Method: Wmap::UrlCrawler::AdwareTag#get_ver

Defined in:
lib/wmap/url_crawler/adware_tag.rb

#get_ver(url, tag) ⇒ Object

Search the url payload for known tag version identifier. If found return a string, else empty string.



210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
# File 'lib/wmap/url_crawler/adware_tag.rb', line 210

def get_ver(url,tag)
  puts "Search and return tag version within the url payload: #{url}, #{tag}" if @verbose
  tag_ver=""
  doc = open_page(url)
  case tag
  when "utag.js"          # sample: ...,"code_release_version":"cb20190312032612",...
    doc.text.each_line do |line|
      my_line = line.downcase
      if my_line.include?("code_release_version")
        puts "Extract tag version from line: #{my_line}" if @verbose
        m = my_line.match(/\"code\_release\_version\"\:\"(?<ver>[a-z]+\d+)\"/)
        tag_ver = m[:ver]
        break
      end
    end
  when "analytics.js"         # sample #1:   ga('create', 'UA-19175804-2', 'knopfdoubleday.com');
    doc.text.each_line do |line|
      my_line = line.downcase
      if my_line.include?("ga") && my_line.include?("create")   #sample #2: __gaTracker('create', 'UA-121313929-1', 'auto');
        puts "Extract tag version from line: #{my_line}" if @verbose
        m = my_line.match(/[\'|\"]create[\'|\"]\s*\,\s*[\'|\"](?<ver>\w+\-\d+\-\d+)[\'|\"]\s*\,/)
        tag_ver = m[:ver]
        break
      end
    end
  when "ga.js"
    doc.text.each_line do |line|
      my_line = line.downcase
      puts my_line if @verbose
      if my_line.include?("push") && my_line.include?("_setaccount")  # # sample #1:   _gaq.push(['_setAccount', 'UA-13205363-65']);
        m = my_line.match(/[\'|\"]\_setaccount[\'|\"]\s*\,\s*[\'|\"](?<ver>\w+\-\d+\-\d+)[\'|\"]/)
        tag_ver = m[:ver]
        break
      end
      if my_line.include?("_gettracker")  # sample #2: var pageTracker = _gat._getTracker("UA-12487327-1");
        puts "Extract tag version from line: #{my_line}" if @verbose
        m = my_line.match(/\_gettracker\s*\(\s*[\'|\"](?<ver>\w+\-\d+\-\d+)[\'|\"]/)
        tag_ver = m[:ver]
        break
      end

    end
  when "all.js"          # sample:    appId      : '749936668352954',
    doc.text.each_line do |line|
      my_line = line.downcase
      if my_line.include?("appid") && my_line.include?(":")
        puts "Extract tag version from line: #{my_line}" if @verbose
        m = my_line.match(/appid\s+\:\s+[\'|\"](?<ver>\d+)[\'|\"]\s*\,/)
        tag_ver = m[:ver]
        break
      end
    end

  else
    puts "Don't know how to locate Adware Tag version: #{tag}"
    # do nothing
  end
  doc = nil
  return tag_ver.upcase
rescue => ee
  puts "Exception on method #{__method__}: #{ee}: #{url} : #{tag}" if @verbose
  return tag_ver
end