Contents

require 'web/htmltools/xmltree'
require 'mechanize/rexml'

class WWW::Mechanize::REXMLPage < WWW::Mechanize::Page
  def initialize(uri=nil, response=nil, body=nil, code=nil, mech=nil)
    super(uri, response, body, code)
    @watch_for_set = {}
    @mech          = mech
    
    yield self if block_given?
    
    raise Mechanize::ContentTypeError.new(response['content-type']) unless
        content_type() =~ /^text\/html/ 
    
    # construct parser and feed with HTML
    parser = HTMLTree::XMLParser.new
    begin
      parser.feed(@body)
    rescue => ex
      if ex.message =~ /attempted adding second root element to document/ and
        # Put the whole document inside a single root element, which I
        # simply name <root>, just to make the parser happy. It's no
        #longer valid HTML, but without a single root element, it's not
        # valid HTML as well.

        # TODO: leave a possible doctype definition outside this element.
        parser = HTMLTree::XMLParser.new
        parser.feed("<root>" + @body + "</root>")
      else
        raise
      end
    end

    @root = parser.document
    parse_html if body && response
  end
end

Version data entries

3 entries across 3 versions & 1 rubygems

Version	Path
mechanize-0.6.1	lib/mechanize/parsers/rexml_page.rb
mechanize-0.6.2	lib/mechanize/parsers/rexml_page.rb
mechanize-0.6.3	lib/mechanize/parsers/rexml_page.rb