Class: SpeedSpider::Crawler

Inherits:
Object
  • Object
show all
Defined in:
lib/speed_spider/crawler.rb

Instance Method Summary collapse

Constructor Details

#initialize(start_url, options) ⇒ Crawler 



8
9
10
11
12
 
# File 'lib/speed_spider/crawler.rb', line 8

def initialize(start_url, options)
  @start_url = start_url
  @base_url = options[:base_url]
  @options = options
end

Instance Method Details

#after_crawl ⇒ Object 



56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
 
# File 'lib/speed_spider/crawler.rb', line 56

def after_crawl
  lambda { |pages|
    pages.each do |url, page|
      path = page.url.path
      path += 'index.html' if path.end_with? '/' or path.empty?

      path = "#{@options[:dir]}/#{page.url.host}#{path}"
      dir = File.dirname path

      FileUtils.mkdir_p dir unless dir.empty?
      File.open path, 'w' do |f|
        f.write page.body
      end

      puts "save file #{path}" if @options[:verbose]
    end
  }
end

#crawl ⇒ Object 



75
76
77
78
79
80
 
# File 'lib/speed_spider/crawler.rb', line 75

def crawl
  Anemone.crawl @start_url, @options do |spider|
    spider.focus_crawl &focus_crawl
    spider.after_crawl &after_crawl
  end
end

#focus_crawl ⇒ Object 



23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
 
# File 'lib/speed_spider/crawler.rb', line 23

def focus_crawl
  lambda { |page|
    links = []
    if page.doc
      # include javascripts and img files as target links
      page.doc.search('//script[@src]', '//img[@src]', '//iframe[@src]').each do |s|
        u = s['src']
        next if u.nil? or u.empty?
        abs = page.to_absolute u rescue next
        links << abs if page.in_domain? abs
      end

      # include css files as target links
      page.doc.search('//link[@href]').each do |s|
        u = s['href']
        next if u.nil? or u.empty?
        abs = page.to_absolute u rescue next
        links << abs if page.in_domain? abs

      end
    elsif page.url.to_s.end_with? '.css'
      get_urls_from_css(page.body).each do |s|
        u = s.gsub('"', '').gsub("'", '')
        next if u.nil? or u.empty?
        abs = page.to_absolute u rescue next
        links << abs if page.in_domain? abs
      end
    end

    page.links + links.uniq
  }
end

#get_urls_from_css(data, pos = 0) ⇒ Object

return urls from css file contents



15
16
17
18
19
20
21
 
# File 'lib/speed_spider/crawler.rb', line 15

def get_urls_from_css data, pos = 0
  if m = data.match(/url\((.*?)\)/i, pos)
    [ m[1] ] + get_urls_from_css(data, m.end(1) + 1)
  else
    []
  end
end