RubyのプログラムでXML形式のデータをパースするためにREXMLを呼び出す例

<library shelf="Recent Acquisitions"> 
 <section name="Ruby"> 
  <book isbn="0672328844"> 
  <title>The Ruby Way</title> 
  <author>Hal Fulton</author> 
  <description> 
   The book you are now reading. 
   Ain't recursion grand? 
  </description> 
  </book> 
 </section> 
 <section name="Space"> 
  <book isbn="0684835509"> 
   <title>The Case for Mars</title> 
   <author>Robert Zubrin</author> 
   <description>Pushing toward a second home for the human 
    race. 
   </description> 
  </book> 
  <book isbn="074325631X"> 
   <title>First Man: The Life of Neil A. Armstrong</title> 
   <author>James R. Hansen</author> 
   <description>Definitive biography of the first man on 
    the moon. 
   </description> 
  </book> 
 </section> 
</library>

require 'rexml/document' 
include REXML 
 
input = File.new("books.xml") 
doc = Document.new(input) 
 
root = doc.root 
puts root.attributes["shelf"] # Recent Acquisitions 
 
doc.elements.each("library/section") { |e| puts e.attributes["name"] } 
# Output: 
# Ruby 
# Space 
 
doc.elements.each("*/section/book") { |e| puts e.attributes["isbn"] } 
# Output: 
# 0672328844 
# 0321445619 
# 0684835509 
# 074325631X 
 
sec2 = root.elements[2] 
author = sec2.elements[1].elements["author"].text # Robert Zubrin 

require 'rexml/document' 
require 'rexml/streamlistener' 
include REXML 
 
class MyListener 
 include REXML::StreamListener 
 def tag_start(*args) 
 puts "tag_start: #{args.map {|x| x.inspect}.join(', ')}" 
 end 
 
 def text(data) 
 return if data =~ /^\w*$/ # whitespace only 
 abbrev = data[0..40] + (data.length > 40 ? "... " : "") 
 puts " text : #{abbrev.inspect}" 
 end 
end 
 
list = MyListener.new 
source = File.new "books.xml" 
Document.parse_stream(source, list) 

tag_start: "library", {"shelf"=>"Recent Acquisitions"} 
tag_start: "section", {"name"=>"Ruby"} 
tag_start: "book", {"isbn"=>"0672328844"} 
tag_start: "title", {} 
text : "The Ruby Way" 

book1 = XPath.first(doc, "//book") # Info for first book found 
p book1 
 
# Print out all titles 
XPath.each(doc, "//title") { |e| puts e.text } 
 
# Get an array of all of the "author" elements in the document. 
names = XPath.match(doc, "//author").map {|x| x.text } 
p names 

<book isbn='0672328844'> ... </> 
The Ruby Way 
The Case for Mars 
First Man: The Life of Neil A. Armstrong 
["Hal Fulton", "Robert Zubrin", "James R. Hansen"]