Class: Html2Text

Inherits:
Object
  • Object
show all
Defined in:
lib/html2text.rb,
lib/html2text/version.rb

Constant Summary collapse

VERSION =
"0.2.0"

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(doc) ⇒ Html2Text

Returns a new instance of Html2Text


6
7
8
# File 'lib/html2text.rb', line 6

def initialize(doc)
  @doc = doc
end

Instance Attribute Details

#docObject (readonly)

Returns the value of attribute doc


4
5
6
# File 'lib/html2text.rb', line 4

def doc
  @doc
end

Class Method Details

.convert(html) ⇒ Object


10
11
12
13
14
15
# File 'lib/html2text.rb', line 10

def self.convert(html)
  html = fix_newlines(replace_entities(html))
  doc = Nokogiri::HTML(html)

  Html2Text.new(doc).convert
end

.fix_newlines(text) ⇒ Object


17
18
19
# File 'lib/html2text.rb', line 17

def self.fix_newlines(text)
  text.gsub("\r\n", "\n").gsub("\r", "\n")
end

.replace_entities(text) ⇒ Object


21
22
23
# File 'lib/html2text.rb', line 21

def self.replace_entities(text)
  text.gsub(" ", " ").gsub("\u00a0", " ")
end

Instance Method Details

#convertObject


25
26
27
28
29
30
# File 'lib/html2text.rb', line 25

def convert
  output = iterate_over(doc)
  output = remove_leading_and_trailing_whitespace(output)
  output = remove_unnecessary_empty_lines(output)
  output.strip
end

#image_text(node) ⇒ Object


168
169
170
171
172
173
174
175
176
# File 'lib/html2text.rb', line 168

def image_text(node)
  if node.attribute("title")
    "[" + node.attribute("title").to_s + "]"
  elsif node.attribute("alt")
    "[" + node.attribute("alt").to_s + "]"
  else
    ""
  end
end

#iterate_over(node) ⇒ Object


57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
# File 'lib/html2text.rb', line 57

def iterate_over(node)
  return trimmed_whitespace(node.text) if node.text?

  if ["style", "head", "title", "meta", "script"].include?(node.name.downcase)
    return ""
  end

  output = []

  output << prefix_whitespace(node)
  output += node.children.map do |child|
    iterate_over(child)
  end
  output << suffix_whitespace(node)

  output = output.compact.join("") || ""

  if node.name.downcase == "a"
    output = wrap_link(node, output)
  end
  if node.name.downcase == "img"
    output = image_text(node)
  end

  output
end

#next_node_name(node) ⇒ Object


45
46
47
48
49
50
51
52
53
54
55
# File 'lib/html2text.rb', line 45

def next_node_name(node)
  next_node = node.next_sibling
  while next_node != nil
    break if next_node.element?
    next_node = next_node.next_sibling
  end

  if next_node && next_node.element?
    next_node.name.downcase
  end
end

#prefix_whitespace(node) ⇒ Object


84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
# File 'lib/html2text.rb', line 84

def prefix_whitespace(node)
  case node.name.downcase
    when "hr"
      "---------------------------------------------------------------\n"

    when "h1", "h2", "h3", "h4", "h5", "h6", "ol", "ul"
      "\n"

    when "tr", "p", "div"
      "\n"

    when "td", "th"
      "\t"

    when "li"
      "- "
  end
end

#remove_leading_and_trailing_whitespace(text) ⇒ Object


32
33
34
# File 'lib/html2text.rb', line 32

def remove_leading_and_trailing_whitespace(text)
  text.gsub(/[ \t]*\n[ \t]*/im, "\n").gsub(/ *\t */im, "\t")
end

#remove_unnecessary_empty_lines(text) ⇒ Object


36
37
38
# File 'lib/html2text.rb', line 36

def remove_unnecessary_empty_lines(text)
  text.gsub(/\n\n\n*/im, "\n\n")
end

#suffix_whitespace(node) ⇒ Object


103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
# File 'lib/html2text.rb', line 103

def suffix_whitespace(node)
  case node.name.downcase
    when "h1", "h2", "h3", "h4", "h5", "h6"
      # add another line
      "\n"

    when "p", "br"
      "\n" if next_node_name(node) != "div"

    when "li"
      "\n"

    when "div"
      # add one line only if the next child isn't a div
      "\n" if next_node_name(node) != "div" && next_node_name(node) != nil
  end
end

#trimmed_whitespace(text) ⇒ Object


40
41
42
43
# File 'lib/html2text.rb', line 40

def trimmed_whitespace(text)
  # Replace whitespace characters with a space (equivalent to \s)
  text.gsub(/[\t\n\f\r ]+/im, " ")
end

links are returned in [text](link) format


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
161
162
163
164
165
166
# File 'lib/html2text.rb', line 122

def wrap_link(node, output)
  href = node.attribute("href")
  name = node.attribute("name")

  output = output.strip

  # remove double [[ ]]s from linking images
  if output[0] == "[" && output[-1] == "]"
    output = output[1, output.length - 2]

    # for linking images, the title of the <a> overrides the title of the <img>
    if node.attribute("title")
      output = node.attribute("title").to_s
    end
  end

  # if there is no link text, but a title attr
  if output.empty? && node.attribute("title")
    output = node.attribute("title").to_s
  end

  if href.nil?
    if !name.nil?
      output = "[#{output}]"
    end
  else
    href = href.to_s

    if href != output && href != "mailto:#{output}" &&
        href != "http://#{output}" && href != "https://#{output}"
      if output.empty?
        output = href
      else
        output = "[#{output}](#{href})"
      end
    end
  end

  case next_node_name(node)
    when "h1", "h2", "h3", "h4", "h5", "h6"
      output += "\n"
  end

  output
end