"""Convert a valid HTML document to XML
  USAGE: python try_dom1.py < infile.html > outfile.xml
"""
    
    
import
    
     sys
    
    from
    
     xml.dom 
    
    import
    
     core
    
    from
    
     xml.dom.html_builder 
    
    import
    
     HtmlBuilder
    
    # Construct an HtmlBuilder object and feed the data to it
b = HtmlBuilder()
b.feed(sys.stdin.read())
    
    # Get the newly-constructed document object
doc = b.document
    
    # Output it as XML
    
    
print
    
     doc.toxml()

"""Build a DOM instance from scratch, write it to XML
  USAGE: python try_dom2.py > outfile.xml
"""
    
    
import
    
     types
    
    from
    
     xml.dom 
    
    import
    
     core
    
    from
    
     xml.dom.builder 
    
    import
    
     Builder
    
    # Recursive function to build DOM instance from Python instance
    
    
defobject_convert
    
    (builder, inst):
  
    
    # Put entire object inside an elem w/ same name as the class.
  builder.startElement(inst.__class__.__name__)
  
    
    for
    
     attr 
    
    in
    
     inst.__dict__.keys():
    
    
    if
    
     attr[0] == 
    
    '_':   
    
    # Skip internal attributes
              
     
     continue
    
    
    value = getattr(inst, attr)
    
    
    if
    
     type(value) == types.InstanceType:
      
    
    # Recursively process subobjects
      object_convert(builder, value)
    
    
    else
    
    :
      
    
    # Convert anything else to string, put it in an element
      builder.startElement(attr)
      builder.text(str(value))
      builder.endElement(attr)
  builder.endElement(inst.__class__.__name__)
    
    if
    
     __name__ == 
    
    '__main__':
  
    
    # Create container classes
    
    
  classquotations
    
    : 
    
    pass
  classquotation
    
    : 
    
    pass
    # Create an instance, fill it with hierarchy of attributes
    
    
  inst = quotations()
  inst.title = 
    
    "Quotations file (not quotations.dtd conformant)"
  inst.quot1 = quot1 = quotation()
  quot1.text = 
    
    """'"is not a quine" is not a quine' is a quine"""
  quot1.source = 
    
    "Joshua Shagam, kuro5hin.org"
  inst.quot2 = quot2 = quotation()
  quot2.text = 
    
    "Python is not a democracy. Voting doesn't help. "+\
         
    
    "Crying may..."
  quot2.source = 
    
    "Guido van Rossum, comp.lang.python"
    
    

     # Create the DOM Builder
  builder = Builder()
  object_convert(builder, inst)
  
    
    print
    
     builder.document.toxml()

"""Read in a DOM instance, convert it to a Python object
"""
    
    
from
    
     xml.dom.utils 
    
    import
    
     FileReader
    
    classPyObject
    
    : 
    
    pass
defpyobj_printer
    
    (py_obj, level=0):
  
    
    """Return a "deep" string description of a Python object"""
     
     
     from
     
     
    
     string 
    
    import
    
     join, split
  
    
    import
    
     types
  descript = 
    
    ''
     
     
     for
     
     
    
     membname 
    
    in
    
     dir(py_obj):
    member = getattr(py_obj,membname)
    
    
    if
    
     type(member) == types.InstanceType:
      descript = descript + (
    
    ' '*level) + 
    
    '{'+membname+
    
    '}\n'
      descript = descript + pyobj_printer(member, level+3)
    
    
    elif
    
     type(member) == types.ListType:
      descript = descript + (
    
    ' '*level) + 
    
    '['+membname+
    
    ']\n'
             
     
     for
     
     
    
     i 
    
    in
    
     range(len(member)):
        descript = descript+(
    
    ' '*level)+str(i+1)+
    
    ': '+ \
              pyobj_printer(member[i],level+3)
    
    
    else
    
    :
      descript = descript + membname+
    
    '='
      descript = descript + join(split(str(member)[:50]))+
    
    '...\n'
     
     
     return
     
     
    
     descript
    
    defpyobj_from_dom
    
    (dom_node):
  
    
    """Converts a DOM tree to a "native" Python object"""
  py_obj = PyObject()
  py_obj.PCDATA = 
    
    ''
     
     
     for
     
     
    
     node 
    
    in
    
     dom_node.get_childNodes():
    
    
    if
    
     node.name == 
    
    '#text':
      py_obj.PCDATA = py_obj.PCDATA + node.value
    
    
    elif
    
     hasattr(py_obj, node.name):
      getattr(py_obj, node.name).append(pyobj_from_dom(node))
    
    
    else
    
    :
      setattr(py_obj, node.name, [pyobj_from_dom(node)])
  
    
    return
    
     py_obj
    
    # Main test
dom_obj = FileReader(
    
    "quotes.xml").document
py_obj = pyobj_from_dom(dom_obj)
    
    if
    
     __name__ == 
    
    "__main__":
  
    
    print
    
     pyobj_printer(py_obj)

>>> 
    
    from
    
     try_dom3 
    
    import
    
     *
>>> py_obj.quotations[0].quotation[3].source[0].PCDATA
    
    'Guido van Rossum, '

"""Manipulate the arrangement of nodes in a DOM object
"""
    
    
from
    
     try_dom3 
    
    import
    
     *
    
    #-- Var 'doc' will hold the single <quotations> "trunk"
doc = dom_obj.get_childNodes()[0]
    
    #-- Pull off all the nodes into a Python list
# (each node is a <quotation> block, or a whitespace text node)
nodes = []
    
    while
    
     1:
  
    
    try
    
    : node = doc.removeChild(doc.get_childNodes()[0])
  
    
    except
    
    : 
    
    break
    
    
  nodes.append(node)
    
    #-- Reverse the order of the quotations using a list method
# (we could also perform more complicated operations on the list:
# delete elements, add new ones, sort on complex criteria, etc.)
nodes.reverse()
    
    #-- Fill 'doc' back up with our rearranged nodes
    
    
for
    
     node 
    
    in
    
     nodes:
  
    
    # if second arg is None, insert is to end of list
  doc.insertBefore(node, None)
    
    #-- Output the manipulated DOM
    
    
print
    
     dom_obj.toxml()