dmoz_reader.py 文件源码

def dmoz_reader(filename):
    doc = pulldom.parse(filename)
    for event, node in doc:
        if event == pulldom.START_ELEMENT and node.tagName == 'ExternalPage':
            doc.expandNode(node)
            url = node.attributes['about'].value
            topic_node = node.getElementsByTagName('topic')[0]
            topics = topic_node.childNodes[0].data
            yield url, topics