Created
April 7, 2014 19:15
-
-
Save epitron/10033479 to your computer and use it in GitHub Desktop.
This file contains hidden or 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' | |
require 'pp' | |
doc0 = %{ | |
<p>Hello <b>DOM!</b></p> | |
} | |
doc1 = %{ | |
<div> | |
<p>Hello <b>DOM!</b></p> | |
<p>How are you doing?</p> | |
</div> | |
} | |
doc2 = %{ | |
<div> | |
<p>Hello <b>DOM!</b></p> | |
<p>How are you doing?</p> | |
<p>Lovely day, isn't it?</p> | |
</div> | |
} | |
# This one creates an immense amount of repetition | |
crazy_doc = %{ | |
<div id="entryContent" class="entrybox"> | |
<div xmlns:h="http://www.w3.org/1999/xhtml" class="entry" xml:lang="en"> | |
<span class="form_hwd"><h1><span class="seo">motte-and-bailey</span></h1></span><span class="hom"><span class="sense"><a name="motte-and-bailey__1"> </a><span class="span_sensenum">1</span><span class="gramGrp"><span class="pos" xml:lang="en"> noun</span></span><a href="http://www.focloir.ie/en/domain/ei/archit" onclick="javascript:openDomain(this, 'archit');return false;"><span title="ARCHITECTURE" class="lbl_purple_sc_i"> ARCHIT</span></a><a href="http://www.focloir.ie/en/domain/ei/hist" onclick="javascript:openDomain(this, 'hist');return false;"><span title="HISTORY" class="lbl_purple_sc_i"><span class="span_neutral">, </span>HIST</span></a><span class="cit_translation" xml:lang="ga"><span class="quote">móta agus bábhún</span></span></span></span><span class="hom"><span class="sense"><a name="motte-and-bailey__2"> </a><span class="span_sensenum">2</span><span class="gramGrp"><span class="pos" xml:lang="en"> adjective</span></span><a href="http://www.focloir.ie/en/domain/ei/archit" onclick="javascript:openDomain(this, 'archit');return false;"><span title="ARCHITECTURE" class="lbl_purple_sc_i"> ARCHIT</span></a><a href="http://www.focloir.ie/en/domain/ei/hist" onclick="javascript:openDomain(this, 'hist');return false;"><span title="HISTORY" class="lbl_purple_sc_i"><span class="span_neutral">, </span>HIST</span></a><span class="cit_translation" xml:lang="ga"><span class="quote">móta agus bábhúin</span></span><span class="cit_example"><span class="quote">a motte-and-bailey castle</span><span class="cit_translation_noline" xml:lang="ga"> <span class="quote">caisleán móta agus bábhúin</span></span></span></span></span> | |
</div> | |
<!-- End of DIV entry--> | |
</div> | |
} | |
class Nokogiri::XML::NodeSet | |
def nested_text | |
map do |node| | |
print "." | |
if node.text? | |
node | |
else | |
children.nested_text | |
end | |
end | |
end | |
end | |
[doc0, doc1, doc2, crazy_doc].each do |doc| | |
puts "========== About to walk: ===============" | |
puts doc | |
puts | |
print "Press ENTER to continue..." | |
$stdin.gets | |
puts | |
frag = Nokogiri::HTML.fragment(doc) | |
print "Walking" | |
result = frag.children.nested_text | |
puts | |
puts | |
puts "---------- Result: ------------------" | |
puts | |
pp result | |
puts | |
print "Press ENTER for next example..." | |
$stdin.gets | |
puts | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment