网页编码识别

复制import requests

# 通过 HTTP 响应头探测网页编码
url = "https://www.example.com"
response = requests.get(url, timeout=10)

# 从 Content-Type 头提取 charset
content_type = response.headers.get("Content-Type", "")
if "charset=" in content_type:
    charset = content_type.split("charset=")[-1].split(";")[0].strip()
    print(f"编码: {charset}")
else:
    # 无明确声明时，用 chardet 检测字节流
    import chardet
    detected = chardet.detect(response.content)
    print(f"检测编码: {detected['encoding']} (置信度: {detected['confidence']:.2f})")

复制package main

import (
	"fmt"
	"net/http"
	"strings"
)

func main() {
	url := "https://www.example.com"
	resp, err := http.Get(url)
	if err != nil {
		fmt.Println("请求失败:", err)
		return
	}
	defer resp.Body.Close()

	// 从 Content-Type 提取 charset
	ct := resp.Header.Get("Content-Type")
	if idx := strings.Index(ct, "charset="); idx != -1 {
		charset := ct[idx+8:]
		if semi := strings.Index(charset, ";"); semi != -1 {
			charset = charset[:semi]
		}
		fmt.Println("编码:", strings.TrimSpace(charset))
	} else {
		fmt.Println("未声明编码，需进一步检测字节流")
	}
}

复制// 浏览器端：通过 fetch 获取响应头
async function detectEncoding(url) {
  try {
    const response = await fetch(url);
    const contentType = response.headers.get('content-type') || '';
    const match = contentType.match(/charset=([^;]+)/);
    
    if (match) {
      console.log('编码:', match[1].trim());
    } else {
      // 读取部分字节用 TextDecoder 尝试解码
      const buffer = await response.clone().arrayBuffer();
      const bytes = new Uint8Array(buffer.slice(0, 1000));
      // 常见编码探测：先试 UTF-8
      const decoder = new TextDecoder('utf-8', { fatal: false });
      const text = decoder.decode(bytes);
      console.log('尝试 UTF-8 解码成功，长度:', text.length);
    }
  } catch (err) {
    console.error('请求失败:', err);
  }
}

detectEncoding('https://www.example.com');