Python使用SAX解析xml文件

Python使用SAX解析xml文件

• 这里要解析一个早餐菜单的xml文件，包含了name, price, description, calories。

large_intestine.xml

<breakfast_menu year="2023">
    <food>
        <name>Belgian Waffles</name>
        <price>$6.3</price>
        <description>two of our famous Belgian Waffles with plenty of real maple syrup</description>
        <calories>650</calories>
    </food>
    <food>
        <name>九转大肠</name>
        <price>$9.9</price>
        <description>我去除了大部分的腥味，但在清洗的过程中故意保留了一部分</description>
        <calories>999</calories>
    </food>
</breakfast_menu>

解析代码如下:
xml_parse.py

import xml.sax

class MenuHandler(xml.sax.ContentHandler):
    def __init__(self):
        self.curData = ""
        self.name = ""
        self.price = ""
        self.description = ""
        self.calories = ""
    def startElement(self, tag, attributes):
        self.curData = tag
        if self.curData == "breakfast_menu":
            print("This is a breakfast menu")
            year = attributes["year"]
            print(f"年份：{year}")
            print()
        if self.curData == "food":
            print("---------------------------")
    def characters(self, content):
        if self.curData == "name":
            self.name = content
        elif self.curData == "price":
            self.price = content
        elif self.curData == "description":
            self.description = content
        elif self.curData == "calories":
            self.calories = content
        else:
            pass
    def endElement(self, tag):
        if self.curData == "name":
            print(f"name: {self.name}")
        elif self.curData == "price":
            print(f"price: {self.price}")
        elif self.curData == "description":
            print(f"description: {self.description}")
        elif self.curData == "calories":
            print(f"calories: {self.calories}")
        else:
            pass
        self.curData = ""
if __name__ == "__main__":
    parser = xml.sax.make_parser()
    handler = MenuHandler()
    parser.setContentHandler(handler)
    parser.parse("large_intestine.xml")

执行结果如下：