Module: HtmlRadar

Defined in:
lib/html_radar.rb,
lib/html_radar/version.rb

Constant Summary collapse

VERSION =
"0.0.9"

Class Method Summary collapse

Class Method Details

.add_diff(x) ⇒ Object



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
# File 'lib/html_radar.rb', line 49

def self.add_diff(x)

  old_a, old_hsh = get_diff_a_and_hsh(x[:css_selector], x[:old_docs])
  new_a, new_hsh = get_diff_a_and_hsh(x[:css_selector], x[:new_docs])
  diff_a = (new_a - old_a)

  diff_s = ""
  for diff in diff_a
    begin
      if Sanitize.clean( ( (new_hsh[diff]) ) ).present?
        diff_s << "<#{x[:item_tag]}>#{new_hsh[diff]}</#{x[:item_tag]}>"
        diff_s << "<center>#{Time.now.to_s}</center>"
        diff_s << "<center><a href='##{x[:top_id]}'>###</a></center>"
        diff_s << "<hr />"
      end
    end
  end
  x[:diff] = diff_s

  diff_s = ""
  for diff in old_a[0..300]
    diff_s << "<#{x[:item_tag]}>#{new_hsh[diff]}</#{x[:item_tag]}>"
    diff_s << "<center>#{Time.now.to_s}</center>"
    diff_s << "<center><a href='##{x[:top_id]}'>###</a></center>"
    diff_s << "<hr />"
  end
  x[:diff_old] = diff_s

  return x
end

.add_new(x) ⇒ Object



109
110
111
112
113
114
115
# File 'lib/html_radar.rb', line 109

def self.add_new(x)
  x = add_new_content(x)
  x = fix_new_content_base_url(x)
  x = fix_new_content_base_url_target(x)
  x = add_new_docs(x)
  return x
end

.add_new_content(x) ⇒ Object



173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
# File 'lib/html_radar.rb', line 173

def self.add_new_content(x)
  begin
    if x[:url].present?
      if x[:url]=='http://test.html'
        x[:new_content] = "
        <html><body>
          <p><a href='http://www.abcbots.com/test'>Static</a></p>
          <p><a href='http://www.abcbots.com/test'>Dynamic: #{pass=get_random(10)}</a></p>
          <p><a href='http://www.abcbots.com/test'>Dynamic: #{pass}</a></p>
        </body></html>"
      else
        x[:new_content] = open(source_url.to_s).read.to_s.gsub("@", " @")
      end
    else
      x[:new_content] = ""
    end
  rescue
    x[:new_content] = "(Access Denied)"
  end
  return x
end

.add_new_docs(x) ⇒ Object



148
149
150
151
# File 'lib/html_radar.rb', line 148

def self.add_new_docs(x)
  x[:new_docs] = Nokogiri::HTML(x[:new_content])
  return x
end

.add_old(x) ⇒ Object



103
104
105
106
107
# File 'lib/html_radar.rb', line 103

def self.add_old(x)
  x = add_old_content(x)
  x = add_old_docs(x)
  return x
end

.add_old_content(x) ⇒ Object



202
203
204
205
# File 'lib/html_radar.rb', line 202

def self.add_old_content(x)
  x[:old_content] = x[:memory].to_s
  return x
end

.add_old_docs(x) ⇒ Object



153
154
155
156
# File 'lib/html_radar.rb', line 153

def self.add_old_docs(x)
  x[:old_docs] = Nokogiri::HTML(x[:old_content])
  return x
end

.fix_new_content_base_url(x) ⇒ Object



124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
# File 'lib/html_radar.rb', line 124

def self.fix_new_content_base_url(x)
  base_url = x[:base_url]
  content = x[:new_content]
  content = get_content_mix_base_url_selector(base_url, content, "href=\"")
  content = get_content_mix_base_url_selector(base_url, content, "href=\'")
  content = get_content_mix_base_url_selector(base_url, content, "src=\"")
  content = get_content_mix_base_url_selector(base_url, content, "src=\'")
  env_base_url = (base_url+"/") 
  content = content.gsub(env_base_url, base_url)
  double_base_url = base_url + base_url
  content = content.gsub(double_base_url, base_url)
  mutant_base_url = (base_url+"http") 
  content = content.gsub(mutant_base_url, "http")
  x[:new_content] = content
  return x
end

.fix_new_content_base_url_target(x) ⇒ Object



117
118
119
120
121
122
# File 'lib/html_radar.rb', line 117

def self.fix_new_content_base_url_target(x)
  content = x[:new_content]
  content = content.to_s.gsub("href=", "target='_blank' href=")
  x[:new_content] = content
  return x
end

.get_content_mix_base_url_selector(base_url, content, selector) ⇒ Object



141
142
143
144
145
# File 'lib/html_radar.rb', line 141

def self.get_content_mix_base_url_selector(base_url, content, selector)
  selector_with_base_url = selector + base_url
  content = content.to_s.gsub(selector, selector_with_base_url)
  return content.to_s
end

.get_diff_a_and_hsh(css_selector, docs) ⇒ Object



80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
# File 'lib/html_radar.rb', line 80

def self.get_diff_a_and_hsh(css_selector, docs)
  doc_a = []
  doc_hsh = {}
  length = 255
  css_selector = css_selector.split(" ").last
  for doc in docs.css(css_selector)
    d = 1
    doc_s = doc.to_s
    a = doc_s.gsub(/[^a-zA-Z]/i,'').to_s.downcase
    aa = a.split('').uniq
    for b in aa
      d += b.ord
      d *= a.scan(b).size
    end
    doc_id = d.to_s
    unless doc_a.include?(doc_id)
      doc_a << doc_id
      doc_hsh[doc_id] = doc_s
    end
  end
  return doc_a, doc_hsh
end

.get_random(pass_qty = 30) ⇒ Object



195
196
197
198
199
200
# File 'lib/html_radar.rb', line 195

def self.get_random(pass_qty=30)
  s = SecureRandom.base64(pass_qty).to_s
  s = s.gsub("/", SecureRandom.hex(1).first.to_s)
  s = s.gsub("+", SecureRandom.hex(1).first.to_s)
  return s.gsub("==", SecureRandom.hex(1).first.to_s)
end

.get_url(a = "") ⇒ Object

Hola.get_url(“www.google.com”) #=> “<html>…</html>”



214
215
216
217
218
219
220
# File 'lib/html_radar.rb', line 214

def self.get_url(a="")
  content = open(a.to_s).read.to_s.gsub("@", " @_")
  docs = Nokogiri::HTML(content)
  docs = docs.to_s.gsub(" @_", "@").to_s
  puts a+": "+docs
  return docs.to_s
end

.hiObject

Hola.hi #=> “Hello World!”



208
209
210
211
# File 'lib/html_radar.rb', line 208

def self.hi
  puts "Hello World!"
  return "Hello World!"
end

.mix_base_url_to_doc(element, doc, base_url) ⇒ Object



158
159
160
161
162
163
164
165
166
167
168
169
170
171
# File 'lib/html_radar.rb', line 158

def self.mix_base_url_to_doc(element, doc, base_url)

  doc_element = doc[element]
  if doc_element.present? and !get_first_match(doc_element, element)
    doc_element_a = doc_element.split("")
    if (doc_element_a.first == "/")
      doc_element_a.shift
      doc_element = doc_element_a.join
    end
    doc[element] = base_url + doc_element
    doc["target"] = "_blank" if element=="href"
  end
  return doc
end

.prepend_diff(x) ⇒ Object



40
41
42
43
44
45
46
47
# File 'lib/html_radar.rb', line 40

def self.prepend_diff(x)
  if x[:diff].present?
    x[:memory] = ((x[:diff]) + (x[:split_tag]) + (x[:diff_old]) )
  else
    x[:memory] = ((x[:split_tag]) + (x[:diff_old]) )
  end
  return x
end

.refresh(memory, url, css_selector, item_tag, top_id) ⇒ Object

def self.refresh(memory, url, css_selector, top_id) #=> new_memory



12
13
14
15
16
17
18
19
20
21
# File 'lib/html_radar.rb', line 12

def self.refresh(memory, url, css_selector, item_tag, top_id)
  x = set_defaults(memory, url, css_selector, item_tag, top_id)
  if x[:refresh_ready]
    x = add_new(x)
    x = add_old(x)
    x = add_diff(x)
    x = prepend_diff(x)
  end
  return x[:memory]
end

.set_defaults(memory, url = nil, css_selector = nil, item_tag = "p", top_id = "_top_") ⇒ Object



27
28
29
30
31
32
33
34
35
36
37
38
# File 'lib/html_radar.rb', line 27

def self.set_defaults(memory, url=nil, css_selector=nil, item_tag="p", top_id="_top_")
  x={}
  x[:memory] = memory 
  x[:url] = url 
  x[:css_selector] = css_selector
  x[:item_tag] = item_tag 
  x[:top_id] = top_id 
  x[:refresh_ready] = (url.present? and css_selector.present? and item_tag.present? and top_id.present?)
  x[:base_url] = x[:url].to_s.split("/")[0..2].join("/") + "/"
  x[:split_tag] = "<!-- split_tag -->"
  return x
end

.show(memory) ⇒ Object

def self.show(memory) #=> latest_change



6
7
8
9
# File 'lib/html_radar.rb', line 6

def self.show(memory)
  x = set_defaults(memory)
  return show_latest(x)
end

.show_latest(x) ⇒ Object



23
24
25
# File 'lib/html_radar.rb', line 23

def self.show_latest(x)
  return x[:memory].to_s.split(x[:split_tag]).first
end