refactor: slim rust acceleration surface

app/core/meta/metavideo.py

@@ -11,7 +11,6 @@ from app.schemas.types import MediaType
 from app.utils.string import StringUtils
 from app.utils.tokens import Tokens
 from app.core.meta.streamingplatform import StreamingPlatforms
-from app.utils import rust_accel
 
 
 class MetaVideo(MetaBase):
@@ -104,60 +103,58 @@ class MetaVideo(MetaBase):
         # 把年月日去掉
         title = re.sub(r'\d{4}[\s._-]\d{1,2}[\s._-]\d{1,2}', "", title)
         media_exts = settings.RMT_MEDIAEXT + settings.RMT_SUBEXT + settings.RMT_AUDIOEXT
-        rust_parse = rust_accel.parse_video_title(title, isfile=isfile, media_exts=media_exts)
+        # 拆分tokens
-        if not self.__apply_rust_parse(rust_parse):
+        tokens = Tokens(title)
-            # 拆分tokens
+        # 实例化StreamingPlatforms对象
-            tokens = Tokens(title)
+        streaming_platforms = StreamingPlatforms()
-            # 实例化StreamingPlatforms对象
+        # 解析名称、年份、季、集、资源类型、分辨率等
-            streaming_platforms = StreamingPlatforms()
+        token = tokens.get_next()
-            # 解析名称、年份、季、集、资源类型、分辨率等
+        while token:
+            self._index += 1  # 更新当前处理的token索引
+            # Part
+            self.__init_part(token, tokens)
+            # 标题
+            if self._continue_flag:
+                self.__init_name(token, media_exts)
+            # 年份
+            if self._continue_flag:
+                self.__init_year(token)
+            # 分辨率
+            if self._continue_flag:
+                self.__init_resource_pix(token)
+            # 季
+            if self._continue_flag:
+                self.__init_season(token)
+            # 集
+            if self._continue_flag:
+                self.__init_episode(token)
+            # 资源类型
+            if self._continue_flag:
+                self.__init_resource_type(token)
+            # 流媒体平台
+            if self._continue_flag:
+                self.__init_web_source(token, tokens, streaming_platforms)
+            # 视频编码
+            if self._continue_flag:
+                self.__init_video_encode(token)
+            # 视频位深
+            if self._continue_flag:
+                self.__init_video_bit(token)
+            # 音频编码
+            if self._continue_flag:
+                self.__init_audio_encode(token)
+            # 帧率
+            if self._continue_flag:
+                self.__init_fps(token)
+            # 取下一个，直到没有为卡
             token = tokens.get_next()
-            while token:
+            self._continue_flag = True
-                self._index += 1  # 更新当前处理的token索引
+        # 合成质量
-                # Part
+        if self._effect:
-                self.__init_part(token, tokens)
+            self._effect.reverse()
-                # 标题
+            self.resource_effect = " ".join(self._effect)
-                if self._continue_flag:
+        if self._source:
-                    self.__init_name(token, media_exts)
+            self.resource_type = self._source.strip()
-                # 年份
-                if self._continue_flag:
-                    self.__init_year(token)
-                # 分辨率
-                if self._continue_flag:
-                    self.__init_resource_pix(token)
-                # 季
-                if self._continue_flag:
-                    self.__init_season(token)
-                # 集
-                if self._continue_flag:
-                    self.__init_episode(token)
-                # 资源类型
-                if self._continue_flag:
-                    self.__init_resource_type(token)
-                # 流媒体平台
-                if self._continue_flag:
-                    self.__init_web_source(token, tokens, streaming_platforms)
-                # 视频编码
-                if self._continue_flag:
-                    self.__init_video_encode(token)
-                # 视频位深
-                if self._continue_flag:
-                    self.__init_video_bit(token)
-                # 音频编码
-                if self._continue_flag:
-                    self.__init_audio_encode(token)
-                # 帧率
-                if self._continue_flag:
-                    self.__init_fps(token)
-                # 取下一个，直到没有为卡
-                token = tokens.get_next()
-                self._continue_flag = True
-            # 合成质量
-            if self._effect:
-                self._effect.reverse()
-                self.resource_effect = " ".join(self._effect)
-            if self._source:
-                self.resource_type = self._source.strip()
         # 提取原盘DIY
         if self.resource_type and "BluRay" in self.resource_type:
             if (self.subtitle and re.findall(r'D[Ii]Y', self.subtitle)) \
@@ -188,62 +185,6 @@ class MetaVideo(MetaBase):
         if not self.video_bit:
             self.video_bit = self.extract_video_bit(self.video_encode)
 
-    def __apply_rust_parse(self, rust_parse: Optional[dict]) -> bool:
-        """
-        应用 Rust 主识别结果；成功时跳过 Python token 主循环。
-        """
-        if not rust_parse or not rust_parse.get("complete"):
-            return False
-        self.cn_name = rust_parse.get("cn_name")
-        self.en_name = rust_parse.get("en_name")
-        if rust_parse.get("year"):
-            self.year = str(rust_parse.get("year"))
-        self.part = rust_parse.get("part")
-        self.__merge_rust_parse(rust_parse)
-        media_type = rust_parse.get("type")
-        if media_type == "tv":
-            self.type = MediaType.TV
-        elif media_type == "movie":
-            self.type = MediaType.MOVIE
-        return True
-
-    def __merge_rust_parse(self, rust_parse: Optional[dict]) -> None:
-        """
-        合并 Rust 预解析结果，仅补齐 Python 识别未命中的资源字段。
-        """
-        if not rust_parse:
-            return
-        if not self.year and rust_parse.get("year"):
-            self.year = str(rust_parse.get("year"))
-        if self.begin_season is None and rust_parse.get("begin_season") is not None:
-            self.begin_season = int(rust_parse.get("begin_season"))
-            self.type = MediaType.TV
-        if self.end_season is None and rust_parse.get("end_season") is not None:
-            self.end_season = int(rust_parse.get("end_season"))
-        if not self.total_season and rust_parse.get("total_season"):
-            self.total_season = int(rust_parse.get("total_season"))
-        if self.begin_episode is None and rust_parse.get("begin_episode") is not None:
-            self.begin_episode = int(rust_parse.get("begin_episode"))
-            self.type = MediaType.TV
-        if self.end_episode is None and rust_parse.get("end_episode") is not None:
-            self.end_episode = int(rust_parse.get("end_episode"))
-        if not self.total_episode and rust_parse.get("total_episode"):
-            self.total_episode = int(rust_parse.get("total_episode"))
-        if not self.resource_pix and rust_parse.get("resource_pix"):
-            self.resource_pix = rust_parse.get("resource_pix")
-        if not self.resource_type and rust_parse.get("resource_type"):
-            self.resource_type = rust_parse.get("resource_type")
-        if not self.resource_effect and rust_parse.get("resource_effect"):
-            self.resource_effect = rust_parse.get("resource_effect")
-        if not self.video_encode and rust_parse.get("video_encode"):
-            self.video_encode = rust_parse.get("video_encode")
-        if not self.video_bit and rust_parse.get("video_bit"):
-            self.video_bit = rust_parse.get("video_bit")
-        if not self.audio_encode and rust_parse.get("audio_encode"):
-            self.audio_encode = rust_parse.get("audio_encode")
-        if self.fps is None and rust_parse.get("fps") is not None:
-            self.fps = int(rust_parse.get("fps"))
-
     @staticmethod
     def __get_title_from_description(description: str) -> Optional[str]:
         """

app/core/metainfo.py

@@ -12,7 +12,6 @@ from app.core.meta.infopath import (
 from app.core.meta.words import WordsMatcher
 from app.log import logger
 from app.schemas.types import MediaType
-from app.utils import rust_accel
 
 
 _ANIME_BRACKET_RE = re.compile(r'【[+0-9XVPI-]+】\s*【', re.IGNORECASE)
@@ -169,9 +168,6 @@ def is_anime(name: str) -> bool:
     :param name: 名称
     :return: 是否动漫
     """
-    rust_result = rust_accel.is_anime(name)
-    if rust_result is not None:
-        return rust_result
     if not name:
         return False
     if _ANIME_BRACKET_RE.search(name):
@@ -189,9 +185,6 @@ def find_metainfo(title: str) -> Tuple[str, dict]:
     """
     从标题中提取媒体信息
     """
-    rust_result = rust_accel.find_metainfo(title)
-    if rust_result is not None:
-        return rust_result
     metainfo = _empty_metainfo()
     if not title:
         return title, metainfo

app/helper/rss.py

@@ -9,7 +9,6 @@ from lxml import etree
 from app.core.config import settings
 from app.helper.browser import PlaywrightHelper
 from app.log import logger
-from app.utils import rust_accel
 from app.utils.http import RequestUtils
 from app.utils.string import StringUtils
 
@@ -228,32 +227,6 @@ class RssHelper:
         },
     }
 
-    @staticmethod
-    def __format_rust_items(items: List[dict]) -> List[dict]:
-        """
-        将 Rust RSS 解析结果转换为原 Python XPath 解析返回结构。
-        """
-        ret_array = []
-        for item in items:
-            pubdate = ""
-            pubdate_raw = item.get("pubdate_raw")
-            if pubdate_raw:
-                pubdate = StringUtils.get_time(pubdate_raw)
-                if pubdate is not None:
-                    pubdate = pubdate.astimezone(tz=None)
-            tmp_dict = {
-                'title': item.get("title") or "",
-                'enclosure': item.get("enclosure") or "",
-                'size': item.get("size") or 0,
-                'description': item.get("description") or "",
-                'link': item.get("link") or "",
-                'pubdate': pubdate
-            }
-            if item.get("nickname"):
-                tmp_dict['nickname'] = item.get("nickname")
-            ret_array.append(tmp_dict)
-        return ret_array
-
     def parse(self, url, proxy: bool = False,
               timeout: Optional[int] = 15, headers: dict = None, ua: str = None) -> Union[List[dict], None, bool]:
         """
@@ -325,12 +298,6 @@ class RssHelper:
                     logger.error("RSS内容不是有效的XML格式")
                     return False
 
-                rust_items = rust_accel.parse_rss_items(ret_xml, self.MAX_RSS_ITEMS)
-                if rust_items is not None:
-                    if len(rust_items) >= self.MAX_RSS_ITEMS:
-                        logger.warning(f"RSS条目过多，仅处理前{self.MAX_RSS_ITEMS}个")
-                    return self.__format_rust_items(rust_items)
-
                 # 使用lxml.etree解析XML
                 parser = None
                 try:

app/modules/filter/__init__.py

@@ -11,7 +11,6 @@ from app.modules import _ModuleBase
 from app.modules.filter.RuleParser import RuleParser
 from app.modules.filter.builtin_rules import BUILTIN_RULE_SET
 from app.schemas.types import ModuleType, OtherModulesType, SystemConfigKey
-from app.utils import rust_accel
 from app.utils.string import StringUtils
 
 
@@ -139,9 +138,6 @@ class FilterModule(_ModuleBase):
         # 查询规则表详情
         groups = self.rulehelper.get_rule_group_by_media(media=mediainfo, group_names=rule_groups)
         if groups:
-            rust_filtered = self.__filter_torrents_by_rust(groups, torrent_list, mediainfo)
-            if rust_filtered is not None:
-                return rust_filtered
             for group in groups:
                 # 过滤种子
                 torrent_list = self.__filter_torrents(
@@ -154,46 +150,6 @@ class FilterModule(_ModuleBase):
                 )
         return torrent_list
 
-    def __filter_torrents_by_rust(self, groups: list, torrent_list: List[TorrentInfo],
-                                  mediainfo: MediaInfo) -> Optional[List[TorrentInfo]]:
-        """
-        使用 Rust 批量过滤种子；遇到不可支持的规则时返回 None 交由 Python 逻辑处理。
-        """
-        if not torrent_list:
-            return []
-        payloads = [self.__build_rust_torrent_payload(torrent) for torrent in torrent_list]
-        media_payload = mediainfo.to_dict() if mediainfo and hasattr(mediainfo, "to_dict") else (
-            vars(mediainfo).copy() if mediainfo else None
-        )
-        result = rust_accel.filter_torrents(
-            rule_set=self.rule_set,
-            rule_strings=[group.rule_string for group in groups],
-            torrents=payloads,
-            media_info=media_payload,
-        )
-        if result is None:
-            return None
-        filtered_torrents = []
-        for index, pri_order in result:
-            torrent = torrent_list[int(index)]
-            torrent.pri_order = int(pri_order)
-            filtered_torrents.append(torrent)
-        return filtered_torrents
-
-    @staticmethod
-    def __build_rust_torrent_payload(torrent: TorrentInfo) -> dict:
-        """
-        组装 Rust 过滤器需要的纯数据载荷，避免 Rust 直接依赖 Python 业务对象。
-        """
-        payload = torrent.to_dict() if hasattr(torrent, "to_dict") else vars(torrent).copy()
-        payload["pub_minutes"] = torrent.pub_minutes()
-        if payload.get("size"):
-            meta = MetaInfo(title=torrent.title, subtitle=torrent.description)
-            payload["episode_count"] = meta.total_episode or 1
-        else:
-            payload["episode_count"] = 1
-        return payload
-
     def __filter_torrents(self, rule_string: str, rule_name: str,
                           torrent_list: List[TorrentInfo],
                           mediainfo: MediaInfo,

app/modules/indexer/spider/__init__.py

@@ -12,7 +12,6 @@ from pyquery import PyQuery
 from app.core.config import settings
 from app.log import logger
 from app.schemas.types import MediaType
-from app.utils import rust_accel
 from app.utils.http import RequestUtils, AsyncRequestUtils
 from app.utils.string import StringUtils
 from app.utils.url import UrlUtils
@@ -96,19 +95,6 @@ class SiteSpider:
         """
         获取搜索URL
         """
-        rust_url = rust_accel.build_indexer_search_url({
-            "search": self.search,
-            "batch": self.batch,
-            "browse": self.browse,
-            "category": self.category,
-            "domain": self.domain,
-            "keyword": self.keyword,
-            "mtype": self.mtype.value if self.mtype else None,
-            "cat": self.cat,
-            "page": self.page,
-        })
-        if rust_url:
-            return rust_url
         # 种子搜索相对路径
         paths = self.search.get('paths', [])
         torrentspath = ""
@@ -753,16 +739,6 @@ class SiteSpider:
 
         # 清空旧结果
         self.torrents_info_array = []
-        rust_torrents = rust_accel.parse_indexer_torrents(
-            html_text=html_text,
-            domain=self.domain,
-            list_config=self.list,
-            fields=self.fields,
-            category=self.category,
-            result_num=int(self.result_num),
-        )
-        if rust_torrents is not None:
-            return rust_torrents
         html_doc = None
         try:
             # 解析站点文本对象

app/utils/rust_accel.py

@@ -1,7 +1,6 @@
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Optional
 
 from app.log import logger
-from app.schemas.types import MediaType
 
 try:
     import moviepilot_rust as _moviepilot_rust
@@ -26,64 +25,6 @@ def import_error() -> Optional[Exception]:
     return _import_error
 
 
-def is_anime(name: str) -> Optional[bool]:
-    """
-    使用 Rust 快路径判断标题是否为动漫格式，不可用时返回 None。
-    """
-    if not _moviepilot_rust:
-        return None
-    try:
-        return bool(_moviepilot_rust.is_anime_fast(name or ""))
-    except BaseException as err:
-        _raise_non_rust_panic(err)
-        logger.debug(f"Rust 动漫识别失败，回退 Python：{err}")
-        return None
-
-
-def find_metainfo(title: str) -> Optional[Tuple[str, Dict[str, Any]]]:
-    """
-    使用 Rust 快路径提取标题中的内嵌媒体标签，不可用时返回 None。
-    """
-    if not _moviepilot_rust:
-        return None
-    try:
-        result = _moviepilot_rust.find_metainfo_fast(title or "")
-    except BaseException as err:
-        _raise_non_rust_panic(err)
-        logger.debug(f"Rust 内嵌媒体标签识别失败，回退 Python：{err}")
-        return None
-    metainfo = {
-        "tmdbid": result.get("tmdbid"),
-        "doubanid": result.get("doubanid"),
-        "type": _coerce_media_type(result.get("type")),
-        "begin_season": result.get("begin_season"),
-        "end_season": result.get("end_season"),
-        "total_season": result.get("total_season"),
-        "begin_episode": result.get("begin_episode"),
-        "end_episode": result.get("end_episode"),
-        "total_episode": result.get("total_episode"),
-    }
-    return result.get("title"), metainfo
-
-
-def parse_video_title(
-        title: str,
-        isfile: bool = False,
-        media_exts: Optional[List[str]] = None,
-) -> Optional[Dict[str, Any]]:
-    """
-    使用 Rust 执行影视标题主识别流程，不可用时返回 None。
-    """
-    if not _moviepilot_rust:
-        return None
-    try:
-        return _moviepilot_rust.parse_video_title_fast(title or "", isfile, media_exts or [])
-    except BaseException as err:
-        _raise_non_rust_panic(err)
-        logger.debug(f"Rust 影视标题主识别失败，回退 Python：{err}")
-        return None
-
-
 def parse_filter_rule(expression: str) -> Optional[list]:
     """
     使用 Rust 解析过滤规则表达式，不可用时返回 None。
@@ -98,92 +39,6 @@ def parse_filter_rule(expression: str) -> Optional[list]:
         return None
 
 
-def filter_torrents(
-        rule_set: Dict[str, dict],
-        rule_strings: List[str],
-        torrents: List[dict],
-        media_info: Optional[dict] = None,
-) -> Optional[list]:
-    """
-    使用 Rust 批量执行种子过滤，不可用或不兼容时返回 None。
-    """
-    if not _moviepilot_rust:
-        return None
-    try:
-        return _moviepilot_rust.filter_torrents_fast(rule_set, rule_strings, torrents, media_info)
-    except BaseException as err:
-        _raise_non_rust_panic(err)
-        logger.debug(f"Rust 种子过滤失败，回退 Python：{err}")
-        return None
-
-
-def build_indexer_search_url(config: dict) -> Optional[str]:
-    """
-    使用 Rust 根据普通 indexer 配置生成搜索 URL，不可用时返回 None。
-    """
-    if not _moviepilot_rust:
-        return None
-    try:
-        return _moviepilot_rust.build_indexer_search_url_fast(config)
-    except BaseException as err:
-        _raise_non_rust_panic(err)
-        logger.debug(f"Rust 站点搜索 URL 生成失败，回退 Python：{err}")
-        return None
-
-
-def parse_indexer_torrents(
-        html_text: str,
-        domain: str,
-        list_config: dict,
-        fields: dict,
-        category: Optional[dict],
-        result_num: int,
-) -> Optional[List[dict]]:
-    """
-    使用 Rust 批量解析普通 indexer 页面，不支持的配置返回 None。
-    """
-    if not _moviepilot_rust:
-        return None
-    try:
-        return _moviepilot_rust.parse_indexer_torrents_fast(
-            html_text or "",
-            domain or "",
-            list_config or {},
-            fields or {},
-            category,
-            int(result_num or 0),
-        )
-    except BaseException as err:
-        _raise_non_rust_panic(err)
-        logger.debug(f"Rust 站点页面解析失败，回退 Python：{err}")
-        return None
-
-
-def parse_rss_items(xml_text: str, max_items: int) -> Optional[List[dict]]:
-    """
-    使用 Rust 批量解析 RSS/Atom 条目，不可用或解析失败时返回 None。
-    """
-    if not _moviepilot_rust:
-        return None
-    try:
-        return _moviepilot_rust.parse_rss_items_fast(xml_text or "", int(max_items or 0))
-    except BaseException as err:
-        _raise_non_rust_panic(err)
-        logger.debug(f"Rust RSS 条目解析失败，回退 Python：{err}")
-        return None
-
-
-def _coerce_media_type(value: Optional[str]) -> Optional[MediaType]:
-    """
-    将 Rust 返回的媒体类型字符串转换为系统 MediaType。
-    """
-    if value == "movies":
-        return MediaType.MOVIE
-    if value == "tv":
-        return MediaType.TV
-    return None
-
-
 def _raise_non_rust_panic(err: BaseException) -> None:
     """
     只吞掉 Rust 扩展 panic/异常，保留用户中断和进程退出语义。

rust/moviepilot_rust/Cargo.lock

@@ -2,272 +2,24 @@
 # It is not intended for manual editing.
 version = 4
 
-[[package]]
-name = "aho-corasick"
-version = "1.1.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
-dependencies = [
- "memchr",
-]
-
 [[package]]
 name = "autocfg"
 version = "1.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
 
-[[package]]
-name = "bitflags"
-version = "2.11.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4512299f36f043ab09a583e57bceb5a5aab7a73db1805848e8fef3c9e8c78b3"
-
-[[package]]
-name = "byteorder"
-version = "1.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
-
 [[package]]
 name = "cfg-if"
 version = "1.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
 
-[[package]]
-name = "cssparser"
-version = "0.35.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4e901edd733a1472f944a45116df3f846f54d37e67e68640ac8bb69689aca2aa"
-dependencies = [
- "cssparser-macros",
- "dtoa-short",
- "itoa",
- "phf",
- "smallvec",
-]
-
-[[package]]
-name = "cssparser-macros"
-version = "0.6.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "13b588ba4ac1a99f7f2964d24b3d896ddc6bf847ee3855dbd4366f058cfcd331"
-dependencies = [
- "quote",
- "syn",
-]
-
-[[package]]
-name = "derive_more"
-version = "2.1.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d751e9e49156b02b44f9c1815bcb94b984cdcc4396ecc32521c739452808b134"
-dependencies = [
- "derive_more-impl",
-]
-
-[[package]]
-name = "derive_more-impl"
-version = "2.1.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "799a97264921d8623a957f6c3b9011f3b5492f557bbb7a5a19b7fa6d06ba8dcb"
-dependencies = [
- "proc-macro2",
- "quote",
- "rustc_version",
- "syn",
-]
-
-[[package]]
-name = "displaydoc"
-version = "0.2.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
-]
-
-[[package]]
-name = "dtoa"
-version = "1.0.11"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4c3cf4824e2d5f025c7b531afcb2325364084a16806f6d47fbc1f5fbd9960590"
-
-[[package]]
-name = "dtoa-short"
-version = "0.3.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cd1511a7b6a56299bd043a9c167a6d2bfb37bf84a6dfceaba651168adfb43c87"
-dependencies = [
- "dtoa",
-]
-
-[[package]]
-name = "ego-tree"
-version = "0.10.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b2972feb8dffe7bc8c5463b1dacda1b0dfbed3710e50f977d965429692d74cd8"
-
-[[package]]
-name = "form_urlencoded"
-version = "1.2.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cb4cb245038516f5f85277875cdaa4f7d2c9a0fa0468de06ed190163b1581fcf"
-dependencies = [
- "percent-encoding",
-]
-
-[[package]]
-name = "futf"
-version = "0.1.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "df420e2e84819663797d1ec6544b13c5be84629e7bb00dc960d6917db2987843"
-dependencies = [
- "mac",
- "new_debug_unreachable",
-]
-
-[[package]]
-name = "fxhash"
-version = "0.2.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c31b6d751ae2c7f11320402d34e41349dd1016f8d5d45e48c4312bc8625af50c"
-dependencies = [
- "byteorder",
-]
-
-[[package]]
-name = "getopts"
-version = "0.2.24"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cfe4fbac503b8d1f88e6676011885f34b7174f46e59956bba534ba83abded4df"
-dependencies = [
- "unicode-width",
-]
-
 [[package]]
 name = "heck"
 version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
 
-[[package]]
-name = "html5ever"
-version = "0.35.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "55d958c2f74b664487a2035fe1dadb032c48718a03b63f3ab0b8537db8549ed4"
-dependencies = [
- "log",
- "markup5ever",
- "match_token",
-]
-
-[[package]]
-name = "icu_collections"
-version = "2.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2984d1cd16c883d7935b9e07e44071dca8d917fd52ecc02c04d5fa0b5a3f191c"
-dependencies = [
- "displaydoc",
- "potential_utf",
- "utf8_iter",
- "yoke",
- "zerofrom",
- "zerovec",
-]
-
-[[package]]
-name = "icu_locale_core"
-version = "2.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "92219b62b3e2b4d88ac5119f8904c10f8f61bf7e95b640d25ba3075e6cac2c29"
-dependencies = [
- "displaydoc",
- "litemap",
- "tinystr",
- "writeable",
- "zerovec",
-]
-
-[[package]]
-name = "icu_normalizer"
-version = "2.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c56e5ee99d6e3d33bd91c5d85458b6005a22140021cc324cea84dd0e72cff3b4"
-dependencies = [
- "icu_collections",
- "icu_normalizer_data",
- "icu_properties",
- "icu_provider",
- "smallvec",
- "zerovec",
-]
-
-[[package]]
-name = "icu_normalizer_data"
-version = "2.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "da3be0ae77ea334f4da67c12f149704f19f81d1adf7c51cf482943e84a2bad38"
-
-[[package]]
-name = "icu_properties"
-version = "2.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bee3b67d0ea5c2cca5003417989af8996f8604e34fb9ddf96208a033901e70de"
-dependencies = [
- "icu_collections",
- "icu_locale_core",
- "icu_properties_data",
- "icu_provider",
- "zerotrie",
- "zerovec",
-]
-
-[[package]]
-name = "icu_properties_data"
-version = "2.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8e2bbb201e0c04f7b4b3e14382af113e17ba4f63e2c9d2ee626b720cbce54a14"
-
-[[package]]
-name = "icu_provider"
-version = "2.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "139c4cf31c8b5f33d7e199446eff9c1e02decfc2f0eec2c8d71f65befa45b421"
-dependencies = [
- "displaydoc",
- "icu_locale_core",
- "writeable",
- "yoke",
- "zerofrom",
- "zerotrie",
- "zerovec",
-]
-
-[[package]]
-name = "idna"
-version = "1.1.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3b0875f23caa03898994f6ddc501886a45c7d3d62d04d2d90788d47be1b1e4de"
-dependencies = [
- "idna_adapter",
- "smallvec",
- "utf8_iter",
-]
-
-[[package]]
-name = "idna_adapter"
-version = "1.2.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cb68373c0d6620ef8105e855e7745e18b0d00d3bdb07fb532e434244cdb9a714"
-dependencies = [
- "icu_normalizer",
- "icu_properties",
-]
-
 [[package]]
 name = "indoc"
 version = "2.0.7"
@@ -277,79 +29,12 @@ dependencies = [
  "rustversion",
 ]
 
-[[package]]
-name = "itoa"
-version = "1.0.18"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
-
 [[package]]
 name = "libc"
 version = "0.2.186"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66"
 
-[[package]]
-name = "litemap"
-version = "0.8.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
-
-[[package]]
-name = "lock_api"
-version = "0.4.14"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "224399e74b87b5f3557511d98dff8b14089b3dadafcab6bb93eab67d3aace965"
-dependencies = [
- "scopeguard",
-]
-
-[[package]]
-name = "log"
-version = "0.4.29"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5e5032e24019045c762d3c0f28f5b6b8bbf38563a65908389bf7978758920897"
-
-[[package]]
-name = "mac"
-version = "0.1.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
-
-[[package]]
-name = "markup5ever"
-version = "0.35.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "311fe69c934650f8f19652b3946075f0fc41ad8757dbb68f1ca14e7900ecc1c3"
-dependencies = [
- "log",
- "tendril",
- "web_atoms",
-]
-
-[[package]]
-name = "match_token"
-version = "0.35.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ac84fd3f360fcc43dc5f5d186f02a94192761a080e8bc58621ad4d12296a58cf"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
-]
-
-[[package]]
-name = "memchr"
-version = "2.8.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f8ca58f447f06ed17d5fc4043ce1b10dd205e060fb3ce5b979b8ed8e59ff3f79"
-
-[[package]]
-name = "memo-map"
-version = "0.3.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38d1115007560874e373613744c6fba374c17688327a71c1476d1a5954cc857b"
-
 [[package]]
 name = "memoffset"
 version = "0.9.1"
@@ -359,144 +44,25 @@ dependencies = [
  "autocfg",
 ]
 
-[[package]]
-name = "minijinja"
-version = "2.20.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2929e494b2280e1e18959bb2e121da03347ae896896fdfaceaab43c88a02803f"
-dependencies = [
- "memo-map",
- "serde",
-]
-
 [[package]]
 name = "moviepilot-rust"
 version = "0.1.0"
 dependencies = [
- "minijinja",
- "once_cell",
- "percent-encoding",
  "pyo3",
- "quick-xml",
- "regex",
- "scraper",
- "url",
 ]
 
-[[package]]
-name = "new_debug_unreachable"
-version = "1.0.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "650eef8c711430f1a879fdd01d4745a7deea475becfb90269c06775983bbf086"
-
 [[package]]
 name = "once_cell"
 version = "1.21.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
 
-[[package]]
-name = "parking_lot"
-version = "0.12.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "93857453250e3077bd71ff98b6a65ea6621a19bb0f559a85248955ac12c45a1a"
-dependencies = [
- "lock_api",
- "parking_lot_core",
-]
-
-[[package]]
-name = "parking_lot_core"
-version = "0.9.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2621685985a2ebf1c516881c026032ac7deafcda1a2c9b7850dc81e3dfcb64c1"
-dependencies = [
- "cfg-if",
- "libc",
- "redox_syscall",
- "smallvec",
- "windows-link",
-]
-
-[[package]]
-name = "percent-encoding"
-version = "2.3.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9b4f627cb1b25917193a259e49bdad08f671f8d9708acfd5fe0a8c1455d87220"
-
-[[package]]
-name = "phf"
-version = "0.11.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1fd6780a80ae0c52cc120a26a1a42c1ae51b247a253e4e06113d23d2c2edd078"
-dependencies = [
- "phf_macros",
- "phf_shared",
-]
-
-[[package]]
-name = "phf_codegen"
-version = "0.11.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aef8048c789fa5e851558d709946d6d79a8ff88c0440c587967f8e94bfb1216a"
-dependencies = [
- "phf_generator",
- "phf_shared",
-]
-
-[[package]]
-name = "phf_generator"
-version = "0.11.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3c80231409c20246a13fddb31776fb942c38553c51e871f8cbd687a4cfb5843d"
-dependencies = [
- "phf_shared",
- "rand",
-]
-
-[[package]]
-name = "phf_macros"
-version = "0.11.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f84ac04429c13a7ff43785d75ad27569f2951ce0ffd30a3321230db2fc727216"
-dependencies = [
- "phf_generator",
- "phf_shared",
- "proc-macro2",
- "quote",
- "syn",
-]
-
-[[package]]
-name = "phf_shared"
-version = "0.11.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "67eabc2ef2a60eb7faa00097bd1ffdb5bd28e62bf39990626a582201b7a754e5"
-dependencies = [
- "siphasher",
-]
-
 [[package]]
 name = "portable-atomic"
 version = "1.13.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c33a9471896f1c69cecef8d20cbe2f7accd12527ce60845ff44c153bb2a21b49"
 
-[[package]]
-name = "potential_utf"
-version = "0.1.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0103b1cef7ec0cf76490e969665504990193874ea05c85ff9bab8b911d0a0564"
-dependencies = [
- "zerovec",
-]
-
-[[package]]
-name = "precomputed-hash"
-version = "0.1.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "925383efa346730478fb4838dbe9137d2a47675ad789c546d150a6e1dd4ab31c"
-
 [[package]]
 name = "proc-macro2"
 version = "1.0.106"
@@ -569,15 +135,6 @@ dependencies = [
  "syn",
 ]
 
-[[package]]
-name = "quick-xml"
-version = "0.38.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b66c2058c55a409d601666cffe35f04333cf1013010882cec174a7467cd4e21c"
-dependencies = [
- "memchr",
-]
-
 [[package]]
 name = "quote"
 version = "1.0.45"
@@ -587,201 +144,12 @@ dependencies = [
  "proc-macro2",
 ]
 
-[[package]]
-name = "rand"
-version = "0.8.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5ca0ecfa931c29007047d1bc58e623ab12e5590e8c7cc53200d5202b69266d8a"
-dependencies = [
- "rand_core",
-]
-
-[[package]]
-name = "rand_core"
-version = "0.6.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
-
-[[package]]
-name = "redox_syscall"
-version = "0.5.18"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ed2bf2547551a7053d6fdfafda3f938979645c44812fbfcda098faae3f1a362d"
-dependencies = [
- "bitflags",
-]
-
-[[package]]
-name = "regex"
-version = "1.12.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e10754a14b9137dd7b1e3e5b0493cc9171fdd105e0ab477f51b72e7f3ac0e276"
-dependencies = [
- "aho-corasick",
- "memchr",
- "regex-automata",
- "regex-syntax",
-]
-
-[[package]]
-name = "regex-automata"
-version = "0.4.14"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6e1dd4122fc1595e8162618945476892eefca7b88c52820e74af6262213cae8f"
-dependencies = [
- "aho-corasick",
- "memchr",
- "regex-syntax",
-]
-
-[[package]]
-name = "regex-syntax"
-version = "0.8.10"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dc897dd8d9e8bd1ed8cdad82b5966c3e0ecae09fb1907d58efaa013543185d0a"
-
-[[package]]
-name = "rustc_version"
-version = "0.4.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cfcb3a22ef46e85b45de6ee7e79d063319ebb6594faafcf1c225ea92ab6e9b92"
-dependencies = [
- "semver",
-]
-
 [[package]]
 name = "rustversion"
 version = "1.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
 
-[[package]]
-name = "scopeguard"
-version = "1.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
-
-[[package]]
-name = "scraper"
-version = "0.24.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e5f3a24d916e78954af99281a455168d4a9515d65eca99a18da1b813689c4ad9"
-dependencies = [
- "cssparser",
- "ego-tree",
- "getopts",
- "html5ever",
- "precomputed-hash",
- "selectors",
- "tendril",
-]
-
-[[package]]
-name = "selectors"
-version = "0.31.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5685b6ae43bfcf7d2e7dfcfb5d8e8f61b46442c902531e41a32a9a8bf0ee0fb6"
-dependencies = [
- "bitflags",
- "cssparser",
- "derive_more",
- "fxhash",
- "log",
- "new_debug_unreachable",
- "phf",
- "phf_codegen",
- "precomputed-hash",
- "servo_arc",
- "smallvec",
-]
-
-[[package]]
-name = "semver"
-version = "1.0.28"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a7852d02fc848982e0c167ef163aaff9cd91dc640ba85e263cb1ce46fae51cd"
-
-[[package]]
-name = "serde"
-version = "1.0.228"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
-dependencies = [
- "serde_core",
-]
-
-[[package]]
-name = "serde_core"
-version = "1.0.228"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
-dependencies = [
- "serde_derive",
-]
-
-[[package]]
-name = "serde_derive"
-version = "1.0.228"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
-]
-
-[[package]]
-name = "servo_arc"
-version = "0.4.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "170fb83ab34de17dc69aa7c67482b22218ddb85da56546f9bd6b929e32a05930"
-dependencies = [
- "stable_deref_trait",
-]
-
-[[package]]
-name = "siphasher"
-version = "1.0.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8ee5873ec9cce0195efcb7a4e9507a04cd49aec9c83d0389df45b1ef7ba2e649"
-
-[[package]]
-name = "smallvec"
-version = "1.15.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "67b1b7a3b5fe4f1376887184045fcf45c69e92af734b7aaddc05fb777b6fbd03"
-
-[[package]]
-name = "stable_deref_trait"
-version = "1.2.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596"
-
-[[package]]
-name = "string_cache"
-version = "0.8.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bf776ba3fa74f83bf4b63c3dcbbf82173db2632ed8452cb2d891d33f459de70f"
-dependencies = [
- "new_debug_unreachable",
- "parking_lot",
- "phf_shared",
- "precomputed-hash",
- "serde",
-]
-
-[[package]]
-name = "string_cache_codegen"
-version = "0.5.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c711928715f1fe0fe509c53b43e993a9a557babc2d0a3567d0a3006f1ac931a0"
-dependencies = [
- "phf_generator",
- "phf_shared",
- "proc-macro2",
- "quote",
-]
-
 [[package]]
 name = "syn"
 version = "2.0.117"
@@ -793,183 +161,20 @@ dependencies = [
  "unicode-ident",
 ]
 
-[[package]]
-name = "synstructure"
-version = "0.13.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "728a70f3dbaf5bab7f0c4b1ac8d7ae5ea60a4b5549c8a5914361c99147a709d2"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
-]
-
 [[package]]
 name = "target-lexicon"
 version = "0.12.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "61c41af27dd6d1e27b1b16b489db798443478cef1f06a660c96db617ba5de3b1"
 
-[[package]]
-name = "tendril"
-version = "0.4.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d24a120c5fc464a3458240ee02c299ebcb9d67b5249c8848b09d639dca8d7bb0"
-dependencies = [
- "futf",
- "mac",
- "utf-8",
-]
-
-[[package]]
-name = "tinystr"
-version = "0.8.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c8323304221c2a851516f22236c5722a72eaa19749016521d6dff0824447d96d"
-dependencies = [
- "displaydoc",
- "zerovec",
-]
-
 [[package]]
 name = "unicode-ident"
 version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
 
-[[package]]
-name = "unicode-width"
-version = "0.2.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
-
 [[package]]
 name = "unindent"
 version = "0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7264e107f553ccae879d21fbea1d6724ac785e8c3bfc762137959b5802826ef3"
-
-[[package]]
-name = "url"
-version = "2.5.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ff67a8a4397373c3ef660812acab3268222035010ab8680ec4215f38ba3d0eed"
-dependencies = [
- "form_urlencoded",
- "idna",
- "percent-encoding",
- "serde",
-]
-
-[[package]]
-name = "utf-8"
-version = "0.7.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9"
-
-[[package]]
-name = "utf8_iter"
-version = "1.0.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
-
-[[package]]
-name = "web_atoms"
-version = "0.1.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "57ffde1dc01240bdf9992e3205668b235e59421fd085e8a317ed98da0178d414"
-dependencies = [
- "phf",
- "phf_codegen",
- "string_cache",
- "string_cache_codegen",
-]
-
-[[package]]
-name = "windows-link"
-version = "0.2.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
-
-[[package]]
-name = "writeable"
-version = "0.6.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ffae5123b2d3fc086436f8834ae3ab053a283cfac8fe0a0b8eaae044768a4c4"
-
-[[package]]
-name = "yoke"
-version = "0.8.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "abe8c5fda708d9ca3df187cae8bfb9ceda00dd96231bed36e445a1a48e66f9ca"
-dependencies = [
- "stable_deref_trait",
- "yoke-derive",
- "zerofrom",
-]
-
-[[package]]
-name = "yoke-derive"
-version = "0.8.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "de844c262c8848816172cef550288e7dc6c7b7814b4ee56b3e1553f275f1858e"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
- "synstructure",
-]
-
-[[package]]
-name = "zerofrom"
-version = "0.1.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0ec05a11813ea801ff6d75110ad09cd0824ddba17dfe17128ea0d5f68e6c5272"
-dependencies = [
- "zerofrom-derive",
-]
-
-[[package]]
-name = "zerofrom-derive"
-version = "0.1.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "11532158c46691caf0f2593ea8358fed6bbf68a0315e80aae9bd41fbade684a1"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
- "synstructure",
-]
-
-[[package]]
-name = "zerotrie"
-version = "0.2.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0f9152d31db0792fa83f70fb2f83148effb5c1f5b8c7686c3459e361d9bc20bf"
-dependencies = [
- "displaydoc",
- "yoke",
- "zerofrom",
-]
-
-[[package]]
-name = "zerovec"
-version = "0.11.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "90f911cbc359ab6af17377d242225f4d75119aec87ea711a880987b18cd7b239"
-dependencies = [
- "yoke",
- "zerofrom",
- "zerovec-derive",
-]
-
-[[package]]
-name = "zerovec-derive"
-version = "0.11.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "625dc425cab0dca6dc3c3319506e6593dcb08a9f387ea3b284dbd52a92c40555"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
-]

rust/moviepilot_rust/Cargo.toml

@@ -8,11 +8,4 @@ name = "moviepilot_rust"
 crate-type = ["cdylib"]
 
 [dependencies]
-minijinja = "2.20"
-once_cell = "1.20"
-percent-encoding = "2.3"
 pyo3 = { version = "0.23", features = ["abi3-py311", "extension-module"] }
-quick-xml = "0.38"
-regex = "1.11"
-scraper = "0.24"
-url = "2.5"

rust/moviepilot_rust/src/filter.rs

@@ -1,9 +1,6 @@
-use crate::utils::{get_optional_f64, get_optional_i64, get_optional_string};
 use pyo3::exceptions::PyValueError;
 use pyo3::prelude::*;
-use pyo3::types::{PyDict, PyList, PyString};
+use pyo3::types::{PyList, PyString};
-use regex::{Regex, RegexBuilder};
-use std::collections::HashMap;
 
 #[derive(Clone, Debug)]
 enum RuleExpr {
@@ -22,27 +19,6 @@ enum Token {
     LParen,
     RParen,
 }
-
-#[derive(Clone, Debug)]
-struct TorrentPayload {
-    index: usize,
-    title: String,
-    description: String,
-    labels: Vec<String>,
-    size: f64,
-    seeders: i64,
-    downloadvolumefactor: Option<f64>,
-    pub_minutes: f64,
-    episode_count: f64,
-    fields: HashMap<String, FieldValue>,
-}
-
-#[derive(Clone, Debug)]
-enum FieldValue {
-    Scalar(String),
-    List(Vec<String>),
-}
-
 #[pyfunction]
 pub(crate) fn parse_filter_rule_fast(py: Python<'_>, expression: &str) -> PyResult<PyObject> {
     let tokens = tokenize_rule(expression)?;
@@ -56,85 +32,6 @@ pub(crate) fn parse_filter_rule_fast(py: Python<'_>, expression: &str) -> PyResu
     Ok(outer.into())
 }
 
-/// 批量执行种子过滤规则，返回保留项的原始下标和优先级。
-#[pyfunction]
-#[pyo3(signature = (rule_set, rule_strings, torrents, media_info=None))]
-pub(crate) fn filter_torrents_fast(
-    py: Python<'_>,
-    rule_set: &Bound<'_, PyDict>,
-    rule_strings: Vec<String>,
-    torrents: &Bound<'_, PyList>,
-    media_info: Option<&Bound<'_, PyDict>>,
-) -> PyResult<PyObject> {
-    py.allow_threads(|| {});
-    let mut payloads = Vec::with_capacity(torrents.len());
-    for index in 0..torrents.len() {
-        let item = torrents.get_item(index)?;
-        let dict = item.downcast::<PyDict>()?;
-        payloads.push(TorrentPayload::from_py_dict(index, dict)?);
-    }
-
-    let mut expr_cache: HashMap<String, RuleExpr> = HashMap::new();
-    let mut regex_cache: HashMap<String, Regex> = HashMap::new();
-    let mut current_indices: Vec<usize> = (0..payloads.len()).collect();
-    let mut priorities: HashMap<usize, i64> = HashMap::new();
-
-    for rule_string in rule_strings {
-        if current_indices.is_empty() {
-            break;
-        }
-        let levels: Vec<String> = rule_string
-            .split('>')
-            .map(|level| level.trim().to_string())
-            .collect();
-        let mut retained = Vec::new();
-        for payload_index in &current_indices {
-            let payload = &payloads[*payload_index];
-            let mut res_order = 100_i64;
-            let mut matched = false;
-            for level in &levels {
-                let expr = if let Some(cached) = expr_cache.get(level) {
-                    cached.clone()
-                } else {
-                    let parsed = parse_rule_expression(level)?;
-                    expr_cache.insert(level.clone(), parsed.clone());
-                    parsed
-                };
-                if match_expr(&expr, payload, rule_set, media_info, &mut regex_cache)? {
-                    matched = true;
-                    priorities.insert(payload.index, res_order);
-                    break;
-                }
-                res_order -= 1;
-            }
-            if matched {
-                retained.push(*payload_index);
-            }
-        }
-        current_indices = retained;
-    }
-
-    let result = PyList::empty(py);
-    for payload_index in current_indices {
-        let payload = &payloads[payload_index];
-        result.append((
-            payload.index,
-            priorities.get(&payload.index).copied().unwrap_or(0),
-        ))?;
-    }
-    Ok(result.into())
-}
-
-fn parse_rule_expression(expression: &str) -> PyResult<RuleExpr> {
-    let tokens = tokenize_rule(expression)?;
-    let mut parser = RuleParserState::new(tokens);
-    let expr = parser.parse_expression()?;
-    if parser.has_remaining() {
-        return Err(PyValueError::new_err("规则表达式包含无法解析的剩余内容"));
-    }
-    Ok(expr)
-}
-
 /// 将规则字符串切分为名称、逻辑符和括号。
 fn tokenize_rule(expression: &str) -> PyResult<Vec<Token>> {
     let chars: Vec<char> = expression.chars().collect();
@@ -325,316 +222,3 @@ fn expr_binary_to_py(
     list.append(expr_to_py(py, right)?)?;
     Ok(list.into())
 }
-
-impl TorrentPayload {
-    /// 从 Python 字典构造 Rust 过滤载荷。
-    fn from_py_dict(index: usize, dict: &Bound<'_, PyDict>) -> PyResult<Self> {
-        let title = get_optional_string(dict, "title")?.unwrap_or_default();
-        let description = get_optional_string(dict, "description")?.unwrap_or_default();
-        let labels = get_string_list(dict, "labels")?;
-        let size = get_optional_f64(dict, "size")?.unwrap_or(0.0);
-        let seeders = get_optional_i64(dict, "seeders")?.unwrap_or(0);
-        let downloadvolumefactor = get_optional_f64(dict, "downloadvolumefactor")?;
-        let pub_minutes = get_optional_f64(dict, "pub_minutes")?.unwrap_or(0.0);
-        let episode_count = get_optional_f64(dict, "episode_count")?
-            .unwrap_or(1.0)
-            .max(1.0);
-        let mut fields = HashMap::new();
-        for (key, value) in dict.iter() {
-            let key = key.extract::<String>()?;
-            if value.is_none() {
-                continue;
-            }
-            if let Ok(values) = value.extract::<Vec<String>>() {
-                fields.insert(key, FieldValue::List(values));
-            } else {
-                fields.insert(key, FieldValue::Scalar(value.str()?.to_str()?.to_string()));
-            }
-        }
-        Ok(Self {
-            index,
-            title,
-            description,
-            labels,
-            size,
-            seeders,
-            downloadvolumefactor,
-            pub_minutes,
-            episode_count,
-            fields,
-        })
-    }
-
-    /// 返回指定字段的匹配文本。
-    fn content_for_matches(&self, match_fields: &[String]) -> String {
-        if match_fields.is_empty() {
-            return format!(
-                "{} {} {}",
-                self.title,
-                self.description,
-                self.labels.join(" ")
-            );
-        }
-        let mut parts = Vec::new();
-        for field in match_fields {
-            if let Some(value) = self.fields.get(field) {
-                match value {
-                    FieldValue::Scalar(text) => {
-                        if !text.is_empty() {
-                            parts.push(text.clone());
-                        }
-                    }
-                    FieldValue::List(values) => {
-                        parts.extend(values.iter().filter(|v| !v.is_empty()).cloned())
-                    }
-                }
-            }
-        }
-        parts.join(" ")
-    }
-}
-
-/// 从 Python 字典读取字符串列表。
-fn get_string_list(dict: &Bound<'_, PyDict>, key: &str) -> PyResult<Vec<String>> {
-    let Some(value) = dict.get_item(key)? else {
-        return Ok(Vec::new());
-    };
-    if value.is_none() {
-        return Ok(Vec::new());
-    }
-    if let Ok(values) = value.extract::<Vec<String>>() {
-        return Ok(values);
-    }
-    Ok(vec![value.str()?.to_str()?.to_string()])
-}
-
-/// 执行规则 AST 匹配。
-fn match_expr(
-    expr: &RuleExpr,
-    torrent: &TorrentPayload,
-    rule_set: &Bound<'_, PyDict>,
-    media_info: Option<&Bound<'_, PyDict>>,
-    regex_cache: &mut HashMap<String, Regex>,
-) -> PyResult<bool> {
-    match expr {
-        RuleExpr::Name(name) => match_rule(name, torrent, rule_set, media_info, regex_cache),
-        RuleExpr::Not(inner) => Ok(!match_expr(
-            inner,
-            torrent,
-            rule_set,
-            media_info,
-            regex_cache,
-        )?),
-        RuleExpr::And(left, right) => {
-            Ok(
-                match_expr(left, torrent, rule_set, media_info, regex_cache)?
-                    && match_expr(right, torrent, rule_set, media_info, regex_cache)?,
-            )
-        }
-        RuleExpr::Or(left, right) => {
-            Ok(
-                match_expr(left, torrent, rule_set, media_info, regex_cache)?
-                    || match_expr(right, torrent, rule_set, media_info, regex_cache)?,
-            )
-        }
-    }
-}
-
-/// 执行单条规则匹配。
-fn match_rule(
-    rule_name: &str,
-    torrent: &TorrentPayload,
-    rule_set: &Bound<'_, PyDict>,
-    media_info: Option<&Bound<'_, PyDict>>,
-    regex_cache: &mut HashMap<String, Regex>,
-) -> PyResult<bool> {
-    let Some(rule_obj) = rule_set.get_item(rule_name)? else {
-        return Ok(false);
-    };
-    let rule = rule_obj.downcast::<PyDict>()?;
-    if let Some(tmdb_obj) = rule.get_item("tmdb")? {
-        if !tmdb_obj.is_none() {
-            if let Ok(tmdb) = tmdb_obj.downcast::<PyDict>() {
-                if match_tmdb(tmdb, media_info)? {
-                    return Ok(true);
-                }
-            }
-        }
-    }
-
-    let match_fields = get_string_list(rule, "match")?;
-    let content = torrent.content_for_matches(&match_fields);
-    let includes = get_string_list(rule, "include")?;
-    let excludes = get_string_list(rule, "exclude")?;
-
-    if !includes.is_empty() {
-        let mut included = false;
-        for pattern in &includes {
-            if regex_search(pattern, &content, regex_cache)? {
-                included = true;
-                break;
-            }
-        }
-        if !included {
-            return Ok(false);
-        }
-    }
-    for exclude in excludes {
-        if regex_search(&exclude, &content, regex_cache)? {
-            return Ok(false);
-        }
-    }
-    if let Some(size_range) = get_optional_string(rule, "size_range")? {
-        if !match_size(torrent, &size_range)? {
-            return Ok(false);
-        }
-    }
-    if let Some(seeders) = get_optional_i64(rule, "seeders")? {
-        if torrent.seeders < seeders {
-            return Ok(false);
-        }
-    }
-    if let Some(downloadvolumefactor) = get_optional_f64(rule, "downloadvolumefactor")? {
-        if torrent.downloadvolumefactor != Some(downloadvolumefactor) {
-            return Ok(false);
-        }
-    }
-    if let Some(pubdate) = get_optional_string(rule, "publish_time")? {
-        if !match_publish_time(torrent.pub_minutes, &pubdate) {
-            return Ok(false);
-        }
-    }
-    Ok(true)
-}
-
-/// 使用带缓存的忽略大小写正则搜索。
-fn regex_search(
-    pattern: &str,
-    content: &str,
-    cache: &mut HashMap<String, Regex>,
-) -> PyResult<bool> {
-    if !cache.contains_key(pattern) {
-        let regex = RegexBuilder::new(pattern)
-            .case_insensitive(true)
-            .build()
-            .map_err(|err| PyValueError::new_err(err.to_string()))?;
-        cache.insert(pattern.to_string(), regex);
-    }
-    Ok(cache
-        .get(pattern)
-        .is_some_and(|regex| regex.is_match(content)))
-}
-
-/// 匹配 TMDB 媒体属性规则。
-fn match_tmdb(tmdb: &Bound<'_, PyDict>, media_info: Option<&Bound<'_, PyDict>>) -> PyResult<bool> {
-    let Some(media) = media_info else {
-        return Ok(false);
-    };
-    for (attr, value) in tmdb.iter() {
-        if value.is_none() {
-            continue;
-        }
-        let attr_name = attr.extract::<String>()?;
-        let expected = value.str()?.to_str()?.to_string();
-        if expected.is_empty() {
-            continue;
-        }
-        let info_values = media_values(media, &attr_name)?;
-        if info_values.is_empty() {
-            return Ok(false);
-        }
-        let expected_values: Vec<String> = expected
-            .split(',')
-            .filter(|item| !item.is_empty())
-            .map(|item| item.to_uppercase())
-            .collect();
-        if !expected_values.iter().any(|expected_item| {
-            info_values
-                .iter()
-                .any(|info_item| info_item == expected_item)
-        }) {
-            return Ok(false);
-        }
-    }
-    Ok(true)
-}
-
-/// 获取媒体属性的可比较字符串集合。
-fn media_values(media: &Bound<'_, PyDict>, attr_name: &str) -> PyResult<Vec<String>> {
-    let Some(value) = media.get_item(attr_name)? else {
-        return Ok(Vec::new());
-    };
-    if value.is_none() {
-        return Ok(Vec::new());
-    }
-    if attr_name == "production_countries" {
-        let Ok(items) = value.downcast::<PyList>() else {
-            return Ok(Vec::new());
-        };
-        let mut values = Vec::new();
-        for item in items.iter() {
-            if let Ok(dict) = item.downcast::<PyDict>() {
-                if let Some(country) = dict.get_item("iso_3166_1")? {
-                    values.push(country.str()?.to_str()?.to_uppercase());
-                }
-            }
-        }
-        return Ok(values);
-    }
-    if let Ok(items) = value.extract::<Vec<String>>() {
-        return Ok(items.into_iter().map(|item| item.to_uppercase()).collect());
-    }
-    Ok(vec![value.str()?.to_str()?.to_uppercase()])
-}
-
-/// 按每集大小匹配大小范围规则。
-fn match_size(torrent: &TorrentPayload, size_range: &str) -> PyResult<bool> {
-    let torrent_size = torrent.size / torrent.episode_count;
-    let size_range = size_range.trim();
-    let unit = 1024.0 * 1024.0;
-    if let Some((min, max)) = size_range.split_once('-') {
-        let min = min
-            .trim()
-            .parse::<f64>()
-            .map_err(|err| PyValueError::new_err(err.to_string()))?
-            * unit;
-        let max = max
-            .trim()
-            .parse::<f64>()
-            .map_err(|err| PyValueError::new_err(err.to_string()))?
-            * unit;
-        return Ok(min <= torrent_size && torrent_size <= max);
-    }
-    if let Some(min) = size_range.strip_prefix('>') {
-        let min = min
-            .trim()
-            .parse::<f64>()
-            .map_err(|err| PyValueError::new_err(err.to_string()))?
-            * unit;
-        return Ok(torrent_size >= min);
-    }
-    if let Some(max) = size_range.strip_prefix('<') {
-        let max = max
-            .trim()
-            .parse::<f64>()
-            .map_err(|err| PyValueError::new_err(err.to_string()))?
-            * unit;
-        return Ok(torrent_size <= max);
-    }
-    Ok(false)
-}
-
-/// 匹配发布时间分钟数规则。
-fn match_publish_time(pub_minutes: f64, publish_time: &str) -> bool {
-    let values: Vec<f64> = publish_time
-        .split('-')
-        .filter_map(|item| item.parse::<f64>().ok())
-        .collect();
-    if values.len() == 1 {
-        return pub_minutes >= values[0];
-    }
-    if values.len() >= 2 {
-        return values[0] <= pub_minutes && pub_minutes <= values[1];
-    }
-    true
-}

rust/moviepilot_rust/src/lib.rs

@@ -1,8 +1,4 @@
 mod filter;
-mod indexer;
-mod meta;
-mod rss;
-mod utils;
 
 use pyo3::prelude::*;
 
@@ -16,13 +12,6 @@ fn is_available() -> bool {
 #[pymodule]
 fn moviepilot_rust(m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_function(wrap_pyfunction!(is_available, m)?)?;
-    m.add_function(wrap_pyfunction!(meta::is_anime_fast, m)?)?;
-    m.add_function(wrap_pyfunction!(meta::find_metainfo_fast, m)?)?;
-    m.add_function(wrap_pyfunction!(meta::parse_video_title_fast, m)?)?;
     m.add_function(wrap_pyfunction!(filter::parse_filter_rule_fast, m)?)?;
-    m.add_function(wrap_pyfunction!(filter::filter_torrents_fast, m)?)?;
-    m.add_function(wrap_pyfunction!(indexer::build_indexer_search_url_fast, m)?)?;
-    m.add_function(wrap_pyfunction!(indexer::parse_indexer_torrents_fast, m)?)?;
-    m.add_function(wrap_pyfunction!(rss::parse_rss_items_fast, m)?)?;
     Ok(())
 }

rust/moviepilot_rust/src/rss.rs

@@ -1,204 +0,0 @@
-use pyo3::prelude::*;
-use pyo3::types::PyDict;
-use quick_xml::events::{BytesStart, Event};
-use quick_xml::name::QName;
-use quick_xml::Reader;
-
-#[derive(Default)]
-struct RssItem {
-    title: String,
-    description: String,
-    link: String,
-    enclosure: String,
-    size: i64,
-    pubdate: String,
-    nickname: String,
-}
-
-impl RssItem {
-    fn has_output(&self) -> bool {
-        !self.title.is_empty() && (!self.enclosure.is_empty() || !self.link.is_empty())
-    }
-}
-
-#[derive(Clone, Copy, PartialEq, Eq)]
-enum TextField {
-    Title,
-    Description,
-    Link,
-    Pubdate,
-    Nickname,
-}
-
-/// 批量解析 RSS/Atom 条目，返回 Python 侧后续处理需要的核心字段。
-#[pyfunction]
-pub(crate) fn parse_rss_items_fast(
-    py: Python<'_>,
-    xml_text: &str,
-    max_items: usize,
-) -> PyResult<Option<Vec<PyObject>>> {
-    let mut reader = Reader::from_str(xml_text);
-    reader.config_mut().trim_text(true);
-
-    let mut items = Vec::new();
-    let mut current_item: Option<RssItem> = None;
-    let mut current_field: Option<TextField> = None;
-    let mut item_depth = 0usize;
-    let mut parse_failed = false;
-
-    loop {
-        match reader.read_event() {
-            Ok(Event::Start(event)) => {
-                let local = local_name(event.name());
-                if current_item.is_none() && (local == "item" || local == "entry") {
-                    current_item = Some(RssItem::default());
-                    current_field = None;
-                    item_depth = 1;
-                    continue;
-                }
-                if let Some(item) = current_item.as_mut() {
-                    item_depth += 1;
-                    match local.as_str() {
-                        "title" => current_field = Some(TextField::Title),
-                        "description" | "summary" => current_field = Some(TextField::Description),
-                        "pubDate" | "published" | "updated" => current_field = Some(TextField::Pubdate),
-                        "creator" => current_field = Some(TextField::Nickname),
-                        "link" => {
-                            current_field = Some(TextField::Link);
-                            if item.link.is_empty() {
-                                if let Some(href) = attr_value(&event, QName(b"href")) {
-                                    item.link = href;
-                                }
-                            }
-                        }
-                        "enclosure" => {
-                            if let Some(url) = attr_value(&event, QName(b"url")) {
-                                item.enclosure = url;
-                            }
-                            if let Some(length) = attr_value(&event, QName(b"length")) {
-                                item.size = length.parse::<i64>().unwrap_or(0);
-                            }
-                        }
-                        _ => {}
-                    }
-                }
-            }
-            Ok(Event::Empty(event)) => {
-                if let Some(item) = current_item.as_mut() {
-                    match local_name(event.name()).as_str() {
-                        "link" => {
-                            if item.link.is_empty() {
-                                if let Some(href) = attr_value(&event, QName(b"href")) {
-                                    item.link = href;
-                                }
-                            }
-                        }
-                        "enclosure" => {
-                            if let Some(url) = attr_value(&event, QName(b"url")) {
-                                item.enclosure = url;
-                            }
-                            if let Some(length) = attr_value(&event, QName(b"length")) {
-                                item.size = length.parse::<i64>().unwrap_or(0);
-                            }
-                        }
-                        _ => {}
-                    }
-                }
-            }
-            Ok(Event::Text(event)) => {
-                if let (Some(item), Some(field)) = (current_item.as_mut(), current_field) {
-                    if let Ok(value) = event.decode() {
-                        append_field(item, field, value.as_ref());
-                    }
-                }
-            }
-            Ok(Event::CData(event)) => {
-                if let (Some(item), Some(field)) = (current_item.as_mut(), current_field) {
-                    if let Ok(value) = event.decode() {
-                        append_field(item, field, value.as_ref());
-                    }
-                }
-            }
-            Ok(Event::End(event)) => {
-                if current_item.is_some() {
-                    let local = local_name(event.name());
-                    if local == "item" || local == "entry" {
-                        let mut item = current_item.take().unwrap_or_default();
-                        if item.enclosure.is_empty() && !item.link.is_empty() {
-                            item.enclosure = item.link.clone();
-                        }
-                        if item.has_output() {
-                            items.push(item_to_py(py, &item)?.into_any().unbind());
-                            if items.len() >= max_items {
-                                break;
-                            }
-                        }
-                        current_field = None;
-                        item_depth = 0;
-                    } else {
-                        item_depth = item_depth.saturating_sub(1);
-                        if item_depth <= 1 {
-                            current_field = None;
-                        }
-                    }
-                }
-            }
-            Ok(Event::Eof) => break,
-            Err(_) => {
-                parse_failed = true;
-                break;
-            }
-            _ => {}
-        }
-    }
-
-    if parse_failed && items.is_empty() {
-        Ok(None)
-    } else {
-        Ok(Some(items))
-    }
-}
-
-/// 将内部 RSS 条目结构转换为 Python 字典。
-fn item_to_py<'py>(py: Python<'py>, item: &RssItem) -> PyResult<Bound<'py, PyDict>> {
-    let dict = PyDict::new(py);
-    dict.set_item("title", item.title.trim())?;
-    dict.set_item("enclosure", item.enclosure.trim())?;
-    dict.set_item("size", item.size)?;
-    dict.set_item("description", item.description.trim())?;
-    dict.set_item("link", item.link.trim())?;
-    dict.set_item("pubdate_raw", item.pubdate.trim())?;
-    if !item.nickname.trim().is_empty() {
-        dict.set_item("nickname", item.nickname.trim())?;
-    }
-    Ok(dict)
-}
-
-/// 返回 XML 名称去掉命名空间前缀后的本地名称。
-fn local_name(name: QName<'_>) -> String {
-    let raw = name.as_ref();
-    let local = raw.rsplit(|byte| *byte == b':').next().unwrap_or(raw);
-    std::str::from_utf8(local).unwrap_or("").to_string()
-}
-
-/// 读取 XML 节点属性并完成实体反转义。
-fn attr_value(event: &BytesStart<'_>, name: QName<'_>) -> Option<String> {
-    event
-        .try_get_attribute(name)
-        .ok()
-        .flatten()
-        .and_then(|attr| attr.decode_and_unescape_value(event.decoder()).ok())
-        .map(|value| value.into_owned())
-}
-
-/// 追加当前文本节点到对应 RSS 字段。
-fn append_field(item: &mut RssItem, field: TextField, value: &str) {
-    let target = match field {
-        TextField::Title => &mut item.title,
-        TextField::Description => &mut item.description,
-        TextField::Link => &mut item.link,
-        TextField::Pubdate => &mut item.pubdate,
-        TextField::Nickname => &mut item.nickname,
-    };
-    target.push_str(value);
-}

rust/moviepilot_rust/src/utils.rs

@@ -1,103 +0,0 @@
-use pyo3::exceptions::PyValueError;
-use pyo3::prelude::*;
-use pyo3::types::{PyAny, PyDict};
-use regex::Regex;
-
-/// 捕获正则第一组并转换为整数。
-pub(crate) fn capture_i64(regex: &Regex, text: &str) -> Option<i64> {
-    regex
-        .captures(text)
-        .and_then(|caps| caps.get(1))
-        .and_then(|value| value.as_str().parse::<i64>().ok())
-}
-
-/// 捕获正则所有分组中的整数，用于 S01E02 和范围类 token 的多值识别。
-pub(crate) fn capture_all_i64(regex: &Regex, text: &str) -> Vec<i64> {
-    let mut values = Vec::new();
-    for caps in regex.captures_iter(text) {
-        for item in caps.iter().skip(1).flatten() {
-            if let Ok(value) = item.as_str().parse::<i64>() {
-                values.push(value);
-                break;
-            }
-        }
-    }
-    values
-}
-
-/// 计算范围的开始、结束和总数，保持 Python 侧的倒序交换语义。
-pub(crate) fn apply_range_total(
-    mut begin: Option<i64>,
-    mut end: Option<i64>,
-) -> (Option<i64>, Option<i64>, Option<i64>) {
-    let total = match (begin, end) {
-        (Some(begin_value), Some(end_value)) => {
-            if begin_value > end_value {
-                begin = Some(end_value);
-                end = Some(begin_value);
-                Some(begin_value - end_value + 1)
-            } else {
-                Some(end_value - begin_value + 1)
-            }
-        }
-        (Some(_), None) => Some(1),
-        _ => None,
-    };
-    (begin, end, total)
-}
-
-/// 将 Python 对象转换为 usize，用于过滤器下标。
-pub(crate) fn py_i64_to_usize(value: &Bound<'_, PyAny>) -> PyResult<usize> {
-    let index = value.extract::<i64>()?;
-    if index < 0 {
-        return Err(PyValueError::new_err("下标不能为负数"));
-    }
-    Ok(index as usize)
-}
-
-/// 从 Python 字典读取可选字符串。
-pub(crate) fn get_optional_string(dict: &Bound<'_, PyDict>, key: &str) -> PyResult<Option<String>> {
-    let Some(value) = dict.get_item(key)? else {
-        return Ok(None);
-    };
-    if value.is_none() {
-        return Ok(None);
-    }
-    Ok(Some(value.str()?.to_str()?.to_string()))
-}
-
-/// 从 Python 字典读取可选整数。
-pub(crate) fn get_optional_i64(dict: &Bound<'_, PyDict>, key: &str) -> PyResult<Option<i64>> {
-    let Some(value) = dict.get_item(key)? else {
-        return Ok(None);
-    };
-    if value.is_none() {
-        return Ok(None);
-    }
-    if let Ok(parsed) = value.extract::<i64>() {
-        return Ok(Some(parsed));
-    }
-    let text = value.str()?.to_str()?.trim().to_string();
-    if text.is_empty() {
-        return Ok(None);
-    }
-    Ok(text.parse::<i64>().ok())
-}
-
-/// 从 Python 字典读取可选浮点数。
-pub(crate) fn get_optional_f64(dict: &Bound<'_, PyDict>, key: &str) -> PyResult<Option<f64>> {
-    let Some(value) = dict.get_item(key)? else {
-        return Ok(None);
-    };
-    if value.is_none() {
-        return Ok(None);
-    }
-    if let Ok(parsed) = value.extract::<f64>() {
-        return Ok(Some(parsed));
-    }
-    let text = value.str()?.to_str()?.trim().to_string();
-    if text.is_empty() {
-        return Ok(None);
-    }
-    Ok(text.parse::<f64>().ok())
-}

tests/test_rust_accel.py

@@ -1,9 +1,5 @@
 import pytest
 
-from app.core.context import TorrentInfo
-from app.modules.filter import FilterModule
-from app.modules.indexer.spider import SiteSpider
-from app.schemas.types import MediaType
 from app.utils import rust_accel
 
 
@@ -13,445 +9,19 @@ pytestmark = pytest.mark.skipif(
 )
 
 
-def test_rust_metainfo_fast_path_extracts_emby_override():
+def test_rust_filter_rule_parser_matches_boolean_semantics():
     """
-    Rust 内嵌媒体标签识别应保持 Emby tmdbid 标签优先级。
+    Rust 过滤规则解析应保持 pyparsing 的布尔表达式结构。
     """
-    title, metainfo = rust_accel.find_metainfo("Movie {[tmdbid=111;type=movies]} [tmdbid=222]")
+    result = rust_accel.parse_filter_rule("HDR & !BLU")
 
-    assert title == "Movie"
+    assert result == [["HDR", "and", ["not", "BLU"]]]
-    assert metainfo["tmdbid"] == "222"
-    assert metainfo["type"] == MediaType.MOVIE
 
 
-def test_rust_video_title_fast_path_extracts_common_resource_fields():
+def test_rust_filter_rule_parser_handles_parentheses_and_or():
     """
-    Rust 影视标题预解析应能提取常见资源字段。
+    Rust 过滤规则解析应保持括号、与、或的优先级语义。
     """
-    result = rust_accel.parse_video_title(
+    result = rust_accel.parse_filter_rule("CNSUB & (4K | 1080P) & !BLU")
-        "The 355 2022 BluRay 1080p DTS-HD MA5.1 X265.10bit 60FPS"
-    )
 
-    assert result["year"] == "2022"
+    assert result == [[["CNSUB", "and", ["4K", "or", "1080P"]], "and", ["not", "BLU"]]]
-    assert result["resource_pix"] == "1080p"
-    assert result["resource_type"] == "BluRay"
-    assert result["video_encode"] == "x265 10bit"
-    assert result["video_bit"] == "10bit"
-    assert result["fps"] == 60
-
-
-def test_rust_filter_fast_path_matches_priority_semantics():
-    """
-    Rust 批量过滤应保持优先级和布尔表达式语义。
-    """
-    module = FilterModule()
-    module.rule_set = {
-        "HDR": {"include": "HDR"},
-        "DV": {"include": "DOVI"},
-        "BLU": {"include": "BluRay"},
-    }
-    torrents = [
-        TorrentInfo(title="Movie HDR WEB-DL", description=""),
-        TorrentInfo(title="Movie DOVI", description=""),
-        TorrentInfo(title="Movie HDR BluRay", description=""),
-    ]
-
-    result = module._FilterModule__filter_torrents_by_rust(  # noqa: SLF001
-        groups=[type("RuleGroup", (), {"rule_string": "HDR & !BLU > DV"})()],
-        torrent_list=torrents,
-        mediainfo=None,
-    )
-
-    assert result == torrents[:2]
-    assert result[0].pri_order == 100
-    assert result[1].pri_order == 99
-
-
-def test_rust_indexer_search_url_keeps_existing_query_and_category():
-    """
-    Rust URL 生成应保留路径原有查询参数并应用分类参数。
-    """
-    spider = SiteSpider(
-        indexer={
-            "id": "ttg",
-            "name": "TTG",
-            "domain": "https://totheglory.im/",
-            "search": {
-                "paths": [{"path": "browse.php?c=M"}],
-                "params": {"search_field": "{keyword}", "c": "M"},
-                "imdbid_format": "imdb{imdbid_num}",
-            },
-            "category": {
-                "field": "search_field",
-                "delimiter": " 分类:",
-                "movie": [{"id": "电影DVDRip", "cat": "Movies/SD"}],
-            },
-            "torrents": {"list": {}, "fields": {}},
-        },
-        keyword="tt0049406",
-        mtype=MediaType.MOVIE,
-    )
-
-    search_url = spider._SiteSpider__get_search_url()  # noqa: SLF001
-
-    assert search_url.count("?") == 1
-    assert "c=M" in search_url
-    assert "search_field=imdb0049406" in search_url
-
-
-def test_rust_rss_parser_extracts_common_rss_and_atom_fields():
-    """
-    Rust RSS 解析应同时覆盖 RSS item 和 Atom entry 的核心字段。
-    """
-    xml_text = """
-    <rss><channel>
-      <item>
-        <title>Example Torrent</title>
-        <description><![CDATA[Desc]]></description>
-        <link>https://example.org/details/1</link>
-        <enclosure url="https://example.org/download/1.torrent" length="1024" />
-        <pubDate>Tue, 19 May 2026 08:30:00 GMT</pubDate>
-        <dc:creator>豆瓣用户</dc:creator>
-      </item>
-      <entry>
-        <title>Atom Torrent</title>
-        <summary>Atom Desc</summary>
-        <link href="https://example.org/atom/2" />
-        <updated>2026-05-19T09:30:00Z</updated>
-      </entry>
-    </channel></rss>
-    """
-
-    items = rust_accel.parse_rss_items(xml_text, 100)
-
-    assert items[0]["title"] == "Example Torrent"
-    assert items[0]["enclosure"] == "https://example.org/download/1.torrent"
-    assert items[0]["size"] == 1024
-    assert items[0]["nickname"] == "豆瓣用户"
-    assert items[1]["title"] == "Atom Torrent"
-    assert items[1]["enclosure"] == "https://example.org/atom/2"
-
-
-def test_rust_indexer_page_parser_handles_common_fields():
-    """
-    Rust 普通 indexer 页面解析应批量提取列表行核心字段。
-    """
-    spider = SiteSpider(
-        indexer={
-            "id": "demo",
-            "name": "Demo",
-            "domain": "https://example.org/",
-            "search": {"paths": [{"path": "torrents.php"}]},
-            "category": {
-                "movie": [{"id": "401"}],
-                "tv": [{"id": "402"}],
-            },
-            "torrents": {
-                "list": {"selector": "tr.torrent"},
-                "fields": {
-                    "title": {"selector": "a.title"},
-                    "description": {"selector": ".desc"},
-                    "details": {"selector": "a.title", "attribute": "href"},
-                    "download": {"selector": "a.dl", "attribute": "href"},
-                    "size": {"selector": ".size"},
-                    "seeders": {"selector": ".seeders"},
-                    "leechers": {"selector": ".leechers"},
-                    "grabs": {"selector": ".grabs"},
-                    "downloadvolumefactor": {"case": {".free": 0}},
-                    "uploadvolumefactor": {"selector": ".up"},
-                    "labels": {"selector": ".label"},
-                    "hr": {"selector": ".hr"},
-                    "category": {"selector": ".cat"},
-                },
-            },
-        },
-    )
-    html = """
-    <table>
-      <tr class="torrent">
-        <td><a class="title" href="/details/1">Movie 2024 1080p</a><span class="desc">BluRay</span></td>
-        <td><a class="dl" href="/download/1">DL</a></td>
-        <td class="size">1.5 GB</td><td class="seeders">1,234</td><td class="leechers">5/10</td>
-        <td class="grabs">42</td><td class="free">Free</td><td class="up">2x</td>
-        <td><span class="label">DIY</span><span class="label">HDR</span></td>
-        <td class="hr">H&R</td><td class="cat">401</td>
-      </tr>
-    </table>
-    """
-
-    torrents = spider.parse(html)
-
-    assert torrents == [{
-        "title": "Movie 2024 1080p",
-        "description": "BluRay",
-        "page_url": "https://example.org/details/1",
-        "enclosure": "https://example.org/download/1",
-        "size": 1610612736,
-        "seeders": 1234,
-        "peers": 5,
-        "grabs": 42,
-        "downloadvolumefactor": 0,
-        "uploadvolumefactor": 2,
-        "labels": ["DIY", "HDR"],
-        "hit_and_run": True,
-        "category": MediaType.MOVIE.value,
-    }]
-
-
-def test_rust_indexer_page_parser_renders_common_title_template():
-    """
-    Rust 普通 indexer 页面解析应兼容站点构建项目里的 title_optional 模板。
-    """
-    spider = SiteSpider(
-        indexer={
-            "id": "demo",
-            "name": "Demo",
-            "domain": "https://example.org/",
-            "search": {"paths": [{"path": "torrents.php"}]},
-            "torrents": {
-                "list": {"selector": "tr.torrent"},
-                "fields": {
-                    "title_default": {"selector": "a.title"},
-                    "title_optional": {
-                        "selector": "a.title",
-                        "attribute": "title",
-                        "optional": True,
-                    },
-                    "title": {
-                        "text": (
-                            "{% if fields['title_optional'] %}"
-                            "{{ fields['title_optional'] }}"
-                            "{% else %}"
-                            "{{ fields['title_default'] }}"
-                            "{% endif %}"
-                        )
-                    },
-                    "download": {"selector": "a.dl", "attribute": "href"},
-                },
-            },
-        },
-    )
-    html = """
-    <table>
-      <tr class="torrent">
-        <td><a class="title" title="Optional Name" href="/details/1">Default Name</a></td>
-        <td><a class="dl" href="/download/1">DL</a></td>
-      </tr>
-      <tr class="torrent">
-        <td><a class="title" title="" href="/details/2">Default Fallback</a></td>
-        <td><a class="dl" href="/download/2">DL</a></td>
-      </tr>
-    </table>
-    """
-
-    torrents = spider.parse(html)
-
-    assert [item["title"] for item in torrents] == ["Optional Name", "Default Fallback"]
-
-
-def test_rust_indexer_page_parser_renders_literal_title_template_without_default_field():
-    """
-    Rust 普通 indexer 页面解析应在没有 title_default 时渲染 title_optional 的纯文本兜底模板。
-    """
-    spider = SiteSpider(
-        indexer={
-            "id": "demo",
-            "name": "Demo",
-            "domain": "https://example.org/",
-            "search": {"paths": [{"path": "torrents.php"}]},
-            "torrents": {
-                "list": {"selector": "tr.torrent"},
-                "fields": {
-                    "title_optional": {
-                        "selector": "a.title",
-                        "attribute": "title",
-                        "optional": True,
-                    },
-                    "title": {
-                        "text": (
-                            "{% if fields['title_optional'] %}"
-                            "{{ fields['title_optional'] }}"
-                            "{% else %}"
-                            "For All Mankind S05 2019 2160p ATVP WEB-DL "
-                            "DDP5.1 Atmos DV H 265-HHWEB [新]"
-                            "{% endif %}"
-                        )
-                    },
-                    "download": {"selector": "a.dl", "attribute": "href"},
-                },
-            },
-        },
-    )
-    html = """
-    <table>
-      <tr class="torrent">
-        <td><a class="title" title="" href="/details/1">Ignored</a></td>
-        <td><a class="dl" href="/download/1">DL</a></td>
-      </tr>
-    </table>
-    """
-
-    torrents = spider.parse(html)
-
-    assert torrents == [{
-        "title": "For All Mankind S05 2019 2160p ATVP WEB-DL DDP5.1 Atmos DV H 265-HHWEB [新]",
-        "enclosure": "https://example.org/download/1",
-    }]
-
-
-def test_rust_indexer_page_parser_supports_agsvpt_selector_and_embedded_title_template():
-    """
-    Rust 普通 indexer 页面解析应兼容 AGSVPT 的 PyQuery 选择器和字段内嵌 Jinja 模板。
-    """
-    spider = SiteSpider(
-        indexer={
-            "id": "agsvpt",
-            "name": "AGSVPT",
-            "domain": "https://www.agsvpt.com/",
-            "search": {"paths": [{"path": "torrents.php"}]},
-            "torrents": {
-                "list": {"selector": 'table.torrents > tr:has("table.torrentname")'},
-                "fields": {
-                    "title_default": {"selector": 'a[href*="details.php?id="]'},
-                    "title_optional": {
-                        "selector": 'a[title][href*="details.php?id="]',
-                        "attribute": "title",
-                        "optional": True,
-                    },
-                    "title": {
-                        "text": (
-                            "{% if fields['title_optional'] %}"
-                            "{{ fields['title_optional'] }}"
-                            "{% else %}"
-                            "{{ fields['title_default'] }}"
-                            "{% endif %}"
-                        )
-                    },
-                    "details": {
-                        "selector": 'a[href*="details.php?id="]',
-                        "attribute": "href",
-                    },
-                    "download": {
-                        "selector": 'a[href*="download.php?id="]',
-                        "attribute": "href",
-                    },
-                },
-            },
-        },
-    )
-    html = """
-    <table class="torrents">
-      <tr>
-        <td><table class="torrentname"><tr><td>
-          <a href="details.php?id=1" title="{% if fields['title_optional'] %}{% else %}Release that Witch S01 2026 1080p WEB-DL H264 AAC-HHWEB{% endif %}">Ignored</a>
-        </td></tr></table></td>
-        <td><a href="download.php?id=1">DL</a></td>
-      </tr>
-    </table>
-    """
-
-    torrents = spider.parse(html)
-
-    assert torrents == [{
-        "title": "Release that Witch S01 2026 1080p WEB-DL H264 AAC-HHWEB",
-        "page_url": "https://www.agsvpt.com/details.php?id=1",
-        "enclosure": "https://www.agsvpt.com/download.php?id=1",
-    }]
-
-
-def test_rust_indexer_page_parser_renders_common_description_templates():
-    """
-    Rust 普通 indexer 页面解析应兼容站点构建项目里的 description 字段模板。
-    """
-    spider = SiteSpider(
-        indexer={
-            "id": "demo",
-            "name": "Demo",
-            "domain": "https://example.org/",
-            "search": {"paths": [{"path": "torrents.php"}]},
-            "torrents": {
-                "list": {"selector": "tr.torrent"},
-                "fields": {
-                    "title": {"selector": "a.title"},
-                    "subject": {"selector": ".subject"},
-                    "tags": {"selector": ".tags"},
-                    "description": {
-                        "text": (
-                            "{% if fields['tags']%}"
-                            "{{ fields['subject']+' '+fields['tags'] }}"
-                            "{% else %}"
-                            "{{ fields['subject'] }}"
-                            "{% endif %}"
-                        )
-                    },
-                    "download": {"selector": "a.dl", "attribute": "href"},
-                },
-            },
-        },
-    )
-    html = """
-    <table>
-      <tr class="torrent">
-        <td><a class="title">Movie 2024</a><span class="subject">BluRay</span><span class="tags">HDR</span></td>
-        <td><a class="dl" href="/download/1">DL</a></td>
-      </tr>
-      <tr class="torrent">
-        <td><a class="title">Show 2025</a><span class="subject">WEB-DL</span><span class="tags"></span></td>
-        <td><a class="dl" href="/download/2">DL</a></td>
-      </tr>
-    </table>
-    """
-
-    torrents = spider.parse(html)
-
-    assert [item["description"] for item in torrents] == ["BluRay HDR", "WEB-DL"]
-
-
-def test_rust_indexer_page_parser_supports_remove_and_negative_index():
-    """
-    Rust 普通 indexer 页面解析应兼容站点配置常用的 remove 和负索引。
-    """
-    spider = SiteSpider(
-        indexer={
-            "id": "demo",
-            "name": "Demo",
-            "domain": "https://example.org/",
-            "search": {"paths": [{"path": "torrents.php"}]},
-            "torrents": {
-                "list": {"selector": "tr.torrent"},
-                "fields": {
-                    "title": {"selector": ".name", "remove": "a,b"},
-                    "description": {
-                        "selector": ".desc",
-                        "remove": "span,a,img,font,b",
-                        "contents": -1,
-                    },
-                    "labels": {
-                        "selector": ".labels > span",
-                        "remove": "span,a,img,font,b",
-                        "contents": -1,
-                    },
-                    "download": {"selector": "a.dl", "attribute": "href"},
-                },
-            },
-        },
-    )
-    html = """
-    <table>
-      <tr class="torrent">
-        <td class="name">Movie<a>删掉</a><b>也删</b>2024</td>
-        <td class="desc">第一行
-          <span>标签</span><a>链接</a>
-          第二行
-        </td>
-        <td class="labels"><span><i>DIY</i></span><span><i>HDR</i></span></td>
-        <td><a class="dl" href="/download/1">DL</a></td>
-      </tr>
-    </table>
-    """
-
-    torrents = spider.parse(html)
-
-    assert torrents[0]["title"] == "Movie2024"
-    assert torrents[0]["description"] == "第一行 第二行"
-    assert torrents[0]["labels"] == ["DIY", "HDR"]