Apify Unofficial SDK

1FROM ruby:alpine
2#FROM ruby:slim-bullseye
3
4WORKDIR /app
5
6#RUN apt-get update \
7#&& apt-get -y install git \ 
8#&& git clone https://github.com/JupriGH/apify-ruby-sdk.git \
9#&& gem install async-websocket
10
11RUN apk add git --no-cache \
12&& git clone https://github.com/JupriGH/apify-ruby-sdk.git \
13&& apk add build-base --no-cache \
14&& gem install async-websocket sys-proctable mime-types awesome_print colorize  \
15&& apk del build-base \
16&& rm -rf /var/cache/apk/* \
17&& df
18
19COPY . .
20
21CMD ruby -W0 src/main.rb

1{
2    "actorSpecification": 1,
3    "name": "my-actor-4",
4    "title": "Empty Python project",
5    "description": "Empty project in Python.",
6    "version": "0.0",
7    "buildTag": "latest",
8    "meta": {
9        "templateId": "python-empty"
10    },
11    "dockerfile": "./Dockerfile"
12}

1{
2    "title": "Ruby SDK",
3    "description": "Testing Ruby inputs.",
4    "type": "object",
5    "schemaVersion": 1,
6    "properties": {
7        "secret_message": { "title": "Secret",  "type": "string",  "editor": "textfield", "isSecret": true, "description": "" },
8        "proxy_input": { "title": "Proxy", "type": "object", "editor": "proxy", "description": ""}
9    }
10}

1### LESSON 0: line starting with "#" is comment
2"""
3This is also (multiline)comments
4"""
5### LESSON 1: QUICK LEARN RUBY SYNTAX
6
7# import from relative folder location (.rb file)
8require_relative '../apify-ruby-sdk/lib/apify_sdk'
9require_relative 'stackexchange'
10
11# import from installed library, eg: gem install json
12require 'json'
13require 'awesome_print'
14
15# multiline print
16puts "if you love PHP, JavaScript and Python", "then you'll love Ruby more!"
17
18# when variable first letter is UPPERCASE, its automatically become constant (really ?)
19GREEN = "🟩"
20# spread assignment
21RED, YELLOW = "🟥",  "🟧"
22# illegal, this is supposed to be constants! (nevermind, assign it anyway, will just show ugly warnings ...)
23YELLOW = "🟨"
24# string formatting
25TRAFFIC_LIGHTS = "#{GREEN}#{RED}#{YELLOW}"
26
27# lambda
28def pretty(node) = JSON.pretty_generate(node)
29def echo(title, *args) = puts "#{TRAFFIC_LIGHTS} #{title}", *args
30
31### LESSON 2: USING SDK
32
33def on_abort data
34	puts "ON_aborting".red, data
35end
36def on_persistState data
37	puts "ON_persistState".red, data
38end 
39def on_systemInfo data
40	puts "ON_systemInfo".red, data
41end
42def on_dummy data
43	## testing if event manager catch the errors
44	p undefined_variable
45end
46
47def main(actor)
48	### get_env()
49	#echo "ENV :", pretty(actor.get_env)
50	
51	### get_config() awesome_print
52	echo "CONFIG :"
53	ap actor.config.to_h
54
55	### get_input()
56	input = actor.get_input
57	echo "INPUT :", pretty(input)
58
59	### create_proxy_configuration()
60	proxy_input = input['proxy_input'] 
61	if proxy_input
62		proxy_config = actor.create_proxy_configuration proxy_input
63		new_proxy = proxy_config.new_url
64		echo "PROXYURL :", new_proxy
65	end
66
67	### scraping ...
68	echo "Scraping data ..."
69	data = stackexchange(page: 1)["items"]
70
71	### push_data() 
72	if data
73		actor.push_data data
74		echo "PUSHDATA : #{data.length} rows."
75	end
76
77	### open_dataset()
78	dataset = actor.open_dataset
79	info = dataset.get_info
80	echo "DATASET :", pretty(info)
81	
82	### get_data()
83	data = dataset.get_data
84	
85	# print 2 items start from index 5 
86	echo "DATA :", pretty(data.items[5,2])
87
88	# on()
89	echo "Listening platform events ... (try aborting gracefully)"
90	
91	actor.on "aborting", method(:on_abort) 
92	actor.on "persistState", method(:on_persistState)
93	actor.on "systemInfo", method(:on_systemInfo)
94	actor.on "systemInfo", method(:on_dummy)
95
96	echo "sleeping 10 seconds ..."
97	sleep 10
98
99	actor.set_status_message "Another successful mission !!", is_terminal: true
100end
101
102### enable logger
103logger = Apify::Log
104logger.level = Logger::DEBUG
105logger.formatter = Apify::ActorLogFormatter.new
106
107### do the thing!
108# Apify::Actor.main( method(:main) )
109
110Async do
111	with Apify::Actor do |actor|
112		main actor
113	end
114end

1#------------------------------------------------------------------------------------------------------
2def stackexchange page: 1
3	# Define the URL and JSON data
4	url = 'https://api.stackexchange.com/2.2/questions'
5		
6	uri = URI.parse(url)
7	params = { site: 'stackoverflow', page: page }
8	uri.query = URI.encode_www_form params
9
10	# start session
11	Net::HTTP.start(uri.host, uri.port, use_ssl: uri.scheme == 'https') do |http|
12
13		# Create the request
14		req = Net::HTTP::Get.new uri
15		req['User-Agent'] = 'Chrome'
16
17		# Perform the request
18		res = http.request(req)
19	
20		# Handle the response
21		if res.is_a?(Net::HTTPSuccess)			
22			puts "Success: #{res.code}"
23			return JSON.parse res.body 
24		else
25			raise "HTTP Error: #{res.code}"
26		end
27	end
28end