Last active
August 11, 2020 10:20
-
-
Save xijo/35adcb27098164b4f45f46ff098bd188 to your computer and use it in GitHub Desktop.
Ruby script to convert google docs into markdown
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Usage ruby doc-to-md.rb input.html > output.md | |
# Make sure to install reverse_markdown: gem install reverse_markdown | |
require 'reverse_markdown' | |
require 'cgi' | |
input = ARGF.read | |
BOLD_CLASSES = input.scan(/\.(\w+)\s*\{[^}]*font-weight:\s*700[^}]*\}/).flatten | |
module ReverseMarkdown | |
module Converters | |
class Span < Base | |
def convert(node, state = {}) | |
content = treat_children(node, state.merge(already_strong: true)) | |
classes = node.attributes['class']&.value.to_s.split(' ') | |
if content.strip.empty? || state[:already_strong] | |
"" | |
elsif (classes & BOLD_CLASSES).any? | |
"#{content[/^\s*/]}**#{content.strip}**#{content[/\s*$/]}" | |
else | |
content | |
end | |
end | |
def disabled? | |
!enabled? | |
end | |
end | |
class PreventEmptyLinks < A | |
def convert(node, state = {}) | |
content = treat_children(node, state) | |
node['href'] = CGI.unescape(node['href'].gsub!(/https:\/\/www\.google\.com\/url\?q=([^&]+)[^\)]+/, '\1').to_s) | |
content == " " ? ' ' : " #{super}" | |
end | |
end | |
register :span, Span.new | |
register :a, PreventEmptyLinks.new | |
end | |
end | |
puts ReverseMarkdown.convert input |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment