如何使用Python处理XML？ElementTree解析

import xml.etree.ElementTree as ET

# 假设我们有这样一个XML数据，可以是字符串，也可以是文件内容
xml_data = """
<catalog>
    <book id="bk101">
        <author>Gambardella, Matthew</author>
        <title>XML Developer's Guide</title>
        <genre>Computer</genre>
        <price>44.95</price>
        <publish_date>2000-10-01</publish_date>
        <description>An in-depth look at creating applications with XML.</description>
    </book>
    <book id="bk102">
        <author>Ralls, Kim</author>
        <title>Midnight Rain</title>
        <genre>Fantasy</genre>
        <price>5.95</price>
        <publish_date>2000-12-16</publish_date>
        <description>A young woman's journey through the realm of magic.</description>
    </book>
</catalog>
"""

# 1. 解析XML数据
# 从字符串解析
root = ET.fromstring(xml_data)
print(f"根元素标签: {root.tag}\n")

# 如果是从文件解析，可以使用 ET.parse()
# tree = ET.parse('your_file.xml')
# root = tree.getroot()

# 2. 导航和查找元素
# 遍历所有 <book> 元素
print("遍历所有书籍信息:")
for book in root.findall('book'):
    book_id = book.get('id') # 获取属性
    author = book.find('author').text # 获取子元素的文本内容
    title = book.find('title').text
    price = book.find('price').text
    print(f"  ID: {book_id}, 作者: {author}, 标题: {title}, 价格: {price}")

# 查找特定ID的书籍
book_to_find = root.find("./book[@id='bk101']")
if book_to_find is not None:
    print(f"\n找到ID为bk101的书籍，标题是: {book_to_find.find('title').text}")

# 3. 修改XML数据
# 比如，修改第一本书的价格
first_book = root.find('book')
if first_book:
    price_element = first_book.find('price')
    if price_element:
        price_element.text = '39.99' # 修改文本内容
        print(f"\n修改了第一本书的价格为: {price_element.text}")

# 添加一个新属性到某个元素
if first_book:
    first_book.set('edition', 'first')
    print(f"给ID为{first_book.get('id')}的书籍添加了 edition 属性: {first_book.get('edition')}")

# 添加一个新的 <book> 元素
new_book = ET.SubElement(root, 'book', id='bk103')
ET.SubElement(new_book, 'author').text = 'New Author'
ET.SubElement(new_book, 'title').text = 'The New Adventure'
ET.SubElement(new_book, 'genre').text = 'Adventure'
ET.SubElement(new_book, 'price').text = '19.99'
ET.SubElement(new_book, 'publish_date').text = '2023-01-01'
ET.SubElement(new_book, 'description').text = 'A thrilling new story.'
print("\n添加了一本新书，ID为: bk103")

# 移除一个元素
# 比如，移除 ID 为 bk102 的书
book_to_remove = root.find("./book[@id='bk102']")
if book_to_remove is not None:
    root.remove(book_to_remove)
    print("\n移除了ID为bk102的书籍。")

# 4. 将修改后的XML写回文件或字符串
# 将整个树结构转换回字符串
modified_xml_string = ET.tostring(root, encoding='unicode')
print("\n修改后的XML内容 (未格式化):\n", modified_xml_string)

# 如果需要漂亮的格式化输出，ElementTree本身不直接支持，但可以结合 xml.dom.minidom
try:
    from xml.dom import minidom
    def prettify(elem):
        """返回一个美化后的XML字符串"""
        rough_string = ET.tostring(elem, 'utf-8')
        reparsed = minidom.parseString(rough_string)
        return reparsed.toprettyxml(indent="  ")

    print("\n修改后的XML内容 (美化后):\n", prettify(root))
except ImportError:
    print("\n提示: 要美化XML输出，可以安装 'xml.dom.minidom' (Python标准库自带) 或 'lxml' 库。")


# 将修改后的XML写入文件
# tree = ET.ElementTree(root)
# tree.write('modified_catalog.xml', encoding='utf-8', xml_declaration=True)
# print("\n修改后的XML已写入 'modified_catalog.xml' 文件。")