GithubBackup/MoviePilot
1
0
Fork 0
mirror of https://github.com/jxxghp/MoviePilot.git synced 2026-09-08 17:08:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix scraping

Browse Source
This commit is contained in:
jxxghp
2025-01-06 08:22:04 +08:00
parent b6f9315e2b
commit c194e8c59a
2 changed files with 101 additions and 104 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/chain/media.py
+49 -51
View File
@@ -413,31 +413,31 @@ class MediaChain(ChainBase, metaclass=Singleton):
if fileitem.type == "file": if fileitem.type == "file":
# 是否已存在 # 是否已存在
nfo_path = filepath.with_suffix(".nfo") nfo_path = filepath.with_suffix(".nfo")
if not overwrite and self.storagechain.get_file_item(storage=fileitem.storage, path=nfo_path): if overwrite or not self.storagechain.get_file_item(storage=fileitem.storage, path=nfo_path):
logger.info(f"已存在nfo文件：{nfo_path}")
return
# 电影文件 # 电影文件
movie_nfo = self.metadata_nfo(meta=meta, mediainfo=mediainfo) movie_nfo = self.metadata_nfo(meta=meta, mediainfo=mediainfo)
if not movie_nfo: if movie_nfo:
logger.warn(f"{filepath.name} nfo文件生成失败！")
return
# 保存或上传nfo文件到上级目录 # 保存或上传nfo文件到上级目录
__save_file(_fileitem=parent, _path=nfo_path, _content=movie_nfo) __save_file(_fileitem=parent, _path=nfo_path, _content=movie_nfo)
else:
logger.warn(f"{filepath.name} nfo文件生成失败！")
else:
logger.info(f"已存在nfo文件：{nfo_path}")
else: else:
# 电影目录 # 电影目录
if is_bluray_folder(fileitem): if is_bluray_folder(fileitem):
# 原盘目录 # 原盘目录
nfo_path = filepath / (filepath.name + ".nfo") nfo_path = filepath / (filepath.name + ".nfo")
if not overwrite and self.storagechain.get_file_item(storage=fileitem.storage, path=nfo_path): if overwrite or not self.storagechain.get_file_item(storage=fileitem.storage, path=nfo_path):
logger.info(f"已存在nfo文件：{nfo_path}")
return
# 生成原盘nfo # 生成原盘nfo
movie_nfo = self.metadata_nfo(meta=meta, mediainfo=mediainfo) movie_nfo = self.metadata_nfo(meta=meta, mediainfo=mediainfo)
if not movie_nfo: if movie_nfo:
logger.warn(f"{filepath.name} nfo文件生成失败！")
return
# 保存或上传nfo文件到当前目录 # 保存或上传nfo文件到当前目录
__save_file(_fileitem=fileitem, _path=nfo_path, _content=movie_nfo) __save_file(_fileitem=fileitem, _path=nfo_path, _content=movie_nfo)
else:
logger.warn(f"{filepath.name} nfo文件生成失败！")
else:
logger.info(f"已存在nfo文件：{nfo_path}")
else: else:
# 处理目录内的文件 # 处理目录内的文件
files = __list_files(_fileitem=fileitem) files = __list_files(_fileitem=fileitem)
@@ -456,23 +456,18 @@ class MediaChain(ChainBase, metaclass=Singleton):
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
image_path = filepath / image_name image_path = filepath / image_name
if not overwrite and self.storagechain.get_file_item(storage=fileitem.storage, if overwrite or not self.storagechain.get_file_item(storage=fileitem.storage,
path=image_path): path=image_path):
logger.info(f"已存在图片文件：{image_path}")
continue
# 下载图片 # 下载图片
content = __download_image(_url=attr_value) content = __download_image(_url=attr_value)
# 写入图片到当前目录 # 写入图片到当前目录
if content: if content:
__save_file(_fileitem=fileitem, _path=image_path, _content=content) __save_file(_fileitem=fileitem, _path=image_path, _content=content)
else:
logger.info(f"已存在图片文件：{image_path}")
else: else:
# 电视剧 # 电视剧
if fileitem.type == "file": if fileitem.type == "file":
# 是否已存在
nfo_path = filepath.with_suffix(".nfo")
if not overwrite and self.storagechain.get_file_item(storage=fileitem.storage, path=nfo_path):
logger.info(f"已存在nfo文件：{nfo_path}")
return
# 重新识别季集 # 重新识别季集
file_meta = MetaInfoPath(filepath) file_meta = MetaInfoPath(filepath)
if not file_meta.begin_episode: if not file_meta.begin_episode:
@@ -482,25 +477,28 @@ class MediaChain(ChainBase, metaclass=Singleton):
if not file_mediainfo: if not file_mediainfo:
logger.warn(f"{filepath.name} 无法识别文件媒体信息！") logger.warn(f"{filepath.name} 无法识别文件媒体信息！")
return return
# 是否已存在
nfo_path = filepath.with_suffix(".nfo")
if overwrite or not self.storagechain.get_file_item(storage=fileitem.storage, path=nfo_path):
# 获取集的nfo文件 # 获取集的nfo文件
episode_nfo = self.metadata_nfo(meta=file_meta, mediainfo=file_mediainfo, episode_nfo = self.metadata_nfo(meta=file_meta, mediainfo=file_mediainfo,
season=file_meta.begin_season, episode=file_meta.begin_episode) season=file_meta.begin_season, episode=file_meta.begin_episode)
if not episode_nfo: if episode_nfo:
logger.warn(f"{filepath.name} nfo生成失败！")
return
# 保存或上传nfo文件到上级目录 # 保存或上传nfo文件到上级目录
if not parent: if not parent:
parent = self.storagechain.get_parent_item(fileitem) parent = self.storagechain.get_parent_item(fileitem)
__save_file(_fileitem=parent, _path=nfo_path, _content=episode_nfo) __save_file(_fileitem=parent, _path=nfo_path, _content=episode_nfo)
else:
logger.warn(f"{filepath.name} nfo文件生成失败！")
else:
logger.info(f"已存在nfo文件：{nfo_path}")
# 获取集的图片 # 获取集的图片
image_dict = self.metadata_img(mediainfo=file_mediainfo, image_dict = self.metadata_img(mediainfo=file_mediainfo,
season=file_meta.begin_season, episode=file_meta.begin_episode) season=file_meta.begin_season, episode=file_meta.begin_episode)
if image_dict: if image_dict:
for episode, image_url in image_dict.items(): for episode, image_url in image_dict.items():
image_path = filepath.with_suffix(Path(image_url).suffix) image_path = filepath.with_suffix(Path(image_url).suffix)
if not overwrite and self.storagechain.get_file_item(storage=fileitem.storage, path=image_path): if overwrite or not self.storagechain.get_file_item(storage=fileitem.storage, path=image_path):
logger.info(f"已存在图片文件：{image_path}")
continue
# 下载图片 # 下载图片
content = __download_image(image_url) content = __download_image(image_url)
# 保存图片文件到当前目录 # 保存图片文件到当前目录
@@ -508,7 +506,8 @@ class MediaChain(ChainBase, metaclass=Singleton):
if not parent: if not parent:
parent = self.storagechain.get_parent_item(fileitem) parent = self.storagechain.get_parent_item(fileitem)
__save_file(_fileitem=parent, _path=image_path, _content=content) __save_file(_fileitem=parent, _path=image_path, _content=content)
else:
logger.info(f"已存在图片文件：{image_path}")
else: else:
# 当前为目录，处理目录内的文件 # 当前为目录，处理目录内的文件
files = __list_files(_fileitem=fileitem) files = __list_files(_fileitem=fileitem)
@@ -527,25 +526,24 @@ class MediaChain(ChainBase, metaclass=Singleton):
if season_meta.begin_season is not None: if season_meta.begin_season is not None:
# 是否已存在 # 是否已存在
nfo_path = filepath / "season.nfo" nfo_path = filepath / "season.nfo"
if not overwrite and self.storagechain.get_file_item(storage=fileitem.storage, path=nfo_path): if overwrite or not self.storagechain.get_file_item(storage=fileitem.storage, path=nfo_path):
logger.info(f"已存在nfo文件：{nfo_path}")
return
# 当前目录有季号，生成季nfo # 当前目录有季号，生成季nfo
season_nfo = self.metadata_nfo(meta=meta, mediainfo=mediainfo, season=season_meta.begin_season) season_nfo = self.metadata_nfo(meta=meta, mediainfo=mediainfo,
if not season_nfo: season=season_meta.begin_season)
logger.warn(f"无法生成电视剧季nfo文件：{meta.name}") if season_nfo:
return
# 写入nfo到根目录 # 写入nfo到根目录
__save_file(_fileitem=fileitem, _path=nfo_path, _content=season_nfo) __save_file(_fileitem=fileitem, _path=nfo_path, _content=season_nfo)
else:
logger.warn(f"无法生成电视剧季nfo文件：{meta.name}")
else:
logger.info(f"已存在nfo文件：{nfo_path}")
# TMDB季poster图片 # TMDB季poster图片
image_dict = self.metadata_img(mediainfo=mediainfo, season=season_meta.begin_season) image_dict = self.metadata_img(mediainfo=mediainfo, season=season_meta.begin_season)
if image_dict: if image_dict:
for image_name, image_url in image_dict.items(): for image_name, image_url in image_dict.items():
image_path = filepath.with_name(image_name) image_path = filepath.with_name(image_name)
if not overwrite and self.storagechain.get_file_item(storage=fileitem.storage, if overwrite or not self.storagechain.get_file_item(storage=fileitem.storage,
path=image_path): path=image_path):
logger.info(f"已存在图片文件：{image_path}")
continue
# 下载图片 # 下载图片
content = __download_image(image_url) content = __download_image(image_url)
# 保存图片文件到剧集目录 # 保存图片文件到剧集目录
@@ -553,6 +551,8 @@ class MediaChain(ChainBase, metaclass=Singleton):
if not parent: if not parent:
parent = self.storagechain.get_parent_item(fileitem) parent = self.storagechain.get_parent_item(fileitem)
__save_file(_fileitem=parent, _path=image_path, _content=content) __save_file(_fileitem=parent, _path=image_path, _content=content)
else:
logger.info(f"已存在图片文件：{image_path}")
# 额外fanart季图片：poster thumb banner # 额外fanart季图片：poster thumb banner
image_dict = self.metadata_img(mediainfo=mediainfo) image_dict = self.metadata_img(mediainfo=mediainfo)
if image_dict: if image_dict:
@@ -564,10 +564,8 @@ class MediaChain(ChainBase, metaclass=Singleton):
if image_season != str(season_meta.begin_season).rjust(2, '0'): if image_season != str(season_meta.begin_season).rjust(2, '0'):
logger.info(f"当前刮削季为：{season_meta.begin_season}，跳过文件：{image_path}") logger.info(f"当前刮削季为：{season_meta.begin_season}，跳过文件：{image_path}")
continue continue
if not overwrite and self.storagechain.get_file_item(storage=fileitem.storage, if overwrite or not self.storagechain.get_file_item(storage=fileitem.storage,
path=image_path): path=image_path):
logger.info(f"已存在图片文件：{image_path}")
continue
# 下载图片 # 下载图片
content = __download_image(image_url) content = __download_image(image_url)
# 保存图片文件到当前目录 # 保存图片文件到当前目录
@@ -575,21 +573,22 @@ class MediaChain(ChainBase, metaclass=Singleton):
if not parent: if not parent:
parent = self.storagechain.get_parent_item(fileitem) parent = self.storagechain.get_parent_item(fileitem)
__save_file(_fileitem=parent, _path=image_path, _content=content) __save_file(_fileitem=parent, _path=image_path, _content=content)
else:
logger.info(f"已存在图片文件：{image_path}")
# 判断当前目录是不是剧集根目录 # 判断当前目录是不是剧集根目录
if not season_meta.season: if not season_meta.season:
# 是否已存在 # 是否已存在
nfo_path = filepath / "tvshow.nfo" nfo_path = filepath / "tvshow.nfo"
if not overwrite and self.storagechain.get_file_item(storage=fileitem.storage, path=nfo_path): if overwrite or not self.storagechain.get_file_item(storage=fileitem.storage, path=nfo_path):
logger.info(f"已存在nfo文件：{nfo_path}")
return
# 当前目录有名称，生成tvshow nfo 和 tv图片 # 当前目录有名称，生成tvshow nfo 和 tv图片
tv_nfo = self.metadata_nfo(meta=meta, mediainfo=mediainfo) tv_nfo = self.metadata_nfo(meta=meta, mediainfo=mediainfo)
if not tv_nfo: if tv_nfo:
logger.warn(f"无法生成电视剧nfo文件：{meta.name}")
return
# 写入tvshow nfo到根目录 # 写入tvshow nfo到根目录
__save_file(_fileitem=fileitem, _path=nfo_path, _content=tv_nfo) __save_file(_fileitem=fileitem, _path=nfo_path, _content=tv_nfo)
else:
logger.warn(f"无法生成电视剧nfo文件：{meta.name}")
else:
logger.info(f"已存在nfo文件：{nfo_path}")
# 生成目录图片 # 生成目录图片
image_dict = self.metadata_img(mediainfo=mediainfo) image_dict = self.metadata_img(mediainfo=mediainfo)
if image_dict: if image_dict:
@@ -598,14 +597,13 @@ class MediaChain(ChainBase, metaclass=Singleton):
if image_name.startswith("season"): if image_name.startswith("season"):
continue continue
image_path = filepath / image_name image_path = filepath / image_name
if not overwrite and self.storagechain.get_file_item(storage=fileitem.storage, if overwrite or not self.storagechain.get_file_item(storage=fileitem.storage,
path=image_path): path=image_path):
logger.info(f"已存在图片文件：{image_path}")
continue
# 下载图片 # 下载图片
content = __download_image(image_url) content = __download_image(image_url)
# 保存图片文件到当前目录 # 保存图片文件到当前目录
if content: if content:
__save_file(_fileitem=fileitem, _path=image_path, _content=content) __save_file(_fileitem=fileitem, _path=image_path, _content=content)
else:
logger.info(f"已存在图片文件：{image_path}")
logger.info(f"{filepath.name} 刮削完成") logger.info(f"{filepath.name} 刮削完成")
app/chain/transfer.py
+2 -3
View File
@@ -487,8 +487,7 @@ class TransferChain(ChainBase, metaclass=Singleton):
self.eventmanager.send_event(EventType.MetadataScrape, { self.eventmanager.send_event(EventType.MetadataScrape, {
'meta': task.meta, 'meta': task.meta,
'mediainfo': task.mediainfo, 'mediainfo': task.mediainfo,
'fileitem': transferinfo.target_diritem, 'fileitem': transferinfo.target_diritem
'overwrite': True if task.manual else False
}) })
# 移除已完成的任务 # 移除已完成的任务
@@ -619,7 +618,7 @@ class TransferChain(ChainBase, metaclass=Singleton):
# 识别媒体信息 # 识别媒体信息
if download_history.tmdbid or download_history.doubanid: if download_history.tmdbid or download_history.doubanid:
# 下载记录中已存在识别信息 # 下载记录中已存在识别信息
mediainfo: MediaInfo = self.recognize_media(mtype=MediaType(download_history.type), mediainfo: Optional[MediaInfo] = self.recognize_media(mtype=MediaType(download_history.type),
tmdbid=download_history.tmdbid, tmdbid=download_history.tmdbid,
doubanid=download_history.doubanid) doubanid=download_history.doubanid)
if mediainfo: if mediainfo: