Class: WLSearchScraper
- Inherits:
-
Object
- Object
- WLSearchScraper
- Defined in:
- lib/wlsearchscraper.rb
Instance Method Summary collapse
- #cableParser(url) ⇒ Object
-
#initialize(searchterms) ⇒ WLSearchScraper
constructor
A new instance of WLSearchScraper.
-
#scrape ⇒ Object
Returns array of document URLs matching search terms.
Constructor Details
#initialize(searchterms) ⇒ WLSearchScraper
Returns a new instance of WLSearchScraper.
6 7 8 9 |
# File 'lib/wlsearchscraper.rb', line 6 def initialize(searchterms) @searchterms = searchterms @resultlist = Array.new end |
Instance Method Details
#cableParser(url) ⇒ Object
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 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
# File 'lib/wlsearchscraper.rb', line 25 def cableParser(url) cablehash = Hash.new html = Nokogiri::HTML(open(url)) # Go through and get all the metadata and content html.css("td").each do |t| a = t.css("a") if !(a.empty?) && (a[0]["title"] == "Date") cablehash[:date] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Canonical ID") cablehash[:id] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Original Classification") cablehash[:original_classification] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Current Classification") cablehash[:current_classification] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Handling Restrictions") cablehash[:handling_restrictions] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Character Count") cablehash[:character_count] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Executive Order") cablehash[:executive_order] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Locator") cablehash[:locator] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "TAGS") cablehash[:tags] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Concepts") cablehash[:concepts] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Enclosure") cablehash[:enclosure] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Type") cablehash[:type] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Office Origin") cablehash[:office_origin] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Office Action") cablehash[:office_action] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Archive Status") cablehash[:archive_status] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "From") cablehash[:from] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "Markings") cablehash[:markings] = t.css("div[2]").text elsif !(a.empty?) && (a[0]["title"] == "To") to = t.css("div[2]").text splitto = to.split(" | ") splitarray = Array.new splitto.each do |s| splitarray.push(s.strip) end cablehash[:to] = splitarray elsif !(a.empty?) && (a[0]["title"] == "Linked documents or other documents with the same ID") cablehash[:linked_docs] = t.css("div[2]").text end end # Get cable content contentcount = 0 html.css("div").each do |d| if d["class"] == "text-content" contentcount += 1 if contentcount == 2 cablehash[:content] = d.text end end end return cablehash end |
#scrape ⇒ Object
Returns array of document URLs matching search terms
12 13 14 15 16 17 18 19 20 21 22 23 |
# File 'lib/wlsearchscraper.rb', line 12 def scrape @searchterms.gsub!(" ", "+") url = "https://search.wikileaks.org/advanced?q=" + @searchterms + "&exclude_words=&words_title_only=&words_content_only=&publication_type[]=3" html = Nokogiri::HTML(open(url)) html.css("h4").each do |h| href = h.css("a")[0]["href"] @resultlist.push(cableParser(href)) end return JSON.pretty_generate(@resultlist) end |