更新 version.py

携带UA以避免被反爬虫脚本过滤

app/api/endpoints/mediaserver.py

@@ -82,7 +82,7 @@ def exists(media_in: schemas.MediaInfo,
     mediainfo.from_dict(media_in.model_dump())
     existsinfo: schemas.ExistMediaInfo = MediaServerChain().media_exists(mediainfo=mediainfo)
     if not existsinfo:
-        return []
+        return {}
     if media_in.season:
         return {
             media_in.season: existsinfo.seasons.get(media_in.season) or []

app/api/endpoints/system.py

@@ -149,7 +149,9 @@ def get_global_setting(token: str):
     info.update({
         "USER_UNIQUE_ID": SubscribeHelper().get_user_uuid(),
         "SUBSCRIBE_SHARE_MANAGE": share_admin,
-        "WORKFLOW_SHARE_MANAGE": share_admin
+        "WORKFLOW_SHARE_MANAGE": share_admin,
+        "FRONTEND_VERSION": SystemChain.get_frontend_version(),
+        "BACKEND_VERSION": APP_VERSION
     })
     return schemas.Response(success=True,
                             data=info)

app/db/__init__.py

@@ -454,7 +454,6 @@ class Base:
 
     @db_update
     def update(self, db: Session, payload: dict):
-        payload = {k: v for k, v in payload.items() if v is not None}
         for key, value in payload.items():
             setattr(self, key, value)
         if inspect(self).detached:
@@ -462,7 +461,6 @@ class Base:
 
     @async_db_update
     async def async_update(self, db: AsyncSession, payload: dict):
-        payload = {k: v for k, v in payload.items() if v is not None}
         for key, value in payload.items():
             setattr(self, key, value)
         if inspect(self).detached:

app/modules/discord/__init__.py

@@ -23,6 +23,7 @@ class DiscordModule(_ModuleBase, _MessageBase[Discord]):
         if not Discord:
             logger.error("Discord 依赖未就绪（需要安装 discord.py==2.6.4），模块未启动")
             return
+        self.stop()
         super().init_service(service_name=Discord.__name__.lower(),
                              service_type=Discord)
         self._channel = MessageChannel.Discord
@@ -154,7 +155,8 @@ class DiscordModule(_ModuleBase, _MessageBase[Discord]):
                                 image=message.image, userid=userid, link=message.link,
                                 buttons=message.buttons,
                                 original_message_id=message.original_message_id,
-                                original_chat_id=message.original_chat_id)
+                                original_chat_id=message.original_chat_id,
+                                mtype=message.mtype)
 
     def post_medias_message(self, message: Notification, medias: List[MediaInfo]) -> None:
         """

app/modules/discord/discord.py

@@ -1,7 +1,7 @@
 import asyncio
 import re
 import threading
-from typing import Optional, List, Dict, Any, Union
+from typing import Optional, List, Dict, Any, Tuple, Union
 
 import discord
 from discord import app_commands
@@ -11,8 +11,18 @@ from app.core.config import settings
 from app.core.context import MediaInfo, Context
 from app.core.metainfo import MetaInfo
 from app.log import logger
+from app.schemas.types import NotificationType
 from app.utils.string import StringUtils
 
+# Discord embed 字段解析白名单
+# 只有这些消息类型会使用复杂的字段解析逻辑
+PARSE_FIELD_TYPES = {
+    NotificationType.Download,      # 资源下载
+    NotificationType.Organize,      # 整理入库
+    NotificationType.Subscribe,     # 订阅
+    NotificationType.Manual,        # 手动处理
+}
+
 
 class Discord:
     """
@@ -40,7 +50,10 @@ class Discord:
         intents.messages = True
         intents.guilds = True
 
-        self._client: Optional[discord.Client] = discord.Client(intents=intents)
+        self._client: Optional[discord.Client] = discord.Client(
+            intents=intents,
+            proxy=settings.PROXY_HOST
+        )
         self._tree: Optional[app_commands.CommandTree] = None
         self._loop: asyncio.AbstractEventLoop = asyncio.new_event_loop()
         self._thread: Optional[threading.Thread] = None
@@ -153,7 +166,8 @@ class Discord:
                  userid: Optional[str] = None, link: Optional[str] = None,
                  buttons: Optional[List[List[dict]]] = None,
                  original_message_id: Optional[Union[int, str]] = None,
-                 original_chat_id: Optional[str] = None) -> Optional[bool]:
+                 original_chat_id: Optional[str] = None,
+                 mtype: Optional['NotificationType'] = None) -> Optional[bool]:
         if not self.get_state():
             return False
         if not title and not text:
@@ -165,7 +179,8 @@ class Discord:
                 self._send_message(title=title, text=text, image=image, userid=userid,
                                    link=link, buttons=buttons,
                                    original_message_id=original_message_id,
-                                   original_chat_id=original_chat_id),
+                                   original_chat_id=original_chat_id,
+                                   mtype=mtype),
                 self._loop)
             return future.result(timeout=30)
         except Exception as err:
@@ -237,13 +252,14 @@ class Discord:
                             userid: Optional[str], link: Optional[str],
                             buttons: Optional[List[List[dict]]],
                             original_message_id: Optional[Union[int, str]],
-                            original_chat_id: Optional[str]) -> bool:
+                            original_chat_id: Optional[str],
+                            mtype: Optional['NotificationType'] = None) -> bool:
         channel = await self._resolve_channel(userid=userid, chat_id=original_chat_id)
         if not channel:
             logger.error("未找到可用的 Discord 频道或私聊")
             return False
 
-        embed = self._build_embed(title=title, text=text, image=image, link=link)
+        embed = self._build_embed(title=title, text=text, image=image, link=link, mtype=mtype)
         view = self._build_view(buttons=buttons, link=link)
         content = None
 
@@ -315,21 +331,92 @@ class Discord:
 
     @staticmethod
     def _build_embed(title: str, text: Optional[str], image: Optional[str],
-                     link: Optional[str]) -> discord.Embed:
-        description = ""
+                     link: Optional[str], mtype: Optional['NotificationType'] = None) -> discord.Embed:
         fields: List[Dict[str, str]] = []
+        desc_lines: List[str] = []
+        should_parse_fields = mtype in PARSE_FIELD_TYPES if mtype else False
+        def _collect_spans(s: str, left: str, right: str) -> List[Tuple[int, int]]:
+            spans: List[Tuple[int, int]] = []
+            start = 0
+            while True:
+                l_idx = s.find(left, start)
+                if l_idx == -1:
+                    break
+                r_idx = s.find(right, l_idx + 1)
+                if r_idx == -1:
+                    break
+                spans.append((l_idx, r_idx))
+                start = r_idx + 1
+            return spans
+
+        def _find_colon_index(s: str, m: re.Match) -> Optional[int]:
+            segment = s[m.start():m.end()]
+            for i, ch in enumerate(segment):
+                if ch in (":", "："):
+                    return m.start() + i
+            return None
+
         if text:
-            for line in text.splitlines():
-                if "：" in line:
-                    name, value = line.split("：", 1)
-                    fields.append({"name": name.strip(), "value": value.strip() or "-", "inline": False})
-                else:
-                    description += f"{line}\n"
-        description = description.strip()
+            # 处理上游未反序列化的 "\n" 等转义换行，避免被当成普通字符
+            if "\\n" in text or "\\r" in text:
+                text = text.replace("\\r\\n", "\n").replace("\\n", "\n").replace("\\r", "\n")
+            if not should_parse_fields:
+                desc_lines.append(text.strip())
+            else:
+                # 匹配形如 "字段：值" 的片段，字段名不允许包含常见分隔符；
+                # 下一个字段需以顿号/逗号/分号等分隔开，且不能是 URL 协议开头，避免值里出现 URL 的":" 被误拆
+                name_re = r"[A-Za-z0-9\u4e00-\u9fa5_\-&]+"
+                pair_pattern = re.compile(
+                    rf"({name_re})[：:](.*?)(?=(?:[，,。；;、]+\s*(?!https?://|ftp://|ftps://|magnet:){name_re}[：:])|$)",
+                    re.IGNORECASE,
+                )
+                for line in text.splitlines():
+                    line = line.strip()
+                    if not line:
+                        continue
+                    matches = list(pair_pattern.finditer(line))
+                    if matches:
+                        book_spans = _collect_spans(line, "《", "》") + _collect_spans(line, "【", "】")
+                        if book_spans:
+                            has_book_colon = False
+                            for m in matches:
+                                colon_idx = _find_colon_index(line, m)
+                                if colon_idx is not None and any(l < colon_idx < r for l, r in book_spans):
+                                    has_book_colon = True
+                                    break
+                            if has_book_colon:
+                                desc_lines.append(line)
+                                continue
+                        # 若整行只是 URL/时间等自然包含":"的内容，则不当作字段
+                        url_like_names = {"http", "https", "ftp", "ftps", "magnet"}
+                        if all(m.group(1).lower() in url_like_names or m.group(1).isdigit() for m in matches):
+                            desc_lines.append(line)
+                            continue
+                        last_end = 0
+                        for m in matches:
+                            # 追加匹配前的非空文本到描述
+                            prefix = line[last_end:m.start()].strip(" ，,;；。、")
+                            # 仅当前缀不全是分隔符/空白时才记录
+                            if prefix and prefix.strip(" ，,;；。、"):
+                                desc_lines.append(prefix)
+                            name = m.group(1).strip()
+                            value = m.group(2).strip(" ，,;；。、\t") or "-"
+                            if name:
+                                fields.append({"name": name, "value": value, "inline": False})
+                            last_end = m.end()
+                        # 匹配末尾后的文本
+                        suffix = line[last_end:].strip(" ，,;；。、")
+                        if suffix and suffix.strip(" ，,;；。、"):
+                            desc_lines.append(suffix)
+                    else:
+                        desc_lines.append(line)
+        description = "\n".join(desc_lines).strip()
+        if not description and not fields and text:
+            description = text.strip()
         embed = discord.Embed(
             title=title,
             url=link or "https://github.com/jxxghp/MoviePilot",
-            description=description if description else (text or None),
+            description=description if description else None,
             color=0xE67E22
         )
         for field in fields:

app/modules/indexer/spider/mtorrent.py

@@ -2,6 +2,7 @@ import base64
 import json
 import re
 from typing import Tuple, List, Optional
+from urllib.parse import urlparse
 
 from app.core.config import settings
 from app.db.systemconfig_oper import SystemConfigOper
@@ -25,6 +26,9 @@ class MTorrentSpider:
     _size = 100
     _searchurl = "https://api.%s/api/torrent/search"
     _downloadurl = "https://api.%s/api/torrent/genDlToken"
+    _subtitle_list_url = "https://api.%s/api/subtitle/list"
+    _subtitle_genlink_url = "https://api.%s/api/subtitle/genlink"
+    _subtitle_download_url ="https://api.%s/api/subtitle/dlV2?credential=%s"
     _pageurl = "%sdetail/%s"
     _timeout = 15
 
@@ -262,3 +266,110 @@ class MTorrentSpider:
         # base64编码
         base64_str = base64.b64encode(json.dumps(params).encode('utf-8')).decode('utf-8')
         return f"[{base64_str}]{url}"
+
+    def get_subtitle_links(self, page_url: str) -> List[str]:
+        """
+        获取指定页面的字幕下载链接
+
+        :param page_url: 种子详情页网址
+        :type page_url: str
+        :return: 字幕下载链接
+        :rtype: List[str]
+        """
+        if not page_url:
+            return []
+        # 从馒头的详情页网址中提取种子id
+        torrent_id = urlparse(page_url).path.rsplit("/", 1)[-1].strip()
+        if not torrent_id:
+            return []
+        return self.get_subtitle_links_by_id(torrent_id)
+
+    def get_subtitle_links_by_id(self, torrent_id: str) -> List[str]:
+        """
+        获取指定种子的字幕下载链接
+
+        :param torrent_id: 种子ID
+        :type torrent_id: str
+        :return: 字幕下载链接
+        :rtype: List[str]
+        """
+        results = []
+        try:
+            for subtitle_id in self.__subtitle_ids(torrent_id) or []:
+                if link := self.__subtitle_genlink(subtitle_id):
+                    results.append(link)
+        except Exception as e:
+            logger.error(f"{self._name} 获取字幕失败：{e}")
+        return results
+
+    def __subtitle_ids(self, torrent_id: str) -> Optional[List[str]]:
+        """
+        获取指定种子的字幕列表
+
+        :param torrent_id: 种子ID
+        :type torrent_id: str
+        :return: 字幕ID
+        :rtype: List[str] | None
+        """
+        url = self._subtitle_list_url % self._domain
+        # 发送请求
+        res = RequestUtils(
+            headers={
+                "Accept": "application/json, text/plain, */*",
+                "User-Agent": f"{self._ua}",
+                "x-api-key": self._apikey,
+            },
+            proxies=self._proxy,
+            timeout=self._timeout,
+        ).post_res(url, data={"id": torrent_id})
+        if res and res.status_code == 200:
+            result = res.json()
+            if int(result.get("code", -1)) == 0:
+                return [item["id"] for item in result.get("data", []) if "id" in item]
+            else:
+                logger.warn(
+                    f"{self._name} 获取字幕列表失败，返回：{result.get("message", "未知")}"
+                )
+                return None
+        elif res is not None:
+            logger.warn(f"{self._name} 获取字幕列表失败，错误码：{res.status_code}")
+            return None
+        else:
+            logger.warn(f"{self._name} 获取字幕列表失败，无法连接 {self._domain}")
+            return None
+
+    def __subtitle_genlink(self, subtitle_id: str) -> Optional[str]:
+        """
+        获取字幕下载链接
+
+        :param subtitle_id: 字幕ID
+        :type subtitle_id: str
+        :return: 下载链接
+        :rtype: str | None
+        """
+        url = self._subtitle_genlink_url % self._domain
+        # 发送请求
+        res = RequestUtils(
+            headers={
+                "Accept": "application/json, text/plain, */*",
+                "User-Agent": f"{self._ua}",
+                "x-api-key": self._apikey,
+            },
+            proxies=self._proxy,
+            timeout=self._timeout,
+        ).post_res(url, data={"id": subtitle_id})
+        if res and res.status_code == 200:
+            result = res.json()
+            if int(result.get("code", -1)) == 0 and isinstance(result.get("data"), str):
+                return self._subtitle_download_url % (self._domain, result["data"])
+            else:
+                logger.warn(
+                    f"{self._name} 获取字幕下载链接失败，返回：{result.get("message", "未知")}"
+                )
+                return None
+        elif res is not None:
+            logger.warn(f"{self._name} 获取字幕下载链接失败，错误码：{res.status_code}")
+            return None
+        else:
+            logger.warn(f"{self._name} 获取字幕下载链接失败，无法连接 {self._domain}")
+            return None

app/modules/subtitle/__init__.py

@@ -8,9 +8,13 @@ from lxml import etree
 from app.chain.storage import StorageChain
 from app.core.config import settings
 from app.core.context import Context
+from app.db.site_oper import SiteOper
+from app.helper.sites import SitesHelper  # noqa
 from app.helper.torrent import TorrentHelper
 from app.log import logger
 from app.modules import _ModuleBase
+from app.modules.indexer.spider.mtorrent import MTorrentSpider
+from app.schemas import TorrentInfo
 from app.schemas.file import FileURI 
 from app.schemas.types import ModuleType, OtherModulesType
 from app.utils.http import RequestUtils
@@ -25,7 +29,9 @@ class SubtitleModule(_ModuleBase):
 
     # 站点详情页字幕下载链接识别XPATH
     _SITE_SUBTITLE_XPATH = [
+        '//td[@class="rowhead"][text()="字幕"]/following-sibling::td//a[not(@class)]/@href',
         '//td[@class="rowhead"][text()="字幕"]/following-sibling::td//a/@href',
+        '//div[contains(@class, "font-bold")][text()="字幕"]/following-sibling::div[1]//a[not(@class)]/@href', # 憨憨
     ]
 
     def init_module(self) -> None:
@@ -65,6 +71,54 @@ class SubtitleModule(_ModuleBase):
     def test(self):
         pass
 
+    def _get_subtitle_links(self, torrent: TorrentInfo):
+        """
+        获取字幕链接
+        """
+        # API请求方式的站点需要特殊处理
+        if torrent.site is not None:
+            site = SiteOper().get(torrent.site)
+            if indexer := SitesHelper().get_indexer(site.domain):
+                if indexer.get("parser") == "mTorrent":
+                    return MTorrentSpider(indexer).get_subtitle_links(
+                        torrent.page_url
+                    )
+                # TODO 其它采用API访问的站点
+        # 普通站点通过解析网站代码的方式获取
+        request = RequestUtils(cookies=torrent.site_cookie, ua=torrent.site_ua)
+        res = request.get_res(torrent.page_url)
+        if res and res.status_code == 200:
+            if not res.text:
+                logger.warn(f"读取页面代码失败：{torrent.page_url}")
+                return []
+            html = etree.HTML(res.text)
+            try:
+                sublink_list = []
+                for xpath in self._SITE_SUBTITLE_XPATH:
+                    sublinks = html.xpath(xpath)
+                    if sublinks:
+                        for sublink in sublinks:
+                            if not sublink:
+                                continue
+                            if not sublink.startswith("http"):
+                                base_url = StringUtils.get_base_url(torrent.page_url)
+                                if sublink.startswith("/"):
+                                    sublink = "%s%s" % (base_url, sublink)
+                                else:
+                                    sublink = "%s/%s" % (base_url, sublink)
+                            sublink_list.append(sublink)
+                        # 已成功获取了链接，后续xpath可以忽略
+                        break
+                return sublink_list
+            finally:
+                if html is not None:
+                    del html
+        elif res is not None:
+            logger.warn(f"连接 {torrent.page_url} 失败，状态码：{res.status_code}")
+        else:
+            logger.warn(f"无法打开链接：{torrent.page_url}")
+        return None
+
     def download_added(self, context: Context, download_dir: Path, torrent_content: Union[str, bytes] = None):
         """
         添加下载任务成功后，从站点下载字幕，保存到下载目录
@@ -117,83 +171,56 @@ class SubtitleModule(_ModuleBase):
             logger.error(f"下载目录不存在，无法保存字幕：{download_dir / folder_name}")
             return
         # 读取网站代码
+        sublink_list = self._get_subtitle_links(torrent)
+        if not sublink_list:
+            logger.warn(f"{torrent.page_url} 页面未找到字幕下载链接")
+            return
+        # 下载所有字幕文件
         request = RequestUtils(cookies=torrent.site_cookie, ua=torrent.site_ua)
-        res = request.get_res(torrent.page_url)
-        if res and res.status_code == 200:
-            if not res.text:
-                logger.warn(f"读取页面代码失败：{torrent.page_url}")
-                return
-            html = etree.HTML(res.text)
-            try:
-                sublink_list = []
-                for xpath in self._SITE_SUBTITLE_XPATH:
-                    sublinks = html.xpath(xpath)
-                    if sublinks:
-                        for sublink in sublinks:
-                            if not sublink:
-                                continue
-                            if not sublink.startswith("http"):
-                                base_url = StringUtils.get_base_url(torrent.page_url)
-                                if sublink.startswith("/"):
-                                    sublink = "%s%s" % (base_url, sublink)
-                                else:
-                                    sublink = "%s/%s" % (base_url, sublink)
-                            sublink_list.append(sublink)
-            finally:
-                if html is not None:
-                    del html
-            # 下载所有字幕文件
-            for sublink in sublink_list:
-                logger.info(f"找到字幕下载链接：{sublink}，开始下载...")
-                # 下载
-                ret = request.get_res(sublink)
-                if ret and ret.status_code == 200:
-                    # 保存ZIP
-                    file_name = TorrentHelper.get_url_filename(ret, sublink)
-                    if not file_name:
-                        logger.warn(f"链接不是字幕文件：{sublink}")
-                        continue
-                    if file_name.lower().endswith(".zip"):
-                        # ZIP包
-                        zip_file = settings.TEMP_PATH / file_name
-                        # 保存
-                        zip_file.write_bytes(ret.content)
-                        # 解压路径
-                        zip_path = zip_file.with_name(zip_file.stem)
-                        # 解压文件
-                        shutil.unpack_archive(zip_file, zip_path, format='zip')
-                        # 遍历转移文件
-                        for sub_file in SystemUtils.list_files(zip_path, settings.RMT_SUBEXT):
-                            target_sub_file = Path(working_dir_item.path) / Path(sub_file.name)
-                            if storageChain.get_file_item(storage, target_sub_file):
-                                logger.info(f"字幕文件已存在：{target_sub_file}")
-                                continue
-                            logger.info(f"转移字幕 {sub_file} 到 {target_sub_file} ...")
-                            storageChain.upload_file(working_dir_item, sub_file)
-                        # 删除临时文件
-                        try:
-                            shutil.rmtree(zip_path)
-                            zip_file.unlink()
-                        except Exception as err:
-                            logger.error(f"删除临时文件失败：{str(err)}")
-                    else:
-                        sub_file = settings.TEMP_PATH / file_name
-                        # 保存
-                        sub_file.write_bytes(ret.content)
+        for sublink in sublink_list:
+            logger.info(f"找到字幕下载链接：{sublink}，开始下载...")
+            # 下载
+            ret = request.get_res(sublink)
+            if ret and ret.status_code == 200:
+                # 保存ZIP
+                file_name = TorrentHelper.get_url_filename(ret, sublink)
+                if not file_name:
+                    logger.warn(f"链接不是字幕文件：{sublink}")
+                    continue
+                if file_name.lower().endswith(".zip"):
+                    # ZIP包
+                    zip_file = settings.TEMP_PATH / file_name
+                    # 保存
+                    zip_file.write_bytes(ret.content)
+                    # 解压路径
+                    zip_path = zip_file.with_name(zip_file.stem)
+                    # 解压文件
+                    shutil.unpack_archive(zip_file, zip_path, format='zip')
+                    # 遍历转移文件
+                    for sub_file in SystemUtils.list_files(zip_path, settings.RMT_SUBEXT):
                         target_sub_file = Path(working_dir_item.path) / Path(sub_file.name)
                         if storageChain.get_file_item(storage, target_sub_file):
                             logger.info(f"字幕文件已存在：{target_sub_file}")
                             continue
                         logger.info(f"转移字幕 {sub_file} 到 {target_sub_file} ...")
                         storageChain.upload_file(working_dir_item, sub_file)
+                    # 删除临时文件
+                    try:
+                        shutil.rmtree(zip_path)
+                        zip_file.unlink()
+                    except Exception as err:
+                        logger.error(f"删除临时文件失败：{str(err)}")
                 else:
-                    logger.error(f"下载字幕文件失败：{sublink}")
-                    continue
-            if sublink_list:
-                logger.info(f"{torrent.page_url} 页面字幕下载完成")
+                    sub_file = settings.TEMP_PATH / file_name
+                    # 保存
+                    sub_file.write_bytes(ret.content)
+                    target_sub_file = Path(working_dir_item.path) / Path(sub_file.name)
+                    if storageChain.get_file_item(storage, target_sub_file):
+                        logger.info(f"字幕文件已存在：{target_sub_file}")
+                        continue
+                    logger.info(f"转移字幕 {sub_file} 到 {target_sub_file} ...")
+                    storageChain.upload_file(working_dir_item, sub_file)
             else:
-                logger.warn(f"{torrent.page_url} 页面未找到字幕下载链接")
-        elif res is not None:
-            logger.warn(f"连接 {torrent.page_url} 失败，状态码：{res.status_code}")
-        else:
-            logger.warn(f"无法打开链接：{torrent.page_url}")
+                logger.error(f"下载字幕文件失败：{sublink}")
+                continue
+        logger.info(f"{torrent.page_url} 页面字幕下载完成")

app/modules/themoviedb/__init__.py

@@ -78,7 +78,7 @@ class TheMovieDbModule(_ModuleBase):
         """
         测试模块连接性
         """
-        ret = RequestUtils(proxies=settings.PROXY).get_res(
+        ret = RequestUtils(ua=settings.NORMAL_USER_AGENT, proxies=settings.PROXY).get_res(
             f"https://{settings.TMDB_API_DOMAIN}/3/movie/550?api_key={settings.TMDB_API_KEY}")
         if ret and ret.status_code == 200:
             return True, ""

version.py

@@ -1,2 +1,2 @@
-APP_VERSION = 'v2.8.9'
-FRONTEND_VERSION = 'v2.8.9'
+APP_VERSION = 'v2.9.1'
+FRONTEND_VERSION = 'v2.9.1'