regex.rb

#!/usr/bin/env ruby

html = %{This is a test

This is only a test

<pre>This is

some text
in a PRE.</pre>

omg<pre></pre>
<pre></pre>stuff<pre></pre>

More text.

<pre>This is another</pre>}

regex = %r{<pre>[\s\S]*?</pre>|[^\r\n]+}

p html.scan(regex)

# => ["This is a test", "This is only a test", "<pre>This is\n\nsome text\nin a PRE.</pre>", "omg<pre></pre>", "<pre></pre>", "stuff<pre></pre>", "More text.", "<pre>This is another</pre>"]