feat: parse url with js plugins support (#96)

* 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
This commit is contained in:
Krau
2025-08-21 23:48:17 +08:00
committed by GitHub
parent 79386bdd7d
commit 302db2fe75
47 changed files with 1348 additions and 47 deletions

View File

@@ -32,8 +32,7 @@ func GetFileFromMessageWithReply(ctx *ext.Context, update *ext.Update, message *
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)

View File

@@ -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
}

View File

@@ -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{

View File

@@ -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,