Python XML自动化处理全攻略分享

import xml.etree.ElementTree as ET

# 从字符串解析
root = ET.fromstring("<root><child>text</child></root>")

# 从文件解析
tree = ET.parse("file.xml")
root = tree.getroot()

# 遍历子元素
for child in root:
    print(child.tag, child.attrib)

# 查找元素
element = root.find("child")  
element.text = "new_text"      # 修改文本
element.set("attr", "value")   # 修改属性

root = ET.Element("root")
child = ET.SubElement(root, "child", attrib={"key": "value"})
child.text = "content"

tree = ET.ElementTree(root)
tree.write("output.xml", encoding="utf-8", xml_declaration=True)

from lxml import etree

tree = etree.parse("file.xml")
elements = tree.xpath("//book[price>20]/title/text()")  # 查询价格>20的书名

schema = etree.XMLSchema(etree.parse("schema.xsd"))
parser = etree.XMLParser(schema=schema)
try:
    etree.parse("data.xml", parser)
except etree.XMLSchemaError as e:
    print("验证失败:", e)

from openpyxl import Workbook
import xml.etree.ElementTree as ET

tree = ET.parse("books.xml")
root = tree.getroot()

wb = Workbook()
ws = wb.active
ws.append(["书名", "作者", "价格"])

for book in root.findall("book"):
    title = book.find("title").text
    author = book.find("author").text
    price = book.find("price").text
    ws.append([title, author, price])

wb.save("books.xlsx")

from openpyxl import load_workbook
import xml.etree.ElementTree as ET

def xlsx_to_xml(input_file, output_file):
    wb = load_workbook(input_file)
    ws = wb.active
    root = ET.Element("bookstore")

    headers = [cell.value.strip() for cell in ws[1]]
    for row in ws.iter_rows(min_row=2, values_only=True):
        book = ET.SubElement(root, "book")
        for idx, value in enumerate(row):
            tag = ET.SubElement(book, headers[idx])
            tag.text = str(value)

    ET.ElementTree(root).write(output_file, encoding="utf-8", xml_declaration=True)

xlsx_to_xml("books.xlsx", "books_from_excel.xml")

import sqlite3
import xml.etree.ElementTree as ET

conn = sqlite3.connect("books.db")
cursor = conn.cursor()
cursor.execute("CREATE TABLE IF NOT EXISTS books (title TEXT, author TEXT, price REAL)")

tree = ET.parse("books.xml")
for book in tree.findall("book"):
    title = book.find("title").text
    author = book.find("author").text
    price = float(book.find("price").text)
    cursor.execute("INSERT INTO books VALUES (?, ?, ?)", (title, author, price))

conn.commit()
conn.close()

import xmltodict
import json

with open("books.xml") as f:
    xml_data = f.read()

data_dict = xmltodict.parse(xml_data)
with open("books.json", "w") as f:
    json.dump(data_dict, f, indent=4, ensure_ascii=False)

import xmltodict
import json

with open("books.json") as f:
    json_data = json.load(f)

xml_data = xmltodict.unparse(json_data, pretty=True)
with open("books_from_json.xml", "w") as f:
    f.write(xml_data)

# lxml 示例
namespaces = {"ns": "http://example.com/ns"}
elements = root.xpath("//ns:book", namespaces=namespaces)

element.text = ET.CDATA("<特殊字符>&")

pip install lxml openpyxl xmltodict

<bookstore>
  <book>
    <title>Python编程</title>
    <author>John</author>
    <price>50.0</price>
  </book>
</bookstore>

{
  "bookstore": {
    "book": {
      "title": "Python编程",
      "author": "John",
      "price": "50.0"
    }
  }
}