Class: Polipus::Page

Inherits:
Object
  • Object
show all
Defined in:
lib/polipus/page.rb

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(url, params = {}) ⇒ Page

Create a new page



41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
# File 'lib/polipus/page.rb', line 41

def initialize(url, params = {})
  @url = url.kind_of?(URI) ? url : URI(url)
  @code = params[:code]
  @headers = params[:headers] || {}
  @headers['content-type'] ||= ['']
  @aliases = Array(params[:aka]).compact
  @referer = params[:referer]
  @depth = params[:depth] || 0
  @redirect_to = to_absolute(params[:redirect_to])
  @response_time = params[:response_time]
  @body = params[:body]
  @error = params[:error]
  @fetched = !params[:code].nil?
  @user_data = OpenStruct.new
  @domain_aliases = params[:domain_aliases] ||= []
  @storable = true
end

Instance Attribute Details

#aliasesObject

Returns the value of attribute aliases.



30
31
32
# File 'lib/polipus/page.rb', line 30

def aliases
  @aliases
end

#bodyObject (readonly)

The raw HTTP response body of the page



11
12
13
# File 'lib/polipus/page.rb', line 11

def body
  @body
end

#codeObject

Integer response code of the page



19
20
21
# File 'lib/polipus/page.rb', line 19

def code
  @code
end

#depthObject

Depth of this page from the root of the crawl. This is not necessarily the shortest path; use PageStore#shortest_paths! to find that value.



22
23
24
# File 'lib/polipus/page.rb', line 22

def depth
  @depth
end

#domain_aliasesObject

Returns the value of attribute domain_aliases.



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

def domain_aliases
  @domain_aliases
end

#errorObject (readonly)

Exception object, if one was raised during HTTP#fetch_page



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

def error
  @error
end

#headersObject (readonly)

Headers of the HTTP response



13
14
15
# File 'lib/polipus/page.rb', line 13

def headers
  @headers
end

#redirect_toObject (readonly)

URL of the page this one redirected to, if any



15
16
17
# File 'lib/polipus/page.rb', line 15

def redirect_to
  @redirect_to
end

#refererObject

URL of the page that brought us to this page



24
25
26
# File 'lib/polipus/page.rb', line 24

def referer
  @referer
end

#response_timeObject

Response time of the request for this page in milliseconds



26
27
28
# File 'lib/polipus/page.rb', line 26

def response_time
  @response_time
end

#storableObject

Whether the current page should be stored Default: true



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

def storable
  @storable
end

#urlObject (readonly)

The URL of the page



9
10
11
# File 'lib/polipus/page.rb', line 9

def url
  @url
end

#user_dataObject

OpenStruct it holds users defined data



28
29
30
# File 'lib/polipus/page.rb', line 28

def user_data
  @user_data
end

Class Method Details

.from_hash(hash) ⇒ Object



205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
# File 'lib/polipus/page.rb', line 205

def self.from_hash(hash)
  page = self.new(URI(hash['url']))
  {'@headers' => hash['headers'] ? Marshal.load(hash['headers']) : {'content-type' => ['']},
   '@body'    => hash['body'],
   '@links'   => hash['links'] ? hash['links'].map { |link| URI(link) } : [],
   '@code'    => hash['code'].to_i,
   '@depth'   => hash['depth'].to_i,
   '@referer' => hash['referer'],
   '@redirect_to' => (!!hash['redirect_to'] && !hash['redirect_to'].empty?) ? URI(hash['redirect_to']) : nil,
   '@response_time' => hash['response_time'].to_i,
   '@fetched' => hash['fetched'],
   '@user_data' => hash['user_data'] ? OpenStruct.new(hash['user_data']) : nil
  }.each do |var, value|
    page.instance_variable_set(var, value)
  end
  page
end

.from_json(json) ⇒ Object



223
224
225
226
# File 'lib/polipus/page.rb', line 223

def self.from_json(json)
  hash = JSON.parse json
  self.from_hash hash
end

Instance Method Details

#baseObject

Base URI from the HTML doc head element www.w3.org/TR/html4/struct/links.html#edef-BASE



142
143
144
145
146
147
148
149
150
# File 'lib/polipus/page.rb', line 142

def base
  @base = if doc
    href = doc.search('//head/base/@href')
    URI(href.to_s) unless href.nil? rescue nil
  end unless @base
  
  return nil if @base && @base.to_s().empty?
  @base
end

#content_typeObject

The content-type returned by the HTTP request for this page



110
111
112
# File 'lib/polipus/page.rb', line 110

def content_type
  headers['content-type'].first
end

#discard_doc!Object

Delete the Nokogiri document and response body to conserve memory



94
95
96
97
# File 'lib/polipus/page.rb', line 94

def discard_doc!
  links # force parsing of page links before we trash the document
  @doc = @body = nil
end

#discard_links!Object

Discard links, a next call of page.links will return an empty array



87
88
89
# File 'lib/polipus/page.rb', line 87

def discard_links!
  @links = []
end

#docObject

Nokogiri document for the HTML body



79
80
81
82
# File 'lib/polipus/page.rb', line 79

def doc
  return @doc if @doc
  @doc = Nokogiri::HTML(@body) if @body && html? rescue nil
end

#fetched?Boolean

Was the page successfully fetched? true if the page was fetched with no error, false otherwise.

Returns:

  • (Boolean)


103
104
105
# File 'lib/polipus/page.rb', line 103

def fetched?
  @fetched
end

#html?Boolean

Returns true if the page is a HTML document, returns false otherwise.

Returns:

  • (Boolean)


118
119
120
# File 'lib/polipus/page.rb', line 118

def html?
  !!(content_type =~ %r{^(text/html|application/xhtml+xml)\b})
end

#in_domain?(uri) ⇒ Boolean

Returns true if uri is in the same domain as the page, returns false otherwise

Returns:

  • (Boolean)


174
175
176
177
# File 'lib/polipus/page.rb', line 174

def in_domain?(uri)
  @domain_aliases ||= []
  uri.host == @url.host || @domain_aliases.include?(uri.host)
end

Array of distinct A tag HREFs from the page



62
63
64
65
66
67
68
69
70
71
72
73
74
# File 'lib/polipus/page.rb', line 62

def links
  return @links.to_a unless @links.nil?
  @links = Set.new
  return [] if !doc
  
  doc.search("//a[@href]").each do |a|
    u = a['href']
    next if u.nil? or u.empty?
    abs = to_absolute(u) rescue next
    @links << abs if in_domain?(abs)
  end
  @links.to_a
end

#not_found?Boolean

Returns true if the page was not found (returned 404 code), returns false otherwise.

Returns:

  • (Boolean)


134
135
136
# File 'lib/polipus/page.rb', line 134

def not_found?
  404 == @code
end

#redirect?Boolean

Returns true if the page is a HTTP redirect, returns false otherwise.

Returns:

  • (Boolean)


126
127
128
# File 'lib/polipus/page.rb', line 126

def redirect?
  (300..307).include?(@code)
end

#storable?Boolean

Returns:

  • (Boolean)


201
202
203
# File 'lib/polipus/page.rb', line 201

def storable?
  @storable
end

#to_absolute(link) ⇒ Object

Converts relative URL link into an absolute URL based on the location of the page



156
157
158
159
160
161
162
163
164
165
166
167
168
# File 'lib/polipus/page.rb', line 156

def to_absolute(link)
  return nil if link.nil?

  # remove anchor
  link = URI.encode(URI.decode(link.to_s.gsub(/#[a-zA-Z0-9_-]*$/,'')))

  relative = URI(link)
  absolute = base ? base.merge(relative) : @url.merge(relative)

  absolute.path = '/' if absolute.path.empty?

  return absolute
end

#to_hashObject



179
180
181
182
183
184
185
186
187
188
189
190
191
192
# File 'lib/polipus/page.rb', line 179

def to_hash
  {'url' => @url.to_s,
   'headers' => Marshal.dump(@headers),
   'body' => @body,
   'links' => links.map(&:to_s), 
   'code' => @code,
   'depth' => @depth,
   'referer' => @referer.to_s,
   'redirect_to' => @redirect_to.to_s,
   'response_time' => @response_time,
   'fetched' => @fetched,
   'user_data' => @user_data.nil? ? {} : @user_data.marshal_dump
 }
end

#to_jsonObject



194
195
196
197
198
199
# File 'lib/polipus/page.rb', line 194

def to_json
  th = to_hash.dup
  th.each {|k,v| th.delete(k) if v.nil? || (v.respond_to?(:empty?) && v.empty?)}
  th.delete('headers') if content_type.empty?
  th.to_json
end