Created
February 5, 2019 10:59
-
-
Save henrikj242/66201c7a3f2980513e0e7a4fc9f86b61 to your computer and use it in GitHub Desktop.
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
require 'nokogiri' | |
unordered_list = <<~END | |
<ul> | |
<li> | |
First item | |
</li> | |
<li> | |
Second item | |
<ul> | |
<li> | |
Second item's first item | |
<ul> | |
<li> | |
Second item's first item's first item | |
</li> | |
<li> | |
Second item's first item's second item | |
</li> | |
</ul> | |
</li> | |
</ul> | |
</li> | |
</ul> | |
END | |
def parse_html_list_item(li, indents) | |
first_text_child = li.children.select{|c| c.text? }[0].text.strip | |
ul = li.at_css('ul') | |
if ul | |
' ' * indents + "• #{first_text_child}\n" + parse_html_list(ul, indents + 1) | |
else | |
' ' * indents + "• #{first_text_child}\n" | |
end | |
end | |
def parse_html_list(ul, indents) | |
text = '' | |
ul.children.select{|l| l.name == 'li' }.each do |li| | |
text += parse_html_list_item(li, indents) | |
end | |
text | |
end | |
def parse_html(content) | |
all = Nokogiri::HTML(content) | |
ul = all.css('ul')[0] | |
parse_html_list(ul, 0) if ul | |
end | |
puts parse_html(unordered_list) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment