Class: MeetupCli::Scraper

Inherits:
Object
  • Object
show all
Defined in:
lib/meetup_cli/scraper.rb

Class Method Summary collapse

Class Method Details

.activities(category) ⇒ Object



26
27
28
29
30
31
32
33
34
35
36
37
38
39
# File 'lib/meetup_cli/scraper.rb', line 26

def self.activities(category)
  url = category.url
  activity_list = []
  doc = Nokogiri::HTML(open(url))
  activity_elements = doc.css("a.groupCard--photo.loading.nametag-photo")
  activity_elements.each do |element|
    name =  element.css("h3.padding-none.inline-block.loading").text.strip
    url = element['href']
    tag_line = element.css("p.small.ellipsize").text.strip
    activity = MeetupCli::Activity.new(name, url, tag_line)
    activity_list << activity
  end
  activity_list
end

.categoriesObject



12
13
14
15
16
17
18
19
20
21
22
23
24
# File 'lib/meetup_cli/scraper.rb', line 12

def self.categories
  #scrape the site and list activities
  category_list = []
  doc = Nokogiri::HTML(open("https://www.meetup.com/"))
  category_elements = doc.css(".exploreHome-categories-card")
  category_elements.each do |element|
    url = element.css("a")[0]['href']
    name = element.css("h4").text
    category = MeetupCli::Category.new(name, url)
    category_list << category
  end
  category_list
end

.list_meetup(activity) ⇒ Object



41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
# File 'lib/meetup_cli/scraper.rb', line 41

def self.list_meetup(activity)
url = activity.url
doc = Nokogiri::HTML(open(url))
activity.about = doc.css("div.group-description.runningText").css("p").text
activity.organiser = doc.css("span.text--bold.text--small")[0].text
#others = doc.css("p.orgInfo-otherLeadership.display--inline.text--small")[0].text
#[activity.organiser, others].join(' ')
activity.location = doc.css("ul.inlineblockList.inlineblockList--separated").css("span")[0].text
activity.total_members = doc.css("ul.inlineblockList.inlineblockList--separated").css("span")[1].text
activity.type_of_group = doc.css("ul.inlineblockList.inlineblockList--separated").css("span")[2].text

meetup = MeetupCli::Meetup.new
#use poltergiest to extract java script data from website
new_url = [url, "events"].join
session = Capybara::Session.new(:poltergeist)
session.visit(new_url)
#check if it has upcoming meetups
upcoming = false
begin
  session.first(".emptyEventCard").text
rescue
  Capybara::ExpectationNotMet
  upcoming = true
end
if upcoming == true
  begin
  meetup.name = session.first(".eventCardHead--title")['innerHTML']
  meetup.time_object = session.first(".eventTimeDisplay-startDate span")['innerHTML']
  meetup.venue = session.first(".venueDisplay").text
  meetup.host = session.first(".text--secondary.text--tiny").text
  meetup.about =session.first(".eventCard--MainContent div").text
  meetup.attendees =session.first(".avatarRow--attendingCount").text
  meetup.upcoming = upcoming
rescue
  Capybara::ExpectationNotMet
end
else
   meetup.upcoming = upcoming
end
  activity.meetup = meetup
end