python爬虫(六)-------------------XML解析模块之SAX 流模式

基本的固定格式就这么写的:

(边读边解析，占用内存小，解析快，缺点是需要自己处理事件)

import string
from xml.parsers.expat import ParserCreate

class DefaultSaxHandler(object):
    def start_element(self, name, attrs):
        self.element = name
        print('element: %s, attrs: %s' % (name, str(attrs)))

    def end_element(self, name):
        print('end element: %s' % name)

    def char_data(self, text):
        if text.strip():
            print("%s's text is %s" % (self.element, text))

handler = DefaultSaxHandler()
parser = ParserCreate()
parser.StartElementHandler = handler.start_element
parser.EndElementHandler = handler.end_element
parser.CharacterDataHandler = handler.char_data
with open('book.xml', 'r') as f:
    parser.Parse(f.read())