Module: Wmap::Utils::UrlMagic

Extended by:
UrlMagic
Included in:
Wmap::Utils, UrlMagic
Defined in:
lib/wmap/utils/url_magic.rb

Constant Summary collapse

Max_http_timeout =

set hard stop limit of http time-out to 8 seconds, in order to avoid severe performance penalty for certain ‘weird’ site(s)

15000

Instance Method Summary collapse

Instance Method Details

#create_absolute_url_from_base(potential_base, relative_url) ⇒ Object

Create / construct the absolute URL from a known URL and relative file path. For example, ‘images.search.yahoo.com/images’ + ‘/search/images?p=raiders’ => ‘images.search.yahoo.com/search/images?p=raiders’



231
232
233
234
235
236
237
238
239
 
# File 'lib/wmap/utils/url_magic.rb', line 231

def create_absolute_url_from_base(potential_base, relative_url)
#puts "Determine the absolute URL from potential base #{potential_base} and relative URL #{relative_url}" if @verbose
naked_base = url_2_site(potential_base).strip.chop
puts "Found absolute URL: #{naked_base+relative_url}" if @verbose
return naked_base + relative_url
rescue => ee
puts "Exception on method #{__method__}: #{ee}" if @verbose
  return nil
end

#create_absolute_url_from_context(potential_base, relative_url) ⇒ Object

Construct the absolute URL by comparing a known URL and the relative file path



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
 
# File 'lib/wmap/utils/url_magic.rb', line 242

def create_absolute_url_from_context(potential_base, relative_url)
  puts "Determine the absolute URL from context:\n Known base: #{potential_base}, Relative path: #{relative_url}" if @verbose
absolute_url = nil
# make relative URL naked by removing the beginning '/'
relative_url.sub!(/^\//,'')
if potential_base =~ /\/$/
  absolute_url = potential_base+relative_url.strip
else
  last_index_of_slash = potential_base.rindex('/')
  if potential_base[last_index_of_slash-2, 2] == ':/'
    absolute_url = potential_base+relative_url
  else
    last_index_of_dot = potential_base.rindex('.')
    if last_index_of_dot < last_index_of_slash
      absolute_url = potential_base.strip.chop+relative_url
    else
      absolute_url = potential_base[0, last_index_of_slash+1] + relative_url
    end
  end
end
puts "Found absolute URL: #{absolute_url}" if @verbose
return absolute_url
rescue => ee
puts "Exception on method #{__method__}: #{ee}" if @verbose
        return nil
end

#host_2_url(host, port = 80) ⇒ Object

Input is host and open port, output is a URL for valid http response code or nil



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
 
# File 'lib/wmap/utils/url_magic.rb', line 186

def host_2_url (host,port=80)
  puts "Perform simple http(s) service detection on host #{host}, port #{port}" if @verbose
  host=host.strip
  if port.to_i == 80
    url_1 = "http://" + host + "/"
  elsif port.to_i ==443
    url_1 = "https://" + host + "/"
  else
    url_1 = "http://" + host + ":" + port.to_s + "/"
    url_2 = "https://" + host + ":" + port.to_s + "/"
  end
  puts "Please ensure your internet connection is active before running this method: #{__method__}" if @verbose
  checker=Wmap::UrlChecker.new
  if checker.response_code(url_1) != 10000
    puts "Found URL: #{url_1}" if @verbose
    return url_1
  elsif checker.response_code(url_2) != 10000
    puts "Found URL: #{url_2}" if @verbose
    return url_2
  else
    puts "No http(s) service found on: #{host}:#{port}" if @verbose
    return nil
  end
rescue => ee
  puts "Exception on method #{__method__}: #{ee}" if @verbose
  return nil
end

#is_site?(url) ⇒ Boolean

Simple sanity check on a ‘claimed’ web site base string.

Returns:

  • (Boolean) 


55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
 
# File 'lib/wmap/utils/url_magic.rb', line 55

def is_site?(url)
  puts "Validate the website string format for: #{url}" if @verbose
  url=url.strip.downcase
  if is_url?(url)
    if url == url_2_site(url)
      return true
    else
      return false
    end
  else
    puts "Unknown site format: #{url}" if @verbose
    return false
  end
rescue => ee
  puts "Exception on method #{__method__}: #{ee}" if @verbose
  return nil
end

#is_ssl?(url) ⇒ Boolean Also known as: is_https?

Simple sanity check on a ‘claimed’ SSL enabled URL string

Returns:

  • (Boolean) 


40
41
42
43
44
45
46
47
48
49
50
51
 
# File 'lib/wmap/utils/url_magic.rb', line 40

def is_ssl?(url)
  puts "Validate if SSL is enabled on: #{url}" if @verbose
  url=url.strip
  if is_url?(url) && url =~ /https/i
    return true
  else
    return false
  end
rescue => ee
  puts "Exception on method #{__method__}: #{ee}" if @verbose
  return false
end

#is_url?(url) ⇒ Boolean

Simple sanity check on a ‘claimed’ URL string.

Returns:

  • (Boolean) 


20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
 
# File 'lib/wmap/utils/url_magic.rb', line 20

def is_url?(url)
  puts "Validate the URL format is valid: #{url}" if @verbose
  if url =~ /(http|https)\:\/\/((.)+)/i
    host=$2.split('/')[0]
    host=host.split(':')[0]
    if is_ip?(host) or is_fqdn?(host)
      return true
    else
      return false
    end
  else
    puts "Unknown URL format: #{url}" if @verbose
    return false
  end
rescue => ee
  puts "Exception on method #{__method__}: #{ee}" if @verbose
  return false
end

#landing_location(depth = 5, url) ⇒ Object

Test the URL / Site and return the landing url location (recursive with the depth = 4 )



406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
 
# File 'lib/wmap/utils/url_magic.rb', line 406

def landing_location (depth=5, url)
  depth -= 1
  return url if depth < 1
  timeo = Max_http_timeout/1000.0
  uri = URI.parse(url)
  code = response_code (url)
  if code >= 300 && code < 400
    url = redirect_location (url)
    url = landing_location(depth,url)
  else
    return url
  end
  return url
rescue Exception => ee
  puts "Exception on method #{__method__} on URL #{url}: #{ee}" if @verbose
end

#make_absolute(base, relative_url) ⇒ Object

Convert a relative URL to an absolute one. For example, from URL base ‘games.yahoo.com/’ and file path ‘/game/the-magic-snowman-flash.html’ => ‘games.yahoo.com/game/the-magic-snowman-flash.html’



215
216
217
218
219
220
221
222
223
224
225
226
227
228
 
# File 'lib/wmap/utils/url_magic.rb', line 215

def make_absolute(base, relative_url)
  puts "Determine and return the absolute URL:\n Base: #{base}, Relative: #{relative_url} " if @verbose
absolute_url = nil;
if relative_url =~ /^\//
  absolute_url = create_absolute_url_from_base(base, relative_url)
else
  absolute_url = create_absolute_url_from_context(base, relative_url)
end
puts "Found absolute URL: #{absolute_url}" if @verbose
return absolute_url
rescue => ee
puts "Exception on method #{__method__}: #{ee}" if @verbose
  return nil
end

#normalize_url(url) ⇒ Object

Normalize the URL to a consistent manner in order to determine if a link has been visited or cached before See en.wikipedia.org/wiki/URL_normalization for more explanation



271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
 
# File 'lib/wmap/utils/url_magic.rb', line 271

def normalize_url(url)
  url.strip!
  # Converting the scheme and host to lower case in the process, i.e. 'HTTP://www.Example.com/' => 'http://www.example.com/'
  # Normalize the base
  base=url_2_site(url)
  # Case#1, remove the trailing dot after the hostname, i.e, 'http://www.yahoo.com./' => 'http://www.yahoo.com/'
  base=base.sub(/\.\/$/,'/')
  # Normalize the relative path, case#1
  # retrieve the file path and remove the first '/' or '.',
  # i.e. 'http://www.example.com/mypath' or 'http://www.example.com/./mypath' => 'mypath'
  path=url_2_path(url).sub(/^(\/|\.)*/,'')
  # Normalize the relative path, case#2
  # Replace dot-segments. "/../" and "/./" with "/", i.e. 'http://www.example.com/../a/b/../c/./d.html" => 'http://www.example.com/a/c/d.html'
  path=path.gsub(/\/\.{1,2}\//,'/')
  if path.nil?
    return base
  else
    return base+path
  end
rescue => ee
  puts "Exception on method #{__method__} for #{url}: #{ee}" if @verbose
  return url
end

#open_page(url) ⇒ Object

Given an URL, open the page, then return the DOM text from a normal user perspective



348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
 
# File 'lib/wmap/utils/url_magic.rb', line 348

def open_page(url)
  args = {ssl_verify_mode: OpenSSL::SSL::VERIFY_NONE, allow_redirections: :safe, read_timeout: Max_http_timeout/1000}
  doc = Nokogiri::HTML(open(url, args))
  if doc.text.include?("Please enable JavaScript to view the page content")
    puts "Invoke headless chrome through webdriver ..." if @verbose
    #Selenium::WebDriver::Chrome.path = "/usr/local/bin/chromedriver"
    #driver = Selenium::WebDriver.for :chrome
    # http://watir.com/guides/chrome/
    args = ['--ignore-certificate-errors', '--disable-popup-blocking', '--disable-translate', '--disk-cache-size 8192']
    browser = Watir::Browser.new :chrome, headless: true, options: {args: args}
    browser.goto(url)
    sleep(2) # wait for the loading
    doc = Nokogiri::HTML(browser.html)
    browser.close
  end
  puts doc.text if @verbose
  return doc
rescue => ee
  puts "Exception on method #{__method__} for #{url}: #{ee}"
  browser.close unless browser.nil?
  return doc.text
end

#redirect_location(url) ⇒ Object Also known as: location

Test the URL / site and return the redirection location (3xx response code only)



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
 
# File 'lib/wmap/utils/url_magic.rb', line 372

def redirect_location (url)
  puts "Test the redirection location for the url: #{url}" if @verbose
  location=""
  raise "Invalid url: #{url}" unless is_url?(url)
  url=url.strip.downcase
  timeo = Max_http_timeout/1000.0
  uri = URI.parse(url)
  code = response_code (url)
  if code >= 300 && code < 400
    http = Net::HTTP.new(uri.host, uri.port)
    http.open_timeout = timeo
    http.read_timeout = timeo
    if (url =~ /https\:/i)
      http.use_ssl = true
      # Bypass the remote web server cert validation test
      http.verify_mode = OpenSSL::SSL::VERIFY_NONE
      http.ssl_version = @ssl_version
    end
    request = Net::HTTP::Get.new(uri.request_uri)
    response = http.request(request)
    puts "Response: #{response}" if @verbose
    case response
    when Net::HTTPRedirection then
      location = response['location']
    end
  end
  return location
rescue Exception => ee
  puts "Exception on method redirect_location for URL #{url}: #{ee}" if @verbose
  return ""
end

#response_code(url) ⇒ Object

Test the URL and return the response code



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
 
# File 'lib/wmap/utils/url_magic.rb', line 297

def response_code (url)
  puts "Check the http response code on the url: #{url}" if @verbose
  code = 10000 # All unknown url connection exceptions go here
  raise "Invalid url: #{url}" unless is_url?(url)
  url=url.strip.downcase
  timeo = Max_http_timeout/1000.0
  uri = URI.parse(url)
  http = Net::HTTP.new(uri.host, uri.port)
  http.open_timeout = timeo
  http.read_timeout = timeo
  if (url =~ /https\:/i)
    http.use_ssl = true
    #http.ssl_version = :SSLv3
    # Bypass the remote web server cert validation test
    http.verify_mode = OpenSSL::SSL::VERIFY_NONE
  end
  request = Net::HTTP::Get.new(uri.request_uri)
  response = http.request(request)
  puts "Server response the following: #{response}" if @verbose
  code = response.code.to_i
  #response.finish if response.started?()
  @url_code=Hash.new unless @url_code
   @url_code[url]=code
  puts "Response code on #{url}: #{code}" if @verbose
  return code
rescue Exception => ee
  puts "Exception on method #{__method__} for #{url}: #{ee}" if @verbose
  case ee
  # rescue "Connection reset by peer" error type
  when Errno::ECONNRESET
    code=104
  when Errno::ECONNABORTED,Errno::ETIMEDOUT
    #code=10000
  when Timeout::Error        # Quick fix
    if (url =~ /https\:/i)    # try again for ssl timeout session, in case of default :TLSv1 failure
      http.ssl_version = :SSLv3
      response = http.request(request)
      code = response.code.to_i
      unless code.nil?
        @ssl_version = http.ssl_version
      end
    end
  else
    #code=10000
  end
   @url_code=Hash.new unless @url_code
  @url_code[url]=code
  return code
end

#url_2_host(url) ⇒ Object

Extract the web server host’s Fully Qualified Domain Name (FQDN) from the url. For example: “login.yahoo.com/email/help” -> “login.yahoo.com”



74
75
76
77
78
79
80
81
82
83
84
85
86
87
 
# File 'lib/wmap/utils/url_magic.rb', line 74

def url_2_host (url)
  url = url.strip.downcase.gsub(/(http:\/\/|https:\/\/)/, "")
  record1 = url.split('/')
  if record1[0].nil?
    puts "Error process url: #{url}"
    return nil
  else
    record2 = record1[0].split(':')
    return record2[0]
  end
rescue => ee
  puts "Exception on method #{__method__}: #{ee}" if @verbose
  return nil
end

#url_2_path(url) ⇒ Object

Wrapper to return relative path component of the URL. i.e. www.yahoo.com/login.html => /login.html



163
164
165
166
167
168
169
170
171
172
 
# File 'lib/wmap/utils/url_magic.rb', line 163

def url_2_path(url)
  #puts "Retrieve the relative path component of the url: #{url}" if @verbose
  url.strip!
  base = url_2_site(url).chop
  path=url.sub(base,'')
  #puts "Path component found: #{path}" if @verbose
  return path
rescue => ee
  puts "Exception on method #{__method__} for #{url}: #{ee}" if @verbose
end

#url_2_port(url) ⇒ Object

Extract web service port from the url. For example: “login.yahoo.com/email/help” -> 443



90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
 
# File 'lib/wmap/utils/url_magic.rb', line 90

def url_2_port (url)
  puts "Retrieve service port on URL: #{url}" if @verbose
  ssl = (url =~ /https/i)
  url = url.downcase.gsub(/(http:\/\/|https:\/\/)/, "")
  record1 = url.split('/')
  record2 = record1[0].split(':')
  if (record2.length == 2)
    puts "The service port: #{record2[1]}" if @verbose
    return record2[1].to_i
  elsif ssl
    puts "The service port: 443" if @verbose
    return 443
  else
    puts "The service port: 80" if @verbose
    return 80
  end
rescue => ee
  puts "Exception on method #{__method__}: #{ee}" if @verbose
  return nil
end

#url_2_site(url) ⇒ Object

Extract site in (host:port) format from a url: “login.yahoo.com:8443/email/help” -> “login.yahoo.com:8443/”



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

def url_2_site (url)
  puts "Retrieve the web site base for url: #{url}" if @verbose
  url = url.downcase
  url = url.sub(/^(.*?)http/i,'http')
  entry = url.split(%r{\/\/})
  prot=entry[0]
  # step 1, extract the host:port pair from the url
  host_port=entry[1].split(%r{\/})[0]
  if host_port =~ /\:/
    host=host_port.split(%r{\:})[0]
    port=host_port.split(%r{\:})[1].to_i
  elsif prot =~ /https/i
    host=host_port
    port=443
  elsif prot =~ /http/i
    host=host_port
    port=80
  else
    host=host_port
    #raise "Unknown url format: #{url}"
  end
  # additional logic to handle uncommon url base structures
  unless is_fqdn?(host)
    case host
      # "https://letmechoose.barclays.co.uk?source=btorganic/" => "https://letmechoose.barclays.co.uk"
      when /\?|\#/
        host=host.split(%r{\?|\#})[0]
      else
        #do nothing
    end
  end
  # step 2, put the host:port pair back to the normal site format
  prot="https:" if port==443
  if port==80 || port==443
    site=prot+"//"+host+"/"
  else
    site=prot+"//"+host+":"+port.to_s+"/"
  end
  if site=~ /http/i
    #puts "Base found: #{site}" if @verbose
    return site
  else
    raise "Problem encountered on method url_2_site: Unable to convert #{url}"
    return nil
  end
rescue => ee
  puts "Exception on method #{__method__}: #{ee}" if @verbose
  return nil
end

#urls_on_same_domain?(url1, url2) ⇒ Boolean

Test if the two URLs are both under the same domain: login.yahoo.com, mail.yahoo.com => true

Returns:

  • (Boolean) 


175
176
177
178
179
180
181
182
183
 
# File 'lib/wmap/utils/url_magic.rb', line 175

def urls_on_same_domain?(url1, url2)
puts "Determine if two URLs under the same domain: #{url1}, #{url2}" if @verbose
host1=url_2_host(url1)
host2=url_2_host(url2)
return get_domain_root(host1) == get_domain_root(host2)
rescue => ee
puts "Error searching the object content: #{ee}" if @verbose
  return nil
end