Class: Retriever::Page

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

Constant Summary collapse

HTTP_RE =
Regexp.new(/^http/i).freeze
H1_RE =
Regexp.new(/<h1>(.*)<\/h1>/i).freeze
H2_RE =
Regexp.new(/<h2>(.*)<\/h2>/i).freeze
TITLE_RE =
Regexp.new(/<title>(.*)<\/title>/i).freeze
DESC_RE =
Regexp.new(/<meta[^>]*name=[\"|\']description[\"|\']
[^>]*content=[\"]
(
  [^\"]*
)
[\"]
[^>]
*>
/ix).freeze
HREF_CONTENTS_RE =
Regexp.new(/\shref=
['|"]
(
  [^\s]
  [a-z0-9\.\/\:\-\%\+\?\!\=\&\,\:\;\~\_]+
)
['|"]
[\s|\W]
/ix).freeze
NONPAGE_EXT_RE =
Regexp.new(/\.
(?:css|js|png|gif|jpg|mp4|
wmv|flv|mp3|wav|doc|txt|ico|xml)
/ix).freeze

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(url, source, t) ⇒ Page

Returns a new instance of Page.



36
37
38
39
40
41
# File 'lib/retriever/page.rb', line 36

def initialize(url, source, t)
  @url = url
  @t = t
  @source = source.encode_utf8_and_replace
  @links = nil
end

Instance Attribute Details

recieves page source as string returns array of unique href links



45
46
47
# File 'lib/retriever/page.rb', line 45

def links
  @links
end

#sourceObject (readonly)

Returns the value of attribute source.



34
35
36
# File 'lib/retriever/page.rb', line 34

def source
  @source
end

#tObject (readonly)

Returns the value of attribute t.



34
35
36
# File 'lib/retriever/page.rb', line 34

def t
  @t
end

#urlObject (readonly)

Returns the value of attribute url.



34
35
36
# File 'lib/retriever/page.rb', line 34

def url
  @url
end

Instance Method Details

#descObject



72
73
74
# File 'lib/retriever/page.rb', line 72

def desc
  DESC_RE =~ @source ? @source.match(DESC_RE)[1].decode_html  : ''
end

#h1Object



76
77
78
# File 'lib/retriever/page.rb', line 76

def h1
  H1_RE =~ @source ? @source.match(H1_RE)[1].decode_html  : ''
end

#h2Object



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

def h2
  H2_RE =~ @source ? @source.match(H2_RE)[1].decode_html  : ''
end

#parse_files(arr = parse_internal) ⇒ Object



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

def parse_files(arr = parse_internal)
  arr.select { |x| @t.file_re =~ x }
end

#parse_internalObject



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

def parse_internal
  links.select { |x| @t.host == Addressable::URI.parse(Addressable::URI.encode(x)).host }
end

#parse_internal_visitableObject



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

def parse_internal_visitable
  parse_internal.select { |x| !(NONPAGE_EXT_RE =~ x) }
end

#parse_seoObject



84
85
86
# File 'lib/retriever/page.rb', line 84

def parse_seo
  [title, desc, h1, h2]
end

#titleObject



68
69
70
# File 'lib/retriever/page.rb', line 68

def title
  TITLE_RE =~ @source ? @source.match(TITLE_RE)[1].decode_html : ''
end