Module: Wwwtf::HTTP

Defined in:
lib/wwwtf/http.rb,
lib/wwwtf/http/url.rb

Defined Under Namespace

Modules: URL

Class Attribute Summary collapse

Class Method Summary collapse

Class Attribute Details

.curl_headers ⇒ Object

Returns the value of attribute curl_headers.



7
8
9
 
# File 'lib/wwwtf/http.rb', line 7

def curl_headers
  @curl_headers
end

Class Method Details

.body(url) ⇒ Object 



21
22
23
 
# File 'lib/wwwtf/http.rb', line 21

def self.body(url)
  %x{curl -kLs -H '#{curl_headers}' #{url}}
end

.fix_urls(base_url, src_string) ⇒ Object 



36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
 
# File 'lib/wwwtf/http.rb', line 36

def self.fix_urls(base_url, src_string)
  begin
    src_string = src_string.unescape.strip
    src_string = src_string[1..-2] if src_string.match(/^\".*\"$/)
    http = base_url.scan(/^(https*)\:\/\//).flatten.join
    if src_string.match(/^https*\:\/\//i)
      src_string
    elsif src_string.match(/^\/\//)
      "#{http}:#{src_string}"
    else
      File.join base_url, src_string
    end
  rescue
    puts "ERR: #{src_string}"
    return nil
  end
end

.headers(url) ⇒ Object 



11
12
13
14
15
16
17
18
19
 
# File 'lib/wwwtf/http.rb', line 11

def self.headers(url)
  hdrs = %x{curl -IkLs -H '#{curl_headers}' #{url}}
  headr = {}
  return headr if hdrs.match(/HTTP\/1\.[01]\s*[45][0-9][0-9]\s*\w/)
  hdr = hdrs.split("\r\n")
  hdr = hdr.collect{|h| {h.split(':')[0].strip => h.split(':')[1..-1].join.strip} }
  hdr.each{|h| headr = headr.merge h}
  headr
end

.page_dependency(url) ⇒ Object 



25
26
27
28
29
30
31
32
33
34
 
# File 'lib/wwwtf/http.rb', line 25

def self.page_dependency(url)
  page_content = body url
  xtmp_nodes   = XMLMotor.splitter page_content
  xtmp_tags    = XMLMotor.indexify xtmp_nodes
  tag_src      = XMLMotor.xmlattrib 'src', xtmp_nodes, xtmp_tags
  src_in_page = tag_src.uniq.collect{|src|
                  fix_urls url, src
                }
  Wwwtf::HTTP::URL.uniq([url] + src_in_page).compact
end