feat: add Kemono parser with download info extraction and API handling

* feat: WIP. add parser functionality and text message handling

* fix: use json to marshal js result

* feat: add metadata handling and version validation for jsParser

* refactor: rename parser package to parsers and restructure parser handling

* refactor: core code struct and impl parse task handle

* feat: impl parsed download

* fix: seek cache file when processing tph picture

* feat: implement parsed task handling and progress tracking

* feat: enhance task processing with concurrency control and progress tracking

* feat: add resource ID generation and improve resource processing handling

* feat: improve message formatting in parsed text and progress completion

* feat: add example js plugin

* feat: implement Twitter parser

* fix: twitter parse video json decode error

* feat: impl stream mode for parse task

.github/workflows/build-release.yml

@@ -63,9 +63,9 @@ jobs:
             README.md
           ldflags: >-
             -s -w
-            -X "github.com/krau/SaveAny-Bot/pkg/consts.Version=${{ env.VERSION }}"
-            -X "github.com/krau/SaveAny-Bot/pkg/consts.BuildTime=${{ format(github.event.repository.updated_at, 'yyyy-MM-dd HH:mm:ss') }}"
-            -X "github.com/krau/SaveAny-Bot/pkg/consts.GitCommit=${{ github.sha }}"
+            -X "github.com/krau/SaveAny-Bot/config.Version=${{ env.VERSION }}"
+            -X "github.com/krau/SaveAny-Bot/config.BuildTime=${{ format(github.event.repository.updated_at, 'yyyy-MM-dd HH:mm:ss') }}"
+            -X "github.com/krau/SaveAny-Bot/config.GitCommit=${{ github.sha }}"
           binary_name: saveany-bot
         env:
           VERSION: ${{ env.VERSION }}

.gitignore

@@ -7,4 +7,4 @@ session.*
 cache.db
 .vscode/
 temp/
-.hugo_build.lock
+.hugo_build.lock

Dockerfile

@@ -17,9 +17,9 @@ RUN --mount=type=cache,target=/root/.cache/go-build \
     go build -trimpath \
     -ldflags=" \
     -s -w \
-    -X 'github.com/krau/SaveAny-Bot/common.Version=${VERSION}' \
-    -X 'github.com/krau/SaveAny-Bot/common.GitCommit=${GitCommit}' \
-    -X 'github.com/krau/SaveAny-Bot/common.BuildTime=${BuildTime}' \
+    -X 'github.com/krau/SaveAny-Bot/config.Version=${VERSION}' \
+    -X 'github.com/krau/SaveAny-Bot/config.GitCommit=${GitCommit}' \
+    -X 'github.com/krau/SaveAny-Bot/config.BuildTime=${BuildTime}' \
     " \
     -o saveany-bot .
 

README.md

@@ -4,28 +4,70 @@
 
 **简体中文** | [English](https://sabot.unv.app/en/)
 
-把 Telegram 上的文件转存到多种存储端.
+> **把 Telegram 上的文件转存到多种存储端.**
+
+[![Release Date](https://img.shields.io/github/release-date/krau/saveany-bot?label=release)](https://github.com/krau/saveany-bot/releases)
+[![tag](https://img.shields.io/github/v/tag/krau/saveany-bot.svg)](https://github.com/krau/saveany-bot/releases)
+[![Build Status](https://img.shields.io/github/actions/workflow/status/krau/saveany-bot/build-release.yml)](https://github.com/krau/saveany-bot/actions/workflows/build-release.yml)
+[![Stars](https://img.shields.io/github/stars/krau/saveany-bot?style=flat)](https://github.com/krau/saveany-bot/stargazers)
+[![Downloads](https://img.shields.io/github/downloads/krau/saveany-bot/total)](https://github.com/krau/saveany-bot/releases)
+[![Issues](https://img.shields.io/github/issues/krau/saveany-bot)](https://github.com/krau/saveany-bot/issues)
+[![Pull Requests](https://img.shields.io/github/issues-pr/krau/saveany-bot?label=pr)](https://github.com/krau/saveany-bot/pulls)
+[![License](https://img.shields.io/github/license/krau/saveany-bot)](./LICENSE)
 
 </div>
 
-## 部署
+## 🎯 Features
 
-请参考 [部署文档](https://sabot.unv.app/deployment/installation/)
-
-## Features
-
-- 支持文档/视频/图片/贴纸… 甚至还有 Telegraph
+- 支持文档/视频/图片/贴纸…甚至还有 [Telegraph](https://telegra.ph/)
 - 破解禁止保存的文件
 - 批量下载
 - 流式传输
-- 多用户
+- 多用户使用
 - 基于存储规则的自动整理
-- 支持多种存储端:
+- 监听并自动转存指定聊天的消息, 支持过滤
+- 使用 js 编写解析器插件以转存任意网站的文件
+- 存储端支持:
   - Alist
-  - Minio (S3 兼容)
+  - S3 (MinioSDK)
   - WebDAV
-  - Telegram (重传回指定聊天)
   - 本地磁盘
+  - Telegram (重传回指定聊天)
+
+## 📦 Quick Start
+
+创建文件 `config.toml` 并填入以下内容:
+
+```toml
+[telegram]
+token = "" # 你的 Bot Token, 在 @BotFather 获取
+[telegram.proxy]
+# 启用代理连接 telegram, 当前只支持 socks5
+enable = false
+url = "socks5://127.0.0.1:7890"
+
+[[storages]]
+name = "本地磁盘"
+type = "local"
+enable = true
+base_path = "./downloads"
+
+[[users]]
+id = 114514 # 你的 Telegram 账号 id
+storages = []
+blacklist = true
+```
+
+使用 Docker 运行 Save Any Bot:
+
+```bash
+docker run -d --name saveany-bot \
+    -v ./config.toml:/app/config.toml \
+    -v ./downloads:/app/downloads \
+    ghcr.io/krau/saveany-bot:latest
+```
+
+请 [**查看文档**](https://sabot.unv.app/) 以获取更多配置选项和使用方法.
 
 ## Sponsors
 
@@ -88,3 +130,9 @@
 - [gotgproto](https://github.com/celestix/gotgproto)
 - [tdl](https://github.com/iyear/tdl)
 - All the dependencies
+
+## Contact
+
+- [![Group](https://img.shields.io/badge/ProjectSaveAny-Group-blue)](https://t.me/ProjectSaveAny)
+- [![Discussion](https://img.shields.io/badge/Github-Discussion-white)](https://github.com/krau/saveany-bot/discussions)
+- [![PersonalChannel](https://img.shields.io/badge/Krau-PersonalChannel-cyan)](https://t.me/acherkrau)

client/bot/bot.go

@@ -27,8 +27,8 @@ func Init(ctx context.Context) {
 	})
 	go func() {
 		var resolver dcs.Resolver
-		if config.Cfg.Telegram.Proxy.Enable && config.Cfg.Telegram.Proxy.URL != "" {
-			dialer, err := netutil.NewProxyDialer(config.Cfg.Telegram.Proxy.URL)
+		if config.C().Telegram.Proxy.Enable && config.C().Telegram.Proxy.URL != "" {
+			dialer, err := netutil.NewProxyDialer(config.C().Telegram.Proxy.URL)
 			if err != nil {
 				resultChan <- struct {
 					client *gotgproto.Client
@@ -43,16 +43,16 @@ func Init(ctx context.Context) {
 			resolver = dcs.DefaultResolver()
 		}
 		client, err := gotgproto.NewClient(
-			config.Cfg.Telegram.AppID,
-			config.Cfg.Telegram.AppHash,
-			gotgproto.ClientTypeBot(config.Cfg.Telegram.Token),
+			config.C().Telegram.AppID,
+			config.C().Telegram.AppHash,
+			gotgproto.ClientTypeBot(config.C().Telegram.Token),
 			&gotgproto.ClientOpts{
-				Session:          sessionMaker.SqlSession(gormlite.Open(config.Cfg.DB.Session)),
+				Session:          sessionMaker.SqlSession(gormlite.Open(config.C().DB.Session)),
 				DisableCopyright: true,
 				Middlewares:      middleware.NewDefaultMiddlewares(ctx, 5*time.Minute),
 				Resolver:         resolver,
 				Context:          ctx,
-				MaxRetries:       config.Cfg.Telegram.RpcRetry,
+				MaxRetries:       config.C().Telegram.RpcRetry,
 				AutoFetchReply:   true,
 				ErrorHandler: func(ctx *ext.Context, u *ext.Update, s string) error {
 					log.FromContext(ctx).Errorf("Unhandled error: %s", s)
@@ -79,7 +79,7 @@ func Init(ctx context.Context) {
 			{Command: "dir", Description: "管理存储文件夹"},
 			{Command: "rule", Description: "管理规则"},
 		}
-		if config.Cfg.Telegram.Userbot.Enable {
+		if config.C().Telegram.Userbot.Enable {
 			commands = append(commands, tg.BotCommand{Command: "watch", Description: "监听聊天"})
 			commands = append(commands, tg.BotCommand{Command: "unwatch", Description: "取消监听聊天"})
 		}

client/bot/handlers/add_task.go

@@ -72,7 +72,9 @@ func handleAddCallback(ctx *ext.Context, update *ext.Update) error {
 		}
 		return shortcut.CreateAndAddTGFileTaskWithEdit(ctx, userID, selectedStorage, dirPath, data.Files[0], msgID)
 	case tasktype.TaskTypeTphpics:
-		return shortcut.CreateAndAddTphTaskWithEdit(ctx, userID, data.TphPageNode, data.TphDirPath, data.TphPics, selectedStorage, msgID)
+		return shortcut.CreateAndAddtelegraphWithEdit(ctx, userID, data.TphPageNode, data.TphDirPath, data.TphPics, selectedStorage, msgID)
+	case tasktype.TaskTypeParseditem:
+		shortcut.CreateAndAddParsedTaskWithEdit(ctx, selectedStorage, dirPath, data.ParsedItem, msgID, userID)
 	default:
 		log.FromContext(ctx).Errorf("Unsupported task type: %s", data.TaskType)
 	}

client/bot/handlers/config.go

@@ -0,0 +1,103 @@
+package handlers
+
+import (
+	"fmt"
+	"strings"
+
+	"github.com/celestix/gotgproto/dispatcher"
+	"github.com/celestix/gotgproto/ext"
+	"github.com/gotd/td/tg"
+	"github.com/krau/SaveAny-Bot/database"
+	"github.com/krau/SaveAny-Bot/pkg/enums/fnamest"
+	"github.com/krau/SaveAny-Bot/pkg/tcbdata"
+)
+
+func handleConfigCmd(ctx *ext.Context, update *ext.Update) error {
+	ctx.Reply(update, ext.ReplyTextString("请选择要配置的选项"), &ext.ReplyOpts{
+		Markup: &tg.ReplyInlineMarkup{
+			Rows: []tg.KeyboardButtonRow{
+				{
+					Buttons: []tg.KeyboardButtonClass{
+						&tg.KeyboardButtonCallback{
+							Text: "文件名策略",
+							Data: fmt.Appendf(nil, "%s %s", tcbdata.TypeConfig, "fnamest"),
+						},
+					},
+				},
+			},
+		},
+	})
+	return dispatcher.EndGroups
+}
+
+func handleConfigCallback(ctx *ext.Context, update *ext.Update) error {
+	args := strings.Fields(string(update.CallbackQuery.Data))
+	invaildDataAnswer := func() error {
+		ctx.AnswerCallback(&tg.MessagesSetBotCallbackAnswerRequest{
+			QueryID:   update.CallbackQuery.GetQueryID(),
+			Alert:     true,
+			Message:   "无效的回调数据",
+			CacheTime: 5,
+		})
+		return dispatcher.EndGroups
+	}
+	if len(args) < 2 {
+		return invaildDataAnswer()
+	}
+	switch args[1] {
+	case "fnamest":
+		return handleConfigFnameSTCallback(ctx, update)
+	default:
+		return invaildDataAnswer()
+	}
+}
+
+func handleConfigFnameSTCallback(ctx *ext.Context, update *ext.Update) error {
+	userID := update.CallbackQuery.GetUserID()
+	user, err := database.GetUserByChatID(ctx, userID)
+	if err != nil {
+		return err
+	}
+	args := strings.Fields(string(update.CallbackQuery.Data))
+	if len(args) == 3 {
+		selected := args[2]
+		st, err := fnamest.ParseFnameST(selected)
+		if err != nil {
+			return err
+		}
+		user.FilenameStrategy = st.String()
+		if err := database.UpdateUser(ctx, user); err != nil {
+			return err
+		}
+		ctx.EditMessage(userID, &tg.MessagesEditMessageRequest{
+			ID:      update.CallbackQuery.GetMsgID(),
+			Message: fmt.Sprintf("已将文件名策略设置为: %s", fnamest.FnameSTDisplay[st]),
+		})
+		return dispatcher.EndGroups
+	}
+	opts := fnamest.FnameSTValues()
+	buttons := make([]tg.KeyboardButtonClass, 0, len(opts))
+	for _, opt := range opts {
+		buttons = append(buttons, &tg.KeyboardButtonCallback{
+			Text: fnamest.FnameSTDisplay[opt],
+			Data: fmt.Appendf(nil, "%s %s %s", tcbdata.TypeConfig, "fnamest", opt),
+		})
+	}
+	markup := &tg.ReplyInlineMarkup{Rows: []tg.KeyboardButtonRow{
+		{Buttons: buttons},
+	}}
+	currentStStr := user.FilenameStrategy
+	if currentStStr == "" {
+		currentStStr = fnamest.Default.String()
+	}
+	currentSt, err := fnamest.ParseFnameST(currentStStr)
+	if err != nil {
+		currentSt = fnamest.Default
+	}
+	ctx.EditMessage(userID, &tg.MessagesEditMessageRequest{
+		ID:          update.CallbackQuery.GetMsgID(),
+		Message:     fmt.Sprintf("请选择文件名策略, 当前策略: %s", fnamest.FnameSTDisplay[currentSt]),
+		ReplyMarkup: markup,
+	})
+	return dispatcher.EndGroups
+}

client/bot/handlers/help.go

@@ -5,7 +5,7 @@ import (
 
 	"github.com/celestix/gotgproto/dispatcher"
 	"github.com/celestix/gotgproto/ext"
-	"github.com/krau/SaveAny-Bot/pkg/consts"
+	"github.com/krau/SaveAny-Bot/config"
 )
 
 func handleHelpCmd(ctx *ext.Context, update *ext.Update) error {
@@ -24,10 +24,10 @@ Save Any Bot - 转存你的 Telegram 文件
 
 使用帮助: https://sabot.unv.app/usage/
 `
-	shortHash := consts.GitCommit
+	shortHash := config.GitCommit
 	if len(shortHash) > 7 {
 		shortHash = shortHash[:7]
 	}
-	ctx.Reply(update, ext.ReplyTextString(fmt.Sprintf(helpText, consts.Version, shortHash)), nil)
+	ctx.Reply(update, ext.ReplyTextString(fmt.Sprintf(helpText, config.Version, shortHash)), nil)
 	return dispatcher.EndGroups
 }

client/bot/handlers/media.go

@@ -13,6 +13,8 @@ import (
 	"github.com/krau/SaveAny-Bot/client/bot/handlers/utils/msgelem"
 	"github.com/krau/SaveAny-Bot/client/bot/handlers/utils/shortcut"
 	"github.com/krau/SaveAny-Bot/common/utils/tgutil"
+	"github.com/krau/SaveAny-Bot/database"
+	"github.com/krau/SaveAny-Bot/pkg/enums/fnamest"
 	"github.com/krau/SaveAny-Bot/pkg/tcbdata"
 	"github.com/krau/SaveAny-Bot/pkg/tfile"
 	"github.com/krau/SaveAny-Bot/storage"
@@ -26,12 +28,22 @@ func handleMediaMessage(ctx *ext.Context, update *ext.Update) error {
 		return handleGroupMediaMessage(ctx, update, message, groupID)
 	}
 	logger.Debugf("Got media: %s", message.Media.TypeName())
-
-	msg, file, err := shortcut.GetFileFromMessageWithReply(ctx, update, message)
+	userId := update.GetUserChat().GetID()
+	userDB, err := database.GetUserByChatID(ctx, userId)
 	if err != nil {
 		return err
 	}
-	userId := update.GetUserChat().GetID()
+	tfOpts := make([]tfile.TGFileOption, 0)
+	switch userDB.FilenameStrategy {
+	case fnamest.Message.String():
+		tfOpts = append(tfOpts, tfile.WithName(tgutil.GenFileNameFromMessage(*message)))
+	default:
+	}
+	msg, file, err := shortcut.GetFileFromMessageWithReply(ctx, update, message, tfOpts...)
+	if err != nil {
+		return err
+	}
+
 	stors := storage.GetUserStorages(ctx, userId)
 	req, err := msgelem.BuildAddOneSelectStorageMessage(ctx, stors, file, msg.ID)
 	if err != nil {
@@ -58,7 +70,17 @@ func handleSilentSaveMedia(ctx *ext.Context, update *ext.Update) error {
 	}
 	logger.Debugf("Got media: %s", message.Media.TypeName())
 	userID := update.GetUserChat().GetID()
-	msg, file, err := shortcut.GetFileFromMessageWithReply(ctx, update, message)
+	userDB, err := database.GetUserByChatID(ctx, userID)
+	if err != nil {
+		return err
+	}
+	tfOpts := make([]tfile.TGFileOption, 0)
+	switch userDB.FilenameStrategy {
+	case fnamest.Message.String():
+		tfOpts = append(tfOpts, tfile.WithName(tgutil.GenFileNameFromMessage(*message)))
+	default:
+	}
+	msg, file, err := shortcut.GetFileFromMessageWithReply(ctx, update, message, tfOpts...)
 	if err != nil {
 		return err
 	}

client/bot/handlers/middleware.go

@@ -11,7 +11,7 @@ import (
 
 func checkPermission(ctx *ext.Context, update *ext.Update) error {
 	userID := update.GetUserChat().GetID()
-	if !slice.Contain(config.Cfg.GetUsersID(), userID) {
+	if !slice.Contain(config.C().GetUsersID(), userID) {
 		const noPermissionText string = `
 您不在白名单中, 无法使用此 Bot.
 您可以部署自己的实例: https://github.com/krau/SaveAny-Bot

client/bot/handlers/parse.go

@@ -0,0 +1,110 @@
+// 处理任意文本消息, 用于通用地从外部源下载文件
+
+package handlers
+
+import (
+	"errors"
+
+	"github.com/celestix/gotgproto/dispatcher"
+	"github.com/celestix/gotgproto/ext"
+	"github.com/charmbracelet/log"
+	"github.com/gotd/td/tg"
+	"github.com/krau/SaveAny-Bot/client/bot/handlers/utils/msgelem"
+	"github.com/krau/SaveAny-Bot/client/bot/handlers/utils/shortcut"
+	"github.com/krau/SaveAny-Bot/parsers"
+	"github.com/krau/SaveAny-Bot/pkg/enums/tasktype"
+	"github.com/krau/SaveAny-Bot/pkg/tcbdata"
+	"github.com/krau/SaveAny-Bot/storage"
+)
+
+func handleTextMessage(ctx *ext.Context, u *ext.Update) error {
+	logger := log.FromContext(ctx)
+	text := u.EffectiveMessage.Text
+	ok, pser := parsers.CanHandle(text)
+	if !ok {
+		return dispatcher.EndGroups
+	}
+	msg, err := ctx.Reply(u, ext.ReplyTextString("正在解析..."), nil)
+	if err != nil {
+		return err
+	}
+
+	item, err := pser.Parse(ctx, text)
+	if errors.Is(err, parsers.ErrNoParserFound) {
+		return dispatcher.EndGroups
+	}
+	if err != nil {
+		logger.Error("Failed to parse text", "error", err)
+		ctx.Reply(u, ext.ReplyTextString("Failed to parse text: "+err.Error()), nil)
+		return dispatcher.EndGroups
+	}
+	logger.Debug("Parsed item from text message", "title", item.Title, "url", item.URL)
+	userID := u.GetUserChat().GetID()
+	markup, err := msgelem.BuildAddSelectStorageKeyboard(storage.GetUserStorages(ctx, userID), tcbdata.Add{
+		TaskType:   tasktype.TaskTypeParseditem,
+		ParsedItem: item,
+	})
+	if err != nil {
+		logger.Errorf("Failed to build storage selection keyboard: %s", err)
+		ctx.Reply(u, ext.ReplyTextString("Failed to build storage selection keyboard: "+err.Error()), nil)
+		return dispatcher.EndGroups
+	}
+	text, entities, err := msgelem.BuildParsedTextEntity(*item)
+	if err != nil {
+		logger.Errorf("Failed to build parsed text entity: %s", err)
+		ctx.Reply(u, ext.ReplyTextString("Failed to build parsed text entity: "+err.Error()), nil)
+		return dispatcher.EndGroups
+	}
+	ctx.EditMessage(userID, &tg.MessagesEditMessageRequest{
+		Message:     text,
+		ReplyMarkup: markup,
+		Entities:    entities,
+		ID:          msg.ID,
+	})
+
+	return dispatcher.EndGroups
+}
+
+func handleSilentSaveText(ctx *ext.Context, u *ext.Update) error {
+	logger := log.FromContext(ctx)
+	stor := storage.FromContext(ctx)
+	if stor == nil {
+		logger.Warn("Context storage is nil")
+		ctx.Reply(u, ext.ReplyTextString("未找到存储"), nil)
+		return dispatcher.EndGroups
+	}
+	text := u.EffectiveMessage.Text
+	if text == "" {
+		return dispatcher.EndGroups
+	}
+	item, err := parsers.ParseWithContext(ctx, text)
+	if errors.Is(err, parsers.ErrNoParserFound) {
+		return dispatcher.EndGroups
+	}
+	if err != nil {
+		logger.Error("Failed to parse text", "error", err)
+		ctx.Reply(u, ext.ReplyTextString("Failed to parse text: "+err.Error()), nil)
+		return dispatcher.EndGroups
+	}
+	logger.Debug("Parsed item from text message", "title", item.Title, "url", item.URL)
+	userID := u.GetUserChat().GetID()
+	text, entities, err := msgelem.BuildParsedTextEntity(*item)
+	if err != nil {
+		logger.Errorf("Failed to build parsed text entity: %s", err)
+		ctx.Reply(u, ext.ReplyTextString("Failed to build parsed text entity: "+err.Error()), nil)
+		return dispatcher.EndGroups
+	}
+	msg, err := ctx.SendMessage(userID, &tg.MessagesSendMessageRequest{
+		Message:  text,
+		Entities: entities,
+		ReplyTo: &tg.InputReplyToMessage{
+			ReplyToMsgID:  u.EffectiveMessage.ID,
+			ReplyToPeerID: u.GetUserChat().AsInputPeer(),
+		},
+	})
+	if err != nil {
+		logger.Errorf("Failed to send message: %s", err)
+		return dispatcher.EndGroups
+	}
+	return shortcut.CreateAndAddParsedTaskWithEdit(ctx, stor, "", item, msg.ID, userID)
+}

client/bot/handlers/register.go

@@ -16,7 +16,7 @@ import (
 	"github.com/krau/SaveAny-Bot/common/utils/tgutil"
 	"github.com/krau/SaveAny-Bot/config"
 	"github.com/krau/SaveAny-Bot/core"
-	"github.com/krau/SaveAny-Bot/core/tftask"
+	"github.com/krau/SaveAny-Bot/core/tasks/tfile"
 	"github.com/krau/SaveAny-Bot/database"
 	"github.com/krau/SaveAny-Bot/pkg/tcbdata"
 	"github.com/krau/SaveAny-Bot/storage"
@@ -40,9 +40,11 @@ func Register(disp dispatcher.Dispatcher) {
 	disp.AddHandler(handlers.NewCommand("watch", handleWatchCmd))
 	disp.AddHandler(handlers.NewCommand("unwatch", handleUnwatchCmd))
 	disp.AddHandler(handlers.NewCommand("save", handleSilentMode(handleSaveCmd, handleSilentSaveReplied)))
+	disp.AddHandler(handlers.NewCommand("config", handleConfigCmd))
 	disp.AddHandler(handlers.NewCallbackQuery(filters.CallbackQuery.Prefix(tcbdata.TypeAdd), handleAddCallback))
 	disp.AddHandler(handlers.NewCallbackQuery(filters.CallbackQuery.Prefix(tcbdata.TypeSetDefault), handleSetDefaultCallback))
-	disp.AddHandler(handlers.NewCallbackQuery(filters.CallbackQuery.Prefix("cancel"), handleCancelCallback))
+	disp.AddHandler(handlers.NewCallbackQuery(filters.CallbackQuery.Prefix(tcbdata.TypeCancel), handleCancelCallback))
+	disp.AddHandler(handlers.NewCallbackQuery(filters.CallbackQuery.Prefix(tcbdata.TypeConfig), handleConfigCallback))
 	linkRegexFilter, err := filters.Message.Regex(re.TgMessageLinkRegexString)
 	if err != nil {
 		panic("failed to create regex filter: " + err.Error())
@@ -54,8 +56,9 @@ func Register(disp dispatcher.Dispatcher) {
 	}
 	disp.AddHandler(handlers.NewMessage(telegraphUrlRegexFilter, handleSilentMode(handleTelegraphUrlMessage, handleSilentSaveTelegraph)))
 	disp.AddHandler(handlers.NewMessage(filters.Message.Media, handleSilentMode(handleMediaMessage, handleSilentSaveMedia)))
+	disp.AddHandler(handlers.NewMessage(filters.Message.Text, handleSilentMode(handleTextMessage, handleSilentSaveText)))
 
-	if config.Cfg.Telegram.Userbot.Enable {
+	if config.C().Telegram.Userbot.Enable {
 		go listenMediaMessageEvent(userclient.GetMediaMessageCh())
 	}
 }
@@ -122,7 +125,7 @@ func listenMediaMessageEvent(ch chan userclient.MediaMessageEvent) {
 			storagePath := stor.JoinStoragePath(path.Join(dirPath, file.Name()))
 			injectCtx := tgutil.ExtWithContext(ctx.Context, ctx)
 			taskid := xid.New().String()
-			task, err := tftask.NewTGFileTask(taskid, injectCtx, file, stor, storagePath, nil)
+			task, err := tfile.NewTGFileTask(taskid, injectCtx, file, stor, storagePath, nil)
 			if err != nil {
 				logger.Errorf("create task failed: %s", err)
 				continue

client/bot/handlers/rule.go

@@ -11,7 +11,7 @@ import (
 	"github.com/duke-git/lancet/v2/slice"
 	"github.com/krau/SaveAny-Bot/client/bot/handlers/utils/msgelem"
 	"github.com/krau/SaveAny-Bot/database"
-	"github.com/krau/SaveAny-Bot/pkg/enums/rule"
+	"github.com/krau/SaveAny-Bot/pkg/rule"
 )
 
 func handleRuleCmd(ctx *ext.Context, update *ext.Update) error {

client/bot/handlers/telegraph.go

@@ -71,6 +71,6 @@ func handleSilentSaveTelegraph(ctx *ext.Context, update *ext.Update) error {
 		return err
 	}
 	userID := update.GetUserChat().GetID()
-	return shortcut.CreateAndAddTphTaskWithEdit(ctx, userID, result.Page, result.TphDir, result.Pics, stor, msg.ID)
+	return shortcut.CreateAndAddtelegraphWithEdit(ctx, userID, result.Page, result.TphDir, result.Pics, stor, msg.ID)
 
 }

client/bot/handlers/utils/msgelem/parse.go

@@ -0,0 +1,39 @@
+package msgelem
+
+import (
+	"fmt"
+
+	"github.com/duke-git/lancet/v2/strutil"
+	"github.com/gotd/td/telegram/message/entity"
+	"github.com/gotd/td/telegram/message/styling"
+	"github.com/gotd/td/tg"
+	"github.com/krau/SaveAny-Bot/pkg/parser"
+)
+
+func BuildParsedTextEntity(item parser.Item) (string, []tg.MessageEntityClass, error) {
+	eb := entity.Builder{}
+	if err := styling.Perform(&eb,
+		styling.Bold(fmt.Sprintf("[%s]%s", item.Site, item.Title)),
+		styling.Plain("\n链接: "),
+		styling.Code(item.URL),
+		styling.Plain("\n作者: "),
+		styling.Code(item.Author),
+		styling.Plain("\n描述: "),
+		styling.Code(strutil.Ellipsis(item.Description, 233)),
+		styling.Plain("\n文件数量: "),
+		styling.Code(fmt.Sprintf("%d", len(item.Resources))),
+		styling.Plain("\n预计总大小: "),
+		styling.Code(fmt.Sprintf("%.2f MB", func() float64 {
+			var totalSize int64
+			for _, res := range item.Resources {
+				totalSize += res.Size
+			}
+			return float64(totalSize) / 1024 / 1024
+		}())),
+		styling.Plain("\n请选择存储位置"),
+	); err != nil {
+		return "", nil, fmt.Errorf("构建消息失败: %w", err)
+	}
+	text, entities := eb.Complete()
+	return text, entities, nil
+}

client/bot/handlers/utils/msgelem/storage.go

@@ -24,6 +24,8 @@ func BuildAddSelectStorageKeyboard(stors []storage.Storage, adddata tcbdata.Add)
 			taskType = tasktype.TaskTypeTgfiles
 		} else if adddata.TphPageNode != nil {
 			taskType = tasktype.TaskTypeTphpics
+		} else if adddata.ParsedItem != nil {
+			taskType = tasktype.TaskTypeParseditem
 		} else {
 			return nil, fmt.Errorf("unknown task type: %s", taskType)
 		}
@@ -41,6 +43,8 @@ func BuildAddSelectStorageKeyboard(stors []storage.Storage, adddata tcbdata.Add)
 			TphPageNode: adddata.TphPageNode,
 			TphPics:     adddata.TphPics,
 			TphDirPath:  adddata.TphDirPath,
+
+			ParsedItem: adddata.ParsedItem,
 		}
 		dataid := xid.New().String()
 		err := cache.Set(dataid, data)

client/bot/handlers/utils/ruleutil/rule.go

@@ -7,8 +7,6 @@ import (
 
 	"github.com/charmbracelet/log"
 	"github.com/krau/SaveAny-Bot/database"
-	"github.com/krau/SaveAny-Bot/pkg/consts"
-	ruleenum "github.com/krau/SaveAny-Bot/pkg/enums/rule"
 	"github.com/krau/SaveAny-Bot/pkg/rule"
 	"github.com/krau/SaveAny-Bot/pkg/tfile"
 )
@@ -37,7 +35,7 @@ func (m matchedStorName) String() string {
 
 // can we use this storage name directly?
 func (m matchedStorName) IsUsable() bool {
-	return m != "" && m != consts.RuleStorNameChosen
+	return m != "" && m != rule.RuleStorNameChosen
 }
 
 type MatchedDirPath string
@@ -47,7 +45,7 @@ func (m MatchedDirPath) String() string {
 }
 
 func (m MatchedDirPath) NeedNewForAlbum() bool {
-	return m != "" && m == consts.RuleDirPathNewForAlbum
+	return m != "" && m == rule.RuleDirPathNewForAlbum
 }
 
 func ApplyRule(ctx context.Context, rules []database.Rule, inputs *ruleInput) (matchedStorageName matchedStorName, dirPath MatchedDirPath) {
@@ -57,7 +55,7 @@ func ApplyRule(ctx context.Context, rules []database.Rule, inputs *ruleInput) (m
 	logger := log.FromContext(ctx)
 	for _, ur := range rules {
 		switch ur.Type {
-		case ruleenum.FileNameRegex.String():
+		case rule.FileNameRegex.String():
 			ru, err := rule.NewRuleFileNameRegex(ur.StorageName, ur.DirPath, ur.Data)
 			if err != nil {
 				logger.Errorf("Failed to create rule: %s", err)
@@ -72,7 +70,7 @@ func ApplyRule(ctx context.Context, rules []database.Rule, inputs *ruleInput) (m
 				dirPath = MatchedDirPath(ru.StoragePath())
 				matchedStorageName = matchedStorName(ru.StorageName())
 			}
-		case ruleenum.MessageRegex.String():
+		case rule.MessageRegex.String():
 			ru, err := rule.NewRuleMessageRegex(ur.StorageName, ur.DirPath, ur.Data)
 			if err != nil {
 				logger.Errorf("Failed to create rule: %s", err)
@@ -87,7 +85,7 @@ func ApplyRule(ctx context.Context, rules []database.Rule, inputs *ruleInput) (m
 				dirPath = MatchedDirPath(ru.StoragePath())
 				matchedStorageName = matchedStorName(ru.StorageName())
 			}
-		case ruleenum.IsAlbum.String():
+		case rule.IsAlbum.String():
 			matchAlbum, err := convertor.ToBool(ur.Data)
 			if err != nil {
 				matchAlbum = false

client/bot/handlers/utils/shortcut/message.go

@@ -20,20 +20,21 @@ import (
 	"github.com/krau/SaveAny-Bot/common/utils/tgutil"
 	"github.com/krau/SaveAny-Bot/common/utils/tphutil"
 	"github.com/krau/SaveAny-Bot/config"
+	"github.com/krau/SaveAny-Bot/database"
+	"github.com/krau/SaveAny-Bot/pkg/enums/fnamest"
 	"github.com/krau/SaveAny-Bot/pkg/telegraph"
 	"github.com/krau/SaveAny-Bot/pkg/tfile"
 )
 
 // 获取消息中的文件并回复等待消息, 返回等待消息, 获取到的文件
-func GetFileFromMessageWithReply(ctx *ext.Context, update *ext.Update, message *tg.Message, tfileopts ...tfile.TGFileOptions) (replied *types.Message,
+func GetFileFromMessageWithReply(ctx *ext.Context, update *ext.Update, message *tg.Message, tfileopts ...tfile.TGFileOption) (replied *types.Message,
 	file tfile.TGFileMessage, err error,
 ) {
 	logger := log.FromContext(ctx)
 	media := message.Media
 	supported := mediautil.IsSupported(media)
 	if !supported {
-		ctx.Reply(update, ext.ReplyTextString("不支持的消息类型"), nil)
-		return nil, nil, dispatcher.EndGroups
+		return nil, nil, dispatcher.ContinueGroups
 	}
 
 	replied, err = ctx.Reply(update, ext.ReplyTextString("正在获取文件信息..."), nil)
@@ -41,7 +42,7 @@ func GetFileFromMessageWithReply(ctx *ext.Context, update *ext.Update, message *
 		logger.Errorf("Failed to reply: %s", err)
 		return nil, nil, dispatcher.EndGroups
 	}
-	options := []tfile.TGFileOptions{
+	options := []tfile.TGFileOption{
 		tfile.WithMessage(message),
 	}
 	if len(tfileopts) > 0 {
@@ -82,7 +83,12 @@ func GetFilesFromUpdateLinkMessageWithReplyEdit(ctx *ext.Context, update *ext.Up
 			logger.Errorf("failed to edit message: %s", err)
 		}
 	}
-
+	user, err := database.GetUserByChatID(ctx, update.GetUserChat().GetID())
+	if err != nil {
+		logger.Errorf("failed to get user from db: %s", err)
+		editReplied("获取用户信息失败: "+err.Error(), nil)
+		return nil, nil, nil, dispatcher.EndGroups
+	}
 	files = make([]tfile.TGFileMessage, 0, len(msgLinks))
 	addFile := func(client downloader.Client, msg *tg.Message) {
 		if msg == nil || msg.Media == nil {
@@ -94,7 +100,14 @@ func GetFilesFromUpdateLinkMessageWithReplyEdit(ctx *ext.Context, update *ext.Up
 			logger.Debugf("message %d has no media", msg.GetID())
 			return
 		}
-		file, err := tfile.FromMediaMessage(media, client, msg, tfile.WithNameIfEmpty(tgutil.GenFileNameFromMessage(*msg)))
+		var opt tfile.TGFileOption
+		switch user.FilenameStrategy {
+		case fnamest.Message.String():
+			opt = tfile.WithName(tgutil.GenFileNameFromMessage(*msg))
+		default:
+			opt = tfile.WithNameIfEmpty(tgutil.GenFileNameFromMessage(*msg))
+		}
+		file, err := tfile.FromMediaMessage(media, client, msg, opt)
 		if err != nil {
 			logger.Errorf("failed to create file from media: %s", err)
 			return
@@ -103,7 +116,7 @@ func GetFilesFromUpdateLinkMessageWithReplyEdit(ctx *ext.Context, update *ext.Up
 	}
 
 	tctx := ctx
-	if config.Cfg.Telegram.Userbot.Enable {
+	if config.C().Telegram.Userbot.Enable {
 		tctx = uc.GetCtx()
 	}
 

client/bot/handlers/utils/shortcut/parsed.go

@@ -0,0 +1,35 @@
+package shortcut
+
+import (
+	"github.com/celestix/gotgproto/dispatcher"
+	"github.com/celestix/gotgproto/ext"
+	"github.com/charmbracelet/log"
+	"github.com/gotd/td/tg"
+	"github.com/krau/SaveAny-Bot/client/bot/handlers/utils/msgelem"
+	"github.com/krau/SaveAny-Bot/common/utils/tgutil"
+	"github.com/krau/SaveAny-Bot/core"
+	"github.com/krau/SaveAny-Bot/core/tasks/parsed"
+	"github.com/krau/SaveAny-Bot/pkg/parser"
+	"github.com/krau/SaveAny-Bot/storage"
+	"github.com/rs/xid"
+)
+
+func CreateAndAddParsedTaskWithEdit(ctx *ext.Context, stor storage.Storage, dirPath string, item *parser.Item, msgID int, userID int64) error {
+	injectCtx := tgutil.ExtWithContext(ctx.Context, ctx)
+	task := parsed.NewTask(xid.New().String(), injectCtx, stor, stor.JoinStoragePath(dirPath), item, parsed.NewProgress(msgID, userID))
+	if err := core.AddTask(injectCtx, task); err != nil {
+		log.FromContext(ctx).Errorf("Failed to add task: %s", err)
+		ctx.EditMessage(userID, &tg.MessagesEditMessageRequest{
+			ID:      msgID,
+			Message: "任务添加失败: " + err.Error(),
+		})
+		return dispatcher.EndGroups
+	}
+	text, entities := msgelem.BuildTaskAddedEntities(ctx, item.Title, core.GetLength(ctx))
+	ctx.EditMessage(userID, &tg.MessagesEditMessageRequest{
+		ID:       msgID,
+		Message:  text,
+		Entities: entities,
+	})
+	return dispatcher.EndGroups
+}

client/bot/handlers/utils/shortcut/tftask.go

@@ -13,15 +13,15 @@ import (
 	"github.com/krau/SaveAny-Bot/client/bot/handlers/utils/ruleutil"
 	"github.com/krau/SaveAny-Bot/common/utils/tgutil"
 	"github.com/krau/SaveAny-Bot/core"
-	"github.com/krau/SaveAny-Bot/core/batchtftask"
-	"github.com/krau/SaveAny-Bot/core/tftask"
+	"github.com/krau/SaveAny-Bot/core/tasks/batchtfile"
+	tftask "github.com/krau/SaveAny-Bot/core/tasks/tfile"
 	"github.com/krau/SaveAny-Bot/database"
 	"github.com/krau/SaveAny-Bot/pkg/tfile"
 	"github.com/krau/SaveAny-Bot/storage"
 	"github.com/rs/xid"
 )
 
-// 创建一个 tftask.TGFileTask 并添加到任务队列中, 以编辑消息的方式反馈结果
+// 创建一个 tfile.TGFileTask 并添加到任务队列中, 以编辑消息的方式反馈结果
 func CreateAndAddTGFileTaskWithEdit(ctx *ext.Context, userID int64, stor storage.Storage, dirPath string, file tfile.TGFileMessage, trackMsgID int) error {
 	logger := log.FromContext(ctx)
 	user, err := database.GetUserByChatID(ctx, userID)
@@ -82,7 +82,7 @@ func CreateAndAddTGFileTaskWithEdit(ctx *ext.Context, userID int64, stor storage
 	return dispatcher.EndGroups
 }
 
-// 创建一个 batchtftask.BatchTGFileTask 并添加到任务队列中, 以编辑消息的方式反馈结果
+// 创建一个 batchtfile.BatchTGFileTask 并添加到任务队列中, 以编辑消息的方式反馈结果
 func CreateAndAddBatchTGFileTaskWithEdit(ctx *ext.Context, userID int64, stor storage.Storage, dirPath string, files []tfile.TGFileMessage, trackMsgID int) error {
 	logger := log.FromContext(ctx)
 	user, err := database.GetUserByChatID(ctx, userID)
@@ -110,7 +110,7 @@ func CreateAndAddBatchTGFileTaskWithEdit(ctx *ext.Context, userID int64, stor st
 		return storname, dirP
 	}
 
-	elems := make([]batchtftask.TaskElement, 0, len(files))
+	elems := make([]batchtfile.TaskElement, 0, len(files))
 	type albumFile struct {
 		file    tfile.TGFileMessage
 		storage storage.Storage
@@ -132,7 +132,7 @@ func CreateAndAddBatchTGFileTaskWithEdit(ctx *ext.Context, userID int64, stor st
 		}
 		if !dirPath.NeedNewForAlbum() {
 			storPath := fileStor.JoinStoragePath(path.Join(dirPath.String(), file.Name()))
-			elem, err := batchtftask.NewTaskElement(fileStor, storPath, file)
+			elem, err := batchtfile.NewTaskElement(fileStor, storPath, file)
 			if err != nil {
 				logger.Errorf("Failed to create task element: %s", err)
 				ctx.EditMessage(userID, &tg.MessagesEditMessageRequest{
@@ -167,7 +167,7 @@ func CreateAndAddBatchTGFileTaskWithEdit(ctx *ext.Context, userID int64, stor st
 		albumStor := afiles[0].storage
 		for _, af := range afiles {
 			afstorPath := af.storage.JoinStoragePath(path.Join(dirPath, albumDir, af.file.Name()))
-			elem, err := batchtftask.NewTaskElement(albumStor, afstorPath, af.file)
+			elem, err := batchtfile.NewTaskElement(albumStor, afstorPath, af.file)
 			if err != nil {
 				logger.Errorf("Failed to create task element for album file: %s", err)
 				ctx.EditMessage(userID, &tg.MessagesEditMessageRequest{
@@ -182,7 +182,7 @@ func CreateAndAddBatchTGFileTaskWithEdit(ctx *ext.Context, userID int64, stor st
 
 	injectCtx := tgutil.ExtWithContext(ctx.Context, ctx)
 	taskid := xid.New().String()
-	task := batchtftask.NewBatchTGFileTask(taskid, injectCtx, elems, batchtftask.NewProgressTracker(trackMsgID, userID), true)
+	task := batchtfile.NewBatchTGFileTask(taskid, injectCtx, elems, batchtfile.NewProgressTracker(trackMsgID, userID), true)
 	if err := core.AddTask(injectCtx, task); err != nil {
 		logger.Errorf("Failed to add batch task: %s", err)
 		ctx.EditMessage(userID, &tg.MessagesEditMessageRequest{

client/bot/handlers/utils/shortcut/tphtask.go

@@ -9,19 +9,21 @@ import (
 	"github.com/krau/SaveAny-Bot/common/utils/tgutil"
 	"github.com/krau/SaveAny-Bot/common/utils/tphutil"
 	"github.com/krau/SaveAny-Bot/core"
-	"github.com/krau/SaveAny-Bot/core/tphtask"
+	tphtask "github.com/krau/SaveAny-Bot/core/tasks/telegraph"
 	"github.com/krau/SaveAny-Bot/pkg/telegraph"
 	"github.com/krau/SaveAny-Bot/storage"
 	"github.com/rs/xid"
 )
 
-func CreateAndAddTphTaskWithEdit(ctx *ext.Context,
+func CreateAndAddtelegraphWithEdit(
+	ctx *ext.Context,
 	userID int64,
 	tphpage *telegraph.Page,
 	dirPath string, // unescaped ph path for file storage
 	pics []string,
 	stor storage.Storage,
 	trackMsgID int) error {
+		
 	injectCtx := tgutil.ExtWithContext(ctx.Context, ctx)
 	task := tphtask.NewTask(xid.New().String(),
 		injectCtx,

client/bot/handlers/watch.go

@@ -14,7 +14,7 @@ import (
 
 func handleWatchCmd(ctx *ext.Context, update *ext.Update) error {
 	logger := log.FromContext(ctx)
-	args := strings.Split(string(update.EffectiveMessage.Text), " ")
+	args := strings.Split(update.EffectiveMessage.Text, " ")
 	if len(args) < 2 {
 		ctx.Reply(update, ext.ReplyTextString(msgelem.WatchHelpText), nil)
 		return dispatcher.EndGroups
@@ -82,7 +82,7 @@ func handleWatchCmd(ctx *ext.Context, update *ext.Update) error {
 
 func handleUnwatchCmd(ctx *ext.Context, update *ext.Update) error {
 	logger := log.FromContext(ctx)
-	args := strings.Split(string(update.EffectiveMessage.Text), " ")
+	args := strings.Split(update.EffectiveMessage.Text, " ")
 	if len(args) < 2 {
 		ctx.Reply(update, ext.ReplyTextString("请提供要取消监听的聊天ID或用户名"), nil)
 		return dispatcher.EndGroups

client/middleware/default.go

@@ -16,7 +16,7 @@ import (
 func NewDefaultMiddlewares(ctx context.Context, timeout time.Duration) []telegram.Middleware {
 	return []telegram.Middleware{
 		recovery.New(ctx, newBackoff(timeout)),
-		retry.New(config.Cfg.Telegram.RpcRetry),
+		retry.New(config.C().Telegram.RpcRetry),
 		floodwait.NewSimpleWaiter(),
 	}
 }

client/middleware/recovery/recovery.go

@@ -2,11 +2,11 @@ package recovery
 
 import (
 	"context"
+	"fmt"
 	"time"
 
 	"github.com/cenkalti/backoff/v4"
 	"github.com/charmbracelet/log"
-	"github.com/go-faster/errors"
 	"github.com/gotd/td/bin"
 	"github.com/gotd/td/telegram"
 	"github.com/gotd/td/tg"
@@ -31,7 +31,7 @@ func (r *recovery) Handle(next tg.Invoker) telegram.InvokeFunc {
 		return backoff.RetryNotify(func() error {
 			if err := next.Invoke(ctx, input, output); err != nil {
 				if r.shouldRecover(ctx, err) {
-					return errors.Wrap(err, "recover")
+					return fmt.Errorf("recovery: %w", err)
 				}
 
 				return backoff.Permanent(err)

client/user/userclient.go

@@ -54,8 +54,8 @@ func Login(ctx context.Context) (*gotgproto.Client, error) {
 	})
 	go func() {
 		var resolver dcs.Resolver
-		if config.Cfg.Telegram.Proxy.Enable && config.Cfg.Telegram.Proxy.URL != "" {
-			dialer, err := netutil.NewProxyDialer(config.Cfg.Telegram.Proxy.URL)
+		if config.C().Telegram.Proxy.Enable && config.C().Telegram.Proxy.URL != "" {
+			dialer, err := netutil.NewProxyDialer(config.C().Telegram.Proxy.URL)
 			if err != nil {
 				res <- struct {
 					client *gotgproto.Client
@@ -70,16 +70,16 @@ func Login(ctx context.Context) (*gotgproto.Client, error) {
 			resolver = dcs.DefaultResolver()
 		}
 		tclient, err := gotgproto.NewClient(
-			config.Cfg.Telegram.AppID,
-			config.Cfg.Telegram.AppHash,
+			config.C().Telegram.AppID,
+			config.C().Telegram.AppHash,
 			gotgproto.ClientTypePhone(""),
 			&gotgproto.ClientOpts{
-				Session:          sessionMaker.SqlSession(gormlite.Open(config.Cfg.Telegram.Userbot.Session)),
+				Session:          sessionMaker.SqlSession(gormlite.Open(config.C().Telegram.Userbot.Session)),
 				AuthConversator:  &terminalAuthConversator{},
 				Context:          ctx,
 				DisableCopyright: true,
 				Resolver:         resolver,
-				MaxRetries:       config.Cfg.Telegram.RpcRetry,
+				MaxRetries:       config.C().Telegram.RpcRetry,
 				AutoFetchReply:   true,
 				Middlewares:      middleware.NewDefaultMiddlewares(ctx, 5*time.Minute),
 				ErrorHandler: func(ctx *ext.Context, u *ext.Update, s string) error {

cmd/run.go

@@ -19,6 +19,7 @@ import (
 	"github.com/krau/SaveAny-Bot/config"
 	"github.com/krau/SaveAny-Bot/core"
 	"github.com/krau/SaveAny-Bot/database"
+	"github.com/krau/SaveAny-Bot/parsers"
 	"github.com/krau/SaveAny-Bot/storage"
 	"github.com/spf13/cobra"
 )
@@ -49,11 +50,20 @@ func initAll(ctx context.Context) {
 	}
 	cache.Init()
 	logger := log.FromContext(ctx)
-	i18n.Init(config.Cfg.Lang)
+	i18n.Init(config.C().Lang)
 	logger.Info(i18n.T(i18nk.Initing))
 	database.Init(ctx)
 	storage.LoadStorages(ctx)
-	if config.Cfg.Telegram.Userbot.Enable {
+	if config.C().Parser.PluginEnable {
+		for _, dir := range config.C().Parser.PluginDirs {
+			if err := parsers.LoadPlugins(ctx, dir); err != nil {
+				logger.Error("Failed to load parser plugins", "dir", dir, "error", err)
+			} else {
+				logger.Debug("Loaded parser plugins", "dir", dir)
+			}
+		}
+	}
+	if config.C().Telegram.Userbot.Enable {
 		_, err := userclient.Login(ctx)
 		if err != nil {
 			logger.Fatalf("User client login failed: %s", err)
@@ -63,13 +73,13 @@ func initAll(ctx context.Context) {
 }
 
 func cleanCache() {
-	if config.Cfg.NoCleanCache {
+	if config.C().NoCleanCache {
 		return
 	}
-	if config.Cfg.Temp.BasePath != "" && !config.Cfg.Stream {
-		if slices.Contains([]string{"/", ".", "\\", ".."}, filepath.Clean(config.Cfg.Temp.BasePath)) {
+	if config.C().Temp.BasePath != "" && !config.C().Stream {
+		if slices.Contains([]string{"/", ".", "\\", ".."}, filepath.Clean(config.C().Temp.BasePath)) {
 			log.Error(i18n.T(i18nk.InvalidCacheDir, map[string]any{
-				"Path": config.Cfg.Temp.BasePath,
+				"Path": config.C().Temp.BasePath,
 			}))
 			return
 		}
@@ -80,7 +90,7 @@ func cleanCache() {
 			}))
 			return
 		}
-		cachePath := filepath.Join(currentDir, config.Cfg.Temp.BasePath)
+		cachePath := filepath.Join(currentDir, config.C().Temp.BasePath)
 		cachePath, err = filepath.Abs(cachePath)
 		if err != nil {
 			log.Error(i18n.T(i18nk.GetCacheAbsPathFailed, map[string]any{

cmd/version.go

@@ -4,7 +4,7 @@ import (
 	"fmt"
 	"runtime"
 
-	"github.com/krau/SaveAny-Bot/pkg/consts"
+	"github.com/krau/SaveAny-Bot/config"
 	"github.com/rhysd/go-github-selfupdate/selfupdate"
 
 	"github.com/blang/semver"
@@ -16,7 +16,7 @@ var VersionCmd = &cobra.Command{
 	Aliases: []string{"v"},
 	Short:   "Print the version number of saveany-bot",
 	Run: func(cmd *cobra.Command, args []string) {
-		fmt.Printf("saveany-bot version: %s %s/%s\nBuildTime: %s, Commit: %s\n", consts.Version, runtime.GOOS, runtime.GOARCH, consts.BuildTime, consts.GitCommit)
+		fmt.Printf("saveany-bot version: %s %s/%s\nBuildTime: %s, Commit: %s\n", config.Version, runtime.GOOS, runtime.GOARCH, config.BuildTime, config.GitCommit)
 	},
 }
 
@@ -25,14 +25,14 @@ var upgradeCmd = &cobra.Command{
 	Aliases: []string{"up"},
 	Short:   "Upgrade saveany-bot to the latest version",
 	Run: func(cmd *cobra.Command, args []string) {
-		v := semver.MustParse(consts.Version)
+		v := semver.MustParse(config.Version)
 		latest, err := selfupdate.UpdateSelf(v, "krau/SaveAny-Bot")
 		if err != nil {
 			fmt.Println("Binary update failed:", err)
 			return
 		}
 		if latest.Version.Equals(v) {
-			fmt.Println("Current binary is the latest version", consts.Version)
+			fmt.Println("Current binary is the latest version", config.Version)
 		} else {
 			fmt.Println("Successfully updated to version", latest.Version)
 			fmt.Println("Release note:\n", latest.ReleaseNotes)

common/cache/ristretto.go

@@ -16,8 +16,8 @@ func Init() {
 		panic("cache already initialized")
 	}
 	c, err := ristretto.NewCache(&ristretto.Config[string, any]{
-		NumCounters: config.Cfg.Cache.NumCounters,
-		MaxCost:     config.Cfg.Cache.MaxCost,
+		NumCounters: config.C().Cache.NumCounters,
+		MaxCost:     config.C().Cache.MaxCost,
 		BufferItems: 64,
 		OnReject: func(item *ristretto.Item[any]) {
 			log.Warnf("Cache item rejected: key=%d, value=%v", item.Key, item.Value)
@@ -30,7 +30,7 @@ func Init() {
 }
 
 func Set(key string, value any) error {
-	ok := cache.SetWithTTL(key, value, 0, time.Duration(config.Cfg.Cache.TTL)*time.Second)
+	ok := cache.SetWithTTL(key, value, 0, time.Duration(config.C().Cache.TTL)*time.Second)
 	if !ok {
 		return fmt.Errorf("failed to set value in cache")
 	}

common/utils/netutil/proxy.go

@@ -1,8 +1,15 @@
 package netutil
 
 import (
+	"context"
+	"fmt"
+	"net"
+	"net/http"
 	"net/url"
+	"sync"
 
+	"github.com/charmbracelet/log"
+	"github.com/krau/SaveAny-Bot/config"
 	"golang.org/x/net/proxy"
 )
 
@@ -13,3 +20,60 @@ func NewProxyDialer(proxyUrl string) (proxy.Dialer, error) {
 	}
 	return proxy.FromURL(url, proxy.Direct)
 }
+
+func NewProxyHTTPClient(proxyUrl string) (*http.Client, error) {
+	if proxyUrl == "" {
+		return &http.Client{
+			Transport: &http.Transport{
+				Proxy: http.ProxyFromEnvironment,
+			},
+		}, nil
+	}
+
+	u, err := url.Parse(proxyUrl)
+	if err != nil {
+		return nil, err
+	}
+
+	switch u.Scheme {
+	case "http", "https":
+		return &http.Client{
+			Transport: &http.Transport{
+				Proxy: http.ProxyURL(u),
+			},
+		}, nil
+	case "socks5":
+		dialer, err := proxy.SOCKS5("tcp", u.Host, nil, proxy.Direct)
+		if err != nil {
+			return nil, err
+		}
+
+		return &http.Client{
+			Transport: &http.Transport{
+				DialContext: func(ctx context.Context, network, addr string) (net.Conn, error) {
+					return dialer.Dial(network, addr)
+				},
+			},
+		}, nil
+	default:
+		return nil, fmt.Errorf("unsupported proxy scheme: %s", u.Scheme)
+	}
+}
+
+var (
+	defaultProxyHttpClient         *http.Client
+	onceLoadDefaultProxyHttpClient sync.Once
+)
+
+func DefaultParserHTTPClient() *http.Client {
+	onceLoadDefaultProxyHttpClient.Do(func() {
+		client, err := NewProxyHTTPClient(config.C().Parser.Proxy)
+		if err != nil {
+			log.Warn("Failed to create default proxy HTTP client, using http.DefaultClient", "error", err)
+			defaultProxyHttpClient = http.DefaultClient
+		} else {
+			defaultProxyHttpClient = client
+		}
+	})
+	return defaultProxyHttpClient
+}

common/utils/tphutil/tph.go

@@ -13,8 +13,8 @@ func DefaultClient() *telegraph.Client {
 	if tphClient != nil {
 		return tphClient
 	}
-	if config.Cfg.Telegram.Proxy.Enable && config.Cfg.Telegram.Proxy.URL != "" {
-		proxyUrl := config.Cfg.Telegram.Proxy.URL
+	if config.C().Telegram.Proxy.Enable && config.C().Telegram.Proxy.URL != "" {
+		proxyUrl := config.C().Telegram.Proxy.URL
 		var err error
 		tphClient, err = telegraph.NewClientWithProxy(proxyUrl)
 		if err != nil {

config/parser.go

@@ -0,0 +1,15 @@
+package config
+
+type parserConfig struct {
+	PluginEnable bool                      `toml:"plugin_enable" mapstructure:"plugin_enable" json:"plugin_enable"`
+	PluginDirs   []string                  `toml:"plugin_dirs" mapstructure:"plugin_dirs" json:"plugin_dirs"`
+	Proxy        string                    `toml:"proxy" mapstructure:"proxy" json:"proxy"`
+	ParserCfgs   map[string]map[string]any `mapstructure:",remain"`
+}
+
+func (c Config) GetParserConfigByName(name string) map[string]any {
+	if c.Parser.ParserCfgs == nil {
+		return nil
+	}
+	return c.Parser.ParserCfgs[name]
+}

config/tg.go

@@ -6,7 +6,7 @@ type telegramConfig struct {
 	AppHash  string        `toml:"app_hash" mapstructure:"app_hash" json:"app_hash"`
 	Proxy    tgProxyConfig `toml:"proxy" mapstructure:"proxy"`
 	RpcRetry int           `toml:"rpc_retry" mapstructure:"rpc_retry" json:"rpc_retry"`
-	Userbot  userbotConfig `toml:"userbot" mapstructure:"userbot" json:"userbot"` // [TODO]
+	Userbot  userbotConfig `toml:"userbot" mapstructure:"userbot" json:"userbot"`
 }
 
 type userbotConfig struct {

config/user.go

@@ -14,7 +14,7 @@ var userIDs []int64
 var storages []string
 var userStorages = make(map[int64][]string)
 
-func (c *Config) GetStorageNamesByUserID(userID int64) []string {
+func (c Config) GetStorageNamesByUserID(userID int64) []string {
 	us, ok := userStorages[userID]
 	if ok {
 		return us
@@ -22,11 +22,11 @@ func (c *Config) GetStorageNamesByUserID(userID int64) []string {
 	return nil
 }
 
-func (c *Config) GetUsersID() []int64 {
+func (c Config) GetUsersID() []int64 {
 	return userIDs
 }
 
-func (c *Config) HasStorage(userID int64, storageName string) bool {
+func (c Config) HasStorage(userID int64, storageName string) bool {
 	us, ok := userStorages[userID]
 	if !ok {
 		return false

config/version.go

@@ -1,7 +1,7 @@
-package consts
+package config
 
 // inject version by '-X' flag
-// go build -ldflags "-X github.com/krau/SaveAny-Bot/pkg/consts.Version=${{ env.VERSION }}"
+// go build -ldflags "-X github.com/krau/SaveAny-Bot/config.Version=${{ env.VERSION }}"
 var (
 	Version   string = "dev"
 	BuildTime string = "unknown"

config/viper.go

@@ -28,10 +28,15 @@ type Config struct {
 	DB       dbConfig                `toml:"db" mapstructure:"db"`
 	Telegram telegramConfig          `toml:"telegram" mapstructure:"telegram"`
 	Storages []storage.StorageConfig `toml:"-" mapstructure:"-" json:"storages"`
+	Parser   parserConfig            `toml:"parser" mapstructure:"parser" json:"parser"`
 	Hook     hookConfig              `toml:"hook" mapstructure:"hook" json:"hook"`
 }
 
-var Cfg *Config = &Config{}
+var cfg = &Config{}
+
+func C() Config {
+	return *cfg
+}
 
 func (c Config) GetStorageByName(name string) storage.StorageConfig {
 	for _, storage := range c.Storages {
@@ -94,7 +99,7 @@ func Init(ctx context.Context) error {
 		os.Exit(1)
 	}
 
-	if err := viper.Unmarshal(Cfg); err != nil {
+	if err := viper.Unmarshal(cfg); err != nil {
 		fmt.Println("Error unmarshalling config file, ", err)
 		os.Exit(1)
 	}
@@ -103,36 +108,36 @@ func Init(ctx context.Context) error {
 	if err != nil {
 		return fmt.Errorf("error loading storage configs: %w", err)
 	}
-	Cfg.Storages = storagesConfig
+	cfg.Storages = storagesConfig
 
 	storageNames := make(map[string]struct{})
-	for _, storage := range Cfg.Storages {
+	for _, storage := range cfg.Storages {
 		if _, ok := storageNames[storage.GetName()]; ok {
-			return errors.New(i18n.TWithoutInit(Cfg.Lang, i18nk.ConfigInvalidDuplicateStorageName, map[string]any{
+			return errors.New(i18n.TWithoutInit(cfg.Lang, i18nk.ConfigInvalidDuplicateStorageName, map[string]any{
 				"Name": storage.GetName(),
 			}))
 		}
 		storageNames[storage.GetName()] = struct{}{}
 	}
 
-	fmt.Println(i18n.TWithoutInit(Cfg.Lang, i18nk.LoadedStorages, map[string]any{
-		"Count": len(Cfg.Storages),
+	fmt.Println(i18n.TWithoutInit(cfg.Lang, i18nk.LoadedStorages, map[string]any{
+		"Count": len(cfg.Storages),
 	}))
-	for _, storage := range Cfg.Storages {
+	for _, storage := range cfg.Storages {
 		fmt.Printf("  - %s (%s)\n", storage.GetName(), storage.GetType())
 	}
 
-	if Cfg.Workers < 1 || Cfg.Retry < 1 {
-		return errors.New(i18n.TWithoutInit(Cfg.Lang, i18nk.ConfigInvalidWorkersOrRetry, map[string]any{
-			"Workers": Cfg.Workers,
-			"Retry":   Cfg.Retry,
+	if cfg.Workers < 1 || cfg.Retry < 1 {
+		return errors.New(i18n.TWithoutInit(cfg.Lang, i18nk.ConfigInvalidWorkersOrRetry, map[string]any{
+			"Workers": cfg.Workers,
+			"Retry":   cfg.Retry,
 		}))
 	}
 
-	for _, storage := range Cfg.Storages {
+	for _, storage := range cfg.Storages {
 		storages = append(storages, storage.GetName())
 	}
-	for _, user := range Cfg.Users {
+	for _, user := range cfg.Users {
 		userIDs = append(userIDs, user.ID)
 		if user.Blacklist {
 			userStorages[user.ID] = slice.Compact(slice.Difference(storages, user.Storages))
@@ -142,20 +147,3 @@ func Init(ctx context.Context) error {
 	}
 	return nil
 }
-
-func Set(key string, value any) {
-	viper.Set(key, value)
-}
-
-func ReloadConfig() error {
-	if err := viper.WriteConfig(); err != nil {
-		return err
-	}
-	if err := viper.ReadInConfig(); err != nil {
-		return err
-	}
-	if error := viper.Unmarshal(Cfg); error != nil {
-		return error
-	}
-	return nil
-}

core/core.go

@@ -20,7 +20,7 @@ type Exectable interface {
 
 func worker(ctx context.Context, qe *queue.TaskQueue[Exectable], semaphore chan struct{}) {
 	logger := log.FromContext(ctx)
-	execHooks := config.Cfg.Hook.Exec
+	execHooks := config.C().Hook.Exec
 	for {
 		semaphore <- struct{}{}
 		qtask, err := qe.Get()
@@ -58,11 +58,11 @@ func worker(ctx context.Context, qe *queue.TaskQueue[Exectable], semaphore chan
 
 func Run(ctx context.Context) {
 	log.FromContext(ctx).Info("Start processing tasks...")
-	semaphore := make(chan struct{}, config.Cfg.Workers)
+	semaphore := make(chan struct{}, config.C().Workers)
 	if queueInstance == nil {
 		queueInstance = queue.NewTaskQueue[Exectable]()
 	}
-	for range config.Cfg.Workers {
+	for range config.C().Workers {
 		go worker(ctx, queueInstance, semaphore)
 	}
 

core/tasks/batchtfile/execute.go

@@ -1,4 +1,4 @@
-package batchtftask
+package batchtfile
 
 import (
 	"context"
@@ -21,18 +21,23 @@ func (t *Task) Execute(ctx context.Context) error {
 	logger := log.FromContext(ctx).WithPrefix(fmt.Sprintf("batch_file[%s]", t.ID))
 	logger.Info("Starting batch file task")
 	t.Progress.OnStart(ctx, t)
-	workers := config.Cfg.Workers
+	workers := config.C().Workers
 	eg, gctx := errgroup.WithContext(ctx)
 	eg.SetLimit(workers)
 	for _, elem := range t.Elems {
-		elem := elem
 		eg.Go(func() error {
+			t.processingMu.RLock()
 			if t.processing[elem.ID] != nil {
 				return fmt.Errorf("element with ID %s is already being processed", elem.ID)
 			}
+			t.processingMu.RUnlock()
+			t.processingMu.Lock()
 			t.processing[elem.ID] = &elem
+			t.processingMu.Unlock()
 			defer func() {
+				t.processingMu.Lock()
 				delete(t.processing, elem.ID)
+				t.processingMu.Unlock()
 			}()
 			return t.processElement(gctx, elem)
 		})
@@ -119,6 +124,6 @@ func (t *Task) processElement(ctx context.Context, elem TaskElement) error {
 			return err
 		}
 		return nil
-	}, retry.Context(vctx), retry.RetryTimes(uint(config.Cfg.Retry)))
+	}, retry.Context(vctx), retry.RetryTimes(uint(config.C().Retry)))
 	return err
 }

core/tasks/batchtfile/progress.go

@@ -1,4 +1,4 @@
-package batchtftask
+package batchtfile
 
 import (
 	"context"

core/tasks/batchtfile/task.go

@@ -1,9 +1,10 @@
-package batchtftask
+package batchtfile
 
 import (
 	"context"
 	"fmt"
 	"path/filepath"
+	"sync"
 	"sync/atomic"
 
 	"github.com/krau/SaveAny-Bot/config"
@@ -31,7 +32,8 @@ type Task struct {
 	downloaded   atomic.Int64
 	totalSize    int64
 	processing   map[string]TaskElementInfo
-	failed       map[string]error // errors for each element
+	processingMu sync.RWMutex
+	failed       map[string]error // [TODO] errors for each element
 }
 
 func (t *Task) Type() tasktype.TaskType {
@@ -45,8 +47,8 @@ func NewTaskElement(
 ) (*TaskElement, error) {
 	id := xid.New().String()
 	_, ok := stor.(storage.StorageCannotStream)
-	if !config.Cfg.Stream || ok {
-		cachePath, err := filepath.Abs(filepath.Join(config.Cfg.Temp.BasePath, fmt.Sprintf("%s_%s", id, file.Name())))
+	if !config.C().Stream || ok {
+		cachePath, err := filepath.Abs(filepath.Join(config.C().Temp.BasePath, fmt.Sprintf("%s_%s", id, file.Name())))
 		if err != nil {
 			return nil, fmt.Errorf("failed to get absolute path for cache: %w", err)
 		}
@@ -89,6 +91,7 @@ func NewBatchTGFileTask(
 		}(),
 		processing:   make(map[string]TaskElementInfo),
 		IgnoreErrors: ignoreErrors,
+		processingMu: sync.RWMutex{},
 		failed:       make(map[string]error),
 	}
 	return task

core/tasks/batchtfile/taskinfo.go

@@ -1,4 +1,4 @@
-package batchtftask
+package batchtfile
 
 type TaskElementInfo interface {
 	FileName() string

core/tasks/batchtfile/utils.go

@@ -1,4 +1,4 @@
-package batchtftask
+package batchtfile
 
 var progressUpdatesLevels = []struct {
 	size        int64 // 文件大小阈值

core/tasks/parsed/execute.go

@@ -0,0 +1,139 @@
+package parsed
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"path"
+	"path/filepath"
+
+	"github.com/charmbracelet/log"
+	"github.com/duke-git/lancet/v2/retry"
+	"github.com/krau/SaveAny-Bot/common/utils/fsutil"
+	"github.com/krau/SaveAny-Bot/common/utils/ioutil"
+	"github.com/krau/SaveAny-Bot/config"
+	"github.com/krau/SaveAny-Bot/pkg/enums/ctxkey"
+	"github.com/krau/SaveAny-Bot/pkg/parser"
+	"golang.org/x/sync/errgroup"
+)
+
+func (t *Task) Execute(ctx context.Context) error {
+	logger := log.FromContext(ctx)
+	logger.Infof("Starting Parsed item task %s", t.item.Title)
+	if t.progress != nil {
+		t.progress.OnStart(ctx, t)
+	}
+	eg, gctx := errgroup.WithContext(ctx)
+	eg.SetLimit(config.C().Workers)
+	for _, resource := range t.item.Resources {
+		eg.Go(func() error {
+			t.processingMu.RLock()
+			if t.processing[resource.ID()] != nil {
+				return fmt.Errorf("resource %s is already being processed", resource.ID())
+			}
+			t.processingMu.RUnlock()
+			t.processingMu.Lock()
+			t.processing[resource.ID()] = &resource
+			t.processingMu.Unlock()
+			defer func() {
+				t.processingMu.Lock()
+				delete(t.processing, resource.URL)
+				t.processingMu.Unlock()
+			}()
+			err := t.processResource(gctx, resource)
+			t.downloaded.Add(1)
+			if errors.Is(err, context.Canceled) {
+				logger.Debug("Resource processing canceled")
+				return err
+			}
+			if err != nil {
+				logger.Errorf("Error processing resource %s: %v", resource.URL, err)
+				return fmt.Errorf("failed to process resource %s: %w", resource.URL, err)
+			}
+			return nil
+		})
+	}
+	err := eg.Wait()
+	if err != nil {
+		logger.Errorf("Error during Parsed item task execution: %v", err)
+	} else {
+		logger.Infof("Parsed item task %s completed successfully", t.item.Title)
+	}
+	if t.progress != nil {
+		t.progress.OnDone(ctx, t, err)
+	}
+	return err
+}
+
+func (t *Task) processResource(ctx context.Context, resource parser.Resource) error {
+	logger := log.FromContext(ctx)
+	err := retry.Retry(func() error {
+		req, err := http.NewRequestWithContext(ctx, http.MethodGet, resource.URL, nil)
+		if err != nil {
+			return err
+		}
+		if resource.Headers != nil {
+			for k, v := range resource.Headers {
+				req.Header.Set(k, v)
+			}
+		}
+		resp, err := t.httpClient.Do(req)
+		if err != nil {
+			return fmt.Errorf("failed to download resource %s: %w", resource.URL, err)
+		}
+		defer resp.Body.Close()
+		if resp.StatusCode != http.StatusOK {
+			return fmt.Errorf("failed to download resource %s: %s", resource.URL, resp.Status)
+		}
+		ctx = context.WithValue(ctx, ctxkey.ContentLength, func() int64 {
+			if resource.Size > 0 {
+				return resource.Size
+			}
+			return resp.ContentLength
+		}())
+		if t.stream {
+			return t.Stor.Save(ctx, resp.Body, path.Join(t.StorPath, resource.Filename))
+		}
+		cacheFile, err := fsutil.CreateFile(filepath.Join(config.C().Temp.BasePath,
+			fmt.Sprintf("resource_%s_%s", t.ID, resource.Filename)))
+		if err != nil {
+			return fmt.Errorf("failed to create cache file for resource %s: %w", resource.URL, err)
+		}
+		defer func() {
+			if err := cacheFile.CloseAndRemove(); err != nil {
+				logger.Errorf("Failed to close and remove cache file: %v", err)
+			}
+		}()
+		wr := ioutil.NewProgressWriter(cacheFile, func(n int) {
+			t.downloadedBytes.Add(int64(n))
+			if t.progress != nil {
+				t.progress.OnProgress(ctx, t)
+			}
+		})
+
+		copyResultCh := make(chan error, 1)
+		go func() {
+			_, err := io.Copy(wr, resp.Body)
+			copyResultCh <- err
+		}()
+		select {
+		case err := <-copyResultCh:
+			if err != nil {
+				return fmt.Errorf("failed to copy resource %s to cache file: %w", resource.URL, err)
+			}
+		case <-ctx.Done():
+			return ctx.Err()
+		}
+		_, err = cacheFile.Seek(0, 0)
+		if err != nil {
+			return fmt.Errorf("failed to seek cache file for resource %s: %w", resource.URL, err)
+		}
+		return t.Stor.Save(ctx, cacheFile, path.Join(t.StorPath, resource.Filename))
+	}, retry.Context(ctx), retry.RetryTimes(uint(config.C().Retry)))
+	if ctx.Err() != nil {
+		return ctx.Err()
+	}
+	return err
+}

core/tasks/parsed/progress.go

@@ -0,0 +1,209 @@
+package parsed
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"sync/atomic"
+	"time"
+
+	"github.com/charmbracelet/log"
+	"github.com/duke-git/lancet/v2/slice"
+	"github.com/gotd/td/telegram/message/entity"
+	"github.com/gotd/td/telegram/message/styling"
+	"github.com/gotd/td/tg"
+	"github.com/krau/SaveAny-Bot/common/utils/dlutil"
+	"github.com/krau/SaveAny-Bot/common/utils/tgutil"
+)
+
+var progressUpdatesLevels = []struct {
+	size        int64 // 文件大小阈值
+	stepPercent int   // 每多少 % 更新一次
+}{
+	{10 << 20, 100},
+	{50 << 20, 50},
+	{200 << 20, 20},
+	{500 << 20, 10},
+}
+
+func shouldUpdateProgress(total, downloaded int64, lastUpdatePercent int) bool {
+	if total <= 0 || downloaded <= 0 {
+		return false
+	}
+
+	percent := int((downloaded * 100) / total)
+	if percent <= lastUpdatePercent {
+		return false
+	}
+
+	step := progressUpdatesLevels[len(progressUpdatesLevels)-1].stepPercent
+	for _, lvl := range progressUpdatesLevels {
+		if total < lvl.size {
+			step = lvl.stepPercent
+			break
+		}
+	}
+
+	return percent >= lastUpdatePercent+step
+}
+
+type ProgressTracker interface {
+	OnStart(ctx context.Context, info TaskInfo)
+	OnProgress(ctx context.Context, info TaskInfo)
+	OnDone(ctx context.Context, info TaskInfo, err error)
+}
+
+type Progress struct {
+	MessageID         int
+	ChatID            int64
+	start             time.Time
+	lastUpdatePercent atomic.Int32
+}
+
+func (p *Progress) OnStart(ctx context.Context, info TaskInfo) {
+	logger := log.FromContext(ctx)
+	p.start = time.Now()
+	p.lastUpdatePercent.Store(0)
+	logger.Debugf("Parsed task progress tracking started for message %d in chat %d", p.MessageID, p.ChatID)
+	entityBuilder := entity.Builder{}
+	var entities []tg.MessageEntityClass
+	if err := styling.Perform(&entityBuilder,
+		styling.Plain(fmt.Sprintf("开始下载 %s 的资源\n总大小: ", info.Site())),
+		styling.Code(fmt.Sprintf("%.2f MB (%d个资源)", float64(info.TotalBytes())/(1024*1024), info.TotalResources())),
+	); err != nil {
+		log.FromContext(ctx).Errorf("Failed to build entities: %s", err)
+		return
+	}
+	text, entities := entityBuilder.Complete()
+	req := &tg.MessagesEditMessageRequest{
+		ID: p.MessageID,
+	}
+	req.SetMessage(text)
+	req.SetEntities(entities)
+	req.SetReplyMarkup(&tg.ReplyInlineMarkup{
+		Rows: []tg.KeyboardButtonRow{
+			{
+				Buttons: []tg.KeyboardButtonClass{
+					tgutil.BuildCancelButton(info.TaskID()),
+				},
+			},
+		}},
+	)
+	ext := tgutil.ExtFromContext(ctx)
+	if ext != nil {
+		ext.EditMessage(p.ChatID, req)
+		return
+	}
+}
+
+func (p *Progress) OnProgress(ctx context.Context, info TaskInfo) {
+	if !shouldUpdateProgress(info.TotalBytes(), info.DownloadedBytes(), int(p.lastUpdatePercent.Load())) {
+		return
+	}
+	percent := int((info.DownloadedBytes() * 100) / info.TotalBytes())
+	if p.lastUpdatePercent.Load() == int32(percent) {
+		return
+	}
+	p.lastUpdatePercent.Store(int32(percent))
+	log.FromContext(ctx).Debugf("Progress update: %s, %d/%d", info.TaskID(), info.DownloadedBytes(), info.TotalBytes())
+	entityBuilder := entity.Builder{}
+	var entities []tg.MessageEntityClass
+	if err := styling.Perform(&entityBuilder,
+		styling.Plain("正在下载\n总大小: "),
+		styling.Code(fmt.Sprintf("%.2f MB (%d个文件)", float64(info.TotalBytes())/(1024*1024), info.TotalResources())),
+		styling.Plain("\n正在处理:\n"),
+		func() styling.StyledTextOption {
+			var lines []string
+			for _, elem := range info.Processing() {
+				lines = append(lines, fmt.Sprintf("  - %s (%.2f MB)", elem.FileName(), float64(elem.FileSize())/(1024*1024)))
+			}
+			if len(lines) == 0 {
+				lines = append(lines, "  - 无")
+			}
+			return styling.Plain(slice.Join(lines, "\n"))
+		}(),
+		styling.Plain("\n平均速度: "),
+		styling.Bold(fmt.Sprintf("%.2f MB/s", dlutil.GetSpeed(info.DownloadedBytes(), p.start)/(1024*1024))),
+		styling.Plain("\n当前进度: "),
+		styling.Bold(fmt.Sprintf("%.2f%%", float64(info.DownloadedBytes())/float64(info.TotalBytes())*100)),
+	); err != nil {
+		log.FromContext(ctx).Errorf("Failed to build entities: %s", err)
+		return
+	}
+	text, entities := entityBuilder.Complete()
+	req := &tg.MessagesEditMessageRequest{
+		ID: p.MessageID,
+	}
+	req.SetMessage(text)
+	req.SetEntities(entities)
+	req.SetReplyMarkup(&tg.ReplyInlineMarkup{
+		Rows: []tg.KeyboardButtonRow{
+			{
+				Buttons: []tg.KeyboardButtonClass{
+					tgutil.BuildCancelButton(info.TaskID()),
+				},
+			},
+		}},
+	)
+	ext := tgutil.ExtFromContext(ctx)
+	if ext != nil {
+		ext.EditMessage(p.ChatID, req)
+		return
+	}
+}
+
+func (p *Progress) OnDone(ctx context.Context, info TaskInfo, err error) {
+	logger := log.FromContext(ctx)
+	if err != nil {
+		if errors.Is(err, context.Canceled) {
+			logger.Infof("Parsed task %s was canceled", info.TaskID())
+			ext := tgutil.ExtFromContext(ctx)
+			if ext != nil {
+				ext.EditMessage(p.ChatID, &tg.MessagesEditMessageRequest{
+					ID:      p.MessageID,
+					Message: fmt.Sprintf("处理已取消: %s", info.TaskID()),
+				})
+			}
+		} else {
+			logger.Errorf("Parsed task %s failed: %s", info.TaskID(), err)
+			ext := tgutil.ExtFromContext(ctx)
+			if ext != nil {
+				ext.EditMessage(p.ChatID, &tg.MessagesEditMessageRequest{
+					ID:      p.MessageID,
+					Message: fmt.Sprintf("处理失败: %s", err.Error()),
+				})
+			}
+		}
+		return
+	}
+	logger.Infof("Parsed task %s completed successfully", info.TaskID())
+
+	entityBuilder := entity.Builder{}
+	if err := styling.Perform(&entityBuilder,
+		styling.Plain("处理完成, 资源数量: "),
+		styling.Code(fmt.Sprintf("%d", info.TotalResources())),
+		styling.Plain("\n保存路径: "),
+		styling.Code(fmt.Sprintf("[%s]:%s", info.StorageName(), info.StoragePath())),
+	); err != nil {
+		logger.Errorf("Failed to build entities: %s", err)
+		return
+	}
+	text, entities := entityBuilder.Complete()
+	req := &tg.MessagesEditMessageRequest{
+		ID: p.MessageID,
+	}
+	req.SetMessage(text)
+	req.SetEntities(entities)
+
+	ext := tgutil.ExtFromContext(ctx)
+	if ext != nil {
+		ext.EditMessage(p.ChatID, req)
+	}
+}
+
+func NewProgress(messageID int, chatID int64) *Progress {
+	return &Progress{
+		MessageID: messageID,
+		ChatID:    chatID,
+	}
+}

core/tasks/parsed/task.go

@@ -0,0 +1,84 @@
+package parsed
+
+import (
+	"context"
+	"net/http"
+	"sync"
+	"sync/atomic"
+
+	"github.com/krau/SaveAny-Bot/config"
+	"github.com/krau/SaveAny-Bot/pkg/enums/tasktype"
+	"github.com/krau/SaveAny-Bot/pkg/parser"
+	"github.com/krau/SaveAny-Bot/storage"
+)
+
+type Task struct {
+	ID         string
+	Ctx        context.Context
+	Stor       storage.Storage
+	StorPath   string
+	item       *parser.Item
+	httpClient *http.Client
+	progress   ProgressTracker
+	stream     bool
+
+	totalResources  int64
+	downloaded      atomic.Int64 // downloaded resources count
+	totalBytes      int64        // total bytes to download
+	downloadedBytes atomic.Int64 // downloaded bytes count
+	processing      map[string]ResourceInfo
+	processingMu    sync.RWMutex
+	failed          map[string]error // [TODO] errors for each resource
+}
+
+func (t *Task) Type() tasktype.TaskType {
+	return tasktype.TaskTypeParseditem
+}
+
+func (t *Task) TaskID() string {
+	return t.ID
+}
+
+func NewTask(
+	id string,
+	ctx context.Context,
+	stor storage.Storage,
+	storPath string,
+	item *parser.Item,
+	progressTracker ProgressTracker,
+) *Task {
+	client := &http.Client{
+		Transport: &http.Transport{
+			// [TODO] configure it via config
+			Proxy: http.ProxyFromEnvironment,
+		},
+	}
+	_, ok := stor.(storage.StorageCannotStream)
+	stream := config.C().Stream && !ok
+	return &Task{
+		ID:             id,
+		Ctx:            ctx,
+		Stor:           stor,
+		StorPath:       storPath,
+		item:           item,
+		totalResources: int64(len(item.Resources)),
+		downloaded:     atomic.Int64{},
+		totalBytes: func() int64 {
+			var total int64
+			for _, res := range item.Resources {
+				if res.Size < 0 {
+					continue // skip resources with unknown size
+				}
+				total += res.Size
+			}
+			return total
+		}(),
+		stream:          stream,
+		downloadedBytes: atomic.Int64{},
+		httpClient:      client,
+		progress:        progressTracker,
+		processing:      make(map[string]ResourceInfo),
+		processingMu:    sync.RWMutex{},
+		failed:          make(map[string]error),
+	}
+}

core/tasks/parsed/taskinfo.go

@@ -0,0 +1,51 @@
+package parsed
+
+type TaskInfo interface {
+	TaskID() string
+	Site() string
+	TotalResources() int64
+	Downloaded() int64
+	TotalBytes() int64
+	DownloadedBytes() int64
+	Processing() map[string]ResourceInfo
+	StorageName() string
+	StoragePath() string
+}
+
+func (t *Task) StoragePath() string {
+	return t.StorPath
+}
+func (t *Task) TotalResources() int64 {
+	return t.totalResources
+}
+
+func (t *Task) Downloaded() int64 {
+	return t.downloaded.Load()
+}
+
+func (t *Task) StorageName() string {
+	return t.Stor.Name()
+}
+
+func (t *Task) Site() string {
+	return t.item.Site
+}
+
+func (t *Task) TotalBytes() int64 {
+	return t.totalBytes
+}
+
+func (t *Task) DownloadedBytes() int64 {
+	return t.downloadedBytes.Load()
+}
+
+func (t *Task) Processing() map[string]ResourceInfo {
+	t.processingMu.RLock()
+	defer t.processingMu.RUnlock()
+	return t.processing
+}
+
+type ResourceInfo interface {
+	FileName() string
+	FileSize() int64
+}

core/tasks/telegraph/execute.go

@@ -1,4 +1,4 @@
-package tphtask
+package telegraph
 
 import (
 	"context"
@@ -20,10 +20,8 @@ func (t *Task) Execute(ctx context.Context) error {
 	logger.Infof("Starting Telegraph task %s", t.PhPath)
 	t.progress.OnStart(ctx, t)
 	eg, gctx := errgroup.WithContext(ctx)
-	eg.SetLimit(config.Cfg.Workers)
+	eg.SetLimit(config.C().Workers)
 	for i, pic := range t.Pics {
-		pic := pic
-		i := i
 		eg.Go(func() error {
 			err := t.processPic(gctx, pic, i)
 			if err != nil {
@@ -48,7 +46,7 @@ func (t *Task) Execute(ctx context.Context) error {
 func (t *Task) processPic(ctx context.Context, picUrl string, index int) error {
 	retryOpts := []retry.Option{
 		retry.Context(ctx),
-		retry.RetryTimes(uint(config.Cfg.Retry)),
+		retry.RetryTimes(uint(config.C().Retry)),
 	}
 	var lastErr error
 	err := retry.Retry(func() error {
@@ -61,7 +59,7 @@ func (t *Task) processPic(ctx context.Context, picUrl string, index int) error {
 		defer body.Close()
 		filename := fmt.Sprintf("%d%s", index+1, path.Ext(picUrl))
 		if t.cannotStream {
-			cacheFile, err := fsutil.CreateFile(filepath.Join(config.Cfg.Temp.BasePath,
+			cacheFile, err := fsutil.CreateFile(filepath.Join(config.C().Temp.BasePath,
 				fmt.Sprintf("tph_%s_%s", t.TaskID(), filename),
 			))
 			if err != nil {
@@ -79,6 +77,11 @@ func (t *Task) processPic(ctx context.Context, picUrl string, index int) error {
 				lastErr = fmt.Errorf("failed to copy picture %s to cache file: %w", filename, lastErr)
 				return lastErr
 			}
+			_, err = cacheFile.Seek(0, 0)
+			if err != nil {
+				lastErr = fmt.Errorf("failed to seek cache file for picture %s: %w", filename, err)
+				return lastErr
+			}
 			lastErr = t.Stor.Save(ctx, cacheFile, path.Join(t.StorPath, filename))
 		} else {
 			lastErr = t.Stor.Save(ctx, body, path.Join(t.StorPath, filename))

core/tasks/telegraph/progress.go

@@ -1,4 +1,4 @@
-package tphtask
+package telegraph
 
 import (
 	"context"

core/tasks/telegraph/task.go

@@ -1,4 +1,4 @@
-package tphtask
+package telegraph
 
 import (
 	"context"
@@ -39,7 +39,7 @@ func NewTask(
 	progress ProgressTracker,
 ) *Task {
 	_, cannotStream := stor.(storage.StorageCannotStream)
-	tphtask := &Task{
+	telegraph := &Task{
 		ID:           id,
 		Ctx:          ctx,
 		PhPath:       phPath,
@@ -52,5 +52,5 @@ func NewTask(
 		totalpics:    len(pics),
 		downloaded:   atomic.Int64{},
 	}
-	return tphtask
+	return telegraph
 }

core/tasks/telegraph/taskinfo.go

@@ -1,4 +1,4 @@
-package tphtask
+package telegraph
 
 type TaskInfo interface {
 	TaskID() string

core/tasks/telegraph/utils.go

@@ -1,4 +1,4 @@
-package tphtask
+package telegraph
 
 func shouldUpdateProgress(downloaded int64, total int64) bool {
 	if total <= 0 || downloaded <= 0 {

core/tasks/tfile/execute.go

@@ -1,4 +1,4 @@
-package tftask
+package tfile
 
 import (
 	"context"
@@ -57,7 +57,7 @@ func (t *Task) Execute(ctx context.Context) error {
 		return fmt.Errorf("failed to get file stat: %w", err)
 	}
 	vctx := context.WithValue(ctx, ctxkey.ContentLength, fileStat.Size())
-	for i := range config.Cfg.Retry + 1 {
+	for i := range config.C().Retry + 1 {
 		if err = vctx.Err(); err != nil {
 			return fmt.Errorf("context canceled while saving file: %w", err)
 		}
@@ -68,7 +68,7 @@ func (t *Task) Execute(ctx context.Context) error {
 		}
 		defer file.Close()
 		if err = t.Storage.Save(vctx, file, t.Path); err != nil {
-			if i == config.Cfg.Retry {
+			if i == config.C().Retry {
 				return fmt.Errorf("failed to save file: %w", err)
 			}
 			logger.Errorf("Failed to save file: %s, retrying...", err)

core/tasks/tfile/progress.go

@@ -1,4 +1,4 @@
-package tftask
+package tfile
 
 import (
 	"context"

core/tasks/tfile/stream.go

@@ -1,4 +1,4 @@
-package tftask
+package tfile
 
 import (
 	"context"

core/tasks/tfile/taskinfo.go

@@ -1,4 +1,4 @@
-package tftask
+package tfile
 
 type TaskInfo interface {
 	TaskID() string

core/tasks/tfile/tftask.go

@@ -1,4 +1,4 @@
-package tftask
+package tfile
 
 import (
 	"context"
@@ -35,12 +35,12 @@ func NewTGFileTask(
 	progress ProgressTracker,
 ) (*Task, error) {
 	_, ok := stor.(storage.StorageCannotStream)
-	if !config.Cfg.Stream || ok {
-		cachePath, err := filepath.Abs(filepath.Join(config.Cfg.Temp.BasePath, fmt.Sprintf("%s_%s", id, file.Name())))
+	if !config.C().Stream || ok {
+		cachePath, err := filepath.Abs(filepath.Join(config.C().Temp.BasePath, fmt.Sprintf("%s_%s", id, file.Name())))
 		if err != nil {
 			return nil, fmt.Errorf("failed to get absolute path for cache: %w", err)
 		}
-		tftask := &Task{
+		tfile := &Task{
 			ID:        id,
 			Ctx:       ctx,
 			File:      file,
@@ -49,7 +49,7 @@ func NewTGFileTask(
 			Progress:  progress,
 			localPath: cachePath,
 		}
-		return tftask, nil
+		return tfile, nil
 	}
 	tfileTask := &Task{
 		ID:       id,

core/tasks/tfile/util.go

@@ -1,4 +1,4 @@
-package tftask
+package tfile
 
 var progressUpdatesLevels = []struct {
 	size        int64 // 文件大小阈值

core/tasks/tfile/writer.go

@@ -1,4 +1,4 @@
-package tftask
+package tfile
 
 import (
 	"context"

database/db.go

@@ -19,11 +19,11 @@ var db *gorm.DB
 
 func Init(ctx context.Context) {
 	logger := log.FromContext(ctx)
-	if err := os.MkdirAll(filepath.Dir(config.Cfg.DB.Path), 0755); err != nil {
+	if err := os.MkdirAll(filepath.Dir(config.C().DB.Path), 0755); err != nil {
 		logger.Fatal("Failed to create data directory: ", err)
 	}
 	var err error
-	db, err = gorm.Open(gormlite.Open(config.Cfg.DB.Path), &gorm.Config{
+	db, err = gorm.Open(gormlite.Open(config.C().DB.Path), &gorm.Config{
 		Logger: glogger.New(logger, glogger.Config{
 			Colorful:                  true,
 			SlowThreshold:             time.Second * 5,
@@ -60,7 +60,7 @@ func syncUsers(ctx context.Context) error {
 	}
 
 	cfgUserMap := make(map[int64]struct{})
-	for _, u := range config.Cfg.Users {
+	for _, u := range config.C().Users {
 		cfgUserMap[u.ID] = struct{}{}
 	}
 

database/model.go

@@ -6,13 +6,14 @@ import (
 
 type User struct {
 	gorm.Model
-	ChatID         int64 `gorm:"uniqueIndex;not null"`
-	Silent         bool
-	DefaultStorage string
-	Dirs           []Dir
-	ApplyRule      bool
-	Rules          []Rule
-	WatchChats     []WatchChat
+	ChatID           int64 `gorm:"uniqueIndex;not null"`
+	Silent           bool
+	DefaultStorage   string
+	Dirs             []Dir
+	ApplyRule        bool
+	Rules            []Rule
+	WatchChats       []WatchChat
+	FilenameStrategy string
 }
 
 type WatchChat struct {

docs/content/zh/_index.md

@@ -11,20 +11,22 @@ title: 介绍
 
 把 Telegram 上的文件转存到多种存储端.
 
-## 特性
+## 🎯 特性
 
-- 支持文档/视频/图片/贴纸... 甚至还有 Telegraph
+- 支持文档/视频/图片/贴纸…甚至还有 [Telegraph](https://telegra.ph/)
 - 破解禁止保存的文件
 - 批量下载
 - 流式传输
-- 多用户
+- 多用户使用
 - 基于存储规则的自动整理
-- 支持多种存储端:
-    - Alist
-    - Minio (S3 兼容)
-    - WebDAV
-    - Telegram (重传回指定聊天)
-    - 本地磁盘
+- 监听并自动转存指定聊天的消息, 支持过滤
+- 使用 js 编写解析器插件以转存任意网站的文件
+- 存储端支持:
+  - Alist
+  - S3 (MinioSDK)
+  - WebDAV
+  - 本地磁盘
+  - Telegram (重传回指定聊天)
 
 ## [贡献者](https://github.com/krau/SaveAny-Bot/graphs/contributors)
 

docs/content/zh/contribute/_index.md

@@ -5,10 +5,30 @@ weight: 20
 
 # 参与开发
 
+在开始之前, 请 Fork 本项目, 并克隆到本地, 并确保 Go 版本 >= 1.23. 
+
+以下是一些贡献代码的指南或建议, 你不必完全遵守, 但将有助于快速 review 并合并你的提交:
+
+- **新功能请先提交 Issue**, 以便讨论设计和实现细节, 并避免因与项目设计不符而被拒绝.
+- **使用现代开发工具**, 确保提交前格式化代码, 并保持风格一致.
+- **使用[语义化提交](https://www.conventionalcommits.org/zh-hans/v1.0.0/)**, 避免提交消息模糊或过于简单.
+
 ## 贡献新存储端
 
-1. Fork 本项目, 克隆到本地
-2. 在 `pkg/enums/storage/storages.go` 中添加新的存储端类型, 并运行代码生成
-3. 在 `config/storage` 目录下定义存储端配置, 并添加到 `config/storage/factory.go` 中
-4. 在 `storage` 目录下新建一个包, 编写存储端实现, 然后在 `storage/storage.go` 中导入并添加它
-5. 更新文档, 添加配置说明
+1. 在 `pkg/enums/storage/storages.go` 中添加新的存储端类型, 并运行代码生成
+2. 在 `config/storage` 目录下定义存储端配置, 并添加到 `config/storage/factory.go` 中
+3. 在 `storage` 目录下新建一个包, 编写存储端实现, 然后在 `storage/storage.go` 中导入并添加它
+4. 更新文档, 添加配置说明
+
+## 贡献新解析器
+
+你可以选择使用 Go 编写原生的解析器实现(推荐), 或是使用 JavaScript 以插件的方式实现.
+
+如果使用 Go 编写, 请:
+
+1. 在 `parsers` 目录下新建一个包, 编写解析器实现
+2. 在 `parsers/parser.go` 的 `init` 中注册解析器
+
+如果使用 JavaScript 编写, 请参考 `plugins/example_parser.js` 的实现, 并在该文件夹下新建一个 js 文件, 实现你的解析逻辑.
+
+需要注意, `plugins` 目录下解析器默认不会被编译到二进制文件中, 用户需要手动下载它们并放到本地指定目录下以启用它们.

docs/content/zh/deployment/configuration/_index.md

@@ -164,6 +164,18 @@ task_fail = "curl -X POST https://example.com/api/notify -d '任务失败'"
 task_cancel = "bash /path/to/cancel_script.sh"
 ```
 
+### 解析器
+
+解析器为 Bot 提供了处理非 Telegram 文件的能力, 例如从其他网站下载文件. 使用 `[parsers]` 配置.
+
+```toml
+[parsers]
+plugin_enable = true # 是否启用解析器插件
+plugin_dirs = ["./plugins"] # 插件目录, 可以是多个目录
+```
+
+上述两个配置项只用于控制以 JavaScript 编写的解析器插件, Bot 还有内置的使用 Go 实现的解析器, 目前默认开启.
+
 ### 杂项
 
 ```toml

docs/content/zh/usage/_index.md

@@ -9,12 +9,11 @@ weight: 10
 
 ## 转存文件
 
-Bot 接受两种消息: 文件和链接.
+要使用 Bot 的转存 Telegram 文件功能, 需要向 Bot 发送或转发以下类型的消息.
 
-对于链接, 目前支持以下类型的链接:
-
-1. Telegram 消息链接, 例如: `https://t.me/acherkrau/1097`. **即使频道禁止了转发和保存, Bot 依然可以下载其文件.**
-2. Telegra.ph 的文章链接, Bot 将下载其中的所有图片
+1. 文件或媒体消息, 如图片, 视频, 文档等
+2. Telegram 消息链接, 例如: `https://t.me/acherkrau/1097`. **即使频道禁止了转发和保存, Bot 依然可以下载其文件.**
+3. Telegra.ph 的文章链接, Bot 将下载其中的所有图片
 
 ## 静默模式 (silent)
 
@@ -112,3 +111,13 @@ IS-ALBUM true MyWebdav NEW-FOR-ALBUM
 ```
 
 这将会监听 ID 为 12345678 的聊天, 并且只保存消息文本中包含 "hello" 的消息.
+
+## 转存 Telegram 之外的文件
+
+除了 Telegram 上的文件, Bot 还可通过 JavaScript 插件或内置解析器来支持转存其他网站的文件.
+
+> 查看[贡献解析器](../contribute)文档了解详情
+
+只需向 Bot 发送符合解析器要求的链接即可使用, 当前内置的解析器:
+
+- Twitter

go.mod

@@ -10,7 +10,6 @@ require (
 	github.com/charmbracelet/log v0.4.2
 	github.com/fatih/color v1.18.0
 	github.com/gabriel-vasile/mimetype v1.4.9
-	github.com/go-faster/errors v0.7.1
 	github.com/gotd/contrib v0.21.0
 	github.com/gotd/td v0.129.0
 	github.com/minio/minio-go/v7 v7.0.95
@@ -42,15 +41,18 @@ require (
 	github.com/erikgeiser/coninput v0.0.0-20211004153227-1c3628e74d0f // indirect
 	github.com/ghodss/yaml v1.0.0 // indirect
 	github.com/glebarez/go-sqlite v1.22.0 // indirect
+	github.com/go-faster/errors v0.7.1 // indirect
 	github.com/go-faster/jx v1.1.0 // indirect
 	github.com/go-faster/xor v1.0.0 // indirect
 	github.com/go-faster/yaml v0.4.6 // indirect
 	github.com/go-ini/ini v1.67.0 // indirect
 	github.com/go-logfmt/logfmt v0.6.0 // indirect
+	github.com/go-sourcemap/sourcemap v2.1.3+incompatible // indirect
 	github.com/go-viper/mapstructure/v2 v2.4.0 // indirect
 	github.com/goccy/go-json v0.10.5 // indirect
 	github.com/google/go-github/v30 v30.1.0 // indirect
 	github.com/google/go-querystring v1.1.0 // indirect
+	github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e // indirect
 	github.com/google/uuid v1.6.0 // indirect
 	github.com/gotd/ige v0.2.2 // indirect
 	github.com/gotd/neo v0.1.5 // indirect
@@ -102,6 +104,7 @@ require (
 
 require (
 	github.com/dgraph-io/ristretto/v2 v2.2.0
+	github.com/dop251/goja v0.0.0-20250630131328-58d95d85e994
 	github.com/duke-git/lancet/v2 v2.3.7
 	github.com/fsnotify/fsnotify v1.9.0 // indirect
 	github.com/glebarez/sqlite v1.11.0 // indirect
@@ -128,4 +131,4 @@ require (
 	gorm.io/gorm v1.30.1
 )
 
-replace github.com/celestix/gotgproto v1.0.0-beta21 => github.com/krau/gotgproto v0.0.0-20250730080659-caaadb4b1f35
+replace github.com/celestix/gotgproto v1.0.0-beta21 => github.com/krau/gotgproto v0.0.0-20250815074212-7fbd56c33c00

go.sum

@@ -4,6 +4,8 @@ github.com/BurntSushi/toml v1.5.0 h1:W5quZX/G/csjUnuI8SUYlsHs9M38FC7znL0lIO+DvMg
 github.com/BurntSushi/toml v1.5.0/go.mod h1:ukJfTF/6rtPPRCnwkur4qwRxa8vTRFBF0uk2lLoLwho=
 github.com/MakeNowJust/heredoc v1.0.0 h1:cXCdzVdstXyiTqTvfqk9SDHpKNjxuom+DOlyEeQ4pzQ=
 github.com/MakeNowJust/heredoc v1.0.0/go.mod h1:mG5amYoWBHf8vpLOuehzbGGw0EHxpZZ6lCpQ4fNJ8LE=
+github.com/Masterminds/semver/v3 v3.2.1 h1:RN9w6+7QoMeJVGyfmbcgs28Br8cvmnucEXnY0rYXWg0=
+github.com/Masterminds/semver/v3 v3.2.1/go.mod h1:qvl/7zhW3nngYb5+80sSMF+FG2BjYrf8m9wsX0PNOMQ=
 github.com/atotto/clipboard v0.1.4 h1:EH0zSVneZPSuFR11BlR9YppQTVDbh5+16AmcJi4g1z4=
 github.com/atotto/clipboard v0.1.4/go.mod h1:ZY9tmq7sm5xIbd9bOK4onWV4S6X0u6GY7Vn0Yu86PYI=
 github.com/aymanbagabas/go-osc52/v2 v2.0.1 h1:HwpRHbFMcZLEVr42D4p7XBqjyuxQH5SMiErDT4WkJ2k=
@@ -61,6 +63,8 @@ github.com/dgryski/go-farm v0.0.0-20240924180020-3414d57e47da h1:aIftn67I1fkbMa5
 github.com/dgryski/go-farm v0.0.0-20240924180020-3414d57e47da/go.mod h1:SqUrOPUnsFjfmXRMNPybcSiG0BgUW2AuFH8PAnS2iTw=
 github.com/dlclark/regexp2 v1.11.5 h1:Q/sSnsKerHeCkc/jSTNq1oCm7KiVgUMZRDUoRu0JQZQ=
 github.com/dlclark/regexp2 v1.11.5/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
+github.com/dop251/goja v0.0.0-20250630131328-58d95d85e994 h1:aQYWswi+hRL2zJqGacdCZx32XjKYV8ApXFGntw79XAM=
+github.com/dop251/goja v0.0.0-20250630131328-58d95d85e994/go.mod h1:MxLav0peU43GgvwVgNbLAj1s/bSGboKkhuULvq/7hx4=
 github.com/duke-git/lancet/v2 v2.3.7 h1:nnNBA9KyoqwbPm4nFmEFVIbXeAmpqf6IDCH45+HHHNs=
 github.com/duke-git/lancet/v2 v2.3.7/go.mod h1:zGa2R4xswg6EG9I6WnyubDbFO/+A/RROxIbXcwryTsc=
 github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
@@ -99,6 +103,8 @@ github.com/go-logr/logr v1.4.3 h1:CjnDlHq8ikf6E492q6eKboGOC0T8CDaOvkHCIg8idEI=
 github.com/go-logr/logr v1.4.3/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
 github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
 github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
+github.com/go-sourcemap/sourcemap v2.1.3+incompatible h1:W1iEw64niKVGogNgBN3ePyLFfuisuzeidWPMPWmECqU=
+github.com/go-sourcemap/sourcemap v2.1.3+incompatible/go.mod h1:F8jJfvm2KbVjc5NqelyYJmf/v5J0dwNLS2mL4sNA1Jg=
 github.com/go-viper/mapstructure/v2 v2.4.0 h1:EBsztssimR/CONLSZZ04E8qAkxNYq4Qp9LvH92wZUgs=
 github.com/go-viper/mapstructure/v2 v2.4.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
 github.com/goccy/go-json v0.10.5 h1:Fq85nIqj+gXn/S5ahsiTlK3TmC85qgirsdTP/+DeaC4=
@@ -147,8 +153,8 @@ github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
-github.com/krau/gotgproto v0.0.0-20250730080659-caaadb4b1f35 h1:CVzeQNKRgkXm8DQX5bszxI73RcOVGTOFbMynhgjA2lQ=
-github.com/krau/gotgproto v0.0.0-20250730080659-caaadb4b1f35/go.mod h1:xjZlGA8ABRKkfGMmkHKyz520hK6pMfyE8yxpSTqohME=
+github.com/krau/gotgproto v0.0.0-20250815074212-7fbd56c33c00 h1:Evg8e3u5ZuqkqdwzrmiQZrTiFUas00Pw99hQK9PGX7A=
+github.com/krau/gotgproto v0.0.0-20250815074212-7fbd56c33c00/go.mod h1:xjZlGA8ABRKkfGMmkHKyz520hK6pMfyE8yxpSTqohME=
 github.com/lucasb-eyer/go-colorful v1.2.0 h1:1nnpGOrhyZZuNyfu1QjKiUICQ74+3FNCN69Aj6K7nkY=
 github.com/lucasb-eyer/go-colorful v1.2.0/go.mod h1:R4dSotOR9KMtayYi1e77YzuveK+i7ruzyGqttikkLy0=
 github.com/mattn/go-colorable v0.1.14 h1:9A9LHSqF/7dyVVX6g0U9cwm9pG3kP9gSzcuIPHPsaIE=

parsers/js.go

@@ -0,0 +1,244 @@
+package parsers
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"os"
+	"path/filepath"
+
+	"github.com/blang/semver"
+	"github.com/charmbracelet/log"
+	"github.com/dop251/goja"
+	"github.com/krau/SaveAny-Bot/pkg/parser"
+)
+
+type jsParser struct {
+	meta  PluginMeta
+	vm    *goja.Runtime
+	reqCh chan jsParserReq
+}
+
+type jsParserReq struct {
+	method ParserMethod
+	url    string
+	respCh chan jsParserResp
+}
+
+type jsParserResp struct {
+	item *parser.Item
+	ok   bool
+	err  error
+}
+
+func (p *jsParser) CanHandle(url string) bool {
+	respCh := make(chan jsParserResp, 1)
+	p.reqCh <- jsParserReq{method: ParserMethodCanHandle, url: url, respCh: respCh}
+	resp := <-respCh
+	return resp.ok && resp.err == nil
+}
+
+func (p *jsParser) Parse(ctx context.Context, url string) (*parser.Item, error) {
+	respCh := make(chan jsParserResp, 1)
+	p.reqCh <- jsParserReq{method: ParserMethodParse, url: url, respCh: respCh}
+	select {
+	case resp := <-respCh:
+		return resp.item, resp.err
+	case <-ctx.Done():
+		return nil, ctx.Err()
+	}
+}
+
+func newJSParser(vm *goja.Runtime, canHandleFunc, parseFunc goja.Value, metadata PluginMeta) *jsParser {
+	p := &jsParser{
+		vm:    vm,
+		reqCh: make(chan jsParserReq, 10),
+		meta:  metadata,
+	}
+
+	go func() {
+		for req := range p.reqCh {
+			switch req.method {
+			case ParserMethodCanHandle:
+				fn, _ := goja.AssertFunction(canHandleFunc)
+				res, err := fn(goja.Undefined(), p.vm.ToValue(req.url))
+				if err != nil {
+					req.respCh <- jsParserResp{ok: false, err: err}
+					continue
+				}
+				req.respCh <- jsParserResp{ok: res.ToBoolean()}
+			case ParserMethodParse:
+				fn, _ := goja.AssertFunction(parseFunc)
+				result, err := fn(goja.Undefined(), p.vm.ToValue(req.url))
+				if err != nil {
+					req.respCh <- jsParserResp{err: err}
+					continue
+				}
+
+				var item parser.Item
+				if exported := result.Export(); exported != nil {
+					data, err := json.Marshal(exported)
+					if err != nil {
+						req.respCh <- jsParserResp{err: fmt.Errorf("failed to marshal result to JSON: %w", err)}
+						continue
+					}
+
+					if err := json.Unmarshal(data, &item); err != nil {
+						req.respCh <- jsParserResp{err: fmt.Errorf("failed to unmarshal JSON to Item: %w", err)}
+						continue
+					}
+				} else {
+					req.respCh <- jsParserResp{err: fmt.Errorf("JS function returned null or undefined")}
+					continue
+				}
+				req.respCh <- jsParserResp{item: &item}
+			}
+		}
+	}()
+
+	return p
+}
+
+func registerParser(vm *goja.Runtime) func(call goja.FunctionCall) goja.Value {
+	return func(call goja.FunctionCall) goja.Value {
+		jsObj := call.Argument(0)
+		if jsObj == nil || goja.IsUndefined(jsObj) || goja.IsNull(jsObj) {
+			panic("registerParser expects an object { canHandle, parse }")
+		}
+
+		obj := jsObj.ToObject(vm)
+		if obj == nil {
+			panic("registerParser: cannot convert argument to object")
+		}
+		metaValue := obj.Get("metadata")
+		if metaValue == nil || goja.IsUndefined(metaValue) {
+			panic("parser must provide metadata")
+		}
+		var metadata PluginMeta
+		if exported := metaValue.Export(); exported != nil {
+			data, err := json.Marshal(exported)
+			if err != nil {
+				panic(fmt.Sprintf("failed to marshal metadata to JSON: %v", err))
+			}
+			if err := json.Unmarshal(data, &metadata); err != nil {
+				panic(fmt.Sprintf("failed to unmarshal JSON to PluginMeta: %v", err))
+			}
+		} else {
+			panic("metadata cannot be null or undefined")
+		}
+
+		pluginV := semver.MustParse(metadata.Version)
+		if pluginV.LT(MinimumParserVersion) || pluginV.GT(LatestParserVersion) {
+			panic(fmt.Sprintf("parser version %s is not supported, must be between %s and %s", metadata.Version, MinimumParserVersion, LatestParserVersion))
+		}
+
+		handleFn := obj.Get("canHandle")
+		parseFn := obj.Get("parse")
+		if parseFn == nil || goja.IsUndefined(parseFn) {
+			panic("parser must provide a parse function")
+		}
+
+		parsers = append(parsers, newJSParser(vm, handleFn, parseFn, metadata))
+		return goja.Undefined()
+	}
+}
+
+func LoadPlugins(ctx context.Context, dir string) error {
+	entries, err := os.ReadDir(dir)
+	if err != nil {
+		return err
+	}
+
+	for _, e := range entries {
+		if filepath.Ext(e.Name()) != ".js" {
+			continue
+		}
+		scriptPath := filepath.Join(dir, e.Name())
+		code, err := os.ReadFile(scriptPath)
+		if err != nil {
+			return err
+		}
+
+		vm := goja.New()
+		vm.Set("registerParser", registerParser(vm))
+		// Inject some utils to vm
+		logger := log.FromContext(ctx).WithPrefix(fmt.Sprintf("[plugin|parser]/%s", e.Name()))
+		vm.Set("console", map[string]any{
+			"log": func(args ...any) {
+				if len(args) == 0 {
+					return
+				}
+				if len(args) > 1 {
+					logger.Info(args[0], args[1:]...)
+				} else {
+					logger.Info(args[0])
+				}
+			},
+		})
+		// http fetch funcs
+		ghttp := vm.NewObject()
+		ghttp.Set("get", func(call goja.FunctionCall) goja.Value {
+			url := call.Argument(0).String()
+			resp, err := http.Get(url)
+			if err != nil {
+				return vm.ToValue(map[string]any{
+					"error": fmt.Sprintf("failed to fetch %s: %v", url, err),
+				})
+			}
+			defer resp.Body.Close()
+			if resp.StatusCode != http.StatusOK {
+				return vm.ToValue(map[string]any{
+					"error":  fmt.Sprintf("failed to fetch %s: %s", url, resp.Status),
+					"status": resp.StatusCode,
+				})
+			}
+			body, err := io.ReadAll(resp.Body)
+			if err != nil {
+				return vm.ToValue(map[string]any{
+					"error": fmt.Errorf("failed to read response body: %w", err).Error(),
+				})
+			}
+			return vm.ToValue(string(body))
+		})
+		ghttp.Set("getJSON", func(call goja.FunctionCall) goja.Value {
+			url := call.Argument(0).String()
+
+			resp, err := http.Get(url)
+			if err != nil {
+				return vm.ToValue(map[string]any{
+					"error": fmt.Sprintf("failed to fetch %s: %v", url, err),
+				})
+			}
+			defer resp.Body.Close()
+			if resp.StatusCode != http.StatusOK {
+				return vm.ToValue(map[string]any{
+					"error":  fmt.Sprintf("failed to fetch %s: %s", url, resp.Status),
+					"status": resp.StatusCode,
+				})
+			}
+			body, err := io.ReadAll(resp.Body)
+			if err != nil {
+				return vm.ToValue(map[string]any{
+					"error": fmt.Errorf("failed to read response body: %w", err).Error(),
+				})
+			}
+			var jsonData map[string]any
+			if err := json.Unmarshal(body, &jsonData); err != nil {
+				return vm.ToValue(map[string]any{
+					"error": fmt.Errorf("failed to unmarshal JSON: %w", err).Error(),
+				})
+			}
+			return vm.ToValue(map[string]any{
+				"data": jsonData,
+			})
+		})
+		vm.Set("ghttp", ghttp)
+
+		if _, err := vm.RunString(string(code)); err != nil {
+			return fmt.Errorf("error loading plugin %s: %w", e.Name(), err)
+		}
+	}
+	return nil
+}

parsers/kemono/download.go

@@ -0,0 +1,36 @@
+package kemono
+
+import (
+	"net/url"
+	"strings"
+)
+
+type DownloadInfo struct {
+	ServiceName string
+	UserID      string
+	PostID      string
+}
+
+func extractDownloadInfoFromURL(u string) *DownloadInfo {
+	if !strings.HasPrefix(u, "http://") && !strings.HasPrefix(u, "https://") {
+		u = "https://" + u
+	}
+	url, err := url.Parse(u)
+	if err != nil {
+		return nil
+	}
+	parts := strings.Split(strings.Trim(url.Path, "/"), "/")
+	if len(parts) == 3 {
+		return &DownloadInfo{
+			ServiceName: parts[0],
+			UserID:      parts[2],
+		}
+	} else if len(parts) == 5 && parts[3] == "post" {
+		return &DownloadInfo{
+			ServiceName: parts[0],
+			UserID:      parts[2],
+			PostID:      parts[4],
+		}
+	}
+	return nil
+}

parsers/kemono/kemono.go

@@ -0,0 +1,173 @@
+package kemono
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"net/http"
+	"net/url"
+	"path"
+	"strings"
+
+	"github.com/duke-git/lancet/v2/strutil"
+	"github.com/krau/SaveAny-Bot/common/utils/netutil"
+	"github.com/krau/SaveAny-Bot/pkg/parser"
+)
+
+type KemonoParser struct{}
+
+var (
+	kemonoDomains = []string{
+		"kemono.su",
+		"kemono.cr",
+	}
+	ErrFailedToExtractInfo = errors.New("failed to extract download info from URL")
+)
+
+const (
+	kemonoApiBase = "https://kemono.cr/api/v1"
+)
+
+func (k *KemonoParser) CanHandle(text string) bool {
+	text = strings.TrimPrefix(text, "https://")
+	text = strings.TrimPrefix(text, "http://")
+
+	var matchesDomain bool
+	for _, domain := range kemonoDomains {
+		if strings.Contains(text, domain) {
+			matchesDomain = true
+			break
+		}
+	}
+	if !matchesDomain {
+		return false
+	}
+
+	var path string
+	for _, domain := range kemonoDomains {
+		if idx := strings.Index(text, domain); idx != -1 {
+			remaining := text[idx+len(domain):]
+			if len(remaining) > 0 && remaining[0] == '/' {
+				path = remaining[1:]
+			}
+			break
+		}
+	}
+
+	if path == "" {
+		return false
+	}
+
+	parts := strings.Split(path, "/")
+	// servicename/user/id (user profile page)
+	// servicename/user/id/post/id (post page)
+	return len(parts) == 3 || (len(parts) == 5 && parts[3] == "post")
+}
+
+func (k *KemonoParser) Parse(ctx context.Context, u string) (*parser.Item, error) {
+	info := extractDownloadInfoFromURL(u)
+	if info == nil {
+		return nil, ErrFailedToExtractInfo
+	}
+	if info.PostID != "" {
+		return k.parseOne(ctx, info)
+	}
+	return k.parseUserPage(ctx, info)
+}
+
+func (k *KemonoParser) parseOne(ctx context.Context, info *DownloadInfo) (*parser.Item, error) {
+	client := netutil.DefaultParserHTTPClient()
+	endpoint := fmt.Sprintf("%s/%s/user/%s/post/%s", kemonoApiBase, info.ServiceName, info.UserID, info.PostID)
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create request to Kemono API: %w", err)
+	}
+	req.Header.Set("Accept", "text/css")
+	resp, err := client.Do(req)
+	if err != nil {
+		return nil, fmt.Errorf("failed to fetch Kemono API: %w", err)
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusOK {
+		return nil, fmt.Errorf("failed to fetch Kemono API, status code: %d", resp.StatusCode)
+	}
+	var postInfo PostInfo
+	if err := json.NewDecoder(resp.Body).Decode(&postInfo); err != nil {
+		return nil, fmt.Errorf("failed to decode Kemono API response: %w", err)
+	}
+	item := &parser.Item{
+		Site:        "kemono",
+		Title:       postInfo.Post.Title,
+		URL:         fmt.Sprintf("https://kemono.cr/%s/user/%s/post/%s", info.ServiceName, info.UserID, info.PostID),
+		Author:      postInfo.Post.User, // [TODO] request user profile
+		Description: postInfo.Post.Content,
+		Tags: func() []string {
+			if postInfo.Post.Tags != nil {
+				return *postInfo.Post.Tags
+			}
+			return nil
+		}(),
+	}
+	resources := make([]parser.Resource, 0)
+	for _, attachment := range postInfo.Attachments {
+		if attachment.Server == nil || attachment.Path == nil || attachment.Name == nil {
+			continue
+		}
+		var size int64
+		fileUrl := fmt.Sprintf("%s/data%s", *attachment.Server, *attachment.Path)
+		headReq, err := http.NewRequestWithContext(ctx, http.MethodHead, fileUrl, nil)
+		if err == nil {
+			resp, err := client.Do(headReq)
+			if err == nil {
+				size = resp.ContentLength
+				resp.Body.Close()
+			}
+		}
+		resources = append(resources, parser.Resource{
+			URL:      fmt.Sprintf("%s/data%s", *attachment.Server, *attachment.Path),
+			Filename: *attachment.Name,
+			Size:     size,
+		})
+	}
+	picCdnMap := make(map[string]string)
+	for _, preview := range postInfo.Previews {
+		if preview.Type == nil || *preview.Type != "thumbnail" {
+			continue
+		}
+		picCdnMap[*preview.Path] = *preview.Server
+	}
+	for _, attachment := range postInfo.Post.Attachments {
+		if !isImageExt(*attachment.Path) {
+			continue
+		}
+		picUrl, err := url.JoinPath(picCdnMap[*attachment.Path], "data", *attachment.Path)
+		if err != nil {
+			continue
+		}
+		var size int64
+		headReq, err := http.NewRequestWithContext(ctx, http.MethodHead, picUrl, nil)
+		if err == nil {
+			resp, err := client.Do(headReq)
+			if err == nil {
+				size = resp.ContentLength
+				resp.Body.Close()
+			}
+		}
+		resources = append(resources, parser.Resource{
+			URL:      picUrl,
+			Filename: *attachment.Name,
+			Size:     size,
+		})
+	}
+	item.Resources = resources
+	return item, nil
+}
+
+func (k *KemonoParser) parseUserPage(_ context.Context, _ *DownloadInfo) (*parser.Item, error) {
+	return nil, errors.New("kemono user page not implemented")
+}
+
+func isImageExt(attachmentPath string) bool {
+	return strutil.HasSuffixAny(path.Ext(strings.Split(attachmentPath, "?")[0]), []string{".jpg", ".jpeg", ".png", ".webp"})
+}

parsers/kemono/post_info.go

@@ -0,0 +1,62 @@
+// https://github.com/kemono-rs/kemono
+
+package kemono
+
+type PostInfo struct {
+	Post        Post             `json:"post"`
+	Attachments []AttachmentLike `json:"attachments"`
+	Previews    []AttachmentLike `json:"previews"`
+}
+
+type AttachmentLike struct {
+	Type   *string `json:"type,omitempty"`
+	Server *string `json:"server,omitempty"`
+	Name   *string `json:"name,omitempty"`
+	Path   *string `json:"path,omitempty"`
+}
+
+type Post struct {
+	ID          string           `json:"id"`
+	User        string           `json:"user"`
+	Service     string           `json:"service"`
+	Title       string           `json:"title"`
+	Content     string           `json:"content"`
+	Embed       Embed            `json:"embed"`
+	SharedFile  bool             `json:"shared_file"`
+	Added       *string          `json:"added,omitempty"`
+	Published   string           `json:"published"`
+	Edited      *string          `json:"edited,omitempty"`
+	File        File             `json:"file"`
+	Attachments []AttachmentLike `json:"attachments"`
+	Poll        *Poll            `json:"poll,omitempty"`
+	Captions    *string          `json:"captions,omitempty"`
+	Tags        *[]string        `json:"tags,omitempty"`
+	Next        *string          `json:"next,omitempty"`
+	Prev        *string          `json:"prev,omitempty"`
+}
+
+type File struct {
+	Name *string `json:"name,omitempty"`
+	Path *string `json:"path,omitempty"`
+}
+
+type Embed struct {
+	URL         *string `json:"url,omitempty"`
+	Subject     *string `json:"subject,omitempty"`
+	Description *string `json:"description,omitempty"`
+}
+
+type Poll struct {
+	Title          string   `json:"title"`
+	Choices        []Choice `json:"choices"`
+	ClosesAt       *string  `json:"closes_at,omitempty"`
+	CreatedAt      string   `json:"created_at"`
+	Description    *string  `json:"description,omitempty"`
+	AllowsMultiple bool     `json:"allows_multiple"`
+	TotalVotes     int64    `json:"total_votes"`
+}
+
+type Choice struct {
+	Text  string `json:"text"`
+	Votes int64  `json:"votes"`
+}

parsers/kemono/post_legacy.go

@@ -0,0 +1,16 @@
+package kemono
+
+type PostLegacy struct {
+	Props   Props    `json:"props"`
+	Results []Result `json:"results"`
+}
+
+type Props struct {
+	Count uint `json:"count"`
+	Limit uint `json:"limit"`
+}
+
+type Result struct {
+	ID    string `json:"id"`
+	Title string `json:"title"`
+}

parsers/kemono/user_profile.go

@@ -0,0 +1,8 @@
+package kemono
+
+type UserProfile struct {
+	ID       string  `json:"id"`
+	Name     string  `json:"name"`
+	Service  string  `json:"service"`
+	PublicID *string `json:"public_id,omitempty"`
+}

parsers/parser.go

@@ -0,0 +1,88 @@
+package parsers
+
+import (
+	"context"
+	"fmt"
+	"sync"
+
+	"github.com/krau/SaveAny-Bot/config"
+	"github.com/krau/SaveAny-Bot/parsers/kemono"
+	"github.com/krau/SaveAny-Bot/parsers/twitter"
+	"github.com/krau/SaveAny-Bot/pkg/parser"
+)
+
+var (
+	parsers       []parser.Parser
+	parsersMu     sync.Mutex
+	doConfig      sync.Once
+	configParsers = func() {
+		if len(parsers) == 0 {
+			return
+		}
+		for _, pser := range parsers {
+			if configurable, ok := pser.(parser.ConfigurableParser); ok {
+				cfg := config.C().GetParserConfigByName(configurable.Name())
+				if cfg != nil {
+					if err := configurable.Configure(cfg); err != nil {
+						fmt.Printf("Error configuring parser %s: %v\n", configurable.Name(), err)
+					}
+				}
+			}
+		}
+	}
+)
+
+func AddParser(p ...parser.Parser) {
+	parsersMu.Lock()
+	defer parsersMu.Unlock()
+	parsers = append(parsers, p...)
+}
+
+func init() {
+	AddParser(new(twitter.TwitterParser), new(kemono.KemonoParser))
+}
+
+var (
+	ErrNoParserFound = fmt.Errorf("no parser found for the given URL")
+)
+
+func ParseWithContext(ctx context.Context, url string) (*parser.Item, error) {
+	doConfig.Do(configParsers)
+	ch := make(chan *parser.Item, 1)
+	errCh := make(chan error, 1)
+
+	go func() {
+		for _, pser := range parsers {
+			if !pser.CanHandle(url) {
+				continue
+			}
+			item, err := pser.Parse(ctx, url)
+			if err != nil {
+				errCh <- err
+				return
+			}
+			ch <- item
+			return
+		}
+		errCh <- ErrNoParserFound
+	}()
+
+	select {
+	case item := <-ch:
+		return item, nil
+	case err := <-errCh:
+		return nil, err
+	case <-ctx.Done():
+		return nil, ctx.Err()
+	}
+}
+
+func CanHandle(url string) (bool, parser.Parser) {
+	doConfig.Do(configParsers)
+	for _, pser := range parsers {
+		if pser.CanHandle(url) {
+			return true, pser
+		}
+	}
+	return false, nil
+}

parsers/plugin.go

@@ -0,0 +1,23 @@
+package parsers
+
+import "github.com/blang/semver"
+
+var (
+	LatestParserVersion  = semver.MustParse("1.0.0")
+	MinimumParserVersion = semver.MustParse("1.0.0")
+)
+
+type PluginMeta struct {
+	Name        string `json:"name"`
+	Version     string `json:"version"` // [TODO] 分版本解析, 但是我们现在只有 v1 所以先不写
+	Description string `json:"description"`
+	Author      string `json:"author"`
+}
+
+type ParserMethod uint
+
+const (
+	_ ParserMethod = iota
+	ParserMethodCanHandle
+	ParserMethodParse
+)

parsers/twitter/parser.go

@@ -0,0 +1,117 @@
+package twitter
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"net/http"
+	"path"
+	"regexp"
+	"strings"
+
+	"github.com/krau/SaveAny-Bot/common/utils/netutil"
+	"github.com/krau/SaveAny-Bot/pkg/parser"
+)
+
+type TwitterParser struct {
+	client    http.Client
+	apiDomain string
+}
+
+const (
+	fxTwitterApi = "api.fxtwitter.com"
+)
+
+var _ parser.ConfigurableParser = (*TwitterParser)(nil)
+
+var (
+	twitterSourceURLRegexp *regexp.Regexp = regexp.MustCompile(`(?:twitter|x)\.com/([^/]+)/status/(\d+)`)
+)
+
+func getTweetID(sourceURL string) string {
+	matches := twitterSourceURLRegexp.FindStringSubmatch(sourceURL)
+	if len(matches) < 3 {
+		return ""
+	}
+	return matches[2]
+}
+
+func (p *TwitterParser) Parse(ctx context.Context, u string) (*parser.Item, error) {
+	id := getTweetID(u)
+	if id == "" {
+		return nil, errors.New("invalid Twitter URL")
+	}
+	apiUrl := fmt.Sprintf("https://%s/_/status/%s", p.apiDomain, id)
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, apiUrl, nil)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create request to Twitter API: %w", err)
+	}
+	resp, err := p.client.Do(req)
+	if err != nil {
+		return nil, fmt.Errorf("failed to fetch Twitter API: %w", err)
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusOK {
+		return nil, fmt.Errorf("failed to fetch Twitter API, status code: %d", resp.StatusCode)
+	}
+	var fxResp FxTwitterApiResp
+	if err := json.NewDecoder(resp.Body).Decode(&fxResp); err != nil {
+		return nil, fmt.Errorf("failed to decode Twitter API response: %w", err)
+	}
+	if fxResp.Code != 200 {
+		return nil, fmt.Errorf("request twitter API error: %s", fxResp.Message)
+	}
+	if len(fxResp.Tweet.Media.All) == 0 {
+		return nil, errors.New("no media found in the tweet")
+	}
+	resources := make([]parser.Resource, 0, len(fxResp.Tweet.Media.All))
+	for _, media := range fxResp.Tweet.Media.All {
+		var size int64
+		resp, err := p.client.Head(media.URL)
+		if err == nil {
+			size = resp.ContentLength
+			resp.Body.Close()
+		}
+		resources = append(resources, parser.Resource{
+			URL:      media.URL,
+			Filename: path.Base(strings.Split(media.URL, "?")[0]),
+			Size:     size,
+		})
+	}
+	item := &parser.Item{
+		Site:        "Twitter",
+		Title:       fmt.Sprintf("Tweet/%s", id),
+		URL:         fxResp.Tweet.URL,
+		Description: fxResp.Tweet.Text,
+		Author:      fxResp.Tweet.Author.Name,
+		Tags:        make([]string, 0),
+		Extra:       make(map[string]any),
+		Resources:   resources,
+	}
+	return item, nil
+}
+
+func (p *TwitterParser) CanHandle(u string) bool {
+	return twitterSourceURLRegexp.MatchString(u)
+}
+
+func (p *TwitterParser) Name() string {
+	return "twitter"
+}
+
+func (p *TwitterParser) Configure(config map[string]any) error {
+	if domain, ok := config["api_domain"].(string); ok && domain != "" {
+		p.apiDomain = domain
+	} else {
+		p.apiDomain = fxTwitterApi
+	}
+	if proxyUrl, ok := config["proxy"].(string); ok && proxyUrl != "" {
+		proxyClient, err := netutil.NewProxyHTTPClient(proxyUrl)
+		if err != nil {
+			return fmt.Errorf("failed to create proxy client: %w", err)
+		}
+		p.client = *proxyClient
+	}
+	return nil
+}

parsers/twitter/types.go

@@ -0,0 +1,122 @@
+package twitter
+
+// type AutoGenerated struct {
+// 	Code    int    `json:"code"`
+// 	Message string `json:"message"`
+// 	Tweet   struct {
+// 		URL     string `json:"url"`
+// 		ID      string `json:"id"`
+// 		Text    string `json:"text"`
+// 		RawText struct {
+// 			Text   string `json:"text"`
+// 			Facets []struct {
+// 				Type        string `json:"type"`
+// 				Indices     []int  `json:"indices"`
+// 				Original    string `json:"original"`
+// 				ID          string `json:"id,omitempty"`
+// 				Display     string `json:"display,omitempty"`
+// 				Replacement string `json:"replacement,omitempty"`
+// 			} `json:"facets"`
+// 		} `json:"raw_text"`
+// 		Author struct {
+// 			ID          string      `json:"id"`
+// 			Name        string      `json:"name"`
+// 			ScreenName  string      `json:"screen_name"`
+// 			AvatarURL   string      `json:"avatar_url"`
+// 			BannerURL   interface{} `json:"banner_url"`
+// 			Description string      `json:"description"`
+// 			Location    string      `json:"location"`
+// 			URL         string      `json:"url"`
+// 			Followers   int         `json:"followers"`
+// 			Following   int         `json:"following"`
+// 			Joined      string      `json:"joined"`
+// 			Likes       int         `json:"likes"`
+// 			MediaCount  int         `json:"media_count"`
+// 			Protected   bool        `json:"protected"`
+// 			Website     struct {
+// 				URL        string `json:"url"`
+// 				DisplayURL string `json:"display_url"`
+// 			} `json:"website"`
+// 			Tweets      int         `json:"tweets"`
+// 			AvatarColor interface{} `json:"avatar_color"`
+// 		} `json:"author"`
+// 		Replies           int         `json:"replies"`
+// 		Retweets          int         `json:"retweets"`
+// 		Likes             int         `json:"likes"`
+// 		Bookmarks         int         `json:"bookmarks"`
+// 		CreatedAt         string      `json:"created_at"`
+// 		CreatedTimestamp  int         `json:"created_timestamp"`
+// 		PossiblySensitive bool        `json:"possibly_sensitive"`
+// 		Views             int         `json:"views"`
+// 		IsNoteTweet       bool        `json:"is_note_tweet"`
+// 		CommunityNote     interface{} `json:"community_note"`
+// 		Lang              string      `json:"lang"`
+// 		ReplyingTo        interface{} `json:"replying_to"`
+// 		ReplyingToStatus  interface{} `json:"replying_to_status"`
+// 		Media             struct {
+// 			All []struct {
+// 				URL          string `json:"url"`
+// 				ThumbnailURL string `json:"thumbnail_url"`
+// 				Duration     int    `json:"duration"`
+// 				Width        int    `json:"width"`
+// 				Height       int    `json:"height"`
+// 				Format       string `json:"format"`
+// 				Type         string `json:"type"`
+// 				Variants     []struct {
+// 					Bitrate     int    `json:"bitrate"`
+// 					ContentType string `json:"content_type"`
+// 					URL         string `json:"url"`
+// 				} `json:"variants"`
+// 			} `json:"all"`
+// 			Photos []struct {
+// 				Type   string `json:"type"`
+// 				URL    string `json:"url"`
+// 				Width  int    `json:"width"`
+// 				Height int    `json:"height"`
+// 			} `json:"photos"`
+// 			Videos []struct {
+// 				URL          string `json:"url"`
+// 				ThumbnailURL string `json:"thumbnail_url"`
+// 				Duration     int    `json:"duration"`
+// 				Width        int    `json:"width"`
+// 				Height       int    `json:"height"`
+// 				Format       string `json:"format"`
+// 				Type         string `json:"type"`
+// 				Variants     []struct {
+// 					Bitrate     int    `json:"bitrate"`
+// 					ContentType string `json:"content_type"`
+// 					URL         string `json:"url"`
+// 				} `json:"variants"`
+// 			} `json:"videos"`
+// 		} `json:"media"`
+// 		Source      string      `json:"source"`
+// 		TwitterCard string      `json:"twitter_card"`
+// 		Color       interface{} `json:"color"`
+// 		Provider    string      `json:"provider"`
+// 	} `json:"tweet"`
+// }
+
+type FxTwitterApiResp struct {
+	Code    int    `json:"code"`
+	Message string `json:"message"`
+	Tweet   struct {
+		URL    string `json:"url"`
+		ID     string `json:"id"`
+		Text   string `json:"text"`
+		Author struct {
+			ID         string `json:"id"`
+			Name       string `json:"name"`
+			ScreenName string `json:"screen_name"`
+			Protected  bool   `json:"protected"`
+		} `json:"author"`
+		PossiblySensitive bool   `json:"possibly_sensitive"`
+		IsNoteTweet       bool   `json:"is_note_tweet"`
+		Lang              string `json:"lang"`
+		Media             struct {
+			All []struct {
+				URL  string `json:"url"`
+				Type string `json:"type"`
+			} `json:"all"`
+		} `json:"media"`
+	} `json:"tweet"`
+}

pkg/enums/fnamest/filename_srategy.go

@@ -0,0 +1,14 @@
+package fnamest
+
+//go:generate go-enum --values --names --noprefix --flag --nocase
+
+// FnameST
+/* ENUM(
+default, message
+) */
+type FnameST string
+
+var FnameSTDisplay = map[FnameST]string{
+	Default: "默认",
+	Message: "优先从消息生成",
+}

pkg/enums/fnamest/filename_srategy_enum.go

@@ -0,0 +1,87 @@
+// Code generated by go-enum DO NOT EDIT.
+// Version: 0.6.1
+// Revision: a6f63bddde05aca4221df9c8e9e6d7d9674b1cb4
+// Build Date: 2025-03-18T23:42:14Z
+// Built By: goreleaser
+
+package fnamest
+
+import (
+	"fmt"
+	"strings"
+)
+
+const (
+	// Default is a FnameST of type default.
+	Default FnameST = "default"
+	// Message is a FnameST of type message.
+	Message FnameST = "message"
+)
+
+var ErrInvalidFnameST = fmt.Errorf("not a valid FnameST, try [%s]", strings.Join(_FnameSTNames, ", "))
+
+var _FnameSTNames = []string{
+	string(Default),
+	string(Message),
+}
+
+// FnameSTNames returns a list of possible string values of FnameST.
+func FnameSTNames() []string {
+	tmp := make([]string, len(_FnameSTNames))
+	copy(tmp, _FnameSTNames)
+	return tmp
+}
+
+// FnameSTValues returns a list of the values for FnameST
+func FnameSTValues() []FnameST {
+	return []FnameST{
+		Default,
+		Message,
+	}
+}
+
+// String implements the Stringer interface.
+func (x FnameST) String() string {
+	return string(x)
+}
+
+// IsValid provides a quick way to determine if the typed value is
+// part of the allowed enumerated values
+func (x FnameST) IsValid() bool {
+	_, err := ParseFnameST(string(x))
+	return err == nil
+}
+
+var _FnameSTValue = map[string]FnameST{
+	"default": Default,
+	"message": Message,
+}
+
+// ParseFnameST attempts to convert a string to a FnameST.
+func ParseFnameST(name string) (FnameST, error) {
+	if x, ok := _FnameSTValue[name]; ok {
+		return x, nil
+	}
+	// Case insensitive parse, do a separate lookup to prevent unnecessary cost of lowercasing a string if we don't need to.
+	if x, ok := _FnameSTValue[strings.ToLower(name)]; ok {
+		return x, nil
+	}
+	return FnameST(""), fmt.Errorf("%s is %w", name, ErrInvalidFnameST)
+}
+
+// Set implements the Golang flag.Value interface func.
+func (x *FnameST) Set(val string) error {
+	v, err := ParseFnameST(val)
+	*x = v
+	return err
+}
+
+// Get implements the Golang flag.Getter interface func.
+func (x *FnameST) Get() interface{} {
+	return *x
+}
+
+// Type implements the github.com/spf13/pFlag Value interface.
+func (x *FnameST) Type() string {
+	return "FnameST"
+}

pkg/enums/tasktype/tasktype.go

@@ -1,5 +1,5 @@
 package tasktype
 
 //go:generate go-enum --values --names --flag --nocase
-// ENUM(tgfiles,tphpics)
+// ENUM(tgfiles,tphpics,parseditem)
 type TaskType string

pkg/enums/tasktype/tasktype_enum.go

@@ -16,6 +16,8 @@ const (
 	TaskTypeTgfiles TaskType = "tgfiles"
 	// TaskTypeTphpics is a TaskType of type tphpics.
 	TaskTypeTphpics TaskType = "tphpics"
+	// TaskTypeParseditem is a TaskType of type parseditem.
+	TaskTypeParseditem TaskType = "parseditem"
 )
 
 var ErrInvalidTaskType = fmt.Errorf("not a valid TaskType, try [%s]", strings.Join(_TaskTypeNames, ", "))
@@ -23,6 +25,7 @@ var ErrInvalidTaskType = fmt.Errorf("not a valid TaskType, try [%s]", strings.Jo
 var _TaskTypeNames = []string{
 	string(TaskTypeTgfiles),
 	string(TaskTypeTphpics),
+	string(TaskTypeParseditem),
 }
 
 // TaskTypeNames returns a list of possible string values of TaskType.
@@ -37,6 +40,7 @@ func TaskTypeValues() []TaskType {
 	return []TaskType{
 		TaskTypeTgfiles,
 		TaskTypeTphpics,
+		TaskTypeParseditem,
 	}
 }
 
@@ -53,8 +57,9 @@ func (x TaskType) IsValid() bool {
 }
 
 var _TaskTypeValue = map[string]TaskType{
-	"tgfiles": TaskTypeTgfiles,
-	"tphpics": TaskTypeTphpics,
+	"tgfiles":    TaskTypeTgfiles,
+	"tphpics":    TaskTypeTphpics,
+	"parseditem": TaskTypeParseditem,
 }
 
 // ParseTaskType attempts to convert a string to a TaskType.

pkg/parser/parser.go

@@ -0,0 +1,70 @@
+package parser
+
+import (
+	"context"
+	"crypto/md5"
+	"fmt"
+)
+
+type Parser interface {
+	CanHandle(url string) bool
+	Parse(ctx context.Context, url string) (*Item, error)
+}
+
+type ConfigurableParser interface {
+	Parser
+	Configure(config map[string]any) error
+	Name() string
+}
+
+// Resource is a single downloadable resource with metadata.
+type Resource struct {
+	URL       string            `json:"url"`
+	Filename  string            `json:"filename"` // with ext
+	MimeType  string            `json:"mime_type"`
+	Extension string            `json:"extension"` // e.g. "mp4"
+	Size      int64             `json:"size"`    // 0 when unknown
+	Hash      map[string]string `json:"hash"`    // {"md5": "...", "sha256": "..."}
+	Headers   map[string]string `json:"headers"` // HTTP headers when downloading
+	Extra     map[string]any    `json:"extra"`
+}
+
+type Item struct {
+	Site        string         `json:"site"`
+	URL         string         `json:"url"` // original URL of the item
+	Title       string         `json:"title"`
+	Author      string         `json:"author"`
+	Description string         `json:"description"`
+	Tags        []string       `json:"tags"`
+	Resources   []Resource     `json:"resources"`
+	Extra       map[string]any `json:"extra"`
+}
+
+func (r *Resource) FileName() string {
+	return r.Filename
+}
+
+func (r *Resource) FileSize() int64 {
+	return r.Size
+}
+
+func (r *Resource) ID() string {
+	h := md5.New()
+	h.Write([]byte(r.URL))
+	h.Write([]byte(r.Filename))
+	h.Write([]byte(r.MimeType))
+	h.Write([]byte(r.Extension))
+	h.Write([]byte(fmt.Sprintf("%d", r.Size)))
+
+	for k, v := range r.Hash {
+		h.Write([]byte(k))
+		h.Write([]byte(v))
+	}
+
+	for k, v := range r.Headers {
+		h.Write([]byte(k))
+		h.Write([]byte(v))
+	}
+
+	return fmt.Sprintf("%x", h.Sum(nil))
+}

pkg/rule/consts.go

@@ -1,4 +1,4 @@
-package consts
+package rule
 
 const (
 	RuleStorNameChosen     = "CHOSEN"

pkg/rule/filename_regex.go

@@ -3,7 +3,6 @@ package rule
 import (
 	"regexp"
 
-	ruleenum "github.com/krau/SaveAny-Bot/pkg/enums/rule"
 	"github.com/krau/SaveAny-Bot/pkg/tfile"
 )
 
@@ -14,8 +13,8 @@ type RuleFileNameRegex struct {
 
 var _ RuleClass[tfile.TGFile] = (*RuleFileNameRegex)(nil)
 
-func (r RuleFileNameRegex) Type() ruleenum.RuleType {
-	return ruleenum.FileNameRegex
+func (r RuleFileNameRegex) Type() RuleType {
+	return FileNameRegex
 }
 
 func (r RuleFileNameRegex) Match(input tfile.TGFile) (bool, error) {

pkg/rule/is_album.go

@@ -1,9 +1,5 @@
 package rule
 
-import (
-	ruleenum "github.com/krau/SaveAny-Bot/pkg/enums/rule"
-)
-
 var _ RuleClass[bool] = (*RuleMediaType)(nil)
 
 type RuleMediaType struct {
@@ -11,8 +7,8 @@ type RuleMediaType struct {
 	matchAlbum bool
 }
 
-func (r RuleMediaType) Type() ruleenum.RuleType {
-	return ruleenum.IsAlbum
+func (r RuleMediaType) Type() RuleType {
+	return IsAlbum
 }
 
 func (r RuleMediaType) Match(input bool) (bool, error) {

pkg/rule/message_regex.go

@@ -2,8 +2,6 @@ package rule
 
 import (
 	"regexp"
-
-	ruleenum "github.com/krau/SaveAny-Bot/pkg/enums/rule"
 )
 
 var _ RuleClass[string] = (*RuleMessageRegex)(nil)
@@ -13,8 +11,8 @@ type RuleMessageRegex struct {
 	regex *regexp.Regexp
 }
 
-func (r RuleMessageRegex) Type() ruleenum.RuleType {
-	return ruleenum.MessageRegex
+func (r RuleMessageRegex) Type() RuleType {
+	return MessageRegex
 }
 
 func (r RuleMessageRegex) Match(input string) (bool, error) {

pkg/rule/rule.go

@@ -1,11 +1,7 @@
 package rule
 
-import (
-	ruleenum "github.com/krau/SaveAny-Bot/pkg/enums/rule"
-)
-
 type RuleClass[InputType any] interface {
-	Type() ruleenum.RuleType
+	Type() RuleType
 	Match(input InputType) (bool, error)
 	StorageName() string
 	StoragePath() string

pkg/tcbdata/data.go

@@ -2,6 +2,7 @@ package tcbdata
 
 import (
 	"github.com/krau/SaveAny-Bot/pkg/enums/tasktype"
+	"github.com/krau/SaveAny-Bot/pkg/parser"
 	"github.com/krau/SaveAny-Bot/pkg/telegraph"
 	"github.com/krau/SaveAny-Bot/pkg/tfile"
 )
@@ -9,6 +10,8 @@ import (
 const (
 	TypeAdd        = "add"
 	TypeSetDefault = "setdefault"
+	TypeConfig  = "config"
+	TypeCancel     = "cancel"
 )
 
 // type TaskDataTGFiles struct {
@@ -26,6 +29,7 @@ const (
 // }
 
 type Add struct {
+	// [TODO] maybe we should to spilit this into different types...
 	TaskType         tasktype.TaskType
 	SelectedStorName string
 	DirID            uint
@@ -37,6 +41,8 @@ type Add struct {
 	TphPageNode *telegraph.Page
 	TphPics     []string
 	TphDirPath  string // unescaped telegraph.Page.Path
+	// parseditem
+	ParsedItem *parser.Item
 }
 
 type SetDefaultStorage struct {

pkg/tfile/dler.go

@@ -9,5 +9,5 @@ import (
 
 func NewDownloader(file TGFile) *downloader.Builder {
 	return downloader.NewDownloader().WithPartSize(tglimit.MaxPartSize).
-		Download(file.Dler(), file.Location()).WithThreads(dlutil.BestThreads(file.Size(), config.Cfg.Threads))
+		Download(file.Dler(), file.Location()).WithThreads(dlutil.BestThreads(file.Size(), config.C().Threads))
 }

pkg/tfile/opts.go

@@ -2,20 +2,21 @@ package tfile
 
 import "github.com/gotd/td/tg"
 
-type TGFileOptions func(*tgFile)
+type TGFileOption func(*tgFile)
 
-func WithMessage(msg *tg.Message) TGFileOptions {
+func WithMessage(msg *tg.Message) TGFileOption {
 	return func(f *tgFile) {
 		f.message = msg
 	}
 }
-func WithName(name string) TGFileOptions {
+
+func WithName(name string) TGFileOption {
 	return func(f *tgFile) {
 		f.name = name
 	}
 }
 
-func WithNameIfEmpty(name string) TGFileOptions {
+func WithNameIfEmpty(name string) TGFileOption {
 	return func(f *tgFile) {
 		if f.name == "" {
 			f.name = name
@@ -23,13 +24,13 @@ func WithNameIfEmpty(name string) TGFileOptions {
 	}
 }
 
-func WithSize(size int64) TGFileOptions {
+func WithSize(size int64) TGFileOption {
 	return func(f *tgFile) {
 		f.size = size
 	}
 }
 
-func WithSizeIfZero(size int64) TGFileOptions {
+func WithSizeIfZero(size int64) TGFileOption {
 	return func(f *tgFile) {
 		if f.size == 0 {
 			f.size = size

pkg/tfile/tgfile.go

@@ -54,7 +54,7 @@ func NewTGFile(
 	dler downloader.Client,
 	size int64,
 	name string,
-	opts ...TGFileOptions,
+	opts ...TGFileOption,
 ) TGFile {
 	f := &tgFile{
 		location: location,
@@ -68,7 +68,7 @@ func NewTGFile(
 	return f
 }
 
-func FromMedia(media tg.MessageMediaClass, client downloader.Client, opts ...TGFileOptions) (TGFile, error) {
+func FromMedia(media tg.MessageMediaClass, client downloader.Client, opts ...TGFileOption) (TGFile, error) {
 	switch m := media.(type) {
 	case *tg.MessageMediaDocument:
 		document, ok := m.Document.AsNotEmpty()
@@ -125,7 +125,7 @@ func FromMedia(media tg.MessageMediaClass, client downloader.Client, opts ...TGF
 	return nil, fmt.Errorf("unsupported media type: %T", media)
 }
 
-func FromMediaMessage(media tg.MessageMediaClass, client downloader.Client, msg *tg.Message, opts ...TGFileOptions) (TGFileMessage, error) {
+func FromMediaMessage(media tg.MessageMediaClass, client downloader.Client, msg *tg.Message, opts ...TGFileOption) (TGFileMessage, error) {
 	file, err := FromMedia(media, client, opts...)
 	if err != nil {
 		return nil, err

plugins/README.md

@@ -0,0 +1,161 @@
+# SaveAnyBot Plugins
+
+SaveAnyBot 可通过插件扩展功能, 目前仅支持 Parser (解析器)插件.
+
+## Parser
+
+解析器为 SaveAnyBot 提供了处理非 Telegram 文件的能力, 例如下载其他网站的图片或视频.
+
+当前解析器接口定义如下:
+
+```go
+type Parser interface {
+	CanHandle(url string) bool // 判断是否能处理给定的 URL
+	Parse(ctx context.Context, url string) (*Item, error) // 解析 URL, 返回 Item
+}
+
+// Resource is a single downloadable resource with metadata.
+type Resource struct {
+	URL       string            `json:"url"`
+	Filename  string            `json:"filename"` // with ext
+	MimeType  string            `json:"mime_type"`
+	Extension string            `json:"extension"`
+	Size      int64             `json:"size"`    // 0 when unknown
+	Hash      map[string]string `json:"hash"`    // {"md5": "...", "sha256": "..."}
+	Headers   map[string]string `json:"headers"` // HTTP headers when downloading
+	Extra     map[string]any    `json:"extra"`
+}
+
+type Item struct {
+	Site        string         `json:"site"`
+	URL         string         `json:"url"` // original URL of the item
+	Title       string         `json:"title"`
+	Author      string         `json:"author"`
+	Description string         `json:"description"`
+	Tags        []string       `json:"tags"`
+	Resources   []Resource     `json:"resources"`
+	Extra       map[string]any `json:"extra"`
+}
+```
+
+### Write a Parser Plugin
+
+解析器插件可使用 JavaScript 编写, SaveAnyBot 使用 [goja](https://github.com/dop251/goja) 提供运行时, 并向其中注入了以下全局函数或对象:
+
+- **registerParser**: 用于注册解析器, 每个插件必须调用此函数以注册
+- **console.log**: 调用 go 端的 logger 打印日志
+- **ghttp**: 提供 HTTP 请求功能
+
+插件需要提供元数据 `metadata` 并实现 `canHandle` 和 `parse` 两个函数, 最后调用 `registerParser` 注册解析器.
+
+#### Plugin Metadata
+
+插件元数据是一个 JavaScript 对象:
+
+```js
+const metadata = {
+    version: "1.0.0", // 插件版本号, 必须提供, 其他字段可选
+    name: "Example Parser", // 插件名称
+    description: "A parser for example links", // 插件描述
+    author: "Krau", // 插件作者
+}
+```
+
+#### canHandle Function
+
+`canHandle`: `canHandle(url: string): boolean` , 用于判断当前解析器能否解析给定的 URL, 返回布尔值, 例如:
+
+```js
+const canHandle = function (url) {
+	return url.includes("youtube.com/watch?v");
+};
+```
+
+这将让 SaveAnyBot 在遇到包含 `youtube.com/watch?v` 的 url 时调用当前解析器的 `parse`.
+
+#### parse Function
+
+`parse`: `parse(url: string): Item` , 是核心解析函数, 用于解析给定的 url, 返回一个 `Item` 对象, 例:
+
+```js
+const parse = function (url) {
+    var result = {
+        // 元信息
+        site: "YouTube",
+        url: url,
+        title: "测试 YouTube 视频",
+        author: "某视频作者",
+        description: "这是一个测试视频",
+        tags: ["test", "youtube"],
+        // 资源(可下载的文件)列表
+        resources: [
+            {
+                url: "https://example.com/video1.mp4", // 文件直链
+                filename: "somevideo.mp4", // 文件名
+                mime_type: "video/mp4", // 文件 MIME 类型, 可选
+                extension: "mp4", // 文件扩展名, 可选
+                size: 100 * 1024 * 1024, // 文件大小, 单位为字节, 未知可以设置为 0
+                hash: {}, // 文件哈希, 可选, 格式为 {"md5": "xxx", "sha256": "xxx"} 等
+                headers: {}, // 下载文件时所需的 HTTP 头部, 可选, 例如 {"User-Agent": "Mozilla/5.0"}
+                extra: {} // 额外信息, 可选, 可以包含任何自定义数据
+            },
+            {
+                url: "https://example.com/picture1.png",
+                filename: "picture1.png",
+                mime_type: "image/png",
+                extension: "png",
+                size: 1 * 1024 * 1024,
+                hash: {},
+                headers: {},
+                extra: {}
+            }
+        ],
+        extra: {}
+    };
+    return result;
+}
+```
+
+#### HTTP Requests
+
+使用 `ghttp` 对象以发起 HTTP 请求.
+
+**ghttp.get(url: string)** 发起 GET 请求, 当成功时返回响应体字符串, 失败时或响应状态码不为 200 时返回一个包含 `error` 字段的对象:
+
+```js
+const response = ghttp.get("https://example.com/someapi");
+if (response.error) {
+	console.log("Request failed:", response.error);
+}
+if (response.status) {
+	console.log("Response status:", response.status);
+}
+```
+
+**ghttp.getJSON(url: string)** 发起 GET 请求并将响应体解析为 JSON 对象, 始终返回以下对象:
+
+```js
+{
+	data?: any, // 当请求成功且响应体为合法 JSON 时包含解析后的数据
+	error?: string, // 当请求失败或响应状态码不为 200 时包含错误信息
+	status?: number, // 响应状态码, 仅当响应状态码不为 200 时包含
+}
+```
+
+---
+
+最后别忘了调用 `registerParser` 注册解析器:
+
+```js
+registerParser({
+	metadata,
+	canHandle,
+	parse
+});
+```
+
+### Examples
+
+请先查看 [example_parser_basic.js](./example_parser_basic.js) 了解最简示例解析器插件的实现.
+
+然后查看 [example_parser_danbooru.js](./example_parser_danbooru.js) , 这是一个可直接使用的插件, 用于解析 Danbooru 图片页面并提取图片资源.

plugins/example_parser_basic.js

@@ -0,0 +1,73 @@
+// 这是一个最简示例解析器插件, 用于展示插件所需实现的基本功能
+// 此插件将会模拟处理 YouTube 的视频链接
+
+/**
+ * 插件元数据
+ * 版本号是 saveany-bot 本体支持的插件规范版本号, 必须提供
+ */
+const metadata = {
+    name: "Example Parser", // 插件名称
+    version: "1.0.0", // 插件版本号
+    description: "A parser for example links", // 插件描述
+    author: "Krau", // 插件作者
+}
+
+// 你可以使用 console.log 来在终端中使用 go 的 logger 打印信息
+console.log("Parser loaded", "name", metadata.name);
+
+/**
+ * canHandle 函数用于判断当前解析器能否解析给定的 URL
+ */
+const canHandle = function (url) {
+    // 这里我们简单地检查 URL 是否包含 "youtube.com/watch?v"
+    return url.includes("youtube.com/watch?v");
+}
+
+/**
+ * 解析 url 并返回一个 Item 对象, 类型定义在 pkg/parser.go 中
+ */
+const parse = function (url) {
+    var result = {
+        // 元信息
+        site: "YouTube",
+        url: url,
+        title: "测试 YouTube 视频",
+        author: "某视频作者",
+        description: "这是一个测试视频",
+        tags: ["test", "youtube"],
+        // 资源(可下载的文件)列表
+        resources: [
+            {
+                url: "https://example.com/video1.mp4", // 文件直链
+                filename: "somevideo.mp4", // 文件名
+                mime_type: "video/mp4", // 文件 MIME 类型, 可选
+                extension: "mp4", // 文件扩展名, 可选
+                size: 100 * 1024 * 1024, // 文件大小, 单位为字节, 未知可以设置为 0
+                hash: {}, // 文件哈希, 可选, 格式为 {"md5": "xxx", "sha256": "xxx"} 等
+                headers: {}, // 下载文件时所需的 HTTP 头部, 可选, 例如 {"User-Agent": "Mozilla/5.0"}
+                extra: {} // 额外信息, 可选, 可以包含任何自定义数据
+            },
+            {
+                url: "https://example.com/picture1.png",
+                filename: "picture1.png",
+                mime_type: "image/png",
+                extension: "png",
+                size: 1 * 1024 * 1024,
+                hash: {},
+                headers: {},
+                extra: {}
+            }
+        ],
+        extra: {}
+    };
+    return result;
+}
+
+// 最后需要调用 registerParser 来注册这个解析器
+registerParser({
+    metadata,
+    canHandle,
+    parse
+});
+
+// 更进一步的插件编写信息, 请查看 plugins/example_parser_danbooru.js

plugins/example_parser_danbooru.js

@@ -0,0 +1,138 @@
+// Danbooru post parser for SaveAnyBot
+// request https://danbooru.donmai.us/posts/{id}.json and parse the response
+
+const metadata = {
+    name: "Danbooru Post Parser",
+    version: "1.0.0",
+    description: "Parse Danbooru post links via official JSON API",
+    author: "Krau",
+};
+
+// some utils
+const danbooruSourceURLRegexp = /danbooru\.donmai\.us\/(posts|post\/show)\/(\d+)/;
+function getPostID(url) {
+    const m = url.match(danbooruSourceURLRegexp);
+    return m ? m[2] : "";
+}
+function normalizePostURL(id) {
+    return `https://danbooru.donmai.us/posts/${id}`;
+}
+function apiURLFor(id) {
+    return `https://danbooru.donmai.us/posts/${id}.json`;
+}
+
+
+function basenameFromURL(u) {
+    try {
+        const q = u.split("?")[0];
+        const parts = q.split("/");
+        const name = parts[parts.length - 1] || "";
+        return name || "file";
+    } catch (_) {
+        return "file";
+    }
+}
+function extFromFilename(name) {
+    const idx = name.lastIndexOf(".");
+    if (idx < 0) return "";
+    return name.slice(idx + 1).toLowerCase();
+}
+function mimeFromExt(ext) {
+    switch (ext) {
+        case "jpg":
+        case "jpeg":
+            return "image/jpeg";
+        case "png":
+            return "image/png";
+        case "gif":
+            return "image/gif";
+        default:
+            return "";
+    }
+}
+
+// implement canHandle and parse
+const canHandle = function (url) {
+    return danbooruSourceURLRegexp.test(url);
+};
+
+const parse = function (sourceURL) {
+    const id = getPostID(sourceURL);
+    if (!id) {
+        throw new Error("invalid danbooru post url");
+    }
+
+    const normURL = normalizePostURL(id);
+
+    const apiURL = apiURLFor(id);
+    console.log("Danbooru requesting", "url", apiURL);
+    // You can use ghttp.getJSON to fetch and parse JSON in one step.
+    // While the ghttp.get can be used to fetch raw response.
+    const data = ghttp.getJSON(apiURL);
+
+    if (data && data.error) {
+        throw new Error(data.message || "danbooru returned error");
+    }
+
+    const fileURL = data.file_url || "";
+    const largeURL = data.large_file_url || "";
+    const width = data.image_width || 0;
+    const height = data.image_height || 0;
+
+    if (!fileURL && !largeURL) {
+        throw new Error("danbooru response has no file_url / large_file_url");
+    }
+
+    const resources = [];
+    if (fileURL) {
+        const name = basenameFromURL(fileURL);
+        const ext = extFromFilename(name);
+        resources.push({
+            url: fileURL,
+            filename: name,
+            mime_type: mimeFromExt(ext),
+            extension: ext,
+            size: 0,
+            hash: {},
+            headers: {},
+            extra: { width, height, kind: "original" },
+        });
+    }
+    if (largeURL && largeURL !== fileURL) {
+        const name = basenameFromURL(largeURL);
+        const ext = extFromFilename(name);
+        resources.push({
+            url: largeURL,
+            filename: name,
+            mime_type: mimeFromExt(ext),
+            extension: ext,
+            size: 0,
+            hash: {},
+            headers: {},
+            extra: { width, height, kind: "large" },
+        });
+    }
+
+    const tags = (data.tag_string ? String(data.tag_string) : "")
+        .split(" ")
+        .filter(Boolean);
+
+    const item = {
+        site: "Danbooru",
+        url: normURL,
+        title: `Danbooru/${data.id || id}`,
+        author: "Danbooru",
+        description: "",
+        tags: tags,
+        resources: resources,
+        extra: {},
+    };
+
+    return item;
+};
+
+registerParser({
+    metadata,
+    canHandle,
+    parse,
+});

storage/load.go

@@ -20,7 +20,7 @@ func getStorageByName(ctx context.Context, name string) (Storage, error) {
 	if ok {
 		return storage, nil
 	}
-	cfg := config.Cfg.GetStorageByName(name)
+	cfg := config.C().GetStorageByName(name)
 	if cfg == nil {
 		return nil, fmt.Errorf("未找到存储 %s", name)
 	}
@@ -39,7 +39,7 @@ func GetStorageByUserIDAndName(ctx context.Context, chatID int64, name string) (
 		return nil, ErrStorageNameEmpty
 	}
 
-	if !config.Cfg.HasStorage(chatID, name) {
+	if !config.C().HasStorage(chatID, name) {
 		return nil, fmt.Errorf("没有找到用户 %d 的存储 %s", chatID, name)
 	}
 
@@ -54,7 +54,7 @@ func GetUserStorages(ctx context.Context, chatID int64) []Storage {
 		return storages
 	}
 	var storages []Storage
-	for _, name := range config.Cfg.GetStorageNamesByUserID(chatID) {
+	for _, name := range config.C().GetStorageNamesByUserID(chatID) {
 		storage, err := getStorageByName(ctx, name)
 		if err != nil {
 			continue
@@ -67,14 +67,14 @@ func GetUserStorages(ctx context.Context, chatID int64) []Storage {
 func LoadStorages(ctx context.Context) {
 	logger := log.FromContext(ctx)
 	logger.Info("加载存储...")
-	for _, storage := range config.Cfg.Storages {
+	for _, storage := range config.C().Storages {
 		_, err := getStorageByName(ctx, storage.GetName())
 		if err != nil {
 			logger.Errorf("加载存储 %s 失败: %v", storage.GetName(), err)
 		}
 	}
 	logger.Infof("成功加载 %d 个存储", len(Storages))
-	for user := range config.Cfg.GetUsersID() {
+	for user := range config.C().GetUsersID() {
 		UserStorages[int64(user)] = GetUserStorages(ctx, int64(user))
 	}
 }

storage/telegram/telegram.go

@@ -100,7 +100,7 @@ func (t *Telegram) Save(ctx context.Context, r io.Reader, storagePath string) er
 	}
 	upler := uploader.NewUploader(tctx.Raw).
 		WithPartSize(tglimit.MaxUploadPartSize).
-		WithThreads(config.Cfg.Threads)
+		WithThreads(config.C().Threads)
 
 	var file tg.InputFileClass
 	size := func() int64 {