xpath

#!/usr/bin/env ruby
require 'nokogiri'
require 'pp'
require 'nkf'
require 'open-uri'
require "optparse"

$verbose = true



def xpath_main(xml_str,expression)
    doc = Nokogiri::HTML(xml_str)

    ret = doc.xpath(expression)

    if ret.class == Nokogiri::XML::NodeSet then

        puts ret.inspect unless ret.size > 0
        ret.each{|e| puts e  }

        if $verbose then
            $stderr.puts "--"*10
            $stderr.puts " xpath: #{expression} "
            $stderr.puts "result: #{ret.size} found" 
        end
    else
        puts "#{ret.inspect}"
        if $verbose then
            $stderr.puts "--"*10
            $stderr.puts " xpath: #{expression} "
            $stderr.puts "result: #{ret.class}"
        end
    end

end

if ARGV.size < 1 then
str =<<-"EOS"
Usage:
#{File.expand_path( __FILE__  )} [filename or url] xpath_expression

  If no filename is given, supply XML on STDIN.

Sample xpath expression :

//*         All nodes.
(//*)[1]    First of all node.
(//a[1])    A Node list of "First child" in a parent node.
//a//span   A span node ancestor of a.
//a/@href   An  attribute  named href in all a node.
//a[@href="/index.html"] A node with href  attribute is  "index.html".
//a[contains(@href,"index.html")] A node contains  "index.html" in its href.
//title | //meta  Node list of <title> or <meta> nodes.(Join result)
//img[ contains(@src,'jpg') or contains(@src,'png')]  Nodes with attributes has some keyword.
//form[ //input[name="username"] ]    A node which has a node of pointed by xpath.
//div[@id=main]//form   A node ancester of node.
//div/*   A node list of children of div.
//div//*  A node list of ancesstor of div.
//table//td[2] A td node second child of parent which in a table node.

Example of Functions.

count(//a)  Number of counts of a <a> node.
substring(//title, 1,2) First 2 letters of title string.




EOS

puts str

    exit
end




f = ( ARGV.size>1) ? open(ARGV[0]) : STDIN
expression = ( ARGV.size >  1 ) ? ARGV[1] : ARGV[0];
str = f.read

str = NKF.nkf("-w", str)


##
if str =~ %r"^https?://"  && str.split("\n").all?{|e| e=~/^http/} then 
    str.split("\n").each{|line|
        next unless line =~/^http/
        str = open(line).read
        xpath_main( str, expression )
    }
else
        xpath_main( str, expression )
end




# Copyright (C) 2014  takuya_1st
# 
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
# 
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
# 
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>. 
#
#
#
#