data()
	data = dataset.get_data
	
	# print 2 items start from index 5 
	echo "DATA :", pretty(data.items[5,2])

	# on()
	echo "Listening platform events ... (try aborting gracefully)"
	
	actor.on "aborting", method(:on_abort) 
	actor.on "persistState", method(:on_persistState)
	actor.on "systemInfo", method(:on_systemInfo)
	actor.on "systemInfo", method(:on_dummy)

	echo "sleeping 10 seconds ..."
	sleep 10

	actor.set_status_message "Another successful mission !!", is_terminal: true
end

### enable logger
logger = Apify::Log
logger.level = Logger::DEBUG
logger.formatter = Apify::ActorLogFormatter.new

### do the thing!
# Apify::Actor.main( method(:main) )

Async do
	with Apify::Actor do |actor|
		main actor
	end
end

src/stackexchange.rb

#------------------------------------------------------------------------------------------------------
def stackexchange page: 1
	# Define the URL and JSON data
	url = 'https://api.stackexchange.com/2.2/questions'
		
	uri = URI.parse(url)
	params = { site: 'stackoverflow', page: page }
	uri.query = URI.encode_www_form params

	# start session
	Net::HTTP.start(uri.host, uri.port, use_ssl: uri.scheme == 'https') do |http|

		# Create the request
		req = Net::HTTP::Get.new uri
		req['User-Agent'] = 'Chrome'

		# Perform the request
		res = http.request(req)
	
		# Handle the response
		if res.is_a?(Net::HTTPSuccess)			
			puts "Success: #{res.code}"
			return JSON.parse res.body 
		else
			raise "HTTP Error: #{res.code}"
		end
	end
end

Taxdeed_Scraper

itz_quinn/taxdeed-scraper

Scrapes tax deed sale data from Duval and Clay County Clerk websites using Playwright and Apify SDK.

Ishara Samarathunga

Example Sitemap Cheerio

jancurn/example-sitemap-cheerio

An example actor that first downloads a sitemap in XML format and the crawls each page from the sitemap using the fast CheerioCrawler from Apify SDK.

Jan Čurn

Bandcamp Crawler

service-paradis/bandcamp-crawler

The Bandcamp.com crawler is a web scraping tool that allows you to extract data from the Bandcamp music platform. With this crawler, you can get information about albums, tracks, and much more. The crawler is built on top of Apify SDK, and you can run it both on the Apify platform and locally.

Alexandre Paradis

Apify Store Scraper 2025

jupri/apify-store

💫 Apify.com Store Extension

cat

🎉 Apify Users

prog-party/apify-users

This Apify Users Actor retrieves data from Apify, allowing to filter, and returns a list of users as a Dataset.

Prog Party

Apify Store Scraper API

louisdeconinck/apify-store-scraper-api

The Apify Store Scraper API allows you to extract detailed information about actors from the Apify Store, including actor details, pricing, metrics, categories, and user information.

Louis Deconinck

5.0

Apify public actor scraper

eloquent_mountain/apify-public-actor-scraper

Apify Store Actor Scraper Efficiently scrape comprehensive data from Apify Store actors using Selenium. Extracts key information such as URL, Title, Creator, Description, Users, and Stars

Paco

Apify Actor Request Collector [not made by Apify]

eloquent_mountain/apify-actor-request-collector

Submit your ideas for new Apify scrapers or actors with the Apify Actor Request Collector. Provide suggestions and an optional email to get updates if your requested actor is built. Created by a community member to enhance your Apify experience!

Paco