Class: Lac::Page

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

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(html: nil) ⇒ Page

Returns a new instance of Page.



50
51
52
 
# File 'lib/lac/page.rb', line 50

def initialize html: nil
  self.html = html
end

Instance Attribute Details

#html ⇒ Object

Returns the value of attribute html.



7
8
9
 
# File 'lib/lac/page.rb', line 7

def html
  @html
end

Class Method Details

.by_html(html) ⇒ Object 



64
65
66
 
# File 'lib/lac/page.rb', line 64

def self.by_html(html)
  self.new(html: html)
end

.by_html_string(html_string) ⇒ Object 



60
61
62
 
# File 'lib/lac/page.rb', line 60

def self.by_html_string(html_string)
  self.new(html: Nokogiri::HTML(html_string))
end

.by_url(url) ⇒ Object

helpers for seamless initialisation no matter what starting point



56
57
58
 
# File 'lib/lac/page.rb', line 56

def self.by_url(url)
  self.new(html: Nokogiri::HTML(get_page(url)))
end

.get_page(url, from_cache = true) ⇒ Object

Simply gets a webpage based on a url. from_cache = true (default) will take a cached version if it exists.



36
37
38
39
40
41
42
43
44
45
46
47
48
 
# File 'lib/lac/page.rb', line 36

def self.get_page(url, from_cache = true)
  url_hash = Digest::SHA256.hexdigest(url)
  filename = "cache/#{url_hash}"
  if from_cache && File.file?(filename)
    result = open(filename).read
    puts "Gotten #{filename} from cache"
  else
    result = open(url).read
    File.write(filename, result)
    puts "Written cache file #{filename}"
  end
  return result
end

Instance Method Details

#collection_by_selector(selector) ⇒ Object

Returns a collection of pages based on a selector. Use to collect a collection of elements from a page.



71
72
73
 
# File 'lib/lac/page.rb', line 71

def collection_by_selector(selector)
  self.html.css(selector).map{|item| Lac::Page.by_html(item)}
end

#try_css(css) ⇒ Object 



27
28
29
 
# File 'lib/lac/page.rb', line 27

def try_css(css)
  self.html.css(css).first
end

#try_css_attr(css, attr) ⇒ Object

Need better flow for what this does.



11
12
13
14
15
16
17
 
# File 'lib/lac/page.rb', line 11

def try_css_attr(css, attr)
  if element = self.try_css(css)
    element.attr(attr)
  else
    nil
  end
end

#try_css_parent_attr(css, attr) ⇒ Object 



19
20
21
22
23
24
25
 
# File 'lib/lac/page.rb', line 19

def try_css_parent_attr(css, attr)
  if element = try_css(css)
    element.parent.attr(attr)
  else
    nil
  end
end