From: 7stud -- <lists@...>
Date: 2012-12-17T06:17:43+09:00
Subject: Re: print - and strip text between tags using Nokogiri

require "nokogiri"

class PlainTextExtractor < Nokogiri::XML::SAX::Document
  attr_reader :plaintext
  # Initialize the state of interest variable with false
  def initialize
    @interesting = false
    @pre = false
    @plaintext = ""
  end

  def start_element(name, attrs = [])
    if name == "pre"
      @pre = true
    end
  end

  # This method is called whenever a comment occurs and
  # the comments text is passed in as string.
  def comment(string)
    case string.strip       # strip leading and trailing whitespaces
      when /^body="start"/     # match starting comment
        @interesting = true
      when /^body="end"/
        @interesting = false  # match closing comment
    end
  end

  # This callback method is called with any string between
  # a tag.
  def characters(string)
    if @interesting and not @pre
      @plaintext << string
    end
  end
end


pte = PlainTextExtractor.new
parser = Nokogiri::HTML::SAX::Parser.new(pte)
parser.parse_file ARGV[0]


p pte.plaintext

--output:--
"\n\nwatching the news\n\nI feel guilty\n\nfor being alive\n\n"

-- 
Posted via http://www.ruby-forum.com/.