Scripts to migrate an existing HTML site to Jekyll when you can't access the source

1-trim-lines.rb

# First grab the remote site
# wget --mirror --convert-links --adjust-extension --page-requisites --no-parent http://yourdomain.co.uk
# If you have images hosted on another site then do
# wget --mirror --convert-links --adjust-extension --page-requisites --span-hosts --domains mydomain.com,imagehostingcdn.com https://mydomain.com
# Then have a look how many lines to trim from beginning and end

htmls = Dir.glob('/**/*.html')

htmls.each do |file|
  # Change numbers to how many lines you want to trim
  output = File.readlines(file).drop(450).reverse.drop(72).reverse

  File.open(file, 'w') do |f|
    output.each do |line|
      f.write line
    end
  end
end

2-add-frontmatter.rb

# Add frontmatter to all your HTML files

htmls = Dir.glob('/**/*.html')

htmls.each do |file|
  output = File.readlines(file).reverse
  output << "---\n\n"
  output << "title: \n"
  output << "---\n"
  output = output.reverse
  File.open(file, 'w') do |f|
    output.each do |line|
      f.write line
    end
  end
end

3-get-files.rb

# Extract links on external CDNs

htmls = Dir.glob('/**/*.html')

htmls.each do |file|
  matches = File.read(file)
                 .scan(/(http\:\/\/cdn[0-9]\.yourdomain\.co\.uk\/.*\.(jpg|png|gif|jpeg|pdf))"/)
  matches.each { |m| puts m[0] }
end

# This isn't perfect but you can then save this to a file and run wget.
# wget -i file-manifest -m

4-delete-params.sh

# If you're importing from Dropbox it might help to run the following to clean up file extensions

find . -exec rename -s '?raw=1' '' {} +
find . -exec rename -s '?dl=0' '' {} +