Class: WebStat::Fetch

Inherits:
Object
  • Object
show all
Defined in:
lib/web_stat/fetch.rb

Direct Known Subclasses

FetchAsHtml, FetchAsWeb

Instance Attribute Summary collapse

Instance Method Summary collapse

Instance Attribute Details

#header ⇒ Object

Returns the value of attribute header.



3
4
5
 
# File 'lib/web_stat/fetch.rb', line 3

def header
  @header
end

#html ⇒ Object

Returns the value of attribute html.



3
4
5
 
# File 'lib/web_stat/fetch.rb', line 3

def html
  @html
end

#nokogiri ⇒ Object

Returns the value of attribute nokogiri.



3
4
5
 
# File 'lib/web_stat/fetch.rb', line 3

def nokogiri
  @nokogiri
end

#status ⇒ Object

Returns the value of attribute status.



3
4
5
 
# File 'lib/web_stat/fetch.rb', line 3

def status
  @status
end

#url ⇒ Object

Returns the value of attribute url.



3
4
5
 
# File 'lib/web_stat/fetch.rb', line 3

def url
  @url
end

#userdic ⇒ Object

Returns the value of attribute userdic.



3
4
5
 
# File 'lib/web_stat/fetch.rb', line 3

def userdic
  @userdic
end

Instance Method Details

#content ⇒ Object

Get main section



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

def content
  Sanitize.clean(Readability::Document.new(@nokogiri.at('body').to_s).content)
end

#eyecatch_image_path ⇒ Object

Get temporary path of image



41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
 
# File 'lib/web_stat/fetch.rb', line 41

def eyecatch_image_path
  # Reuse `path` in this method
  path = nil
  WebStat::Configure.get["eyecatch_image_xpaths"].each do |xpath|
    if @nokogiri.xpath(xpath).first.respond_to?(:value)
      path = @nokogiri.xpath(xpath).first.value
      break
    end
  end
  # If there is a thumbnail rule, apply it.
  WebStat::Configure.get["thumbnail_regex"].each do |provider, v|
    if @url.match(v[0])
      return @url.gsub(v[0], v[1])
    end
  end
  readability_content = ::Nokogiri::HTML(Readability::Document.new(@nokogiri.at('body').to_s).content)
  if (path.nil? || path.empty?) && readability_content.xpath('//img').first
    path =  readability_content.xpath('//img').first.attr('src')
  end
  if (path.nil? || path.empty?) && @nokogiri.xpath('//img').first
    path = @nokogiri.xpath('//img').first.attr('src')
  end
  if ! path.nil? && path.match(/^\//)
    "#{URI.parse(@url).scheme}://#{URI.parse(@url).host}#{path}"
  else
    path
  end
end

#get_last_modified ⇒ Object

Return Date or last modified header.

Parameters:

  • url (String)

Returns:

  • DataTime



122
123
124
125
126
127
128
129
130
131
132
133
134
135
 
# File 'lib/web_stat/fetch.rb', line 122

def get_last_modified
  @header = @header || {}
  if @header.has_key?("date") && @header.has_key?("last-modified")
    if DateTime.parse(@header["date"]) >= DateTime.parse(@header["last-modified"])
      DateTime.parse(@header["date"])
    else
      DateTime.parse(@header["last-modified"])
    end
  elsif @header.has_key?("date")
    DateTime.parse(@header["date"])
  elsif @header.has_key?("last-modified")
    DateTime.parse(@header["last-modified"])
  end
end

#get_url(url) ⇒ Object

Get url

Parameters:

  • url (String)
  • body (String) 


90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
 
# File 'lib/web_stat/fetch.rb', line 90

def get_url(url)
  mech = Mechanize.new { |_mech| _mech.user_agent = WebStat::Configure.get["user_agent"] }
  # Enable to read Robots.txt
  mech.robots = true
  begin
    if mech.agent.robots_disallowed?(url)
      raise Mechanize::RobotsDisallowedError.new(url)
    end
    document = mech.get(url, [], nil, { 'Accept-Language' => 'ja'})
    @header = document.header
    begin
      raise 'not_use_chromedirver' unless WebStat::Configure.get["use_chromedirver"]
      body = WebStat::WebDriverHelper.get_source(url)
      @status = 200
    rescue
      if document.class == Mechanize::File
        body = document.body
      else
        body = document.body.encode('UTF-8', document.encoding)
      end
      @status = document.code
    end
  rescue Mechanize::ResponseCodeError => e
    body = e.page.body
    @status = e.page.code
  end
  body
end

#save_local_path(url) ⇒ Object

Get local path to save url

Parameters:

  • url (String) 


72
73
74
75
76
77
78
79
80
81
82
83
84
85
 
# File 'lib/web_stat/fetch.rb', line 72

def save_local_path(url)
  return nil if url.nil? || ! url.match(%{^http})
  tmp_file = "/tmp/#{Digest::SHA1.hexdigest(url)}"
  agent = Mechanize.new { |_agent| _agent.user_agent = WebStat::Configure.get["user_agent"] }
  image = agent.get(url)
  File.open(tmp_file, "w+b") do |_file|
    if image.class == Mechanize::File
      _file.puts(image.body)
    elsif image.respond_to?(:body_io)
      _file.puts(image.body_io.read)
    end
  end
  tmp_file
end

#site_name ⇒ Object

Get name of domain



23
24
25
26
27
28
29
30
31
32
33
34
 
# File 'lib/web_stat/fetch.rb', line 23

def site_name
  begin
    site_name = @nokogiri.title.split(/#{WebStat::Configure.get["regex_to_sprit_title"]}/, 2).last
  rescue
    site_name = @nokogiri.title
  end
  if site_name.nil?
    "No Sitename"
  else
    site_name.strip
  end
end

#stat(userdics: nil) ⇒ Object

Get the informations of @url

Parameters:

  • Specify (Hash) —

    a dictionary for each language code. example ) /*/.dic, “other”: /***/***.dic



139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
 
# File 'lib/web_stat/fetch.rb', line 139

def stat(userdics: nil)
  clean_content = content.scrub('').gsub(/[\n\t\r　]/, "").gsub(/\s{2,}/, "\s").gsub(URI.regexp, "")
  language_code = CLD.detect_language(clean_content)[:code]
  if userdics && userdics.has_key?(language_code) && File.exists?(userdics[language_code])
    tag = WebStat::Tag.new("#{title} #{content}", userdic: userdics[language_code])
  elsif userdics && userdics.has_key?("other") && File.exists?(userdics["other"])
    tag = WebStat::Tag.new("#{title} #{content}", userdic: userdics["other"])
  else
    tag = WebStat::Tag.new("#{title} #{content}", userdic: WebStat::Configure.get["userdic"])
  end
  {
    title: title,
    site_name: site_name,
    content: clean_content,
    language_code: language_code,
    status: @status,
    url: @url,
    last_modified_at: get_last_modified,
    eyecatch_image_path: save_local_path(eyecatch_image_path),
    tags: tag.nouns
  }
end

#title ⇒ String

Get title

Returns:

  • (String) —

    title



6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
 
# File 'lib/web_stat/fetch.rb', line 6

def title
  begin
    title = @nokogiri.title.split(/#{WebStat::Configure.get["regex_to_sprit_title"]}/, 2).first
    if title.length < WebStat::Configure.get["min_length_of_meta_title"]
      title = @nokogiri.css("h1").first.content
    end
  rescue
    title = @nokogiri.title
  end
  if title.nil?
    "No Title"
  else
    title.strip
  end
end