Class: Socialinvestigator::Client::NetClient

Inherits:
Object
  • Object
show all
Defined in:
lib/socialinvestigator/client/net.rb

Instance Method Summary collapse

Instance Method Details

#check_regex(mashed_regex, value) ⇒ Object 



474
475
476
477
478
479
480
481
482
483
484
485
486
 
# File 'lib/socialinvestigator/client/net.rb', line 474

def check_regex( mashed_regex, value )
  regex,result = mashed_regex.split( /\\;/ )
  md = Regexp.new( regex ).match( value )
  if md
    if result
      result = result.gsub( /\\1/, (md[1] || "" )).gsub( /\\2/, (md[2] || "") )
    else
      true
    end
  else
    false
  end
end

#find_id_path(links, regex) ⇒ Object 



459
460
461
462
463
464
465
466
467
468
469
470
471
472
 
# File 'lib/socialinvestigator/client/net.rb', line 459

def find_id_path( links, regex )
  links.collect do |link|
    if regex.match( link )
      res = $1 || link
      if (res =~ /share/)
        nil
      else
        res
      end
    end
  end.select do |x|
    x
  end.uniq
end

#get_knowledge(url, noreverse = false, debug = false) ⇒ Object

Look up the domain



130
131
132
133
134
135
136
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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
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
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
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
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
 
# File 'lib/socialinvestigator/client/net.rb', line 130

def get_knowledge( url, noreverse = false, debug = false )
  data = Socialinvestigator::Client::Net::PageKnowledge.new( debug )
  dns = Socialinvestigator::Client::Net::DNS.new

  uri = URI( url )

  data.remember( :hostname, uri.hostname )

  domain = dns.find_domain(uri.hostname)

  data.remember( :domain, domain )

  # Look at the domain info

  whois = Whois.lookup( domain )

  data.remember( :registered?, whois.registered? )
  if whois.registrar
    data.remember( :registrar_name, whois.registrar.name )
    data.remember( :registrar_url, whois.registrar.url )
  end

  data.remember( :created_on, whois.created_on.strftime( "%Y-%m-%d") ) if whois.created_on
  data.remember( :expires_on, whois.expires_on.strftime( "%Y-%m-%d") ) if whois.expires_on
  data.remember( :updated_on, whois.updated_on.strftime( "%Y-%m-%d") ) if whois.updated_on

  whois.contacts.each do |c|
    data.another( :emails, c.email.downcase ) if c.email
    case c.type
    when Whois::Record::Contact::TYPE_REGISTRANT
      data.remember( :registrant_contact, c )
    when Whois::Record::Contact::TYPE_ADMINISTRATIVE
      data.remember( :admin_contact, c )
    when Whois::Record::Contact::TYPE_TECHNICAL
      data.remember( :technical_contact, c )
    end
  end

  whois.parts.each do |p|
    if Whois::Record::Parser.parser_for(p).is_a? Whois::Record::Parser::Blank
      puts "Couldn't find a parser for #{p.host}:"
      data.another( :unparsed_whois, p.body )
    end
  end


  if !noreverse
    ip_address = Dnsruby::Resolv.getaddress uri.host

    if ip_address
      data.remember :ip_address, ip_address
      begin
        data.remember :server_name, Dnsruby::Resolv.getname( ip_address )
      rescue Dnsruby::NXDomain
        # Couldn't do the reverse lookup
      end

      location_info = HTTParty.get('http://freegeoip.net/json/' + ip_address)

      data.remember :server_country, location_info['country_name']
      data.remember :server_location, [location_info['city'], location_info['region_name']].collect { |x| (x != nil && x != "") ? x : nil }.select { |x| x }.join( ", ")
      data.remember :server_latitude, location_info['latitude']
      data.remember :server_longitude, location_info['longitude']

      ip_whois = Whois.lookup ip_address

      ip_whois.to_s.each_line.select { |x| x=~/Organization/ }.each do |org|
        if org =~ /Organization:\s*(.*)\n/
          data.another :server_ip_owner, $1
        end
      end
    end
  end

  # Load up the response

  # client = HTTPClient.new
  # client.ssl_config.verify_mode = OpenSSL::SSL::VERIFY_NONE
  # response = client.get( url )
  #       # @ssl = p.peer_cert

  response = HTTParty.get url

  # require 'pp'
  # pp response.headers

  data.remember( :server, response.headers['server'] )


  # Parse the HTML

  parsed = Nokogiri.parse response.body

  data.remember( :page_title, parsed.title )

  # RSS Feed:
  if feed = parsed.css( 'link[type="application/rss+xml"]' ).first
    feed = feed.attributes['href'].value
    data.remember( :rss_feed, feed )
  end

  # Atom Feed:
  if feed = parsed.css( 'link[type="application/atom+xml"]' ).first
    feed = feed.attributes['href'].value
    data.remember( :atom_feed, feed )
  end



  # Meta tags

  meta = {}
  parsed.css( "meta[name]" ).each do |t|
    meta[t.attributes["name"].value] = t.attributes["content"].value if t.attributes["content"]
  end

  parsed.css( "meta[property]" ).each do |t|
    meta[t.attributes["property"].value] = t.attributes["content"].value
  end

  # require 'pp'
  # pp meta

  data.remember( :author, meta['author'] ) 
  data.remember( :description, meta['description'] ) 
  data.remember( :keywords, meta['keywords'] ) 
  data.remember( :generator, meta['generator'])

  data.remember( :responsive, true )  if meta["viewport"] =~ /width=device-width/


  # Check Twitter Card:

  data.remember( :twitter_title, meta["twitter:title"] ) 
  data.remember( :twitter_creator, meta["twitter:creator"] ) 
  if /@(.*)/.match( meta["twitter:creator"] )
    data.another( :twitter_ids, $1 )
  end
  data.remember( :twitter_site_author, meta["twitter:site"] )
  if /@(.*)/.match( meta["twitter:site"] )
    data.another( :twitter_ids, $1 )
  end
  data.remember( :twitter_image, meta["twitter:image"] ) 
  data.remember( :twitter_description, meta["twitter:description"] )

  # Open Graph

  data.remember( :og_title, meta["og:title"] ) 
  data.remember( :og_description, meta["og:description"] )
  data.remember( :og_type, meta["og:type"] ) 
  data.remember( :og_image, meta["og:image"] ) 


  # Look inside the body:


  # Twitter

  # Look for twitter links
  twitter_links = hrefs( matching_links( parsed, /twitter.com\/[^\/]*$/ ), true )
  data.remember( :twitter_links, twitter_links ) 

  twitter_ids = find_id_path( twitter_links, /twitter.com\/([^\/]*$)/  ).each do |id|
    data.another( :twitter_ids, id )
  end

  # Look for twitter shared links

  twitter_shared = matching_links( parsed, /twitter.com\/share/ )

  twitter_shared.each do |l|
    text = l['data-text']

    # See if there's a "by @user" in the text
    if /by\s*@([^\s]*)/.match text
      data.another( :twitter_ids, $1 )
      data.remember( :twitter_by, $1 ) 
    end

    # Look for all "@usernames" in the text
    if text
      text.split.select { |x| x =~ /@\s*/ }.each do |id|
        data.another( :twitter_ids, id.slice( 1,100 ) ) # We don't want the @
      end
    end

    # See if there's a via link on the anchor tag
    if l['data-via']
      data.another( :twitter_ids, l['data-via'])
    end


    possible_via = URI.decode( (URI(l['href']).query) || "" ).split( /&/ ).collect { |x| x.split( /=/  ) }.select { |x| x[0] == 'via' }
    if possible_via.size > 0
      data.another( :twitter_ids, possible_via[0][1] )
    end
  end

  # Look for intent

  twitter_intent = hrefs( matching_links( parsed, /twitter.com\/intent/ ) )

  twitter_intent.each do |t|
    URI.decode( URI(t.gsub( / /, "+" )).query ).split( /&/ ).select do |x| 
      x =~ /via/
    end.collect do |x| 
      x.gsub( /via=/, "" )
    end.each do |via|
      data.another( :twitter_ids, via )
    end
  end
  # Look for email

  email_links = hrefs( matching_links( parsed, /mailto:/ ) )
  email_address = find_id_path( email_links, /mailto:(.*@.*\..*)/ ).each do |email|
    data.another( :emails, email )
  end

  # Linkedin

  linkedin_links = hrefs( matching_links( parsed, /linkedin.com/ ), true )
  data.remember( :linkedin_links, linkedin_links ) 

  # Instagram

  instagram_links = hrefs( matching_links( parsed, /instagram.com/ ) )
  data.remember( :instagram_links, instagram_links ) 

  # Facebook

  facebook_links = hrefs( matching_links( parsed, /facebook.com\/[^\/]*$/ ) )
  data.remember( :facebook_links, facebook_links ) 

  # Google plus

  googleplus_links = hrefs( matching_links( parsed, /plus.google.com\/[^\/]*$/ ) )
  data.remember( :googleplus_links, googleplus_links ) 

  # Github

  github_links = hrefs( matching_links( parsed, /github.com\/[^\/]*$/ ) )
  data.remember( :github_links, github_links ) 


  # Bonus!

  # Get this file from https://github.com/ElbertF/Wappalyzer/tree/master/share

  apps = Socialinvestigator::Config.config.apps_json
  if apps
    scripts = parsed.css( "script" ).collect { |x| x['src'] }.select { |x| x }
    # puts scripts

    apps['apps'].each do |app,checks|
      if checks['html']
        html_array = checks['html']
        html_array = [checks['html']] if html_array.is_a? String

        html_array.each do |html|
          result = check_regex( html, response.body )
          if result
            data.another :technologies, app
            data.another :technologies, checks['implies']
          end
        end
      end

      if checks['meta']
        checks['meta'].each do |k,code|
          result = check_regex( code, meta[k] )
          if result
            data.another :technologies, app
            data.another :technologies, checks['implies']
          end
        end
      end

      if checks['headers']
        checks['headers'].each do |k,code|
          result = check_regex( code, response.headers[k] )
          if result
            data.another :technologies, app
            data.another :technologies, checks['implies']
          end
        end
      end

      if checks['script']
        script_array = checks['script']
        script_array = [checks['script']] if script_array.is_a? String
        script_array.each do |script_regex|
          scripts.each do |script|
            result = check_regex( script_regex, script)
            if result
              data.another :technologies, app
              data.another :technologies, checks['implies']
            end
          end
        end
      end
    end
  end
  data
end

#hrefs(links, filter_shared = false) ⇒ Object 



447
448
449
450
451
452
453
454
455
456
457
 
# File 'lib/socialinvestigator/client/net.rb', line 447

def hrefs( links, filter_shared = false )
  links.collect do |x|
    x['href']
  end.select do |url|
    if filter_shared
      !(url =~ /share/)
    else
      true
    end
  end.uniq
end

#matching_links(parsed, regex) ⇒ Object 



435
436
437
438
439
440
441
442
443
444
445
 
# File 'lib/socialinvestigator/client/net.rb', line 435

def matching_links( parsed, regex )
  parsed.css( "a" ).collect do |x|
    if regex.match( x['href'] )
      x
    else
      nil
    end
  end.select do |x|
    x
  end
end