A simple scraper designed to get a list summary of every event that student organizations have posted to UMD's Orgsync platform.. because they won't allow access to their REST api

UMD_Orgsync_Web_Scraper

# Require the gems
require 'capybara/poltergeist'
require 'selenium-webdriver'
require 'json'

# Configure Poltergeist to not blow up on websites with js errors
Capybara.register_driver :poltergeist do |app|
  Capybara::Poltergeist::Driver.new(app, js_errors: false)
end

# Configure Capybara to use Poltergeist as the driver (good for headless)
Capybara.default_driver = :poltergeist

# Configure Capybara to use Selenium as the driver (good for debugging)
# Capybara.default_driver = :selenium

# Go to the URL
browser = Capybara.current_session
url  = "https://orgsync.com/141/community/calendar"
browser.visit url

# Switch to list view
links = browser.all 'div.osw-events-index-view-tabs button.osw-button'
link = links[1]
link.click

# Get the containing div for events
eventlist = browser.find("div.osw-events-list")
events = eventlist.all("div.osw-events-list-item")


# Iterate through each event in the list, and open the modal when clicked 
events.each do |event|

	event_hash = {}

	event.find(".osw-events-list-item-picture-container").click

	# a popup appears with the condensed information for each event
	title = event.find("a.osw-events-show-title").text
	date = event.all(".osw-events-show-section-main")[0].all("div")[0].text # @hack
	time = event.find(".osw-events-show-time").text
	location = event.find(".osw-events-show-location").text
	organization = event.find(".osw-events-show-portal-name").text
	
	# put it in a hash for organization
	event_hash["organization"] = organization
	event_hash["event_title"] = title
	event_hash["date"] = date
	event_hash["time"] = time
	event_hash["location"] = location

	# print the information out
	puts JSON.pretty_generate(event_hash)

	#close modal
	event.find("i.osw-popup-close-button").click
end