tortitle 0.0.1__tar.gz

tortitle-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) [2025] [ccf2012]
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

tortitle-0.0.1/PKG-INFO

@@ -0,0 +1,36 @@
+Metadata-Version: 2.4
+Name: tortitle
+Version: 0.0.1
+Summary: A title parser for torrent filenames
+Author: ccf2012
+Project-URL: Homepage, https://github.com/ccf-2012/tortitle
+Project-URL: Bug Tracker, https://github.com/ccf-2012/tortitle/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# TorTitle
+
+A title parser for torrent filenames.
+
+This library helps parse torrent filenames to extract structured information like title, year, season, episode, etc.
+
+## Installation
+
+```bash
+pip install tortitle
+```
+
+## Usage
+
+```python
+from tortitle import TorTitle
+
+
+result = TorTitle("The.Mandalorian.S01E01.1080p.WEB-DL.DDP5.1.H.264-NTb.mkv")
+print(result.to_dict())
+```

tortitle-0.0.1/README.md

@@ -0,0 +1,21 @@
+# TorTitle
+
+A title parser for torrent filenames.
+
+This library helps parse torrent filenames to extract structured information like title, year, season, episode, etc.
+
+## Installation
+
+```bash
+pip install tortitle
+```
+
+## Usage
+
+```python
+from tortitle import TorTitle
+
+
+result = TorTitle("The.Mandalorian.S01E01.1080p.WEB-DL.DDP5.1.H.264-NTb.mkv")
+print(result.to_dict())
+```

tortitle-0.0.1/pyproject.toml

@@ -0,0 +1,22 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "tortitle"
+version = "0.0.1"
+authors = [
+  { name="ccf2012" },
+]
+description = "A title parser for torrent filenames"
+readme = "README.md"
+requires-python = ">=3.7"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/ccf-2012/tortitle"
+"Bug Tracker" = "https://github.com/ccf-2012/tortitle/issues"

tortitle-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

tortitle-0.0.1/tests/test_tortitle.py

@@ -0,0 +1,154 @@
+import pytest
+from tortitle import TorTitle
+
+# Test cases formatted as a list of (input_string, expected_dictionary)
+TEST_CASES = [
+    (
+        "The.Matrix.1999.1080p.BluRay.x264-GROUP",
+        {
+            "title": "The Matrix", "year": "1999", "type": "movie",
+            "resolution": "1080p", "media_source": "encode", "group": "GROUP"
+        }
+    ),
+    (
+        "Breaking.Bad.S01E01.720p.BluRay.x264-GROUP",
+        {
+            "title": "Breaking Bad", "year": "", "type": "tv", "season": "S01",
+            "episode": "E01", "resolution": "720p", "media_source": "encode", "group": "GROUP"
+        }
+    ),
+    (
+        "Inception.2010.1080p.BluRay.x264-GROUP",
+        {"title": "Inception", "year": "2010", "type": "movie"}
+    ),
+    (
+        "【囧妈】Lost.in.Russia.2020.WEB-DL.1080p.H264.AAC-CMCTV",
+        {
+            "title": "Lost in Russia", "cntitle": "", "year": "2020",
+            "resolution": "1080p", "media_source": "webdl", "group": "CMCTV"
+        }
+    ),
+    (
+        "[The.Mandalorian].S01E01.(2019).1080p.WEB-DL-GROUP",
+        {
+            "title": "The Mandalorian", "year": "2019", "type": "tv",
+            "season": "S01", "episode": "E01"
+        }
+    ),
+    (
+        "She's Got No Name 2025 2160p WEB-DL H265 DTS5.1-CHDWEB",
+        {"title": "She's Got No Name", "year": "2025",
+            "type": "movie", "audio": "DTS5.1"}
+    ),
+    (
+        "[大陆][绝世天医][Jue Shi Tian Yi 2025 S01 1080p WEB-DL H.264 AAC-GodDramas]",
+        {
+            "title": "Jue Shi Tian Yi", "cntitle": "绝世天医", "year": "2025", "type": "tv",
+            "season": "S01", "episode": "", "resolution": "1080p",
+            "media_source": "webdl", "group": "GodDramas"
+        }
+    ),
+    (
+        "[TV][jsum@U2][我独自升级 第二季 -起于暗影-][Ore dake Level Up na Ken Season 2: Arise from the Shadow][1080p][TV 01-13(13-25) Fin+SP][MKV/BDRip][2025年01月]",
+        {"title": "Ore dake Level Up na Ken", "type": "tv"}
+    ),
+    (
+        "[The.Movie.2023][1080p][BluRay]",
+        {"title": "The Movie", "year": "2023",
+            "resolution": "1080p", "media_source": "bluray"}
+    ),
+    (
+        "[美剧][古战场传奇 第八季][Outlander.Blood.of.My.Blood.S01E03.School.of.the.Moon.2160p.STAN.WEB-DL.DDP5.1.HDR.H.265-NTb]",
+        {
+            "title": "Outlander Blood of My Blood", "cntitle": "古战场传奇", "year": "",
+            "type": "tv", "season": "S01", "episode": "E03", "resolution": "2160p",
+            "media_source": "webdl", "group": "NTb"
+        }
+    ),
+    (
+        "[瑞典][克拉克][Clark.S01.2160p.NF.WEB-DL.DD+5.1.H.265-playWEB]",
+        {"title": "Clark", "cntitle": "克拉克", "year": ""}
+    ),
+    (
+        "[大陆][光·渊][Justice.in.The.Dark.2023.S01.Complete.1080p.WOWOW.WEB-DL.H.264.AAC-UBWEB]",
+        {
+            "title": "Justice in The Dark", "cntitle": "光·渊", "year": "2023",
+            "type": "tv", "season": "S01", "episode": "", "resolution": "1080p",
+            "media_source": "webdl", "group": "UBWEB"
+        }
+    ),
+    # Standard Movie
+    ("Iron.Man.2008.BluRay.1080p.x264.DTS-WiKi",
+     {"title": "Iron Man", "cntitle": '', "year": "2008", "type": "movie", "season": '', "episode": ''}),
+    # Movie with Chinese Title
+    ("[钢铁侠].Iron.Man.2008.BluRay.1080p.x264.DTS-WiKi",
+     {"title": "Iron Man", "cntitle": "钢铁侠", "year": "2008", "type": "movie", "season": '', "episode": ''}),
+    # Standard TV Show
+    ("The.Mandalorian.S01E01.2019.1080p.WEB-DL.DDP5.1.H264-NTb",
+     {"title": "The Mandalorian", "cntitle": '', "year": "2019", "type": "tv", "season": 'S01', "episode": 'E01'}),
+    # TV Show with Chinese Title
+    ("[曼达洛人].The.Mandalorian.S01E01.2019.1080p.WEB-DL.DDP5.1.H264-NTb",
+     {"title": "The Mandalorian", "cntitle": "曼达洛人", "year": "2019", "type": "tv", "season": 'S01', "episode": 'E01'}),
+    # TV Show with Season only
+    ("The.Terminal.List.S01.2022.1080p.AMZN.WEB-DL.DDP5.1.H.264-BlackTV",
+     {"title": "The Terminal List", "cntitle": '', "year": "2022", "type": "tv", "season": 'S01', "episode": ''}),
+    # Movie with long name and dots
+    ("The.Lord.of.the.Rings.The.Fellowship.of.the.Ring.2001.EXTENDED.1080p.BluRay.x264-FSiHD",
+     {"title": "The Lord of the Rings The Fellowship of the Ring", "cntitle": '', "year": "2001", "type": "movie", "season": '', "episode": ''}),
+    # Movie with year at the end
+    ("1917.2019.1080p.BluRay.x264-SPARKS",
+     {"title": "1917", "cntitle": '', "year": "2019", "type": "movie", "season": '', "episode": ''}),
+    # Movie with no clear year (should not find one)
+    ("Top.Gun.Maverick.1080p.BluRay.x264-SPARKS",
+     {"title": "Top Gun Maverick", "cntitle": '', "year": '', "type": "movie", "season": '', "episode": ''}),
+    # TV Show with Chinese title and season
+    ("[终极名单].The.Terminal.List.S01.2022.1080p.AMZN.WEB-DL.DDP5.1.H.264-BlackTV",
+     {"title": "The Terminal List", "cntitle": "终极名单", "year": "2022", "type": "tv", "season": 'S01', "episode": ''}),
+    # Movie with brackets in title
+    ("Zack.Snyders.Justice.League.2021.2160p.WEB-DL.DDP5.1.Atmos.DV.HEVC-CMRG",
+     {"title": "Zack Snyders Justice League", "cntitle": '', "year": "2021", "type": "movie", "season": '', "episode": ''}),
+    # Another TV show format
+    ("Game.of.Thrones.Season.1.Complete.1080p.BluRay.x264-CiNEFiLE",
+     {"title": "Game of Thrones", "cntitle": '', "year": '', "type": "tv", "season": 'S01', "episode": ''}),
+    ('半暖时光.The.Memory.About.You.S01.2021.2160p.WEB-DL.AAC.H265-HDSWEB',
+     {'title': 'The Memory About You', 'cntitle': '半暖时光', 'year': '2021', 'type': 'tv', "season": 'S01', "episode": ''}),
+    ('不惑之旅.To.the.Oak.S01.2021.2160p.WEB-DL.AAC.H265-HDSWEB',
+     {'title': 'To the Oak', 'cntitle': '不惑之旅', 'year': '2021', 'type': 'tv', "season": 'S01', "episode": ''}),
+    ('Dinotrux S03E02 1080p Netflix WEB-DL DD 5.1 H.264-AJP69.mkv',
+     {'title': 'Dinotrux', 'cntitle': '', 'year': '', 'type': 'tv', "season": 'S03', "episode": 'E02'}),
+    ('排球女将.Moero.Attack.1979.Complete.WEB-DL.1080p.H264.DDP.MP3.Mandarin&Japanese-OPS',
+     {'title': 'Moero Attack', 'cntitle': '排球女将', 'year': '1979', 'type': 'movie', "season": '', "episode": ''}),
+    ("【红钻级收藏版】蜘蛛侠：英雄归来.全特效+内封三版字幕.Spider-Man.Homecoming.2017.2160P.BluRay.X265.10bit.HDR.DHD.MA.TrueHD.7.1.Atmos.English&Mandarin-GYT.strm",
+     {'title': 'Spider Man Homecoming', 'cntitle': '蜘蛛侠：英雄归来', 'year': '2017', 'type': 'movie', "season": '', "episode": ''}),
+    ("21座桥-英语.21.Bridges.2019.BluRay.2160p.x265.10bit.HDR.mUHD-FRDS",
+     {'title': '21 Bridges', 'cntitle': '21座桥', 'year': '2019', 'type': 'movie', "season": '', "episode": ''}),
+    ("13.Going.on.30.2004.Bluray.1080p.DTS.x264-CHD.strm",
+     {'title': '13 Going on 30', 'cntitle': '', 'year': '2004', 'type': 'movie', "season": '', "episode": ''}),
+    ('X档案.第一季.1993.中英字幕￡CMCT梦幻', {'title': 'X档案', 'cntitle': 'X档案',
+     'year': '1993', 'type': 'tv', "season": 'S01', "episode": ''}),
+    ('Taxi.4.Director\'s.Cut.2007.Bluray.1080p.x264.DD5.1-wwhhyy@Pter.mkv',
+     {'title': 'Taxi 4', 'cntitle': '', 'year': '2007', 'type': 'movie', "season": '', "episode": ''}),
+    ('豹.1963.JPN.1080p.意大利语中字￡CMCT风潇潇', {
+     'title': '豹', 'cntitle': '豹', 'year': '1963', 'type': 'movie', "season": '', "episode": ''}),
+    ('金刚狼3殊死一战.Logan.2017.BluRay.1080p.x265.10bit.MNHD-FRDS',
+     {'title': 'Logan', 'cntitle': '金刚狼3殊死一战', 'year': '2017', 'type': 'movie', "season": '', "episode": ''}),
+    ('人工智能4K REMUX (2001)', {'title': '人工智能', 'cntitle': '人工智能',
+     'year': '2001', 'type': 'movie', "season": '', "episode": ''}),
+    ('1988 骗徒臭事多 Dirty Rotten Scoundrels 豆瓣：8.2（美国）', {
+     'title': 'Dirty Rotten Scoundrels', 'cntitle': '骗徒臭事多', 'year': '1988', 'type': 'movie', "season": '', "episode": ''}),
+    ('蝙蝠侠前传：黑暗骑士崛起4K REMUX（2012）', {'title': '蝙蝠侠前传：黑暗骑士崛起', 'cntitle': '蝙蝠侠前传：黑暗骑士崛起',
+     'year': '2012', 'type': 'movie', "season": '', "episode": ''}),
+    ('2001太空漫游4K REMUX', {'title': '2001太空漫游', 'cntitle': '2001太空漫游',
+     'year': '', 'type': 'movie', "season": '', "episode": ''}),
+    ('代号47 4K REMUX (2015)', {'title': '代号47', 'cntitle': '代号47',
+     'year': '2015', 'type': 'movie', "season": '', "episode": ''}),
+]
+
+
+@pytest.mark.parametrize("input_string, expected_dict", TEST_CASES)
+def test_title_parsing(input_string, expected_dict):
+    """Tests that various torrent titles are parsed correctly."""
+    tor_title = TorTitle(input_string)
+    for key, value in expected_dict.items():
+        assert getattr(
+            tor_title, key) == value, f"Failed on key '{key}' for input '{input_string}'"

tortitle-0.0.1/tortitle/__init__.py

@@ -0,0 +1 @@
+from .tortitle import parse_tor_name, TorTitle

tortitle-0.0.1/tortitle/tortitle.py

@@ -0,0 +1,293 @@
+import re
+import os
+
+
+def cut_ext(tor_name):
+    if not tor_name:
+        return ''
+    tortup = os.path.splitext(tor_name)
+    torext = tortup[1].lower()
+    # if re.match(r'\.[0-9a-z]{2,5}$', tortup[1], flags=re.I):
+    mvext = ['.mkv', '.ts', '.m2ts', '.vob', '.mpg', '.mp4', '.3gp', '.mov', '.tp', '.zip', '.pdf', '.iso', '.ass', '.srt', '.7z', '.rar']
+    if torext.lower() in mvext:
+        return tortup[0].strip()
+    else:
+        return tor_name
+
+def delimer_to_space(sstr):
+    dilimers = ['[', ']', '.', '{', '}', '_', ',', '(', ')' ]
+    for dchar in dilimers:
+        sstr = sstr.replace(dchar, ' ')
+    return sstr
+
+def hyphen_to_space(sstr):
+    return sstr.replace('-', ' ')
+
+def cutspan(sstr, ifrom, ito):
+    if (ifrom >= 0) and (len(sstr) > ito):
+        sstr = sstr[0:ifrom:] + sstr[ito::]
+    return sstr
+
+def contains_cjk(str):
+    return re.search(r'[\u4e00-\u9fa5\u3041-\u30fc]', str)
+
+def cut_aka(titlestr):
+    m = re.search(r'\s(/|AKA)\s', titlestr, re.I)
+    if m:
+        titlestr = titlestr.split(m.group(0))[0]
+    return titlestr.strip()
+
+def tryint(str):
+    cndigit = '一二三四五六七八九十'
+    if str[0] in cndigit and len(str) == 1:
+        return cndigit.index(str[0]) + 1
+    try:
+        return int(str)
+    except:
+        return 0
+
+def is_0day_name(itemstr):
+    # CoComelon.S03.1080p.NF.WEB-DL.DDP2.0.H.264-NPMS
+    m = re.match(r'^\w+.*\b(BluRay|Blu-?ray|720p|1080[pi]|[xh].?26\d|2160p|576i|WEB-DL|DVD|WEBRip|HDTV)\b.*', itemstr, flags=re.A | re.I)
+    return m
+
+class TorTitle:
+    def __init__(self, name):
+        self.raw_name = name
+        self.title = name
+        self.cntitle = ''
+        self.year = ''
+        self.type = 'movie'
+        self.season = ''
+        self.episode = ''
+        self.sub_episode = ''
+        # self.season_int = None
+        # self.episode_int = None
+        self._se_pos = 0
+        self._year_pos = 0
+        self.parse()
+
+    def parse(self):
+        self._handle_bracket_title()
+        parsing_target = self.raw_name
+        if self.title != self.raw_name:
+            parsing_target = self.title
+        self._prepare_title()
+        self._extract_year()
+        self._extract_type()
+        self._extract_titles()
+        self._polish_title()
+        # self._handle_special_cases()
+        self.media_source, self.video, self.audio = self._parse_more(self.raw_name)
+        self.group = self._parse_group(parsing_target)
+        self.resolution = self._parse_resolution(self.raw_name)
+        self.full_season = (self.type == 'tv') and (self.episode == '')
+
+
+    def _parse_more(self, torName):
+        mediaSource, video, audio = '', '', ''
+        if m := re.search(r"(?<=(1080p|2160p)\s)(((\w+)\s+)?WEB(-DL)?)|\bWEB(-DL)?\b|\bHDTV\b|((UHD )?(BluRay|Blu-ray))", torName, re.I):
+            m0 = m[0].strip()
+            if re.search(r'WEB[-]?(DL)?', m0, re.I):
+                mediaSource = 'webdl'
+            elif re.search(r'BLURAY|BLU-RAY', m0, re.I):
+                if re.search(r'x26[45]', torName, re.I):
+                    mediaSource = 'encode'
+                elif re.search(r'remux', torName, re.I):
+                    mediaSource = 'remux'
+                else:
+                    mediaSource = 'bluray'
+            else:
+                mediaSource = m0
+        if m := re.search(r"AVC|HEVC(\s(DV|HDR))?|H\.?26[456](\s(HDR|DV))?|x26[45]\s?(10bit)?(HDR)?|DoVi (HDR(10)?)? (HEVC)?", torName, re.I):
+            video = m[0].strip()
+        if m := re.search(r"DTS-HD MA \d.\d|LPCM\s?\d.\d|TrueHD\s?\d\.\d( Atmos)?|DDP[\s\.]*\d\.\d( Atmos)?|(AAC|FLAC)(\s*\d\.\d)?( Atmos)?|DTS(\s?\d\.\d)?|DD\+? \d\.\d", torName, re.I):
+            audio = m[0].strip()
+        return mediaSource, video, audio
+
+    def _parse_resolution(self, torName):
+        match = re.search(r'\b(4K|2160p|1080[pi]|720p|576p|480p)\b', torName, re.A | re.I)
+        if match:
+            r = match.group(0).strip().lower()
+            if r == '4k':
+                r = '2160p'
+            return r
+        else:
+            return ''
+        
+    def _parse_group(self, torName):
+        sstr = cut_ext(torName)
+        match = re.search(r'[@\-￡]\s?(\w+)(?!.*[@\-￡].*)$', sstr, re.I)
+        if match:
+            groupName = match.group(1).strip()
+            # # TODO: BD-50_A_PORTRAIT_OF_SHUNKIN_1976_BC
+            if match.span(1)[0] < 4:
+                return None
+            if groupName.startswith('CMCT') and not groupName.startswith('CMCTV'):
+                groupName = 'CMCT'
+            return groupName
+
+        return None
+        
+    def _prepare_title(self):
+        self.title = cut_ext(self.title)
+        self.title = re.sub(r'^【.*】', '', self.title, flags=re.I)
+        self.title = re.sub(r'^\w+TV\b', '', self.title, flags=re.I)
+        self.title = delimer_to_space(self.title)
+
+    def _handle_bracket_title(self):
+        if self.title.startswith('[') and self.title.endswith(']'):
+            parts = [part.strip() for part in self.title[1:-1].split('][') if part.strip()]
+            keyword_pattern = r'1080p|2160p|720p|H\.?26[45]|x26[45]'
+            
+            main_part = ''
+            cjk_parts = []
+
+            keyword_idx = -1
+            for idx, part in enumerate(parts):
+                if re.search(keyword_pattern, part, re.I):
+                    keyword_idx = idx
+                    main_part = part
+            
+            if main_part:
+                if re.match(r'^'+keyword_pattern+'$', main_part, flags=re.I):
+                    if keyword_idx > 0:
+                        self.title = parts[keyword_idx-1]
+                        keyword_idx = keyword_idx - 1
+                else:
+                    self.title = main_part
+                if keyword_idx > 0 and contains_cjk(parts[keyword_idx-1]):
+                    full_cntitle = parts[keyword_idx-1]
+                    full_cntitle = re.sub(r'大陆|港台', '', full_cntitle, flags=re.I)
+                    self.cntitle = full_cntitle.split(' ')[0].strip()
+
+
+    def _extract_year(self):
+        potential_years = re.findall(r'(19\d{2}|20\d{2})(?:\d{4})?\b', self.title)
+        if potential_years:
+            self.year = potential_years[-1]
+            self._year_pos = self.title.rfind(self.year)
+            # if self.title.strip() != self.year:
+            #     self.title = self.title.replace(self.year, ' ')
+
+    def _extract_type(self):
+        patterns = {
+            's_e': r'\b(S\d+)(E\d+(-Ep?\d+)?)\b',
+            'season_only': r'(?<![a-zA-Z])(S\d+([\-\+]S?\d+)?)\b(?!.*\bS\d+)',
+            'season_word': r'\bSeason (\d+)\b',
+            'ep_only': r'\bEp?(\d+)(-Ep?\d+)?\b',
+            'cn_season': r'第([一二三四五六七八九十]|\d+)季',
+            'cn_episode': r'第([一二三四五六七八九十]+|\d+)集'
+        }
+
+        for key, pattern in patterns.items():
+            match = re.search(pattern, self.title, flags=re.IGNORECASE)
+            if match:
+                self.type = 'tv'
+                if key in ['s_e']:
+                    # self.season_int = int(match.group(1))
+                    # self.episode_int = int(match.group(2))
+                    self.season = match.group(1)
+                    self.episode = match.group(2)
+                elif key == 'season_only':
+                    # self.season_int = tryint(match.group(1))
+                    self.season = match.group(0)
+                elif key in ['season_word', 'cn_season']:
+                    # self.season_int = tryint(match.group(1))
+                    season_int = tryint(match.group(1))
+                    self.season = 'S'+ str(season_int).zfill(2) if season_int else ''
+                elif key in ['cn_episode', 'ep_only']:
+                    self.season = 'S01'
+                    self.episode = match.group()
+
+                self._se_pos = match.span(0)[0]
+                return
+
+    def _cut_s_year_season(self):
+        positions = [p for p in [self._year_pos, self._se_pos] if p > 0]
+        if positions:
+            cut_pos = min(positions)
+            self.title = self.title[:cut_pos]
+        self.title = self.title.strip()
+
+    def _cut_s_keyword(self):
+        tags = [
+            '2160p', '1080p', '720p', '480p', 'BluRay', r'(4K)?\s*Remux', 
+            r'WEB-?(DL)?', r'(?<![a-z])4K', r'(?<=\w\s)BDMV',
+        ]
+        pattern = r'(' + '|'.join(tag for tag in tags) + r')\b.*$'
+        self.title = re.sub(pattern, '', self.title, flags=re.IGNORECASE)
+        self.title = self.title.strip()
+    
+    def _extract_titles(self):
+        failsafe = self.title
+        self._cut_s_year_season()
+        failsafe = self.title if len(self.title) > 0 else failsafe
+        self._cut_s_keyword()
+
+        if not self.cntitle:
+            if contains_cjk(self.title):
+                self.cntitle = self.title
+                if m := re.search(r"([一-鿆]+[\-0-9a-zA-Z]*)[ :：]+([^一-鿆]+\b)", self.title, flags=re.I):
+                    self.cntitle = self.cntitle[:m.span(1)[1]]
+                    self.title = m.group(2)
+
+                # 删去：汉字之前，有空格分隔的 ascii 字符串
+                if m1 := re.match(r'^([^一-鿆]*)[\s\(\[]+[一-鿆]', self.cntitle, flags=re.I):
+                    self.cntitle = self.cntitle.replace(m1.group(1), '').strip()
+
+                # 取汉字串中第一个空格前部分
+                if self.cntitle:
+                    match = re.match(r'^([^ \-\(\[]*)', self.cntitle)
+                    if match:
+                        self.cntitle = match.group()
+
+        self.title = self.title.strip()
+        if not self.title:
+            self.title = failsafe
+        return
+
+    def _check_title(self):
+        m1 = re.search('[a-zA-Z]', self.title)
+        if len(self.title) > 2 and m1:
+            return True
+        else:
+            return False
+
+    def _polish_title(self):
+        self.title = re.sub(r'[\._\+]', ' ', self.title)
+        tags = [
+            'BTV', r'CCTV\s*\d+(HD|\+)?', 'HunanTV', r'Top\s*\d+',
+            r'\b\w+版', r'全\d+集', 'BDMV',
+            'COMPLETE', 'REPACK', 'PROPER', r'REMASTER\w*',
+            'iNTERNAL', 'LIMITED', 'EXTENDED', 'UNRATED', 
+            "Director's Cut"
+        ]
+        pattern = r'\b(' + '|'.join(tag for tag in tags) + r')\b'
+        self.title = re.sub(pattern, '', self.title, flags=re.IGNORECASE)
+        self.title = self.title.strip()
+
+        self.title = hyphen_to_space(self.title)
+        self.title = cut_aka(self.title)
+
+        if not self._check_title() and self.cntitle:
+            self.title = self.cntitle
+
+        # self.title = re.sub(r'\s+', ' ', self.title).strip()
+        # self.title = self.title.split('-')[0].strip()
+
+    def _handle_special_cases(self):
+        pass
+
+    def to_dict(self):
+        return {
+            'title': self.title,
+            'cntitle': self.cntitle,
+            'year': self.year,
+            'type': self.type,
+            'season': self.season,
+            'episode': self.episode
+        }
+
+def parse_tor_name(name):
+    return TorTitle(name)

tortitle-0.0.1/tortitle.egg-info/PKG-INFO

@@ -0,0 +1,36 @@
+Metadata-Version: 2.4
+Name: tortitle
+Version: 0.0.1
+Summary: A title parser for torrent filenames
+Author: ccf2012
+Project-URL: Homepage, https://github.com/ccf-2012/tortitle
+Project-URL: Bug Tracker, https://github.com/ccf-2012/tortitle/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# TorTitle
+
+A title parser for torrent filenames.
+
+This library helps parse torrent filenames to extract structured information like title, year, season, episode, etc.
+
+## Installation
+
+```bash
+pip install tortitle
+```
+
+## Usage
+
+```python
+from tortitle import TorTitle
+
+
+result = TorTitle("The.Mandalorian.S01E01.1080p.WEB-DL.DDP5.1.H.264-NTb.mkv")
+print(result.to_dict())
+```

tortitle-0.0.1/tortitle.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+LICENSE
+README.md
+pyproject.toml
+tests/test_tortitle.py
+tortitle/__init__.py
+tortitle/tortitle.py
+tortitle.egg-info/PKG-INFO
+tortitle.egg-info/SOURCES.txt
+tortitle.egg-info/dependency_links.txt
+tortitle.egg-info/top_level.txt

tortitle-0.0.1/tortitle.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

tortitle-0.0.1/tortitle.egg-info/top_level.txt

@@ -0,0 +1 @@
+tortitle