codfrm/MoviePilot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat：刮削模块支持覆盖

Browse Source
This commit is contained in:
jxxghp 2023-12-17 10:49:00 +08:00
parent cb12a052ac
commit cd7f688e78
5 changed files with 86 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
app/chain/__init__.py
View File

@ -421,15 +421,19 @@ class ChainBase(metaclass=ABCMeta):
""" """
return self.run_module("post_torrents_message", message=message, torrents=torrents) return self.run_module("post_torrents_message", message=message, torrents=torrents)
def scrape_metadata(self, path: Path, mediainfo: MediaInfo, transfer_type: str) -> None: def scrape_metadata(self, path: Path, mediainfo: MediaInfo, transfer_type: str,
force_nfo: bool = False, force_img: bool = False) -> None:
""" """
刮削元数据 刮削元数据
:param path: 媒体文件路径 :param path: 媒体文件路径
:param mediainfo: 识别的媒体信息 :param mediainfo: 识别的媒体信息
:param transfer_type: 转移模式 :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 :return: 成功或失败
""" """
self.run_module("scrape_metadata", path=path, mediainfo=mediainfo, transfer_type=transfer_type) self.run_module("scrape_metadata", path=path, mediainfo=mediainfo,
transfer_type=transfer_type, force_nfo=force_nfo, force_img=force_img)
def register_commands(self, commands: Dict[str, dict]) -> None: def register_commands(self, commands: Dict[str, dict]) -> None:
""" """

13
app/modules/douban/__init__.py
View File

@ -588,12 +588,15 @@ class DoubanModule(_ModuleBase):
return [] return []
return infos.get("subject_collection_items") return infos.get("subject_collection_items")
def scrape_metadata(self, path: Path, mediainfo: MediaInfo, transfer_type: str) -> None: def scrape_metadata(self, path: Path, mediainfo: MediaInfo, transfer_type: str,
force_nfo: bool = False, force_img: bool = False) -> None:
""" """
刮削元数据 刮削元数据
:param path: 媒体文件路径 :param path: 媒体文件路径
:param mediainfo: 识别的媒体信息 :param mediainfo: 识别的媒体信息
:param transfer_type: 传输类型 :param transfer_type: 传输类型
: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 :return: 成功或失败
""" """
if settings.SCRAP_SOURCE != "douban": if settings.SCRAP_SOURCE != "douban":
@ -630,7 +633,9 @@ class DoubanModule(_ModuleBase):
self.scraper.gen_scraper_files(meta=meta, self.scraper.gen_scraper_files(meta=meta,
mediainfo=mediainfo, mediainfo=mediainfo,
file_path=scrape_path, file_path=scrape_path,
transfer_type=transfer_type) transfer_type=transfer_type,
force_nfo=force_nfo,
force_img=force_img)
else: else:
# 目录下的所有文件 # 目录下的所有文件
for file in SystemUtils.list_files(path, settings.RMT_MEDIAEXT): for file in SystemUtils.list_files(path, settings.RMT_MEDIAEXT):
@ -667,7 +672,9 @@ class DoubanModule(_ModuleBase):
self.scraper.gen_scraper_files(meta=meta, self.scraper.gen_scraper_files(meta=meta,
mediainfo=mediainfo, mediainfo=mediainfo,
file_path=file, file_path=file,
transfer_type=transfer_type) transfer_type=transfer_type,
force_nfo=force_nfo,
force_img=force_img)
except Exception as e: except Exception as e:
logger.error(f"刮削文件 {file} 失败，原因：{str(e)}") logger.error(f"刮削文件 {file} 失败，原因：{str(e)}")
logger.info(f"{path} 刮削完成") logger.info(f"{path} 刮削完成")

46
app/modules/douban/scraper.py
View File

@ -14,53 +14,67 @@ from app.utils.system import SystemUtils
class DoubanScraper: class DoubanScraper:
_transfer_type = settings.TRANSFER_TYPE _transfer_type = settings.TRANSFER_TYPE
_force_nfo = False
_force_img = False
def gen_scraper_files(self, meta: MetaBase, mediainfo: MediaInfo, def gen_scraper_files(self, meta: MetaBase, mediainfo: MediaInfo,
file_path: Path, transfer_type: str): file_path: Path, transfer_type: str,
force_nfo: bool = False, force_img: bool = False):
""" """
生成刮削文件 生成刮削文件
:param meta: 元数据 :param meta: 元数据
:param mediainfo: 媒体信息 :param mediainfo: 媒体信息
:param file_path: 文件路径或者目录路径 :param file_path: 文件路径或者目录路径
:param transfer_type: 转输类型 :param transfer_type: 转输类型
:param force_nfo: 强制生成NFO
:param force_img: 强制生成图片
""" """
self._transfer_type = transfer_type self._transfer_type = transfer_type
self._force_nfo = force_nfo
self._force_img = force_img
try: try:
# 电影 # 电影
if mediainfo.type == MediaType.MOVIE: if mediainfo.type == MediaType.MOVIE:
# 强制或者不已存在时才处理 # 强制或者不已存在时才处理
if not file_path.with_name("movie.nfo").exists() \ if self._force_nfo or (not file_path.with_name("movie.nfo").exists()
and not file_path.with_suffix(".nfo").exists(): and not file_path.with_suffix(".nfo").exists()):
# 生成电影描述文件 # 生成电影描述文件
self.__gen_movie_nfo_file(mediainfo=mediainfo, self.__gen_movie_nfo_file(mediainfo=mediainfo,
file_path=file_path) file_path=file_path)
# 生成电影图片 # 生成电影图片
self.__save_image(url=mediainfo.poster_path, image_path = file_path.with_name(f"poster{Path(mediainfo.poster_path).suffix}")
file_path=file_path.with_name(f"poster{Path(mediainfo.poster_path).suffix}")) if self._force_img or not image_path.exists():
self.__save_image(url=mediainfo.poster_path,
file_path=image_path)
# 背景图 # 背景图
if mediainfo.backdrop_path: if mediainfo.backdrop_path:
self.__save_image(url=mediainfo.backdrop_path, image_path = file_path.with_name(f"backdrop{Path(mediainfo.backdrop_path).suffix}")
file_path=file_path.with_name(f"backdrop{Path(mediainfo.backdrop_path).suffix}")) if self._force_img or not image_path.exists():
self.__save_image(url=mediainfo.backdrop_path,
file_path=image_path)
# 电视剧 # 电视剧
else: else:
# 不存在时才处理 # 不存在时才处理
if not file_path.parent.with_name("tvshow.nfo").exists(): if self._force_nfo or not file_path.parent.with_name("tvshow.nfo").exists():
# 根目录描述文件 # 根目录描述文件
self.__gen_tv_nfo_file(mediainfo=mediainfo, self.__gen_tv_nfo_file(mediainfo=mediainfo,
dir_path=file_path.parents[1]) dir_path=file_path.parents[1])
# 生成根目录图片 # 生成根目录图片
self.__save_image(url=mediainfo.poster_path, image_path = file_path.with_name(f"poster{Path(mediainfo.poster_path).suffix}")
file_path=file_path.with_name(f"poster{Path(mediainfo.poster_path).suffix}")) if self._force_img or not image_path.exists():
self.__save_image(url=mediainfo.poster_path,
file_path=image_path)
# 背景图 # 背景图
if mediainfo.backdrop_path: if mediainfo.backdrop_path:
self.__save_image(url=mediainfo.backdrop_path, image_path = file_path.with_name(f"backdrop{Path(mediainfo.backdrop_path).suffix}")
file_path=file_path.with_name(f"backdrop{Path(mediainfo.backdrop_path).suffix}")) if self._force_img or not image_path.exists():
self.__save_image(url=mediainfo.backdrop_path,
file_path=image_path)
# 季目录NFO # 季目录NFO
if not file_path.with_name("season.nfo").exists(): if self._force_nfo or not file_path.with_name("season.nfo").exists():
self.__gen_tv_season_nfo_file(mediainfo=mediainfo, self.__gen_tv_season_nfo_file(mediainfo=mediainfo,
season=meta.begin_season, season=meta.begin_season,
season_path=file_path.parent) season_path=file_path.parent)
@ -175,8 +189,6 @@ class DoubanScraper:
""" """
下载图片并保存 下载图片并保存
""" """
if file_path.exists():
return
if not url: if not url:
return return
try: try:
@ -201,8 +213,6 @@ class DoubanScraper:
""" """
保存NFO 保存NFO
""" """
if file_path.exists():
return
xml_str = doc.toprettyxml(indent=" ", encoding="utf-8") xml_str = doc.toprettyxml(indent=" ", encoding="utf-8")
if self._transfer_type in ['rclone_move', 'rclone_copy']: if self._transfer_type in ['rclone_move', 'rclone_copy']:
self.__save_remove_file(file_path, xml_str) self.__save_remove_file(file_path, xml_str)

17
app/modules/themoviedb/__init__.py
View File

@ -212,12 +212,15 @@ class TheMovieDbModule(_ModuleBase):
return [MediaInfo(tmdb_info=info) for info in results] return [MediaInfo(tmdb_info=info) for info in results]
def scrape_metadata(self, path: Path, mediainfo: MediaInfo, transfer_type: str) -> None: def scrape_metadata(self, path: Path, mediainfo: MediaInfo, transfer_type: str,
force_nfo: bool = False, force_img: bool = False) -> None:
""" """
刮削元数据 刮削元数据
:param path: 媒体文件路径 :param path: 媒体文件路径
:param mediainfo: 识别的媒体信息 :param mediainfo: 识别的媒体信息
:param transfer_type: 转移类型 :param transfer_type: 转移类型
:param force_nfo: 强制刮削nfo
:param force_img: 强制刮削图片
:return: 成功或失败 :return: 成功或失败
""" """
if settings.SCRAP_SOURCE != "themoviedb": if settings.SCRAP_SOURCE != "themoviedb":
@ -229,13 +232,17 @@ class TheMovieDbModule(_ModuleBase):
scrape_path = path / path.name scrape_path = path / path.name
self.scraper.gen_scraper_files(mediainfo=mediainfo, self.scraper.gen_scraper_files(mediainfo=mediainfo,
file_path=scrape_path, file_path=scrape_path,
transfer_type=transfer_type) transfer_type=transfer_type,
force_nfo=force_nfo,
force_img=force_img)
elif path.is_file(): elif path.is_file():
# 单个文件 # 单个文件
logger.info(f"开始刮削媒体库文件：{path} ...") logger.info(f"开始刮削媒体库文件：{path} ...")
self.scraper.gen_scraper_files(mediainfo=mediainfo, self.scraper.gen_scraper_files(mediainfo=mediainfo,
file_path=path, file_path=path,
transfer_type=transfer_type) transfer_type=transfer_type,
force_nfo=force_nfo,
force_img=force_img)
else: else:
# 目录下的所有文件 # 目录下的所有文件
logger.info(f"开始刮削目录：{path} ...") logger.info(f"开始刮削目录：{path} ...")
@ -244,7 +251,9 @@ class TheMovieDbModule(_ModuleBase):
continue continue
self.scraper.gen_scraper_files(mediainfo=mediainfo, self.scraper.gen_scraper_files(mediainfo=mediainfo,
file_path=file, file_path=file,
transfer_type=transfer_type) transfer_type=transfer_type,
force_nfo=force_nfo,
force_img=force_img)
logger.info(f"{path} 刮削完成") logger.info(f"{path} 刮削完成")
def tmdb_discover(self, mtype: MediaType, sort_by: str, with_genres: str, with_original_language: str, def tmdb_discover(self, mtype: MediaType, sort_by: str, with_genres: str, with_original_language: str,

47
app/modules/themoviedb/scraper.py
View File

@ -19,19 +19,26 @@ from app.utils.system import SystemUtils
class TmdbScraper: class TmdbScraper:
tmdb = None tmdb = None
_transfer_type = settings.TRANSFER_TYPE _transfer_type = settings.TRANSFER_TYPE
_force_nfo = False
_force_img = False
def __init__(self, tmdb): def __init__(self, tmdb):
self.tmdb = tmdb self.tmdb = tmdb
def gen_scraper_files(self, mediainfo: MediaInfo, file_path: Path, transfer_type: str): def gen_scraper_files(self, mediainfo: MediaInfo, file_path: Path, transfer_type: str,
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 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 mediainfo: 媒体信息
:param file_path: 文件路径或者目录路径 :param file_path: 文件路径或者目录路径
:param transfer_type: 传输类型 :param transfer_type: 传输类型
:param force_nfo: 是否强制生成NFO
:param force_img: 是否强制生成图片
""" """
self._transfer_type = transfer_type self._transfer_type = transfer_type
self._force_nfo = force_nfo
self._force_img = force_img
def __get_episode_detail(_seasoninfo: dict, _episode: int): def __get_episode_detail(_seasoninfo: dict, _episode: int):
""" """
@ -46,8 +53,8 @@ class TmdbScraper:
# 电影，路径为文件名 名称/名称.xxx 或者蓝光原盘目录 名称/名称 # 电影，路径为文件名 名称/名称.xxx 或者蓝光原盘目录 名称/名称
if mediainfo.type == MediaType.MOVIE: if mediainfo.type == MediaType.MOVIE:
# 不已存在时才处理 # 不已存在时才处理
if not file_path.with_name("movie.nfo").exists() \ if self._force_nfo or (not file_path.with_name("movie.nfo").exists()
and not file_path.with_suffix(".nfo").exists(): and not file_path.with_suffix(".nfo").exists()):
# 生成电影描述文件 # 生成电影描述文件
self.__gen_movie_nfo_file(mediainfo=mediainfo, self.__gen_movie_nfo_file(mediainfo=mediainfo,
file_path=file_path) file_path=file_path)
@ -59,14 +66,16 @@ class TmdbScraper:
and isinstance(attr_value, str) \ and isinstance(attr_value, str) \
and attr_value.startswith("http"): and attr_value.startswith("http"):
image_name = attr_name.replace("_path", "") + Path(attr_value).suffix image_name = attr_name.replace("_path", "") + Path(attr_value).suffix
self.__save_image(url=attr_value, image_path = file_path.with_name(image_name)
file_path=file_path.with_name(image_name)) if self._force_img or not image_path.exists():
self.__save_image(url=attr_value,
file_path=image_path)
# 电视剧，路径为每一季的文件名 名称/Season xx/名称 SxxExx.xxx # 电视剧，路径为每一季的文件名 名称/Season xx/名称 SxxExx.xxx
else: else:
# 识别 # 识别
meta = MetaInfo(file_path.stem) meta = MetaInfo(file_path.stem)
# 根目录不存在时才处理 # 根目录不存在时才处理
if not file_path.parent.with_name("tvshow.nfo").exists(): if self._force_nfo or not file_path.parent.with_name("tvshow.nfo").exists():
# 根目录描述文件 # 根目录描述文件
self.__gen_tv_nfo_file(mediainfo=mediainfo, self.__gen_tv_nfo_file(mediainfo=mediainfo,
dir_path=file_path.parents[1]) dir_path=file_path.parents[1])
@ -79,13 +88,15 @@ class TmdbScraper:
and isinstance(attr_value, str) \ and isinstance(attr_value, str) \
and attr_value.startswith("http"): and attr_value.startswith("http"):
image_name = attr_name.replace("_path", "") + Path(attr_value).suffix image_name = attr_name.replace("_path", "") + Path(attr_value).suffix
self.__save_image(url=attr_value, image_path = file_path.parent.with_name(image_name)
file_path=file_path.parent.with_name(image_name)) if self._force_img or not image_path.exists():
self.__save_image(url=attr_value,
file_path=image_path)
# 查询季信息 # 查询季信息
seasoninfo = self.tmdb.get_tv_season_detail(mediainfo.tmdb_id, meta.begin_season) seasoninfo = self.tmdb.get_tv_season_detail(mediainfo.tmdb_id, meta.begin_season)
if seasoninfo: if seasoninfo:
# 季目录NFO # 季目录NFO
if not file_path.with_name("season.nfo").exists(): if self._force_nfo or not file_path.with_name("season.nfo").exists():
self.__gen_tv_season_nfo_file(seasoninfo=seasoninfo, self.__gen_tv_season_nfo_file(seasoninfo=seasoninfo,
season=meta.begin_season, season=meta.begin_season,
season_path=file_path.parent) season_path=file_path.parent)
@ -96,7 +107,9 @@ class TmdbScraper:
ext = Path(seasoninfo.get('poster_path')).suffix ext = Path(seasoninfo.get('poster_path')).suffix
# URL # URL
url = f"https://{settings.TMDB_IMAGE_DOMAIN}/t/p/original{seasoninfo.get('poster_path')}" url = f"https://{settings.TMDB_IMAGE_DOMAIN}/t/p/original{seasoninfo.get('poster_path')}"
self.__save_image(url, file_path.parent.with_name(f"season{sea_seq}-poster{ext}")) image_path = file_path.parent.with_name(f"season{sea_seq}-poster{ext}")
if self._force_img or not image_path.exists():
self.__save_image(url=url, file_path=image_path)
# 季的其它图片 # 季的其它图片
for attr_name, attr_value in vars(mediainfo).items(): for attr_name, attr_value in vars(mediainfo).items():
if attr_value \ if attr_value \
@ -106,13 +119,15 @@ class TmdbScraper:
and isinstance(attr_value, str) \ and isinstance(attr_value, str) \
and attr_value.startswith("http"): and attr_value.startswith("http"):
image_name = attr_name.replace("_path", "") + Path(attr_value).suffix image_name = attr_name.replace("_path", "") + Path(attr_value).suffix
self.__save_image(url=attr_value, image_path = file_path.parent.with_name(image_name)
file_path=file_path.parent.with_name(image_name)) if self._force_img or not image_path.exists():
self.__save_image(url=attr_value,
file_path=image_path)
# 查询集详情 # 查询集详情
episodeinfo = __get_episode_detail(seasoninfo, meta.begin_episode) episodeinfo = __get_episode_detail(seasoninfo, meta.begin_episode)
if episodeinfo: if episodeinfo:
# 集NFO # 集NFO
if not file_path.with_suffix(".nfo").exists(): if self._force_nfo or not file_path.with_suffix(".nfo").exists():
self.__gen_tv_episode_nfo_file(episodeinfo=episodeinfo, self.__gen_tv_episode_nfo_file(episodeinfo=episodeinfo,
tmdbid=mediainfo.tmdb_id, tmdbid=mediainfo.tmdb_id,
season=meta.begin_season, season=meta.begin_season,
@ -121,7 +136,7 @@ class TmdbScraper:
# 集的图片 # 集的图片
episode_image = episodeinfo.get("still_path") episode_image = episodeinfo.get("still_path")
image_path = file_path.with_name(file_path.stem + "-thumb").with_suffix(Path(episode_image).suffix) image_path = file_path.with_name(file_path.stem + "-thumb").with_suffix(Path(episode_image).suffix)
if episode_image: if episode_image and (self._force_img or not image_path.exists()):
self.__save_image( self.__save_image(
f"https://{settings.TMDB_IMAGE_DOMAIN}/t/p/original{episode_image}", f"https://{settings.TMDB_IMAGE_DOMAIN}/t/p/original{episode_image}",
image_path) image_path)
@ -340,8 +355,6 @@ class TmdbScraper:
""" """
下载图片并保存 下载图片并保存
""" """
if file_path.exists():
return
try: try:
logger.info(f"正在下载{file_path.stem}图片：{url} ...") logger.info(f"正在下载{file_path.stem}图片：{url} ...")
r = RequestUtils().get_res(url=url, raise_exception=True) r = RequestUtils().get_res(url=url, raise_exception=True)
@ -362,8 +375,6 @@ class TmdbScraper:
""" """
保存NFO 保存NFO
""" """
if file_path.exists():
return
xml_str = doc.toprettyxml(indent=" ", encoding="utf-8") xml_str = doc.toprettyxml(indent=" ", encoding="utf-8")
if self._transfer_type in ['rclone_move', 'rclone_copy']: if self._transfer_type in ['rclone_move', 'rclone_copy']:
self.__save_remove_file(file_path, xml_str) self.__save_remove_file(file_path, xml_str)