新版可用

2025-11-27 18:40:08 +08:00
parent 46de43ce72
commit 4fef65bd93
26 changed files with 39568 additions and 504 deletions
--- a/backend/api/server.go
+++ b/backend/api/server.go
@@ -0,0 +1,543 @@
+package main
+
+import (
+	"encoding/json"
+	"fmt"
+	"log"
+	"net/http"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"time"
+)
+
+// Response 统一响应结构
+type Response struct {
+	Success bool        `json:"success"`
+	Message string      `json:"message"`
+	Data    interface{} `json:"data,omitempty"`
+}
+
+// 任务状态
+type TaskStatus struct {
+	Running  bool   `json:"running"`
+	Progress int    `json:"progress"`
+	Message  string `json:"message"`
+	Error    string `json:"error,omitempty"`
+}
+
+var currentTask = &TaskStatus{Running: false}
+
+func main() {
+	// 启用CORS
+	http.HandleFunc("/", corsMiddleware(handleRoot))
+	http.HandleFunc("/api/homepage/extract", corsMiddleware(extractHomepageHandler))
+	http.HandleFunc("/api/article/download", corsMiddleware(downloadArticleHandler))
+	http.HandleFunc("/api/article/list", corsMiddleware(getArticleListHandler))
+	http.HandleFunc("/api/article/batch", corsMiddleware(batchDownloadHandler))
+	http.HandleFunc("/api/data/list", corsMiddleware(getDataListHandler))
+	http.HandleFunc("/api/task/status", corsMiddleware(getTaskStatusHandler))
+	http.HandleFunc("/api/download/", corsMiddleware(downloadFileHandler))
+
+	port := ":8080"
+	fmt.Println("===============================================")
+	fmt.Println("   🚀 微信公众号文章爬虫 API 服务器")
+	fmt.Println("===============================================")
+	fmt.Printf("🌐 服务地址: http://localhost%s\n", port)
+	fmt.Printf("⏰ 启动时间: %s\n", time.Now().Format("2006-01-02 15:04:05"))
+	fmt.Println("===============================================\n")
+
+	if err := http.ListenAndServe(port, nil); err != nil {
+		log.Fatal("服务器启动失败:", err)
+	}
+}
+
+// CORS中间件
+func corsMiddleware(next http.HandlerFunc) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Access-Control-Allow-Origin", "*")
+		w.Header().Set("Access-Control-Allow-Methods", "GET, POST, OPTIONS")
+		w.Header().Set("Access-Control-Allow-Headers", "Content-Type")
+
+		if r.Method == "OPTIONS" {
+			w.WriteHeader(http.StatusOK)
+			return
+		}
+
+		next(w, r)
+	}
+}
+
+// 首页处理
+func handleRoot(w http.ResponseWriter, r *http.Request) {
+	w.Header().Set("Content-Type", "text/html; charset=utf-8")
+	html := `
+<!DOCTYPE html>
+<html>
+<head>
+    <meta charset="UTF-8">
+    <title>微信公众号文章爬虫 API</title>
+    <style>
+        body { font-family: Arial, sans-serif; max-width: 800px; margin: 50px auto; padding: 20px; }
+        h1 { color: #333; }
+        .endpoint { background: #f5f5f5; padding: 10px; margin: 10px 0; border-radius: 5px; }
+        .method { color: #4CAF50; font-weight: bold; }
+    </style>
+</head>
+<body>
+    <h1>🚀 微信公众号文章爬虫 API 服务器</h1>
+    <p>当前时间: ` + time.Now().Format("2006-01-02 15:04:05") + `</p>
+    <h2>可用接口:</h2>
+    <div class="endpoint">
+        <span class="method">POST</span> /api/homepage/extract - 提取公众号主页
+    </div>
+    <div class="endpoint">
+        <span class="method">POST</span> /api/article/download - 下载单篇文章
+    </div>
+    <div class="endpoint">
+        <span class="method">POST</span> /api/article/list - 获取文章列表
+    </div>
+    <div class="endpoint">
+        <span class="method">POST</span> /api/article/batch - 批量下载文章
+    </div>
+    <div class="endpoint">
+        <span class="method">GET</span> /api/data/list - 获取数据列表
+    </div>
+    <div class="endpoint">
+        <span class="method">GET</span> /api/task/status - 获取任务状态
+    </div>
+</body>
+</html>
+`
+	w.Write([]byte(html))
+}
+
+// 提取公众号主页
+func extractHomepageHandler(w http.ResponseWriter, r *http.Request) {
+	var req struct {
+		URL string `json:"url"`
+	}
+
+	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
+		writeJSON(w, Response{Success: false, Message: "请求参数错误"})
+		return
+	}
+
+	// 执行命令（使用绝对路径）
+	exePath := filepath.Join("..", "wechat-crawler.exe")
+	absPath, _ := filepath.Abs(exePath)
+	log.Printf("尝试执行: %s", absPath)
+
+	cmd := exec.Command(absPath, req.URL)
+	workDir, _ := filepath.Abs("..")
+	cmd.Dir = workDir
+	output, err := cmd.CombinedOutput()
+
+	if err != nil {
+		log.Printf("执行失败: %v, 输出: %s", err, string(output))
+		writeJSON(w, Response{Success: false, Message: "执行失败: " + string(output)})
+		return
+	}
+
+	// 从输出中提取公众号主页链接
+	outputStr := string(output)
+	lines := strings.Split(outputStr, "\n")
+	var homepageURL string
+
+	for _, line := range lines {
+		if strings.Contains(line, "公众号主页链接") || strings.Contains(line, "https://mp.weixin.qq.com/mp/profile_ext") {
+			// 提取URL
+			if idx := strings.Index(line, "https://"); idx != -1 {
+				homepageURL = strings.TrimSpace(line[idx:])
+				break
+			}
+		}
+	}
+
+	if homepageURL == "" {
+		writeJSON(w, Response{Success: false, Message: "未能提取到主页链接"})
+		return
+	}
+
+	writeJSON(w, Response{
+		Success: true,
+		Message: "提取成功",
+		Data: map[string]string{
+			"homepage": homepageURL,
+			"output":   outputStr,
+		},
+	})
+}
+
+// 下载单篇文章（这里需要实现具体逻辑）
+func downloadArticleHandler(w http.ResponseWriter, r *http.Request) {
+	var req struct {
+		URL         string `json:"url"`
+		SaveImage   bool   `json:"save_image"`
+		SaveContent bool   `json:"save_content"`
+	}
+
+	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
+		writeJSON(w, Response{Success: false, Message: "请求参数错误"})
+		return
+	}
+
+	currentTask.Running = true
+	currentTask.Progress = 0
+	currentTask.Message = "正在下载文章..."
+
+	// 注意：这里需要实际调用爬虫的下载功能
+	// 由于当前后端程序没有单独的下载单篇文章的命令行接口
+	// 需要后续实现或使用其他方式
+
+	writeJSON(w, Response{
+		Success: true,
+		Message: "下载任务已启动",
+		Data: map[string]interface{}{
+			"url": req.URL,
+		},
+	})
+}
+
+// 获取文章列表
+func getArticleListHandler(w http.ResponseWriter, r *http.Request) {
+	var req struct {
+		AccessToken string `json:"access_token"`
+		Pages       int    `json:"pages"`
+	}
+
+	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
+		writeJSON(w, Response{Success: false, Message: "请求参数错误"})
+		return
+	}
+
+	currentTask.Running = true
+	currentTask.Progress = 0
+	currentTask.Message = "正在获取文章列表..."
+
+	// 同步执行爬虫程序（功能3）
+	exePath := filepath.Join("..", "wechat-crawler.exe")
+	absPath, _ := filepath.Abs(exePath)
+	workDir, _ := filepath.Abs("..")
+
+	log.Printf("启动功能3: %s, 工作目录: %s", absPath, workDir)
+	cmd := exec.Command(absPath)
+	cmd.Dir = workDir
+
+	// 创建输入管道
+	stdin, err := cmd.StdinPipe()
+	if err != nil {
+		log.Printf("创建输入管道失败: %v", err)
+		currentTask.Running = false
+		writeJSON(w, Response{Success: false, Message: "创建输入管道失败: " + err.Error()})
+		return
+	}
+
+	// 启动命令
+	if err := cmd.Start(); err != nil {
+		log.Printf("启动命令失败: %v", err)
+		currentTask.Running = false
+		writeJSON(w, Response{Success: false, Message: "启动命令失败: " + err.Error()})
+		return
+	}
+
+	// 发送选项"3"（功能3：通过access_token获取文章列表）
+	fmt.Fprintln(stdin, "3")
+	fmt.Fprintln(stdin, req.AccessToken)
+	if req.Pages > 0 {
+		fmt.Fprintf(stdin, "%d\n", req.Pages)
+	} else {
+		fmt.Fprintln(stdin, "0")
+	}
+	stdin.Close()
+
+	// 等待命令完成
+	if err := cmd.Wait(); err != nil {
+		log.Printf("命令执行失败: %v", err)
+		currentTask.Running = false
+		writeJSON(w, Response{Success: false, Message: "命令执行失败: " + err.Error()})
+		return
+	}
+
+	currentTask.Running = false
+	currentTask.Progress = 100
+	currentTask.Message = "文章列表获取完成"
+
+	// 查找生成的文件并返回下载链接
+	dataDir := "../data"
+	entries, err := os.ReadDir(dataDir)
+	if err != nil {
+		writeJSON(w, Response{Success: false, Message: "读取数据目录失败: " + err.Error()})
+		return
+	}
+
+	// 查找最新创建的公众号目录
+	var latestDir string
+	var latestTime time.Time
+	for _, entry := range entries {
+		if entry.IsDir() && entry.Name() != "." && entry.Name() != ".." {
+			info, _ := entry.Info()
+			if info.ModTime().After(latestTime) {
+				latestTime = info.ModTime()
+				latestDir = entry.Name()
+			}
+		}
+	}
+
+	if latestDir == "" {
+		writeJSON(w, Response{Success: false, Message: "未找到生成的数据目录"})
+		return
+	}
+
+	log.Printf("找到最新目录: %s", latestDir)
+
+	// 查找文章列表文件（优先查找直连链接文件）
+	accountPath := filepath.Join(dataDir, latestDir)
+	files, err := os.ReadDir(accountPath)
+	if err != nil {
+		writeJSON(w, Response{Success: false, Message: "读取公众号目录失败: " + err.Error()})
+		return
+	}
+
+	var excelFile string
+	// 优先查找直连链接文件（.xlsx或.txt）
+	for _, file := range files {
+		if !file.IsDir() && strings.Contains(file.Name(), "直连链接") {
+			if strings.HasSuffix(file.Name(), ".xlsx") || strings.HasSuffix(file.Name(), ".txt") {
+				excelFile = file.Name()
+				log.Printf("找到直连链接文件: %s", excelFile)
+				break
+			}
+		}
+	}
+
+	// 如果没有直连链接文件，查找原始链接文件
+	if excelFile == "" {
+		for _, file := range files {
+			if !file.IsDir() && strings.Contains(file.Name(), "原始链接") {
+				if strings.HasSuffix(file.Name(), ".xlsx") || strings.HasSuffix(file.Name(), ".txt") {
+					excelFile = file.Name()
+					log.Printf("找到原始链接文件: %s", excelFile)
+					break
+				}
+			}
+		}
+	}
+
+	// 如果还是没有，查找任何文章列表文件
+	if excelFile == "" {
+		for _, file := range files {
+			if !file.IsDir() && strings.Contains(file.Name(), "文章列表") {
+				if strings.HasSuffix(file.Name(), ".xlsx") || strings.HasSuffix(file.Name(), ".txt") {
+					excelFile = file.Name()
+					log.Printf("找到文章列表文件: %s", excelFile)
+					break
+				}
+			}
+		}
+	}
+
+	if excelFile == "" {
+		// 列出所有文件用于调试
+		var fileList []string
+		for _, file := range files {
+			fileList = append(fileList, file.Name())
+		}
+		log.Printf("目录 %s 中的文件: %v", latestDir, fileList)
+		writeJSON(w, Response{Success: false, Message: "未找到Excel文件，目录中的文件: " + strings.Join(fileList, ", ")})
+		return
+	}
+
+	writeJSON(w, Response{
+		Success: true,
+		Message: "文章列表获取成功",
+		Data: map[string]interface{}{
+			"account":  latestDir,
+			"filename": excelFile,
+			"download": fmt.Sprintf("/download/%s/%s", latestDir, excelFile),
+		},
+	})
+}
+
+// 批量下载文章
+func batchDownloadHandler(w http.ResponseWriter, r *http.Request) {
+	var req struct {
+		OfficialAccount string `json:"official_account"`
+		SaveImage       bool   `json:"save_image"`
+		SaveContent     bool   `json:"save_content"`
+	}
+
+	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
+		writeJSON(w, Response{Success: false, Message: "请求参数错误"})
+		return
+	}
+
+	currentTask.Running = true
+	currentTask.Progress = 0
+	currentTask.Message = "正在批量下载文章..."
+
+	// 同步执行爬虫程序（功能5）
+	exePath := filepath.Join("..", "wechat-crawler.exe")
+	absPath, _ := filepath.Abs(exePath)
+	workDir, _ := filepath.Abs("..")
+
+	log.Printf("启动功能5: %s, 工作目录: %s", absPath, workDir)
+	cmd := exec.Command(absPath)
+	cmd.Dir = workDir
+
+	// 创建输入管道
+	stdin, err := cmd.StdinPipe()
+	if err != nil {
+		log.Printf("创建输入管道失败: %v", err)
+		currentTask.Running = false
+		writeJSON(w, Response{Success: false, Message: "创建输入管道失败: " + err.Error()})
+		return
+	}
+
+	// 启动命令
+	if err := cmd.Start(); err != nil {
+		log.Printf("启动命令失败: %v", err)
+		currentTask.Running = false
+		writeJSON(w, Response{Success: false, Message: "启动命令失败: " + err.Error()})
+		return
+	}
+
+	// 发送选项"5"（功能5：批量下载）
+	fmt.Fprintln(stdin, "5")
+	fmt.Fprintln(stdin, req.OfficialAccount)
+
+	// 是否保存图片
+	if req.SaveImage {
+		fmt.Fprintln(stdin, "y")
+	} else {
+		fmt.Fprintln(stdin, "n")
+	}
+	stdin.Close()
+
+	// 等待命令完成
+	if err := cmd.Wait(); err != nil {
+		log.Printf("命令执行失败: %v", err)
+		currentTask.Running = false
+		writeJSON(w, Response{Success: false, Message: "命令执行失败: " + err.Error()})
+		return
+	}
+
+	currentTask.Running = false
+	currentTask.Progress = 100
+	currentTask.Message = "批量下载完成"
+
+	// 统计下载的文章数量
+	accountPath := filepath.Join("../data", req.OfficialAccount, "文章详细")
+	var articleCount int
+	if entries, err := os.ReadDir(accountPath); err == nil {
+		articleCount = len(entries)
+	}
+
+	writeJSON(w, Response{
+		Success: true,
+		Message: fmt.Sprintf("批量下载完成，共下载 %d 篇文章", articleCount),
+		Data: map[string]interface{}{
+			"account":      req.OfficialAccount,
+			"articleCount": articleCount,
+			"path":         accountPath,
+		},
+	})
+}
+
+// 获取数据列表
+func getDataListHandler(w http.ResponseWriter, r *http.Request) {
+	dataDir := "../data"
+	var accounts []map[string]interface{}
+
+	entries, err := os.ReadDir(dataDir)
+	if err != nil {
+		// 如果目录不存在，返回空列表而不是错误
+		writeJSON(w, Response{
+			Success: true,
+			Data:    accounts,
+		})
+		return
+	}
+
+	for _, entry := range entries {
+		if entry.IsDir() {
+			accountPath := filepath.Join(dataDir, entry.Name())
+
+			// 统计文章数量
+			detailPath := filepath.Join(accountPath, "文章详细")
+			var articleCount int
+			if detailEntries, err := os.ReadDir(detailPath); err == nil {
+				articleCount = len(detailEntries)
+			}
+
+			// 获取最后更新时间
+			info, _ := entry.Info()
+			lastUpdate := info.ModTime().Format("2006-01-02")
+
+			accounts = append(accounts, map[string]interface{}{
+				"name":         entry.Name(),
+				"articleCount": articleCount,
+				"path":         accountPath,
+				"lastUpdate":   lastUpdate,
+			})
+		}
+	}
+
+	writeJSON(w, Response{
+		Success: true,
+		Data:    accounts,
+	})
+}
+
+// 获取任务状态
+func getTaskStatusHandler(w http.ResponseWriter, r *http.Request) {
+	writeJSON(w, Response{
+		Success: true,
+		Data:    currentTask,
+	})
+}
+
+// 下载文件处理
+func downloadFileHandler(w http.ResponseWriter, r *http.Request) {
+	// 从 URL 中提取路径 /api/download/公众号名称/文件名
+	path := strings.TrimPrefix(r.URL.Path, "/api/download/")
+	parts := strings.SplitN(path, "/", 2)
+
+	if len(parts) != 2 {
+		http.Error(w, "路径错误", http.StatusBadRequest)
+		return
+	}
+
+	accountName := parts[0]
+	filename := parts[1]
+
+	// 构建完整文件路径
+	filePath := filepath.Join("..", "data", accountName, filename)
+	absPath, _ := filepath.Abs(filePath)
+
+	// 检查文件是否存在
+	if _, err := os.Stat(absPath); os.IsNotExist(err) {
+		http.Error(w, "文件不存在", http.StatusNotFound)
+		return
+	}
+
+	log.Printf("下载文件: %s", absPath)
+
+	// 设置响应头
+	contentType := "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+	if strings.HasSuffix(filename, ".txt") {
+		contentType = "text/plain; charset=utf-8"
+	}
+	w.Header().Set("Content-Type", contentType)
+	w.Header().Set("Content-Disposition", fmt.Sprintf("attachment; filename*=UTF-8''%s", filename))
+
+	// 发送文件
+	http.ServeFile(w, r, absPath)
+}
+
+// 写入JSON响应
+func writeJSON(w http.ResponseWriter, data interface{}) {
+	w.Header().Set("Content-Type", "application/json; charset=utf-8")
+	json.NewEncoder(w).Encode(data)
+}