Parse XML stream:
require "rexml/document"
require "rexml/streamlistener"
class MyListener
include REXML::StreamListener
def tag_start(name, attrs)
case name
when "a"
# output href attribute of all <a> tags
puts attrs["href"]
end
end
end
REXML::Document.parse_stream(File.new(ARGV[0]),MyListener.new)