Class: Raev::Url

Inherits:
Object
  • Object
show all
Defined in:
lib/raev/url.rb

Constant Summary collapse

AUTHOR_CSS_SELECTORS =
[
  '.c-byline__item a'.freeze,
  '.author-info .name'.freeze,
  '.author-top a'.freeze,
      '.yt-user-info a'.freeze,
  'a[rel~="author"]'.freeze,
  'a[itemprop~="author"]'.freeze,
  '.author h3 a'.freeze,
  '.author'.freeze,
  '.posted-by a'.freeze,
  '.entryAuthor a'.freeze,
  'a.names'.freeze,
  'a.byline-author'.freeze,
  '.byline a'.freeze,
  '.author.vcard a'.freeze,
  'p.info a'.freeze,
  '.author-name'.freeze,
  '.upcased'.freeze,
  'a[rel~="nofollow"]'.freeze
]
REGEX_UTM =
/(\?|&)utm_/
REGEX_URL_DATE =
/[0-9]{4}\/[0-9]{1,2}\/[0-9]{1,2}/
REGEX_ENTRY_DATE =
/[^a-zA-Z0-9\s]/
REGEX_PAGE_TITLE =
/ +/

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(url) ⇒ Url

Returns a new instance of Url.



40
41
42
43
44
45
# File 'lib/raev/url.rb', line 40

def initialize(url)
  fetch(url)
  @url = Url.remove_utm(@url)
  @doc = nil
  @linked_data = nil
end

Instance Attribute Details

#bodyObject (readonly)

Returns the value of attribute body.



37
38
39
# File 'lib/raev/url.rb', line 37

def body
  @body
end

#docObject (readonly)

Returns the value of attribute doc.



38
39
40
# File 'lib/raev/url.rb', line 38

def doc
  @doc
end

#urlObject (readonly)

Returns the value of attribute url.



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

def url
  @url
end

Class Method Details

.base(url) ⇒ Object



47
48
49
50
51
# File 'lib/raev/url.rb', line 47

def self.base(url)
  base_url = url.split('/'.freeze)[2]  
  base_url.gsub!('www.'.freeze, ''.freeze) unless base_url.nil?
  base_url
end

.remove_utm(url) ⇒ Object



53
54
55
56
57
58
59
60
61
62
# File 'lib/raev/url.rb', line 53

def self.remove_utm(url)
  unless url.nil?
    utm_index = url.index(REGEX_UTM)
    unless(utm_index.nil?)
      url = url.slice(0, utm_index)
    end
  end
  
  url
end

Instance Method Details

#authorObject



165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
# File 'lib/raev/url.rb', line 165

def author
      node = document.search('meta[name="author"]'.freeze).first

      if node && node.attribute("content".freeze)
return node.attribute("content".freeze).value
      end
      
  node = document.search(AUTHOR_CSS_SELECTORS.join(", ".freeze)).first
  
  if node
    words = node.content.split.size
  
    if words <= 4
      return Sanitize.clean(node.content).strip[0..255]
    end
  end
  
  "".freeze
end

#bestRatingObject



203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
# File 'lib/raev/url.rb', line 203

def bestRating
  node = document.search('*[itemprop="bestRating"]'.freeze).first
  
  if node
    if node.attribute("content".freeze)
      value = node.attribute("content".freeze).value
    
      if value
        return value.to_f
      end
    end
  end
  
  nil      
end

#documentObject



219
220
221
222
223
224
225
# File 'lib/raev/url.rb', line 219

def document
  if @doc.nil?
    @doc = Nokogiri::HTML(@body)
  end

  @doc
end

#feedObject



79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
# File 'lib/raev/url.rb', line 79

def feed
  feed_url = nil
  
  node = document.css('link[type="application/rss+xml"][rel="alternate"]'.freeze)
  
  if node.first
    feed_url = node.first["href"]
  else
    node = document.css('a:match_href("http://feeds.")'.freeze, Raev::Parser.new)
            
    if node.first
      feed_url = node.first["href"]
    end
  end
  
  if feed_url && feed_url[0,1] == "/".freeze
    feed_url = @url + feed_url
  end
  
  feed_url
end

#headlineObject



101
102
103
104
105
106
107
108
109
110
111
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
# File 'lib/raev/url.rb', line 101

def headline
  if linked_data && linked_data["headline"]
    return Sanitize.clean(linked_data["headline"])
  end
  
  page_title = nil
  
  node = document.css(".twitter-share-button".freeze)
  
  if node.first
    if node.first['data-text']
      page_title = node.first['data-text']
    end
  end

  if page_title.nil?
    document.css("head meta".freeze).each do |meta|
      if meta['property'] == 'og:title'.freeze || meta['property'] == 'twitter:title'.freeze
        page_title = meta['content']
      end
    end
  end
        
  if page_title.nil?
    node = document.css("#article h1, a[rel=\"bookmark\"], h2[itemprop=\"name\"]".freeze)
            
    if node.first
      page_title = node.first.content
    end
  end
  
  unless page_title.nil?
    page_title.gsub!(REGEX_PAGE_TITLE, ' '.freeze)
  end
  
  page_title
end

#pubdateObject



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
# File 'lib/raev/url.rb', line 139

def pubdate      
  if linked_data && linked_data["datePublished"]
    return Date.parse(linked_data["datePublished"])
  end
  
  date_elements = @url.match(REGEX_URL_DATE).to_s.split("/".freeze)
  
  if date_elements.size == 3
    return Date.new(date_elements[0].to_i, date_elements[1].to_i, date_elements[2].to_i)      
  else
    node = document.search("meta[itemprop='datePublished'], meta[name='pub_date']".freeze).first
    
    if node
      return Date.parse(node.attribute("content".freeze))
    else
      node = document.search(".entryDate, .entrydate".freeze).first

      if node
        return Chronic.parse(node.content.gsub(, "".freeze).strip)
      end
    end
  end
  
  nil
end

#ratingValueObject



185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
# File 'lib/raev/url.rb', line 185

def ratingValue
  node = document.search('*[itemprop="ratingValue"]'.freeze).first
  
  if node
    if node.attribute("content".freeze)
      value = node.attribute("content".freeze).value
    else
      value = node.content
    end
  end

  if value
    value.to_f
  else
    nil
  end
end

#twitterObject



68
69
70
71
72
73
74
75
76
77
# File 'lib/raev/url.rb', line 68

def twitter
  node = document.css('a:match_href("twitter.com")'.freeze, Raev::Parser.new)
        
  if node.first
    twitter_url = node.first["href"]
    twitter_url.split('/'.freeze).last
  else
    nil
  end
end

#without_httpObject



64
65
66
# File 'lib/raev/url.rb', line 64

def without_http
  @url.sub("http://".freeze, "".freeze)
end