Class: ACLUScraper

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

Instance Method Summary collapse

Constructor Details

#initialize(url) ⇒ ACLUScraper

Returns a new instance of ACLUScraper.



7
8
9
10
 
# File 'lib/acluscraper.rb', line 7

def initialize(url)
  @url = url
  @casearray = Array.new
end

Instance Method Details

#scrapeCase ⇒ Object

Get all the case documents



13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
 
# File 'lib/acluscraper.rb', line 13

def scrapeCase
  html = Nokogiri::HTML(open(@url))
  prevdate = ""

  html.css("tbody").each do |t|
    t.css("tr").each do |r|
      if !r.css("a").empty?
        dochash = Hash.new
        
        # Get date for filing
        if r.css("td")[0].text == "\u00a0"
          dochash[:date] = prevdate
        else
          prevdate = r.css("td")[0].text.to_s
          dochash[:date] = r.css("td")[0].text.to_s
        end

        a = r.css("a")
        dochash[:title] = a.text

        # Get URL
        if a[0]["href"].to_s.include? "https://"
          dochash[:url] = a[0]["href"]
        else
          dochash[:url] = "https://www.aclu.org" + a[0]["href"]
        end
        
        # Download documents
        `wget -P public/uploads #{dochash[:url]}`
        path = dochash[:url].split("/")
        dochash[:path] = "public/uploads/" + path[path.length-1].chomp.strip

        # Extract metadata and text
        begin
          u = UploadConvert.new(dochash[:path])
          metadata = u.extractMetadataPDF
          metadata.each{|k, v| dochash[k] = v}
          dochash[:text] = u.detectPDFType
          @casearray.push(dochash)
        rescue
        end
      end
    end
  end
  
  JSON.pretty_generate(@casearray)
end