novel-downloader 1.2.2__py3-none-any.whl → 1.3.0__py3-none-any.whl

novel_downloader/utils/hash_store.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.hash_store
 ---------------------------------
@@ -11,8 +10,8 @@ Supports loading/saving to .json or .npy, and basic CRUD + search.
 import heapq
 import json
 import logging
+from collections.abc import Callable
 from pathlib import Path
-from typing import Callable, Dict, List, Optional, Set, Tuple, Union
 
 import numpy as np
 from PIL import Image
@@ -33,7 +32,7 @@ class _BKNode:
 
     def __init__(self, value: int):
         self.value = value
-        self.children: Dict[int, _BKNode] = {}
+        self.children: dict[int, _BKNode] = {}
 
     def add(self, h: int, dist_fn: Callable[[int, int], int]) -> None:
         d = dist_fn(h, self.value)
@@ -48,12 +47,12 @@ class _BKNode:
         target: int,
         threshold: int,
         dist_fn: Callable[[int, int], int],
-    ) -> List[Tuple[int, int]]:
+    ) -> list[tuple[int, int]]:
         """
         Recursively collect (value, dist) pairs within threshold.
         """
         d0 = dist_fn(target, self.value)
-        matches: List[Tuple[int, int]] = []
+        matches: list[tuple[int, int]] = []
         if d0 <= threshold:
             matches.append((self.value, d0))
         # Only children whose edge-dist \in [d0-threshold, d0+threshold]
@@ -76,7 +75,7 @@ class ImageHashStore:
 
     def __init__(
         self,
-        path: Union[str, Path] = HASH_STORE_FILE,
+        path: str | Path = HASH_STORE_FILE,
         auto_save: bool = False,
         hash_func: Callable[[Image.Image], int] = phash,
         ham_dist: Callable[[int, int], int] = fast_hamming_distance,
@@ -89,11 +88,11 @@ class ImageHashStore:
         self._th = threshold
 
         # label -> set of hashes
-        self._hash: Dict[str, Set[int]] = {}
+        self._hash: dict[str, set[int]] = {}
         # hash -> list of labels (for reverse lookup)
-        self._hash_to_labels: Dict[int, List[str]] = {}
+        self._hash_to_labels: dict[int, list[str]] = {}
         # root of BK-Tree (or None if empty)
-        self._bk_root: Optional[_BKNode] = None
+        self._bk_root: _BKNode | None = None
 
         self.load()
 
@@ -155,7 +154,7 @@ class ImageHashStore:
         if self._auto:
             self.save()
 
-    def add_image(self, img_path: Union[str, Path], label: str) -> int:
+    def add_image(self, img_path: str | Path, label: str) -> int:
         """
         Compute hash for the given image and add it under `label`.
         Updates BK-Tree index incrementally.
@@ -173,7 +172,7 @@ class ImageHashStore:
         self._maybe_save()
         return h
 
-    def add_from_map(self, map_path: Union[str, Path]) -> None:
+    def add_from_map(self, map_path: str | Path) -> None:
         """
         Load a JSON file of the form { "image_path": "label", ... }
         and add each entry.
@@ -191,11 +190,11 @@ class ImageHashStore:
                 )
                 continue
 
-    def labels(self) -> List[str]:
+    def labels(self) -> list[str]:
         """Return a sorted list of all labels in the store."""
         return sorted(self._hash.keys())
 
-    def hashes(self, label: str) -> Set[int]:
+    def hashes(self, label: str) -> set[int]:
         """Return the set of hashes for a given `label` (empty set if none)."""
         return set(self._hash.get(label, ()))
 
@@ -206,7 +205,7 @@ class ImageHashStore:
             logger.debug("[ImageHashStore] Removed label '%s'", label)
             self._maybe_save()
 
-    def remove_hash(self, label: str, this: Union[int, str, Path]) -> bool:
+    def remove_hash(self, label: str, this: int | str | Path) -> bool:
         """
         Remove a specific hash under `label`.
         `this` can be:
@@ -218,7 +217,7 @@ class ImageHashStore:
             return False
 
         h = None
-        if isinstance(this, (str, Path)):
+        if isinstance(this, (str | Path)):
             try:
                 img = Image.open(this).convert("L")
                 h = self._hf(img)
@@ -239,10 +238,10 @@ class ImageHashStore:
 
     def query(
         self,
-        target: Union[int, str, Path, Image.Image],
+        target: int | str | Path | Image.Image,
         k: int = 1,
-        threshold: Optional[int] = None,
-    ) -> List[Tuple[str, float]]:
+        threshold: int | None = None,
+    ) -> list[tuple[str, float]]:
         """
         Find up to `k` distinct labels whose stored hashes are most similar
         to `target` within `threshold`. Returns a list of (label, score),
@@ -259,7 +258,7 @@ class ImageHashStore:
         if isinstance(target, Image.Image):
             img = target.convert("L")
             thash = self._hf(img)
-        elif isinstance(target, (str, Path)):
+        elif isinstance(target, (str | Path)):
             img = Image.open(target).convert("L")
             thash = self._hf(img)
         else:
@@ -272,7 +271,7 @@ class ImageHashStore:
         matches = self._bk_root.query(thash, threshold, self._hd)
 
         # collapse to one best dist per label
-        best_per_label: Dict[str, float] = {}
+        best_per_label: dict[str, float] = {}
         h2l = self._hash_to_labels
         for h, dist in matches:
             for lbl in h2l.get(h, ()):

novel_downloader/utils/hash_utils.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.hash_utils
 ---------------------------------

novel_downloader/utils/i18n.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.i18n
 ---------------------------
@@ -8,17 +7,17 @@ Multilingual text dictionary and utility for CLI and interactive mode.
 """
 
 import json
-from typing import Any, Dict
+from typing import Any
 
 from novel_downloader.utils.constants import LOCALES_DIR
 from novel_downloader.utils.state import state_mgr
 
-_TRANSLATIONS: Dict[str, Dict[str, str]] = {}
+_TRANSLATIONS: dict[str, dict[str, str]] = {}
 
 for locale_path in LOCALES_DIR.glob("*.json"):
     lang = locale_path.stem
     try:
-        with open(locale_path, "r", encoding="utf-8") as f:
+        with open(locale_path, encoding="utf-8") as f:
             _TRANSLATIONS[lang] = json.load(f)
     except Exception:
         continue

novel_downloader/utils/logger.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.logger
 -----------------------------
@@ -12,13 +11,13 @@ import logging
 from datetime import datetime
 from logging.handlers import TimedRotatingFileHandler
 from pathlib import Path
-from typing import Dict, Literal, Optional, Union
+from typing import Literal
 
 from .constants import LOGGER_DIR, LOGGER_NAME
 
 LogLevel = Literal["DEBUG", "INFO", "WARNING", "ERROR"]
 
-LOG_LEVELS: Dict[LogLevel, int] = {
+LOG_LEVELS: dict[LogLevel, int] = {
     "DEBUG": logging.DEBUG,
     "INFO": logging.INFO,
     "WARNING": logging.WARNING,
@@ -27,9 +26,9 @@ LOG_LEVELS: Dict[LogLevel, int] = {
 
 
 def setup_logging(
-    log_filename_prefix: Optional[str] = None,
-    log_level: Optional[LogLevel] = None,
-    log_dir: Optional[Union[str, Path]] = None,
+    log_filename_prefix: str | None = None,
+    log_level: LogLevel | None = None,
+    log_dir: str | Path | None = None,
 ) -> logging.Logger:
     """
     Create and configure a logger for both console and rotating file output.

novel_downloader/utils/model_loader.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.model_loader
 -----------------------------------
@@ -13,7 +12,7 @@ Currently supports:
 from pathlib import Path
 
 from huggingface_hub import hf_hub_download
-from huggingface_hub.utils import LocalEntryNotFoundError
+from huggingface_hub.errors import LocalEntryNotFoundError
 
 from novel_downloader.utils.constants import (
     MODEL_CACHE_DIR,
@@ -38,12 +37,11 @@ def get_rec_chinese_char_model_dir(version: str = "v1.0") -> Path:
                 filename=fname,
                 revision=version,
                 local_dir=model_dir,
-                local_dir_use_symlinks=False,
             )
-        except LocalEntryNotFoundError:
+        except LocalEntryNotFoundError as err:
             raise RuntimeError(
                 f"[model] Missing model file '{fname}' and no internet connection."
-            )
+            ) from err
     return model_dir
 
 
@@ -62,11 +60,10 @@ def get_rec_char_vector_dir(version: str = "v1.0") -> Path:
                 filename=fname,
                 revision=version,
                 local_dir=vector_dir,
-                local_dir_use_symlinks=False,
             )
-        except LocalEntryNotFoundError:
+        except LocalEntryNotFoundError as err:
             raise RuntimeError(
                 f"[vector] Missing vector file '{fname}' and no internet connection."
-            )
+            ) from err
 
     return vector_dir

novel_downloader/utils/network.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.network
 ------------------------------
@@ -11,7 +10,7 @@ import logging
 import random
 import time
 from pathlib import Path
-from typing import Dict, Literal, Optional, Union
+from typing import Literal
 from urllib.parse import unquote, urlparse
 
 import requests
@@ -30,9 +29,9 @@ def http_get_with_retry(
     retries: int = 3,
     timeout: int = 10,
     backoff: float = 0.5,
-    headers: Optional[Dict[str, str]] = None,
+    headers: dict[str, str] | None = None,
     stream: bool = False,
-) -> Optional[requests.Response]:
+) -> requests.Response | None:
     """
     Perform a GET request with retry support.
 
@@ -87,13 +86,13 @@ def image_url_to_filename(url: str) -> str:
 
 def download_image_as_bytes(
     url: str,
-    target_folder: Optional[Union[str, Path]] = None,
+    target_folder: str | Path | None = None,
     *,
     timeout: int = 10,
     retries: int = 3,
     backoff: float = 0.5,
     on_exist: Literal["overwrite", "skip", "rename"] = "overwrite",
-) -> Optional[bytes]:
+) -> bytes | None:
     """
     Download an image from a given URL and return its content as bytes.
 
@@ -155,13 +154,13 @@ def download_image_as_bytes(
 
 def download_font_file(
     url: str,
-    target_folder: Union[str, Path],
+    target_folder: str | Path,
     *,
     timeout: int = 10,
     retries: int = 3,
     backoff: float = 0.5,
     on_exist: Literal["overwrite", "skip", "rename"] = "skip",
-) -> Optional[Path]:
+) -> Path | None:
     """
     Download a font file from a URL and save it locally with retry and overwrite control
 
@@ -226,13 +225,13 @@ def download_font_file(
 
 def download_js_file(
     url: str,
-    target_folder: Union[str, Path],
+    target_folder: str | Path,
     *,
     timeout: int = 10,
     retries: int = 3,
     backoff: float = 0.5,
     on_exist: Literal["overwrite", "skip", "rename"] = "skip",
-) -> Optional[Path]:
+) -> Path | None:
     """
     Download a JavaScript (.js) file from a URL and save it locally.
 

novel_downloader/utils/state.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.state
 ----------------------------
@@ -11,7 +10,7 @@ Supported sections:
 """
 import json
 from pathlib import Path
-from typing import Any, Dict, Union
+from typing import Any
 
 from .constants import STATE_FILE
 
@@ -26,7 +25,7 @@ class StateManager:
         self._path = path
         self._data = self._load()
 
-    def _load(self) -> Dict[str, Any]:
+    def _load(self) -> dict[str, Any]:
         """
         Load the configuration file into a Python dictionary.
 
@@ -50,7 +49,7 @@ class StateManager:
         content = json.dumps(self._data, ensure_ascii=False, indent=2)
         self._path.write_text(content, encoding="utf-8")
 
-    def _parse_cookie_string(self, cookie_str: str) -> Dict[str, str]:
+    def _parse_cookie_string(self, cookie_str: str) -> dict[str, str]:
         """
         Parse a Cookie header string into a dict.
 
@@ -58,7 +57,7 @@ class StateManager:
         :return: mapping cookie names to values (missing '=' yields empty string)
         :rtype: Dict[str, str]
         """
-        cookies: Dict[str, str] = {}
+        cookies: dict[str, str] = {}
         for item in cookie_str.split(";"):
             item = item.strip()
             if not item:
@@ -110,7 +109,7 @@ class StateManager:
         site_data["manual_login"] = flag
         self._save()
 
-    def get_cookies(self, site: str) -> Dict[str, str]:
+    def get_cookies(self, site: str) -> dict[str, str]:
         """
         Retrieve the persisted cookies for a specific site.
 
@@ -120,7 +119,7 @@ class StateManager:
         cookies = self._data.get("sites", {}).get(site, {}).get("cookies", {})
         return {str(k): str(v) for k, v in cookies.items()}
 
-    def set_cookies(self, site: str, cookies: Union[str, Dict[str, str]]) -> None:
+    def set_cookies(self, site: str, cookies: str | dict[str, str]) -> None:
         """
         Persist (overwrite) the cookies for a specific site.
 

novel_downloader/utils/text_utils/__init__.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.text_utils
 ---------------------------------

novel_downloader/utils/text_utils/chapter_formatting.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.text_utils.chapter_formatting
 ----------------------------------------------------
@@ -7,12 +6,8 @@ novel_downloader.utils.text_utils.chapter_formatting
 Format chapter content with title, paragraph blocks, and optional author notes.
 """
 
-from typing import List, Optional
 
-
-def format_chapter(
-    title: str, paragraphs: str, author_say: Optional[str] = None
-) -> str:
+def format_chapter(title: str, paragraphs: str, author_say: str | None = None) -> str:
     """
     Build a formatted chapter string with title, paragraphs, and optional author note.
 
@@ -22,7 +17,7 @@ def format_chapter(
     :return:            A single string where title, paragraphs, and author note
                         are separated by blank lines.
     """
-    parts: List[str] = [title.strip()]
+    parts: list[str] = [title.strip()]
 
     # add each nonempty paragraph line
     for ln in paragraphs.splitlines():

novel_downloader/utils/text_utils/diff_display.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.text_utils.diff_display
 ----------------------------------------------

novel_downloader/utils/text_utils/font_mapping.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.text_utils.font_mapping
 ----------------------------------------------
@@ -11,10 +10,8 @@ where characters are visually disguised via custom font glyphs but can be
 recovered using a known mapping.
 """
 
-from typing import Dict
 
-
-def apply_font_mapping(text: str, font_map: Dict[str, str]) -> str:
+def apply_font_mapping(text: str, font_map: dict[str, str]) -> str:
     """
     Replace each character in `text` using `font_map`,
     leaving unmapped characters unchanged.

novel_downloader/utils/text_utils/text_cleaning.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.text_utils.text_cleaning
 -----------------------------------------------

novel_downloader/utils/time_utils/__init__.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.time_utils
 ---------------------------------

novel_downloader/utils/time_utils/datetime_utils.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.time_utils.datetime_utils
 ------------------------------------------------
@@ -15,8 +14,7 @@ Includes:
 
 import logging
 import re
-from datetime import datetime, timedelta, timezone
-from typing import Optional, Tuple
+from datetime import UTC, datetime, timedelta, timezone
 
 logger = logging.getLogger(__name__)
 
@@ -61,8 +59,8 @@ def _parse_utc_offset(tz_str: str) -> timezone:
     else:
         try:
             hours = int(offset_part)
-        except ValueError:
-            raise ValueError(f"Invalid UTC offset hours: '{offset_part}'")
+        except ValueError as err:
+            raise ValueError(f"Invalid UTC offset hours: '{offset_part}'") from err
     return timezone(timedelta(hours=hours))
 
 
@@ -100,9 +98,9 @@ def _parse_datetime_flexible(dt_str: str) -> datetime:
 def calculate_time_difference(
     from_time_str: str,
     tz_str: str = "UTC",
-    to_time_str: Optional[str] = None,
+    to_time_str: str | None = None,
     to_tz_str: str = "UTC",
-) -> Tuple[int, int, int, int]:
+) -> tuple[int, int, int, int]:
     """
     Calculate the difference between two datetime values.
 
@@ -116,15 +114,15 @@ def calculate_time_difference(
         # parse start time
         tz_from = _parse_utc_offset(tz_str)
         dt_from = _parse_datetime_flexible(from_time_str)
-        dt_from = dt_from.replace(tzinfo=tz_from).astimezone(timezone.utc)
+        dt_from = dt_from.replace(tzinfo=tz_from).astimezone(UTC)
 
         # parse end time or use now
         if to_time_str:
             tz_to = _parse_utc_offset(to_tz_str)
             dt_to = _parse_datetime_flexible(to_time_str)
-            dt_to = dt_to.replace(tzinfo=tz_to).astimezone(timezone.utc)
+            dt_to = dt_to.replace(tzinfo=tz_to).astimezone(UTC)
         else:
-            dt_to = datetime.now(timezone.utc)
+            dt_to = datetime.now(UTC)
 
         delta = dt_to - dt_from
 

novel_downloader/utils/time_utils/sleep_utils.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.time_utils.sleep_utils
 ---------------------------------------------
@@ -14,7 +13,6 @@ Includes:
 import logging
 import random
 import time
-from typing import Optional
 
 logger = logging.getLogger(__name__)
 
@@ -24,7 +22,7 @@ def sleep_with_random_delay(
     add_spread: float = 0.0,
     mul_spread: float = 1.0,
     *,
-    max_sleep: Optional[float] = None,
+    max_sleep: float | None = None,
 ) -> None:
     """
     Sleep for a random duration by combining multiplicative and additive jitter.

{novel_downloader-1.2.2.dist-info → novel_downloader-1.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: novel-downloader
-Version: 1.2.2
+Version: 1.3.0
 Summary: A command-line tool for downloading Chinese web novels from Qidian and similar platforms.
 Author-email: Saudade Z <saudadez217@gmail.com>
 License: MIT License
@@ -34,18 +34,16 @@ Classifier: License :: OSI Approved :: MIT License
 Classifier: Natural Language :: Chinese (Simplified)
 Classifier: Topic :: Utilities
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Python: >=3.8
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: requests
+Requires-Dist: aiohttp
 Requires-Dist: beautifulsoup4
 Requires-Dist: DrissionPage
-Requires-Dist: pyyaml
+Requires-Dist: opencv-python
 Requires-Dist: lxml
 Requires-Dist: platformdirs
 Requires-Dist: click
@@ -64,10 +62,9 @@ Requires-Dist: scipy; extra == "font-recovery"
 Requires-Dist: numpy; extra == "font-recovery"
 Requires-Dist: tinycss2; extra == "font-recovery"
 Requires-Dist: fonttools; extra == "font-recovery"
+Requires-Dist: brotli; extra == "font-recovery"
 Requires-Dist: pillow; extra == "font-recovery"
 Requires-Dist: huggingface_hub; extra == "font-recovery"
-Provides-Extra: async
-Requires-Dist: aiohttp; extra == "async"
 Dynamic: license-file
 
 # novel-downloader
@@ -94,13 +91,10 @@ pip install novel-downloader
 # 如需支持字体解密功能 (decode_font), 请使用:
 # pip install novel-downloader[font-recovery]
 
-# 如需启用异步抓取模式 (mode=async), 请使用:
-# pip install novel-downloader[async]
-
-# 初始化默认配置 (生成 settings.yaml)
+# 初始化默认配置 (生成 settings.toml)
 novel-cli settings init
 
-# 编辑 ./settings.yaml 完成 site/book_ids 等
+# 编辑 ./settings.toml 完成 site/book_ids 等
 # 可查看 docs/4-settings-schema.md
 
 # 运行下载
@@ -117,7 +111,6 @@ cd novel-downloader
 pip install .
 # 或安装带可选功能:
 # pip install .[font-recovery]
-# pip install .[async]
 ```
 
 更多使用方法, 查看 [使用示例](https://github.com/BowenZ217/novel-downloader/blob/main/docs/5-usage-examples.md)
@@ -127,7 +120,10 @@ pip install .
 ## 功能特性
 
 - 爬取起点中文网的小说章节内容 (支持免费与已订阅章节)
-- 自动整合所有章节并输出为完整的 TXT 文件
+- 断点续爬
+- 自动整合所有章节并导出为
+  - TXT
+  - EPUB
 - 支持活动广告过滤:
   - [x] 章节标题
   - [ ] 章节正文
@@ -141,8 +137,9 @@ pip install .
 - [安装](https://github.com/BowenZ217/novel-downloader/blob/main/docs/1-installation.md)
 - [环境准备](https://github.com/BowenZ217/novel-downloader/blob/main/docs/2-environment-setup.md)
 - [配置](https://github.com/BowenZ217/novel-downloader/blob/main/docs/3-configuration.md)
-- [settings.yaml 配置说明](https://github.com/BowenZ217/novel-downloader/blob/main/docs/4-settings-schema.md)
+- [settings.toml 配置说明](https://github.com/BowenZ217/novel-downloader/blob/main/docs/4-settings-schema.md)
 - [使用示例](https://github.com/BowenZ217/novel-downloader/blob/main/docs/5-usage-examples.md)
+- [支持站点列表](https://github.com/BowenZ217/novel-downloader/blob/main/docs/6-supported-sites.md)
 - [文件保存](https://github.com/BowenZ217/novel-downloader/blob/main/docs/file-saving.md)
 - [TODO](https://github.com/BowenZ217/novel-downloader/blob/main/docs/todo.md)
 - [开发](https://github.com/BowenZ217/novel-downloader/blob/main/docs/develop.md)