SiteProxy/proxy/handler.go

// proxy/handler.go
package proxy

import (
    "bytes"
    "fmt"
    "io"
    "log"
    "net/http"
    "net/url"
    "strings"
    "time"
    
    "siteproxy/cache"
    "siteproxy/security"
)

type ProxyHandler struct {
    validator   *security.RequestValidator
    rateLimiter *security.RateLimiter
    cache       *cache.MemoryCache
    client      *http.Client
    userAgent   string
    maxSize     int64
}

func NewHandler(validator *security.RequestValidator, rateLimiter *security.RateLimiter, memCache *cache.MemoryCache, userAgent string, maxSize int64) *ProxyHandler {
    return &ProxyHandler{
        validator:   validator,
        rateLimiter: rateLimiter,
        cache:       memCache,
        userAgent:   userAgent,
        maxSize:     maxSize,
        client: &http.Client{
            Timeout: 30 * time.Second,
            CheckRedirect: func(req *http.Request, via []*http.Request) error {
                if len(via) >= 10 {
                    return fmt.Errorf("too many redirects")
                }
                return nil
            },
        },
    }
}

func (h *ProxyHandler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
    // 获取 session ID
    cookie, err := r.Cookie("session_id")
    if err != nil {
        http.Error(w, "Unauthorized", http.StatusUnauthorized)
        return
    }
    
    sessionID := cookie.Value
    
    // 速率限制检查
    if !h.rateLimiter.Allow(sessionID) {
        http.Error(w, "Rate limit exceeded", http.StatusTooManyRequests)
        return
    }
    
    // 获取目标 URL
    targetURL := r.URL.Query().Get("url")
    if targetURL == "" {
        http.Error(w, "Missing url parameter", http.StatusBadRequest)
        return
    }
    
    // 验证 URL
    if err := h.validator.ValidateURL(targetURL); err != nil {
        log.Printf("URL validation failed: %v", err)
        http.Error(w, "Invalid or blocked URL", http.StatusForbidden)
        return
    }
    
    // 检查缓存
    cacheKey := h.cache.GenerateKey(targetURL)
    if cached, ok := h.cache.Get(cacheKey); ok {
        log.Printf("Cache hit: %s", targetURL)
        h.serveCached(w, cached)
        return
    }
    
    // 发起代理请求
    log.Printf("Proxying: %s", targetURL)
    if err := h.proxyRequest(w, targetURL, cacheKey); err != nil {
        log.Printf("Proxy error: %v", err)
        http.Error(w, "Proxy request failed", http.StatusBadGateway)
        return
    }
}

func (h *ProxyHandler) proxyRequest(w http.ResponseWriter, targetURL, cacheKey string) error {
    // 创建请求
    req, err := http.NewRequest("GET", targetURL, nil)
    if err != nil {
        return err
    }
    
    // 设置请求头
    req.Header.Set("User-Agent", h.userAgent)
    req.Header.Set("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8")
    req.Header.Set("Accept-Language", "en-US,en;q=0.9")
    req.Header.Set("Accept-Encoding", "gzip, deflate, br")
    req.Header.Set("DNT", "1")
    req.Header.Set("Connection", "keep-alive")
    req.Header.Set("Upgrade-Insecure-Requests", "1")
    
    // 发送请求
    resp, err := h.client.Do(req)
    if err != nil {
        return err
    }
    defer resp.Body.Close()
    
    // 限制响应大小
    limitedReader := io.LimitReader(resp.Body, h.maxSize)
    body, err := io.ReadAll(limitedReader)
    if err != nil {
        return err
    }
    
    // 检查内容类型
    contentType := resp.Header.Get("Content-Type")
    
    // 如果是 HTML，进行 URL 重写
    if strings.Contains(contentType, "text/html") {
        body = h.rewriteHTML(body, targetURL)
    } else if strings.Contains(contentType, "text/css") {
        body = h.rewriteCSS(body, targetURL)
    }
    
    // 缓存静态资源
    if h.shouldCache(contentType) {
        headers := make(map[string]string)
        headers["Content-Type"] = contentType
        h.cache.Set(cacheKey, body, headers)
    }
    
    // 设置响应头
    w.Header().Set("Content-Type", contentType)
    w.Header().Set("X-Proxied-By", "SiteProxy")
    
    // 移除可能泄露的头
    for _, header := range []string{"Server", "X-Powered-By", "Set-Cookie"} {
        w.Header().Del(header)
    }
    
    w.WriteHeader(resp.StatusCode)
    w.Write(body)
    
    return nil
}

func (h *ProxyHandler) rewriteHTML(body []byte, baseURL string) []byte {
    content := string(body)
    
    // 解析基础 URL
    base, err := url.Parse(baseURL)
    if err != nil {
        return body
    }
    
    // 重写绝对 URL
    content = strings.ReplaceAll(content, `href="`+base.Scheme+`://`+base.Host, `href="/proxy?url=`+url.QueryEscape(base.Scheme+`://`+base.Host))
    content = strings.ReplaceAll(content, `src="`+base.Scheme+`://`+base.Host, `src="/proxy?url=`+url.QueryEscape(base.Scheme+`://`+base.Host))
    
    // 重写相对 URL（简化版本）
    // 注意：完整实现需要 HTML 解析器
    
    return []byte(content)
}

func (h *ProxyHandler) rewriteCSS(body []byte, baseURL string) []byte {
    content := string(body)
    
    base, err := url.Parse(baseURL)
    if err != nil {
        return body
    }
    
    // 重写 CSS 中的 url()
    content = strings.ReplaceAll(content, `url(`+base.Scheme+`://`+base.Host, `url(/proxy?url=`+url.QueryEscape(base.Scheme+`://`+base.Host))
    
    return []byte(content)
}

func (h *ProxyHandler) shouldCache(contentType string) bool {
    cacheableTypes := []string{
        "image/",
        "text/css",
        "application/javascript",
        "application/json",
        "font/",
    }
    
    for _, t := range cacheableTypes {
        if strings.Contains(contentType, t) {
            return true
        }
    }
    
    return false
}

func (h *ProxyHandler) serveCached(w http.ResponseWriter, entry *cache.CacheEntry) {
    for key, value := range entry.Headers {
        w.Header().Set(key, value)
    }
    w.Header().Set("X-Cache-Status", "HIT")
    w.Header().Set("X-Proxied-By", "SiteProxy")
    w.WriteHeader(http.StatusOK)
    w.Write(entry.Data)
}