设计模式-状态模式

<book>
    <author>Dusty Phillips</author>
    <publisher>Packt Publishing</publisher>
    <title>Python 3 Object Oriented Programming</title>
    <content>
        <chapter>
            <number>1</number>
            <title>Object Oriented Design</title>
        </chapter>
        <chapter>
            <number>2</number>
            <title>Objects In Pyhton</title>
        </chapter>
    </content>
</book>

import sys


class Node:  # 单标签类
    def __init__(self, tag_name, parent=None):
        self.parent = parent
        self.tag_name = tag_name
        self.children = [] # 用来存储每个标签的对象
        self.text = ""

    def __str__(self): # 输出格式化
        if self.text:
            return self.tag_name + "：" +self.text
        else:
            return self.tag_name


class Parser: # 解析器
    def __init__(self, parse_string): 
        self.parse_string = parse_string
        self.root = None
        self.current_node = None
        self.state = FirstTag()

    def process(self, remaining_string):
        remaining = self.state.process(remaining_string, self)  # 根据不同的状态来执行不同的逻辑
        if remaining:
            self.process(remaining)

    def start(self):
        self.process(self.parse_string)


class FirstTag:  # 顶标签的执行逻辑
    def process(self, remaining_string, parser):
        i_start_tag = remaining_string.find(‘<‘)
        i_end_tag = remaining_string.find(‘>‘)
        tag_name = remaining_string[i_start_tag+1:i_end_tag]
        root = Node(tag_name)
        parser.root = parser.current_node = root # 需要把对象赋值给current_node，这点很重要
        parser.state = ChildNode()
        return remaining_string[i_end_tag+1:]


class ChildNode: # 分配器
    def process(self, remaining_string, parser):
        stripped = remaining_string.strip()
        if stripped.startswith("</"):
            parser.state = CloseTag()
        elif stripped.startswith("<"):
            parser.state = OpenTag()
        else:
            parser.state = TextNode()
        return stripped


class OpenTag: # 起始标签的逻辑
    def process(self, remaining_string, parser):
        i_start_tag = remaining_string.find("<")
        i_end_tag = remaining_string.find(">")
        tag_name = remaining_string[i_start_tag+1:i_end_tag]
        node = Node(tag_name, parser.current_node) # 需要包上一个标签的对象一起追加
        parser.current_node.children.append(node)
        parser.current_node = node
        parser.state = ChildNode()
        return remaining_string[i_end_tag+1:]


class CloseTag: # 关闭标签
    def process(self, remaining_string, parser):
        i_start_tag = remaining_string.find(‘<‘)
        i_end_tag = remaining_string.find(">")
        assert remaining_string[i_start_tag+1] == "/"
        tag_name = remaining_string[i_start_tag+2: i_end_tag]
        assert tag_name == parser.current_node.tag_name
        parser.current_node = parser.current_node.parent # 当遇到两个名称一样的标签，说明这是一对，那么需要把parent作为Node对象来操作，这样就不会重复添加了
        parser.state = ChildNode()
        return remaining_string[i_end_tag+1:].strip()


class TextNode: # 文本类容处理
    def process(self, remaining_string, parser):
        i_start_tag = remaining_string.find("<")
        text = remaining_string[:i_start_tag]
        parser.current_node.text = text  # 因为我们在起始标签逻辑处，把Node的对象保留在了current_node，现在就可以使用这个对象来绑定text
        parser.state = ChildNode()
        return remaining_string[i_start_tag:]


with open(‘index.html‘) as file:
    contents = file.read()
    p = Parser(contents)
    p.start()

    nodes = [p.root]
    while nodes:
        node = nodes.pop(0)
        print(node)
        nodes = node.children+nodes # 把所有对象都放在了children列表中，只需要依次拿出来打印就行：__str__格式化输出

结果：

book
author: Dusty Phillips
publisher: Packt Publishing
title: Python 3 Object Oriented Programming
content
chapter
number: 1
title: Object Oriented Design
chapter
number: 2
title: Objects In Pyhton