From 6939bff790db4f4706f07d50cc678391b5998a78 Mon Sep 17 00:00:00 2001 From: jxxghp Date: Sun, 14 Apr 2024 13:47:12 +0800 Subject: [PATCH] fix #1882 --- app/chain/__init__.py | 8 +- app/modules/douban/__init__.py | 114 ++++++++++++++++------------- app/modules/themoviedb/__init__.py | 5 +- app/modules/themoviedb/scraper.py | 10 ++- 4 files changed, 75 insertions(+), 62 deletions(-) diff --git a/app/chain/__init__.py b/app/chain/__init__.py index 2329f22a..687acef1 100644 --- a/app/chain/__init__.py +++ b/app/chain/__init__.py @@ -14,7 +14,6 @@ from app.core.context import Context from app.core.context import MediaInfo, TorrentInfo from app.core.event import EventManager from app.core.meta import MetaBase -from app.core.metainfo import MetaInfo from app.core.module import ModuleManager from app.db.message_oper import MessageOper from app.helper.message import MessageHelper @@ -478,18 +477,19 @@ class ChainBase(metaclass=ABCMeta): return self.run_module("post_torrents_message", message=message, torrents=torrents) def scrape_metadata(self, path: Path, mediainfo: MediaInfo, transfer_type: str, - metainfo: MetaInfo = None, force_nfo: bool = False, force_img: bool = False) -> None: + metainfo: MetaBase = None, force_nfo: bool = False, force_img: bool = False) -> None: """ 刮削元数据 :param path: 媒体文件路径 :param mediainfo: 识别的媒体信息 + :param metainfo: 源文件的识别元数据 :param transfer_type: 转移模式 :param force_nfo: 强制刮削nfo :param force_img: 强制刮削图片 :return: 成功或失败 """ - self.run_module("scrape_metadata", path=path, mediainfo=mediainfo, - metainfo=metainfo, transfer_type=transfer_type, force_nfo=force_nfo, force_img=force_img) + self.run_module("scrape_metadata", path=path, mediainfo=mediainfo, metainfo=metainfo, + transfer_type=transfer_type, force_nfo=force_nfo, force_img=force_img) def register_commands(self, commands: Dict[str, dict]) -> None: """ diff --git a/app/modules/douban/__init__.py b/app/modules/douban/__init__.py index 1b2cb3f3..cd8bf35b 100644 --- a/app/modules/douban/__init__.py +++ b/app/modules/douban/__init__.py @@ -7,7 +7,7 @@ import cn2an from app.core.config import settings from app.core.context import MediaInfo from app.core.meta import MetaBase -from app.core.metainfo import MetaInfo +from app.core.metainfo import MetaInfo, MetaInfoPath from app.log import logger from app.modules import _ModuleBase from app.modules.douban.apiv2 import DoubanApi @@ -629,53 +629,83 @@ class DoubanModule(_ModuleBase): return infos.get("subject_collection_items") def scrape_metadata(self, path: Path, mediainfo: MediaInfo, transfer_type: str, - metainfo: MetaInfo = None, force_nfo: bool = False, force_img: bool = False) -> None: + metainfo: MetaBase = None, force_nfo: bool = False, force_img: bool = False) -> None: """ 刮削元数据 :param path: 媒体文件路径 :param mediainfo: 识别的媒体信息 :param transfer_type: 传输类型 + :param metainfo: 源文件的识别元数据 :param force_nfo: 是否强制刮削nfo :param force_img: 是否强制刮削图片 :return: 成功或失败 """ + + def __get_mediainfo(_meta: MetaBase, _mediainfo: MediaInfo) -> Optional[MediaInfo]: + """ + 获取豆瓣媒体信息 + """ + if not _meta.name: + return None + # 查询豆瓣详情 + if not _mediainfo.douban_id: + # 根据TMDB名称查询豆瓣数据 + _doubaninfo = self.match_doubaninfo(name=_mediainfo.title, + imdbid=_mediainfo.imdb_id, + mtype=_mediainfo.type, + year=_mediainfo.year) + if not _doubaninfo: + logger.warn(f"未找到 {_mediainfo.title} 的豆瓣信息") + return None + _doubaninfo = self.douban_info(doubanid=_doubaninfo.get("id"), mtype=_mediainfo.type) + else: + _doubaninfo = self.douban_info(doubanid=_mediainfo.douban_id, + mtype=_mediainfo.type) + if not _doubaninfo: + logger(f"未获取到 {_mediainfo.douban_id} 的豆瓣媒体信息，无法刮削！") + return None + # 豆瓣媒体信息 + _doubanmedia = MediaInfo(douban_info=_doubaninfo) + # 补充图片 + self.obtain_images(_doubanmedia) + return _doubanmedia + if settings.SCRAP_SOURCE != "douban": return None if SystemUtils.is_bluray_dir(path): # 蓝光原盘 logger.info(f"开始刮削蓝光原盘：{path} ...") - meta = MetaInfo(path.stem) - if not meta.name: - return - # 查询豆瓣详情 - if not mediainfo.douban_id: - # 根据名称查询豆瓣数据 - doubaninfo = self.match_doubaninfo(name=mediainfo.title, - imdbid=mediainfo.imdb_id, - mtype=mediainfo.type, - year=mediainfo.year) - if not doubaninfo: - logger.warn(f"未找到 {mediainfo.title} 的豆瓣信息") - return - doubaninfo = self.douban_info(doubanid=doubaninfo.get("id"), mtype=mediainfo.type) - else: - doubaninfo = self.douban_info(doubanid=mediainfo.douban_id, - mtype=mediainfo.type) - if not doubaninfo: - logger(f"未获取到 {mediainfo.douban_id} 的豆瓣媒体信息，无法刮削！") - return - # 豆瓣媒体信息 - mediainfo = MediaInfo(douban_info=doubaninfo) - # 补充图片 - self.obtain_images(mediainfo) + # 优先使用传入metainfo + meta = metainfo or MetaInfo(path.name) # 刮削路径 scrape_path = path / path.name + # 媒体信息 + doubanmedia = __get_mediainfo(_meta=meta, _mediainfo=mediainfo) + if not doubanmedia: + return + # 刮削 self.scraper.gen_scraper_files(meta=meta, - mediainfo=mediainfo, + mediainfo=doubanmedia, file_path=scrape_path, transfer_type=transfer_type, force_nfo=force_nfo, force_img=force_img) + elif path.is_file(): + # 刮削单个文件 + logger.info(f"开始刮削媒体库文件：{path} ...") + # 优先使用传入metainfo + meta = metainfo or MetaInfoPath(path) + # 媒体信息 + doubanmedia = __get_mediainfo(_meta=meta, _mediainfo=mediainfo) + if not doubanmedia: + return + # 刮削 + self.scraper.gen_scraper_files(meta=meta, + mediainfo=doubanmedia, + file_path=path, + transfer_type=transfer_type, + force_nfo=force_nfo, + force_img=force_img) else: # 目录下的所有文件 for file in SystemUtils.list_files(path, settings.RMT_MEDIAEXT): @@ -683,34 +713,14 @@ class DoubanModule(_ModuleBase): continue logger.info(f"开始刮削媒体库文件：{file} ...") try: - meta = MetaInfo(file.stem) - if not meta.name: - continue - if not mediainfo.douban_id: - # 根据名称查询豆瓣数据 - doubaninfo = self.match_doubaninfo(name=mediainfo.title, - imdbid=mediainfo.imdb_id, - mtype=mediainfo.type, - year=mediainfo.year, - season=meta.begin_season) - if not doubaninfo: - logger.warn(f"未找到 {mediainfo.title} 的豆瓣信息") - break - # 查询豆瓣详情 - doubaninfo = self.douban_info(doubanid=doubaninfo.get("id"), mtype=mediainfo.type) - else: - doubaninfo = self.douban_info(doubanid=mediainfo.douban_id, - mtype=mediainfo.type) - if not doubaninfo: - logger(f"未获取到 {mediainfo.douban_id} 的豆瓣媒体信息，无法刮削！") - continue + meta = MetaInfoPath(file) # 豆瓣媒体信息 - mediainfo = MediaInfo(douban_info=doubaninfo) - # 补充图片 - self.obtain_images(mediainfo) + doubanmedia = __get_mediainfo(_meta=meta, _mediainfo=mediainfo) + if not doubanmedia: + return # 刮削 self.scraper.gen_scraper_files(meta=meta, - mediainfo=mediainfo, + mediainfo=doubanmedia, file_path=file, transfer_type=transfer_type, force_nfo=force_nfo, diff --git a/app/modules/themoviedb/__init__.py b/app/modules/themoviedb/__init__.py index a37c7abb..e5ae52be 100644 --- a/app/modules/themoviedb/__init__.py +++ b/app/modules/themoviedb/__init__.py @@ -7,7 +7,6 @@ from app import schemas from app.core.config import settings from app.core.context import MediaInfo from app.core.meta import MetaBase -from app.core.metainfo import MetaInfo from app.log import logger from app.modules import _ModuleBase from app.modules.themoviedb.category import CategoryHelper @@ -263,11 +262,12 @@ class TheMovieDbModule(_ModuleBase): return [] def scrape_metadata(self, path: Path, mediainfo: MediaInfo, transfer_type: str, - metainfo: MetaInfo = None, force_nfo: bool = False, force_img: bool = False) -> None: + metainfo: MetaBase = None, force_nfo: bool = False, force_img: bool = False) -> None: """ 刮削元数据 :param path: 媒体文件路径 :param mediainfo: 识别的媒体信息 + :param metainfo: 源文件的识别元数据 :param transfer_type: 转移类型 :param force_nfo: 强制刮削nfo :param force_img: 强制刮削图片 @@ -304,7 +304,6 @@ class TheMovieDbModule(_ModuleBase): self.scraper.gen_scraper_files(mediainfo=mediainfo, file_path=file, transfer_type=transfer_type, - metainfo=metainfo, force_nfo=force_nfo, force_img=force_img) logger.info(f"{path} 刮削完成") diff --git a/app/modules/themoviedb/scraper.py b/app/modules/themoviedb/scraper.py index 45dba3c1..4c7e29e3 100644 --- a/app/modules/themoviedb/scraper.py +++ b/app/modules/themoviedb/scraper.py @@ -7,6 +7,7 @@ from requests import RequestException from app.core.config import settings from app.core.context import MediaInfo +from app.core.meta import MetaBase from app.core.metainfo import MetaInfo from app.log import logger from app.schemas.types import MediaType @@ -26,10 +27,11 @@ class TmdbScraper: self.tmdb = tmdb def gen_scraper_files(self, mediainfo: MediaInfo, file_path: Path, transfer_type: str, - metainfo: MetaInfo = None, force_nfo: bool = False, force_img: bool = False): + metainfo: MetaBase = None, force_nfo: bool = False, force_img: bool = False): """ 生成刮削文件，包括NFO和图片，传入路径为文件路径 :param mediainfo: 媒体信息 + :param metainfo: 源文件的识别元数据 :param file_path: 文件路径或者目录路径 :param transfer_type: 传输类型 :param force_nfo: 是否强制生成NFO @@ -76,7 +78,9 @@ class TmdbScraper: # 电视剧，路径为每一季的文件名 名称/Season xx/名称 SxxExx.xxx else: # 如果有上游传入的元信息则使用，否则使用文件名识别 - meta = metainfo or MetaInfo(file_path.stem) + meta = metainfo or MetaInfo(file_path.name) + if meta.begin_season is None: + meta.begin_season = mediainfo.season if mediainfo.season is not None else 1 # 根目录不存在时才处理 if self._force_nfo or not file_path.parent.with_name("tvshow.nfo").exists(): # 根目录描述文件 @@ -96,7 +100,7 @@ class TmdbScraper: self.__save_image(url=attr_value, file_path=image_path) # 查询季信息 - seasoninfo = self.tmdb.get_tv_season_detail(mediainfo.tmdb_id, meta.begin_season or mediainfo.season) + seasoninfo = self.tmdb.get_tv_season_detail(mediainfo.tmdb_id, meta.begin_season) if seasoninfo: # 季目录NFO if self._force_nfo or not file_path.with_name("season.nfo").exists():