Class: WebsiteCloner::Parser

Inherits:
Object
  • Object
show all
Defined in:
lib/website_cloner/parser.rb

Instance Method Summary collapse

Constructor Details

#initialize(downloader) ⇒ Parser

Returns a new instance of Parser.



6
7
8
9
 
# File 'lib/website_cloner/parser.rb', line 6

def initialize(downloader)
  @downloader = downloader
  @file_mapping = {}
end

Instance Method Details

#organize_files ⇒ Object 



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
118
119
120
 
# File 'lib/website_cloner/parser.rb', line 90

def organize_files
  Dir.glob(File.join(@downloader.output_dir, '**', '*')).each do |file|
    next if File.directory?(file)

    relative_path = file.sub(@downloader.output_dir + '/', '')
    dirname = File.dirname(relative_path)
    basename = File.basename(relative_path)

    if dirname.match?(/^[0-9a-f]+$/)
      new_basename = URI.decode_www_form_component(basename).gsub('%20', '-')
      new_path = case
                 when new_basename.end_with?('.css')
                   File.join(@downloader.output_dir, 'css', new_basename.gsub(/^[0-9a-f]+_/, ''))
                 when new_basename.end_with?('.js')
                   File.join(@downloader.output_dir, 'js', new_basename.gsub(/^[0-9a-f]+_/, ''))
                 else
                   File.join(@downloader.output_dir, 'assets', new_basename.gsub(/^[0-9a-f]+_/, ''))
                 end

      FileUtils.mv(file, new_path)
      @file_mapping["/#{relative_path}"] = "#{new_path.sub(@downloader.output_dir + '/', '')}"
    elsif !basename.include?('.') && !dirname.start_with?('css', 'js', 'assets')
      # This is likely a subpage without an extension
      new_path = "#{file}.html"
      FileUtils.mv(file, new_path)
      @file_mapping["/#{relative_path}"] = "#{new_path.sub(@downloader.output_dir + '/', '')}"
    end
  end

  update_references
end

#parse_and_download(content, url) ⇒ Object 



11
12
13
14
15
16
17
18
19
20
21
22
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
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
 
# File 'lib/website_cloner/parser.rb', line 11

def parse_and_download(content, url)
  doc = Nokogiri::HTML(content)
  base_uri = URI.parse(url)

  # Ensure the path is valid and not empty
  path = base_uri.path.empty? || base_uri.path == '/' ? '/index.html' : base_uri.path

  # Calculate the depth of the directory structure
  depth = [path.count('/') - 1, 0].max
  prefix = '../' * depth

  new_pages = []

  # Download and update image sources
  doc.css('img').each do |img|
    src = img['src']
    next if src.nil? || src.empty?
    new_src = @downloader.download_asset(src, 'image')
    img['src'] = prefix + new_src # Add the correct prefix for assets in subdirs
    @file_mapping[src] = new_src

    # Remove srcset attribute to prevent loading from CDN
    img.remove_attribute('srcset')
    img.remove_attribute('imagesrcset')

    # Update sizes attribute if present
    img['sizes'] = '100vw' if img['sizes']
  end

  # Download and update stylesheet links
  doc.css('link[rel="stylesheet"]').each do |link|
    href = link['href']
    next if href.nil? || href.empty?
    new_href = @downloader.download_asset(href, 'css')
    link['href'] = prefix + new_href # Add the correct prefix for assets in subdirs
    @file_mapping[href] = new_href
  end

  # Download and update script sources
  doc.css('script').each do |script|
    src = script['src']
    next if src.nil? || src.empty?
    new_src = @downloader.download_asset(src, 'js')
    script['src'] = prefix + new_src # Add the correct prefix for assets in subdirs
    @file_mapping[src] = new_src
  end

  # Handle internal links starting with '/'
  doc.css('a').each do |a|
    href = a['href']
    next if href.nil? || href.empty?

    # Target only internal links that start with '/'
    if href.start_with?('/')
      # Add the new URL to new_pages for downloading before modification
      new_pages << URI.join(base_uri, href).to_s

      # Special handling for homepage
      if href == '/'
        a['href'] = prefix + 'index.html'
      else
        # Remove leading '/' for saving the local file
        href.sub!(/^\//, '')

        # Append '.html' if it's missing and not a file download (like .pdf)
        href += '.html' unless href =~ /\.\w+$/

        # Update the href attribute
        a['href'] = href
      end
    end
  end

  # Save the updated HTML
  save_html(doc.to_html, url)

  new_pages
end