<?xml version="1.0" encoding="UTF-8"?>
<catalog>
    <book id="1">
        <title>Python編程入門</title>
        <author>張三</author>
        <year>2023</year>
        <price>29.99</price>
    </book>
    <book id="2">
        <title>高級Python開發(fā)</title>
        <author>李四</author>
        <year>2024</year>
        <極速分析price>39.99</price>
    </book>
</catalog>

import xml.etree.ElementTree as ET

# 從文件加載XML
tree = ET.parse('example.xml')
root = tree.getroot()
print(f"根元素標簽: {root.tag}")

# 從字符串加載XML
xml_string = '''
<catalog>
    <book id="1">
        <title>Python編程入門</title>
        <author>張三</author>
    </book>
</catalog>
'''
root = ET.fromstring(xml_string)
print(f"根元素標簽: {root.tag}")

# 遍歷直接子極速分析元素
for child in root:
    print(f"子元素: {child.tag}, 屬性: {child.attrib}")
    
    # 遍歷孫子元素
    for subchild in child:
        print(f"  孫子元素: {subchild.tag}, 內(nèi)容: {subchild.text}")

# 查找第一個匹配的元素
first_book = root.find('book')
print(f"第一本書: {first_book.attrib}")

# 查找所有匹配的元素
all_books = root.findall('book')
print(f"找到 {len(all_books)} 本書")

# 使用iter()遞歸查找所有匹配元素（包括嵌套元素）
for title in root.iter('title'):
    print(f"書名: {title.text}")

# 使用XPath基本語法查找元素（ElementTree有限支持）
for book in root.findall('.//book'):
    print(f"圖書ID: {book.get('id')}")

# 訪問元素屬性
book_id = first_book.get('id')
print(f"圖書ID: {book_id}")

# 訪問元素文本內(nèi)容
title_text = first_book.find('title').text
print(f"書名: {title_text}")

# 訪問所有屬性
print(f"所有屬性: {first_book.attrib}")

# 修改元素文本
first_book.find('price').text = '35.99'

# 修改元素屬性
first_book.set('updated', 'true')

# 添加新屬性
first_book.set('category', 'programming')

# 創(chuàng)建新元素
new_book = ET.SubElement(root, 'book')
new_book.set('id', '3')
title = ET.SubElement(new_book, 'title')
title.text = 'Python數(shù)據(jù)分析'
author = ET.SubElement(new_book, 'author')
author.text = '王五'
year = ET.SubElement(new_book, 'year')
year.text = '2024'
price = ET.SubElement(new_book, '極速分析price')
price.text = '45.99'

# 找到要刪除的元素
for book in root.findall('book'):
    if book.get('id') == '2':
        root.remove(book)
        print("已刪除ID為2的圖書")

# 保存修改后的XML
tree.write('updated_example.xml', encoding='utf-8', xml_declaration=True)

# 美化輸出（ElementTree本身不支持美化輸出，但可以手動添加縮進）
def indent(elem, level=0):
    indent_size = "  "
    i = "\n" + level * indent_size
    if len(elem):
        if not elem.text or not elem.text.strip():
            elem.text = i + indent_size
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
        for child in elem:
            indent(child, level + 1)
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
    else:
        if level and (極速分析 not elem.tail or not elem.tail.strip()):
            elem.tail = i

# 應用縮進
indent(root)
tree.write('pretty_example.xml', encoding='utf-8', xml_declaration=True)

<root xmlns:bk="http://example.com/books">
    <bk:book>
        <bk:title>Python編程</bk:title>
    </bk:book>
</root>

# 定義命名空間字典
namespaces = {'bk': 'http://example.com/books'}

# 查找?guī)臻g的元素
for book in root.findall('bk:book', namespaces):
    title = book.find('bk:title', namespaces).text
    print(f"帶命名空間的書名: {title}")

# 另一種方法是使用全限定名
for book in root.findall('{http://example.com/books}book'):
    title = book.find('{http://example.com/books}title').text
    print(f"帶命名空間的書名: {title}")

# 創(chuàng)建CDATA部分（ElementTree不支持直接創(chuàng)建CDATA，但可以手動處理）
from xml.etree.ElementTree import Element, SubElement, tostring
from xml.dom import minidom

def create_cdata_element(text):
    # 創(chuàng)建一個元素并設置文本內(nèi)容
    element = Element('description')
    # 使用CDATA格式的文本
    element.text = f'<![CDATA[{text}]]>'
    return element

# 使用示例
description = create_cdata_element('這是一段包含<特殊>字符的文本')
root.append(description)

try:
    tree = ET.parse('example.xml')
    root = tree.getroot()
except ET.ParseError as e:
    print(f"XML解析錯誤: {e}")
except FileNotFoundError:
    print("文件未找到")
except Exception as e:
    print(f"其他錯誤: {e}")

# 使用try-except確保程序健壯性
for book in root極速分析.findall('book'):
    try:
        title = book.find('title').text
        price = float(book.find('price').text
        print(f"書名: {title}, 價格: {price}")
    except AttributeError:
        print("缺少必要元素")
    except ValueError:
        print("價格格式錯誤")

# 使用iterparse進行增量解析（適用于大文件）
for event, elem in ET.iterparse('large_file.xml', events=('start', 'end')):
    if event == 'start' and elem.tag == 'book':
        # 處理開始標簽
        print(f"開始處理: {elem.get('id')}")
    elif event == 'end' and elem.tag == 'book':
        # 處理結束標簽
        title = elem.find('title').text
        print(f"完成處理: {title}")
        # 清除已處理的元素以節(jié)省內(nèi)存
        elem.clear()

# 只解析需要的部分
context = ET.iterparse('large_file.xml', events=('start', 'end'))
_, root = next(context)  # 獲取根元素

for event, elem in context:
    if event == 'end' and elem.tag == 'book':
        # 只處理book元素
        process_book(elem)
        elem.clear()  # 清除已處理的元素