expat6.py

python web programming 部分

#!/usr/bin/python
import sys
from xml.parsers import expat

def normalize_whitespace(text):
    return " ".join(text.split())

DOCUMENT_NODE  = 1
ELEMENT_NODE   = 2
TEXT_NODE      = 3

class Node:
    def __init__(self):
        self.nextSibling = None
        self.prevSibling = None
        self.parentNode  = None
        self.firstChild  = None
        self.lastChild   = None
        
    def appendChild(self,c):
        if self.firstChild:
            c.prevSibling = self.lastChild
            self.lastChild.nextSibling = c
        else:
            self.firstChild = c
        c.parentNode = self
        self.lastChild = c

class DocumentNode(Node):
    def __init__(self):
        Node.__init__(self)
        self.nodeType = DOCUMENT_NODE
        
class ElementNode(Node):
    def __init__(self,name,attrs):
        Node.__init__(self)        
        self.nodeType = ELEMENT_NODE
        self.attributes = attrs
        self.nodeName = name

class TextNode(Node):
    def __init__(self,text):
        Node.__init__(self)                
        self.nodeType = TEXT_NODE
        self.nodeValue = text

class TreeParser:
    def __init__(self):
        self.parser   = expat.ParserCreate()
        self.parser.StartElementHandler = self.start_element
        self.parser.EndElementHandler = self.end_element
        self.parser.CharacterDataHandler = self.character_data
        self.topNode = DocumentNode()
        
    def parse(self,file):
        self.parser.ParseFile(file)
        return self.topNode

    def start_element(self,name,attrs):
        n = ElementNode(name,attrs)
        self.topNode.appendChild(n)
        self.topNode = n
            
    def character_data(self,data):
        n = TextNode(data)
        self.topNode.appendChild(n)
            
    def end_element(self,name):
        self.topNode = self.topNode.parentNode

p = TreeParser()
doc = p.parse(open(sys.argv[1]))

def walk_tree(node,indent=0):
    if not node: return
    ispace = " "*4
    while node:
        if node.nodeType == DOCUMENT_NODE:
            print "%sDOCUMENT_NODE" % (ispace*indent,)
            walk_tree(node.firstChild,indent+1)
        elif node.nodeType == ELEMENT_NODE:
            print "%sELEMENT_NODE: %s %s" % (ispace*indent, node.nodeName, node.attributes)
            walk_tree(node.firstChild,indent+1)
        elif node.nodeType == TEXT_NODE:
            print "%sTEXT_NODE   : %s" % (ispace*indent, repr(node.nodeValue))
        node = node.nextSibling
        

walk_tree(doc)