如何用html写书

原理：利用xml.etree.ElementTree对html进行解析和写入

import xml.etree.ElementTree as ET  # 解析html、xml


def circle():
    print(\'输入again回到程序开始处，输入exit退出程序\')
    tree = ET.parse(\'book.html\')  # 解析文件
    root = tree.getroot()  # 获取根节点
    link_div = root.find(\'div[@id=\"link\"]\')  # 获取link区的div节点。注意find和findall只能查找直接子元素
    body_div = root.find(\'div[@id=\"body\"]\')  # 获取body区的div节点
    h1List = link_div.findall(\'div\')
    count1 = 1
    for i in h1List:  # 列出所有h1标题
        print(str(count1) + \'、\' + i.find(\'h1\').find(\'a\').text)
        count1 += 1

    def create_h1():  # 创造h1节点
        h1_text = input(\'输入章节名：\')
        if h1_text == \'again\':
            circle()
        elif h1_text == \'exit\':
            print(\'program terminated!\')
        else:
            h1_link_div = ET.Element(\'div\')  # 创造节点
            h1_link_h1 = ET.Element(\'h1\')
            h1_link_a = ET.Element(\'a\')
            h1_link_a.text = h1_text
            h1_link_a.set(\'href\', f\'#{len(h1List) + 1}\')  # 设置a节点的属性
            h1_link_h1.append(h1_link_a)  # 悬挂节点
            h1_link_div.append(h1_link_h1)
            link_div.append(h1_link_div)  # 写入link区
            h1_body_div = ET.Element(\'div\')  # 创造节点
            h1_body_h1 = ET.Element(\'h1\')
            h1_body_h1.text = h1_text
            h1_body_div.set(\'id\', f\'{len(h1List) + 1}\')
            h1_body_div.append(h1_body_h1)
            body_div.append(h1_body_div)  # 写入body区
            newTree = ET.ElementTree(root)  # root为修改后的root
            newTree.write(\'book.xml\', encoding=\'utf-8\')  # 重新写入xml，进行更新。需要声明编码，否则写入后会乱码
            circle()

    def create_h2():  # 创造h2节点
        h2_text = input(\'输入章节名：\')
        if h2_text == \'again\':
            circle()
        elif h2_text == \'exit\':
            print(\'program terminated!\')
        else:
            h2_link_div = ET.Element(\'div\')
            h2_link_h2 = ET.Element(\'h2\')
            h2_link_a = ET.Element(\'a\')
            h2_link_a.text = h2_text
            h2_link_a.set(\'href\', f\'#{len(h1List)}_{len(h2List) + 1}\')
            h2_link_h2.append(h2_link_a)
            h2_link_div.append(h2_link_h2)
            h1List[int(a) - 1].append(h2_link_div)
            h2_body_div = ET.Element(\'div\')
            h2_body_h2 = ET.Element(\'h2\')
            h2_body_h2.text = h2_text
            h2_body_div.set(\'id\', f\'{len(h1List)}_{len(h2List) + 1}\')
            h2_body_div.append(h2_body_h2)
            body_div.findall(\'div\')[int(a) - 1].append(h2_body_div)
            newTree = ET.ElementTree(root)
            newTree.write(\'book.xml\', encoding=\'utf-8\')
            circle()

    def create_statement():  # 创造h2下的内容
        p_text = input(\'输入内容：\')
        if p_text == \'again\':
            circle()
        elif p_text == \'exit\':
            print(\'program terminated!\')
        else:
            p = ET.Element(\'p\')
            p.text = p_text
            h2.append(p)
            newTree = ET.ElementTree(root)
            newTree.write(\'book.xml\', encoding=\'utf-8\')
            create_statement()

    print(\'在此处创建输入0\\n选择章节输入序号\')
    a = input(\'输入：\')  # 输入的为字符串而非数字
    if a == \'0\':
        create_h1()
    else:
        h2List = link_div.findall(\'div\')[int(a) - 1].findall(\'div\')
        count2 = 1
        for i in h2List:  # 列出所有h2标题
            print(str(count2) + \'、\' + i.find(\'h2\').find(\'a\').text)
            count2 += 1
        print(\'在此处创建输入0\\n选择章节输入序号\')
        b = input(\'输入：\')
        if b == \'0\':
            create_h2()
        else:
            h2 = body_div.findall(\'div\')[int(a) - 1].findall(\'div\')[int(b) - 1]  # 选择的h2节点
            pList = h2.findall(\'p\')  # 列出所有h2标题下的内容
            for i in pList:
                print(i.text)
            create_statement()
    tree = ET.ElementTree(root)  # root为修改后的root
    tree.write(\'book.html\', encoding=\'utf-8\')  # 重新写入xml，进行更新。需要声明编码，否则写入后会乱码


circle()  # 循环往复

注意千万要仔细检查，本人就是因为某个变量打错字了，没有发现，耽搁了很久……总之现在是顺利地解决了

来源：https://www.cnblogs.com/daxiangcai/p/16188213.html
本站部分图文来源于网络，如有侵权请联系删除。