mirror of
https://github.com/jxxghp/MoviePilot.git
synced 2026-09-05 23:47:41 +08:00
优化find_metainfo函数，增加对Emby格式ID标签的支持，并添加相应的测试用例以验证不同ID格式的识别。
This commit is contained in:
jxxghp
+127
-35
@@ -120,41 +120,69 @@ def find_metainfo(title: str) -> Tuple[str, dict]:
|
|||||||
return title, metainfo
|
return title, metainfo
|
||||||
# 从标题中提取媒体信息 格式为{[tmdbid=xxx;type=xxx;s=xxx;e=xxx]}
|
# 从标题中提取媒体信息 格式为{[tmdbid=xxx;type=xxx;s=xxx;e=xxx]}
|
||||||
results = re.findall(r'(?<={\[)[\W\w]+(?=]})', title)
|
results = re.findall(r'(?<={\[)[\W\w]+(?=]})', title)
|
||||||
if not results:
|
if results:
|
||||||
return title, metainfo
|
for result in results:
|
||||||
for result in results:
|
# 查找tmdbid信息
|
||||||
# 查找tmdbid信息
|
tmdbid = re.findall(r'(?<=tmdbid=)\d+', result)
|
||||||
tmdbid = re.findall(r'(?<=tmdbid=)\d+', result)
|
if tmdbid and tmdbid[0].isdigit():
|
||||||
if tmdbid and tmdbid[0].isdigit():
|
metainfo['tmdbid'] = tmdbid[0]
|
||||||
metainfo['tmdbid'] = tmdbid[0]
|
# 查找豆瓣id信息
|
||||||
# 查找豆瓣id信息
|
doubanid = re.findall(r'(?<=doubanid=)\d+', result)
|
||||||
doubanid = re.findall(r'(?<=doubanid=)\d+', result)
|
if doubanid and doubanid[0].isdigit():
|
||||||
if doubanid and doubanid[0].isdigit():
|
metainfo['doubanid'] = doubanid[0]
|
||||||
metainfo['doubanid'] = doubanid[0]
|
# 查找媒体类型
|
||||||
# 查找媒体类型
|
mtype = re.findall(r'(?<=type=)\w+', result)
|
||||||
mtype = re.findall(r'(?<=type=)\w+', result)
|
if mtype:
|
||||||
if mtype:
|
if mtype[0] == "movies":
|
||||||
if mtype[0] == "movies":
|
metainfo['type'] = MediaType.MOVIE
|
||||||
metainfo['type'] = MediaType.MOVIE
|
elif mtype[0] == "tv":
|
||||||
elif mtype[0] == "tv":
|
metainfo['type'] = MediaType.TV
|
||||||
metainfo['type'] = MediaType.TV
|
# 查找季信息
|
||||||
# 查找季信息
|
begin_season = re.findall(r'(?<=s=)\d+', result)
|
||||||
begin_season = re.findall(r'(?<=s=)\d+', result)
|
if begin_season and begin_season[0].isdigit():
|
||||||
if begin_season and begin_season[0].isdigit():
|
metainfo['begin_season'] = int(begin_season[0])
|
||||||
metainfo['begin_season'] = int(begin_season[0])
|
end_season = re.findall(r'(?<=s=\d+-)\d+', result)
|
||||||
end_season = re.findall(r'(?<=s=\d+-)\d+', result)
|
if end_season and end_season[0].isdigit():
|
||||||
if end_season and end_season[0].isdigit():
|
metainfo['end_season'] = int(end_season[0])
|
||||||
metainfo['end_season'] = int(end_season[0])
|
# 查找集信息
|
||||||
# 查找集信息
|
begin_episode = re.findall(r'(?<=e=)\d+', result)
|
||||||
begin_episode = re.findall(r'(?<=e=)\d+', result)
|
if begin_episode and begin_episode[0].isdigit():
|
||||||
if begin_episode and begin_episode[0].isdigit():
|
metainfo['begin_episode'] = int(begin_episode[0])
|
||||||
metainfo['begin_episode'] = int(begin_episode[0])
|
end_episode = re.findall(r'(?<=e=\d+-)\d+', result)
|
||||||
end_episode = re.findall(r'(?<=e=\d+-)\d+', result)
|
if end_episode and end_episode[0].isdigit():
|
||||||
if end_episode and end_episode[0].isdigit():
|
metainfo['end_episode'] = int(end_episode[0])
|
||||||
metainfo['end_episode'] = int(end_episode[0])
|
# 去除title中该部分
|
||||||
# 去除title中该部分
|
if tmdbid or mtype or begin_season or end_season or begin_episode or end_episode:
|
||||||
if tmdbid or mtype or begin_season or end_season or begin_episode or end_episode:
|
title = title.replace(f"{{[{result}]}}", '')
|
||||||
title = title.replace(f"{{[{result}]}}", '')
|
|
||||||
|
# 支持Emby格式的ID标签
|
||||||
|
# 1. [tmdbid=xxxx] 或 [tmdbid-xxxx] 格式
|
||||||
|
tmdb_match = re.search(r'\[tmdbid[=\-](\d+)\]', title)
|
||||||
|
if tmdb_match:
|
||||||
|
metainfo['tmdbid'] = tmdb_match.group(1)
|
||||||
|
title = re.sub(r'\[tmdbid[=\-](\d+)\]', '', title).strip()
|
||||||
|
|
||||||
|
# 2. [tmdb=xxxx] 或 [tmdb-xxxx] 格式
|
||||||
|
if not metainfo['tmdbid']:
|
||||||
|
tmdb_match = re.search(r'\[tmdb[=\-](\d+)\]', title)
|
||||||
|
if tmdb_match:
|
||||||
|
metainfo['tmdbid'] = tmdb_match.group(1)
|
||||||
|
title = re.sub(r'\[tmdb[=\-](\d+)\]', '', title).strip()
|
||||||
|
|
||||||
|
# 3. {tmdbid=xxxx} 或 {tmdbid-xxxx} 格式
|
||||||
|
if not metainfo['tmdbid']:
|
||||||
|
tmdb_match = re.search(r'\{tmdbid[=\-](\d+)\}', title)
|
||||||
|
if tmdb_match:
|
||||||
|
metainfo['tmdbid'] = tmdb_match.group(1)
|
||||||
|
title = re.sub(r'\{tmdbid[=\-](\d+)\}', '', title).strip()
|
||||||
|
|
||||||
|
# 4. {tmdb=xxxx} 或 {tmdb-xxxx} 格式
|
||||||
|
if not metainfo['tmdbid']:
|
||||||
|
tmdb_match = re.search(r'\{tmdb[=\-](\d+)\}', title)
|
||||||
|
if tmdb_match:
|
||||||
|
metainfo['tmdbid'] = tmdb_match.group(1)
|
||||||
|
title = re.sub(r'\{tmdb[=\-](\d+)\}', '', title).strip()
|
||||||
|
|
||||||
# 计算季集总数
|
# 计算季集总数
|
||||||
if metainfo.get('begin_season') and metainfo.get('end_season'):
|
if metainfo.get('begin_season') and metainfo.get('end_season'):
|
||||||
if metainfo['begin_season'] > metainfo['end_season']:
|
if metainfo['begin_season'] > metainfo['end_season']:
|
||||||
@@ -169,3 +197,67 @@ def find_metainfo(title: str) -> Tuple[str, dict]:
|
|||||||
elif metainfo.get('begin_episode') and not metainfo.get('end_episode'):
|
elif metainfo.get('begin_episode') and not metainfo.get('end_episode'):
|
||||||
metainfo['total_episode'] = 1
|
metainfo['total_episode'] = 1
|
||||||
return title, metainfo
|
return title, metainfo
|
||||||
|
|
||||||
|
|
||||||
|
def test_find_metainfo():
|
||||||
|
"""
|
||||||
|
测试find_metainfo函数的各种ID识别格式
|
||||||
|
"""
|
||||||
|
test_cases = [
|
||||||
|
# 测试 [tmdbid=xxxx] 格式
|
||||||
|
("The Vampire Diaries (2009) [tmdbid=18165]", "18165"),
|
||||||
|
# 测试 [tmdbid-xxxx] 格式
|
||||||
|
("Inception (2010) [tmdbid-27205]", "27205"),
|
||||||
|
# 测试 [tmdb=xxxx] 格式
|
||||||
|
("Breaking Bad (2008) [tmdb=1396]", "1396"),
|
||||||
|
# 测试 [tmdb-xxxx] 格式
|
||||||
|
("Interstellar (2014) [tmdb-157336]", "157336"),
|
||||||
|
# 测试 {tmdbid=xxxx} 格式
|
||||||
|
("Stranger Things (2016) {tmdbid=66732}", "66732"),
|
||||||
|
# 测试 {tmdbid-xxxx} 格式
|
||||||
|
("The Matrix (1999) {tmdbid-603}", "603"),
|
||||||
|
# 测试 {tmdb=xxxx} 格式
|
||||||
|
("Game of Thrones (2011) {tmdb=1399}", "1399"),
|
||||||
|
# 测试 {tmdb-xxxx} 格式
|
||||||
|
("Avatar (2009) {tmdb-19995}", "19995"),
|
||||||
|
]
|
||||||
|
|
||||||
|
for title, expected_tmdbid in test_cases:
|
||||||
|
cleaned_title, metainfo = find_metainfo(title)
|
||||||
|
found_tmdbid = metainfo.get('tmdbid')
|
||||||
|
|
||||||
|
print(f"原标题: {title}")
|
||||||
|
print(f"清理后标题: {cleaned_title}")
|
||||||
|
print(f"期望的tmdbid: {expected_tmdbid}")
|
||||||
|
print(f"识别的tmdbid: {found_tmdbid}")
|
||||||
|
print(f"结果: {'通过' if found_tmdbid == expected_tmdbid else '失败'}")
|
||||||
|
print("-" * 50)
|
||||||
|
|
||||||
|
|
||||||
|
def test_meta_info_path():
|
||||||
|
"""
|
||||||
|
测试MetaInfoPath函数
|
||||||
|
"""
|
||||||
|
# 测试文件路径
|
||||||
|
path_tests = [
|
||||||
|
# 文件名中包含tmdbid
|
||||||
|
Path("/movies/The Vampire Diaries (2009) [tmdbid=18165]/The.Vampire.Diaries.S01E01.1080p.mkv"),
|
||||||
|
# 目录名中包含tmdbid
|
||||||
|
Path("/movies/Inception (2010) [tmdbid-27205]/Inception.2010.1080p.mkv"),
|
||||||
|
# 父目录名中包含tmdbid
|
||||||
|
Path("/movies/Breaking Bad (2008) [tmdb=1396]/Season 1/Breaking.Bad.S01E01.1080p.mkv"),
|
||||||
|
# 祖父目录名中包含tmdbid
|
||||||
|
Path("/tv/Game of Thrones (2011) {tmdb=1399}/Season 1/Game.of.Thrones.S01E01.1080p.mkv"),
|
||||||
|
]
|
||||||
|
|
||||||
|
for path in path_tests:
|
||||||
|
meta = MetaInfoPath(path)
|
||||||
|
print(f"测试路径: {path}")
|
||||||
|
print(f"识别结果: tmdbid={meta.tmdbid}")
|
||||||
|
print("-" * 50)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
# 运行测试函数
|
||||||
|
# test_find_metainfo()
|
||||||
|
test_meta_info_path()
|
||||||
|
|||||||
Reference in New Issue
Block a user