Go语言中读取XML元素内部文本的实用指南

type CharData []byte

innerText := string(charData)

<!-- example.xml -->
<bookstore>
    <book category="cooking">
        <title lang="en">Everyday Italian</title>
        <author>Giada De Laurentiis</author>
        <year>2005</year>
        <price>30.00</price>
    </book>
    <book category="children">
        <title lang="en">Harry Potter</title>
        <author>J.K. Rowling</author>
        <year>2005</year>
        <price>29.99</price>
    </book>
</bookstore>

package main

import (
    "encoding/xml"
    "fmt"
    "io"
    "os"
    "strings"
)

func main() {
    // 1. 打开XML文件
    file, err := os.Open("example.xml")
    if err != nil {
        fmt.Printf("Error opening file: %v\n", err)
        return
    }
    defer file.Close()

    // 2. 创建XML解码器
    decoder := xml.NewDecoder(file)

    fmt.Println("Parsing XML document:")

    // 3. 逐令牌解析XML
    for {
        token, err := decoder.Token()
        if err == io.EOF {
            break // 文件结束
        }
        if err != nil {
            fmt.Printf("Error getting token: %v\n", err)
            break
        }

        switch t := token.(type) {
        case xml.StartElement:
            // 处理开始标签
            fmt.Printf("  Start Element: <%s", t.Name.Local)
            for _, attr := range t.Attr {
                fmt.Printf(" %s=\"%s\"", attr.Name.Local, attr.Value)
            }
            fmt.Println(">")
        case xml.EndElement:
            // 处理结束标签
            fmt.Printf("  End Element: </%s>\n", t.Name.Local)
        case xml.CharData:
            // 处理字符数据（元素内部文本）
            // 将xml.CharData转换为string
            data := strings.TrimSpace(string(t))
            if len(data) > 0 {
                fmt.Printf("    Character Data: \"%s\"\n", data)
            }
        case xml.Comment:
            // 处理注释
            fmt.Printf("  Comment: <!--%s-->\n", string(t))
        case xml.ProcInst:
            // 处理处理指令
            fmt.Printf("  Processing Instruction: <?%s %s?>\n", t.Target, string(t.Inst))
        case xml.Directive:
            // 处理指令（如DOCTYPE）
            fmt.Printf("  Directive: <!%s>\n", string(t))
        }
    }
}