Read through an HTML file of anchor tags, parse all of the hyperlinks, and download them

urlFetcher.rb

#!/usr/bin/ruby
#
# License: Public Domain

line_number = 0;
dry_run = ARGV[1]

if ARGV[0].nil? || ARGV[0].empty?
  puts "Usage: ruby urlFetcher.rb [FILE_PATH] [OPTION]"
  puts ""
  puts "The file given to this script must contain <a> tags with 'href' attributes"
  puts "and those links are what will be parsed and downloaded."
  puts ""
  puts "Options"
  puts " ---"
  puts "   --dry-run    It will print out all of the files that will be downloaded"
  puts "                but won't actually download them"
  puts ""

  exit
end

text = File.open(ARGV[0]).read
text.gsub!(/\r\n?/, "\n")

text.each_line do |line|
  current_link = line[/href=\".*?\"/].to_s
  current_link.gsub! 'href=', ''
  current_link.gsub! /\?.+/, ''
  current_link.gsub! '"', ''

  next if current_link.nil? || current_link.empty?

  if dry_run == "--dry-run"
    puts current_link
  else
    `wget #{current_link}`
  end

  line_number += 1
end

puts "#{line_number} files downloaded"