Class: Wmap::WpTracker

Inherits:
Object
  • Object
show all
Includes:
Utils
Defined in:
lib/wmap/wp_tracker.rb

Overview

Main class to automatically track the site inventory

Constant Summary

Constants included from Utils::UrlMagic

Utils::UrlMagic::Max_http_timeout

Constants included from Utils::DomainRoot

Utils::DomainRoot::File_ccsld, Utils::DomainRoot::File_cctld, Utils::DomainRoot::File_gtld, Utils::DomainRoot::File_tld

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from Utils

#cidr_2_ips, #file_2_hash, #file_2_list, #get_nameserver, #get_nameservers, #host_2_ip, #host_2_ips, #is_cidr?, #is_fqdn?, #is_ip?, #list_2_file, #reverse_dns_lookup, #sort_ips, #valid_dns_record?, #zone_transferable?

Methods included from Utils::Logger

#wlog

Methods included from Utils::UrlMagic

#create_absolute_url_from_base, #create_absolute_url_from_context, #host_2_url, #is_site?, #is_ssl?, #is_url?, #landing_location, #make_absolute, #normalize_url, #open_page, #redirect_location, #response_code, #url_2_host, #url_2_path, #url_2_port, #url_2_site, #urls_on_same_domain?

Methods included from Utils::DomainRoot

#get_domain_root, #get_domain_root_by_ccsld, #get_domain_root_by_cctld, #get_domain_root_by_tlds, #get_sub_domain, #is_domain_root?, #print_ccsld, #print_cctld, #print_gtld

Constructor Details

#initialize(params = {}) ⇒ WpTracker

WordPress checker instance default variables



25
26
27
28
29
30
31
32
33
34
35
36
# File 'lib/wmap/wp_tracker.rb', line 25

def initialize (params = {})
	@verbose=params.fetch(:verbose, false)
	@data_dir=params.fetch(:data_dir, File.dirname(__FILE__)+'/../../data/')
	Dir.mkdir(@data_dir) unless Dir.exist?(@data_dir)
   wp_sites=@data_dir+'wp_sites'
   @file_wps=params.fetch(:sites_wp, wp_sites)
	@http_timeout=params.fetch(:http_timeout, 5000)
	@max_parallel=params.fetch(:max_parallel, 40)
	Dir.mkdir(@data_dir) unless Dir.exist?(@data_dir)
	@log_file=@data_dir + "wp_checker.log"
   @known_wp_sites=load_from_file(@file_wps)
end

Instance Attribute Details

#data_dirObject

include Singleton



21
22
23
# File 'lib/wmap/wp_tracker.rb', line 21

def data_dir
  @data_dir
end

#http_timeoutObject

include Singleton



21
22
23
# File 'lib/wmap/wp_tracker.rb', line 21

def http_timeout
  @http_timeout
end

#known_wp_sitesObject (readonly)

Returns the value of attribute known_wp_sites.



22
23
24
# File 'lib/wmap/wp_tracker.rb', line 22

def known_wp_sites
  @known_wp_sites
end

#max_parallelObject

include Singleton



21
22
23
# File 'lib/wmap/wp_tracker.rb', line 21

def max_parallel
  @max_parallel
end

#sites_wpObject

include Singleton



21
22
23
# File 'lib/wmap/wp_tracker.rb', line 21

def sites_wp
  @sites_wp
end

#verboseObject

include Singleton



21
22
23
# File 'lib/wmap/wp_tracker.rb', line 21

def verbose
  @verbose
end

Instance Method Details

#add(url, use_cache = true) ⇒ Object

‘setter’ to add wordpress entry to the cache one at a time



88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
# File 'lib/wmap/wp_tracker.rb', line 88

def add(url, use_cache=true)
  puts "Add entry to the local cache table: #{url}" if @verbose
   site=url_2_site(url)
	if use_cache && @known_wp_sites.key?(site)
		puts "Site is already exist. Skipping: #{site}"
	else
		record=Hash.new
		redirection = landing_location(site)
		if is_wp?(redirection)
			version = wp_ver(site)
       record['site'] = site
			record['version'] = version
			record['redirection'] = redirection
			@known_wp_sites[site]=record
			puts "Entry loaded: #{record}"
		end
	end
   return record
rescue => ee
	puts "Exception on method #{__method__}: #{ee}: #{url}" if @verbose
end

#is_wp?(url) ⇒ Boolean

logic to determin if it’s a wordpress site

Returns:

  • (Boolean)


111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
# File 'lib/wmap/wp_tracker.rb', line 111

def is_wp?(url)
	site=url_2_site(url)
	if wp_readme?(site)
		found=true
	elsif wp_css?(site)
		found=true
	elsif wp_meta?(site)
		found=true
	elsif wp_login?(site)
		found=true
	elsif wp_rpc?(site)
		found=true
	else
		found=false
	end
	return found
rescue => ee
	puts "Exception on method #{__method__}: #{ee}: #{url}" if @verbose
end

#load_from_file(file = @file_stores, lc = true) ⇒ Object

‘setter’ to load the known wordpress sites into an instance variable



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
# File 'lib/wmap/wp_tracker.rb', line 40

def load_from_file (file=@file_stores, lc=true)
	puts "Loading trusted file: #{file}"	if @verbose
	known_wp_sites=Hash.new
	f_wp_sites=File.open(file, 'r')
	f_wp_sites.each_line do |line|
		puts "Processing line: #{line}" if @verbose
		line=line.chomp.strip
		next if line.nil?
		next if line.empty?
		next if line =~ /^\s*#/
		line=line.downcase if lc==true
		entry=line.split(',')
		site = entry[0].strip()
		if known_wp_sites.key?(site)
			next
		else
			known_wp_sites[site] = Hash.new
			known_wp_sites[site]['site'] = site
			known_wp_sites[site]['version'] = entry[1].strip()
			known_wp_sites[site]['redirection'] = entry[2].strip()
		end

	end
	f_wp_sites.close
	return known_wp_sites
rescue => ee
	puts "Exception on method #{__method__}: #{ee}" if @verbose
	return Hash.new
end

#refresh(target, use_cache = false) ⇒ Object

Refresh one site entry then update the instance variable (cache)



132
133
134
# File 'lib/wmap/wp_tracker.rb', line 132

def refresh (target,use_cache=false)
	return add(target,use_cache)
end

#refreshs(num = @max_parallel, use_cache = false) ⇒ Object

Refresh wordpress site entries within the sitetracker list



137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
# File 'lib/wmap/wp_tracker.rb', line 137

def refreshs (num=@max_parallel,use_cache=false)
  puts "Add entries to the local cache table from site tracker: " if @verbose
	results=Hash.new
	wps=Wmap::SiteTracker.instance.known_sites.keys
	if wps.size > 0
		Parallel.map(wps, :in_processes => num) { |target|
			refresh(target,use_cache)
		}.each do |process|
			if process.nil?
				next
			elsif process.empty?
				#do nothing
			else
				site = process['site']
				results[site] = process
			end
		end
		@known_wp_sites.merge!(results)
		puts "Done loading entries."
		return results
	else
		puts "Error: no entry is loaded. Please check your list and try again."
	end
	wps=nil
	return results
rescue => ee
	puts "Exception on method #{__method__}: #{ee}" if @verbose
	return Hash.new
end

#save_to_file!(file_wps = @file_wps, wps = @known_wp_sites) ⇒ Object Also known as: save!

Save the current hash table into a file



71
72
73
74
75
76
77
78
79
80
81
82
83
84
# File 'lib/wmap/wp_tracker.rb', line 71

def save_to_file!(file_wps=@file_wps, wps=@known_wp_sites)
	puts "Saving the current wordpress site table from memory to file: #{file_wps} ..." if @verbose
	timestamp=Time.now
	f=File.open(file_wps, 'w')
	f.write "# Local wps file created by class #{self.class} method #{__method__} at: #{timestamp}\n"
	f.write "# WP Site URL, WP Version, Redirection \n"
	wps.keys.sort.map do |key|
		f.write "#{key}, #{wps[key]['version']}, #{wps[key]['redirection']}\n"
	end
	f.close
	puts "WordPress site cache table is successfully saved: #{file_wps}"
rescue => ee
	puts "Exception on method #{__method__}: #{ee}" if @verbose
end

#wp_css?(url) ⇒ Boolean

Wordpress detection checkpoint - install.css

Returns:

  • (Boolean)


191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
# File 'lib/wmap/wp_tracker.rb', line 191

def wp_css?(url)
site = url_2_site(url)
  css_url = site + "wp-admin/css/install.css"
  k=Wmap::UrlChecker.new
  if k.response_code(css_url) == 200
    k=nil
    parser = CssParser::Parser.new
    parser.load_uri!(css_url)
    rule = parser.find_by_selector('#logo a')
    if rule.length >0
      if rule[0] =~ /wordpress/i
        return true
      end
    end
  else
    k=nil
    return false
  end
  return false
	rescue => ee
puts "Exception on method #{__method__} for site #{url}: #{ee}" if @verbose
return false
end

#wp_login?(url) ⇒ Boolean

Wordpress detection checkpoint - wp-login

Returns:

  • (Boolean)


236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
# File 'lib/wmap/wp_tracker.rb', line 236

def wp_login?(url)
site=url_2_site(url)
=site + "wp-login.php"
  k=Wmap::UrlChecker.new
  if k.response_code() == 200
    k=nil
    doc=open_page()
    links=doc.css('link')
    if links.to_s =~ /login.min.css/i
      return true
    else
      return false
    end
  end
return false
	rescue => ee
puts "Exception on method #{__method__} for url #{url}: #{ee}" if @verbose
return false
end

#wp_meta?(url) ⇒ Boolean

Wordpress detection checkpoint - meta generator

Returns:

  • (Boolean)


216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
# File 'lib/wmap/wp_tracker.rb', line 216

def wp_meta?(url)
site=url_2_site(url)
  k=Wmap::UrlChecker.new
  if k.response_code(site) == 200
    k=nil
    doc=open_page(site)
    meta=doc.css('meta')
    if meta.to_s =~ /wordpress/i
      return true
    else
      return false
    end
  end
return false
	rescue => ee
puts "Exception on method #{__method__} for url #{url}: #{ee}" if @verbose
return false
end

#wp_readme?(url) ⇒ Boolean

Wordpress detection checkpoint - readme.html

Returns:

  • (Boolean)


168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
# File 'lib/wmap/wp_tracker.rb', line 168

def wp_readme?(url)
site = url_2_site(url)
  readme_url=site + "readme.html"
  k=Wmap::UrlChecker.new
  if k.response_code(readme_url) == 200
    k=nil
    doc=open_page(readme_url)
    title=doc.css('title')
    if title.to_s =~ /wordpress/i
      return true
    else
      return false
    end
  else
    k=nil
    return false
  end
	rescue => ee
puts "Exception on method #{__method__} for site #{url}: #{ee}" if @verbose
return false
end

#wp_rpc?(url) ⇒ Boolean

Wordpress detection checkpoint - xml-rpc

Returns:

  • (Boolean)


257
258
259
260
261
262
263
264
265
266
267
268
269
270
# File 'lib/wmap/wp_tracker.rb', line 257

def wp_rpc?(url)
site=url_2_site(url)
rpc_url=site + "xmlrpc.php"
  k=Wmap::UrlChecker.new
#puts "res code", k.response_code(rpc_url)
  if k.response_code(rpc_url) == 405 # method not allowed
    k=nil
    return true
  end
return false
	rescue => ee
puts "Exception on method #{__method__} for url #{url}: #{ee}" if @verbose
return false
end

#wp_ver(url) ⇒ Object

Extract the WordPress version



273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
# File 'lib/wmap/wp_tracker.rb', line 273

def wp_ver(url)
	if !wp_ver_readme(url).nil?
		return wp_ver_readme(url)
	elsif !wp_ver_meta(url).nil?
		return wp_ver_meta(url)
	elsif !(url,"login.min.css").nil?
		return (url,"login.min.css")
	elsif !(url,"buttons.min.css").nil?
		return (url,"buttons.min.css")
	elsif !(url,"wp-admin.min.css").nil?
		return (url,"wp-admin.min.css")
	else
		return nil
	end
rescue => ee
	puts "Exception on method #{__method__} for url #{url}: #{ee}" if @verbose
	return nil
end

#wp_ver_login(url, pattern) ⇒ Object

Identify wordpress version through the login page



293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
# File 'lib/wmap/wp_tracker.rb', line 293

def (url,pattern)
puts "Check for #{pattern}" if @verbose
site=url_2_site(url)
=site + "wp-login.php"
  k=Wmap::UrlChecker.new
#puts "Res code: #{k.response_code(login_url)}" if @verbose
  if k.response_code() == 200
    doc=open_page()
	#puts doc.inspect
    links=doc.css('link')
	#puts links.inspect if @verbose
	links.each do |tag|
     if tag.to_s.include?(pattern)
			puts tag.to_s if @verbose
			k=nil
       return tag.to_s.scan(/[\d+\.]+\d+/).first
     end
	end
  end
  k=nil
  return nil
	rescue => ee
puts "Exception on method #{__method__} for url #{url}: #{ee}" if @verbose
return nil
end

#wp_ver_meta(url) ⇒ Object

Identify wordpress version through the meta link



320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
# File 'lib/wmap/wp_tracker.rb', line 320

def wp_ver_meta(url)
site=url_2_site(url)
  k=Wmap::UrlChecker.new
  if k.response_code(site) == 200
    doc=open_page(site)
	#puts doc.inspect
    meta=doc.css('meta')
	#puts meta.inspect
	meta.each do |tag|
     if tag.to_s =~ /wordpress/i
			#puts tag.to_s
			k=nil
       return tag.to_s.scan(/[\d+\.]+\d+/).first
     end
	end
  end
  k=nil
  return nil
	rescue => ee
puts "Exception on method #{__method__} for url #{url}: #{ee}" if @verbose
return nil
end

#wp_ver_readme(url) ⇒ Object

Wordpress version detection via - readme.html



344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
# File 'lib/wmap/wp_tracker.rb', line 344

def wp_ver_readme(url)
	site=url_2_site(url)
   readme_url=site + "readme.html"
   k=Wmap::UrlChecker.new
	puts "Res code: #{k.response_code(readme_url)}" if @verbose
   if k.response_code(readme_url) == 200
     k=nil
     doc=open_page(readme_url)
		puts doc if @verbose
     =doc.css('h1#logo')[0]
     puts .inspect if @verbose
		return .to_s.scan(/[\d+\.]+\d+/).first
   end
   k=nil
   return nil
rescue => ee
	puts "Exception on method #{__method__} for url #{url}: #{ee}" if @verbose
	return nil
end