HTMLの孤島発見スクリプト ref: http://qiita.com/kaityo256/items/320e31f1200f73706cea

file0.txt

$ cd public_html
$ ruby linkchecker.rb
/path/to/public_html/foo.html is isolated.
/path/to/public_html/bar.html is isolated.

linkchecker.rb

# Copyright kaityo256 2016
# Distributed under the Boost Software License, Version 1.0.
# (See accompanying file LICENSE_1_0.txt or copy at
# http://www.boost.org/LICENSE_1_0.txt)

def findlink(filename,h)
  dir = File.dirname(filename)
  open(filename){|f|
    f.gets(nil).scan(/a href=\"(.*?)\"/).each{|a|
      s = a[0]
      next if s =~ /^http/
      next if s =~/^#/
      if s=~/(.*?html)#/
        s = $1
      end
      next if s !~/html$/
      s =  File.expand_path(s,dir)
      h[s] = true
    }
  }  
end

h = Hash.new
files = Array.new
Dir.glob('./**/*').each{|filename|
  if filename =~ /html$/
    full = File.expand_path(filename)
    files.push full
    findlink(full,h)
  end
}

files.each{|f|
  if !h.has_key?(f)
    puts "#{f} is isolated."
  end
}