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

novel_downloader/core/savers/{common_saver/common_txt.py → common/txt.py}

@@ -1,8 +1,7 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
-novel_downloader.core.savers.common_saver.qidian_txt
-----------------------------------------------------
+novel_downloader.core.savers.common.txt
+---------------------------------------
 
 Contains the logic for exporting novel content as a single `.txt` file.
 
@@ -14,39 +13,17 @@ It is intended to be used by `CommonSaver` as part of the save/export process.
 from __future__ import annotations
 
 import json
-import logging
-from pathlib import Path
-from typing import TYPE_CHECKING, List, Optional
+from typing import TYPE_CHECKING
 
 from novel_downloader.utils.file_utils import save_as_txt
-from novel_downloader.utils.text_utils import clean_chapter_title, format_chapter
+from novel_downloader.utils.text_utils import (
+    clean_chapter_title,
+    format_chapter,
+)
 
 if TYPE_CHECKING:
     from .main_saver import CommonSaver
 
-logger = logging.getLogger(__name__)
-
-CHAPTER_FOLDERS: List[str] = [
-    "chapters",
-    "encrypted_chapters",
-]
-
-
-def _find_chapter_file(
-    raw_base: Path,
-    chapter_id: str,
-) -> Optional[Path]:
-    """
-    Search for `<chapter_id>.json` under each folder in CHAPTER_FOLDERS
-    inside raw_data_dir/site/book_id. Return the first existing Path,
-    or None if not found.
-    """
-    for folder in CHAPTER_FOLDERS:
-        candidate = raw_base / folder / f"{chapter_id}.json"
-        if candidate.exists():
-            return candidate
-    return None
-
 
 def common_save_as_txt(
     saver: CommonSaver,
@@ -80,11 +57,11 @@ def common_save_as_txt(
         info_text = info_path.read_text(encoding="utf-8")
         book_info = json.loads(info_text)
     except Exception as e:
-        logger.error("%s Failed to load %s: %s", TAG, info_path, e)
+        saver.logger.error("%s Failed to load %s: %s", TAG, info_path, e)
         return
 
     # --- Compile chapters ---
-    parts: List[str] = []
+    parts: list[str] = []
     latest_chapter: str = ""
     volumes = book_info.get("volumes", [])
 
@@ -94,18 +71,17 @@ def common_save_as_txt(
         if vol_name:
             volume_header = f"\n\n{'=' * 6} {vol_name} {'=' * 6}\n\n"
             parts.append(volume_header)
-            logger.info("%s Processing volume: %s", TAG, vol_name)
+            saver.logger.info("%s Processing volume: %s", TAG, vol_name)
         for chap in vol.get("chapters", []):
             chap_id = chap.get("chapterId")
             chap_title = chap.get("title", "")
             if not chap_id:
-                logger.warning("%s Missing chapterId, skipping: %s", TAG, chap)
+                saver.logger.warning("%s Missing chapterId, skipping: %s", TAG, chap)
                 continue
 
-            # Find the JSON file in one of the known subfolders
-            json_path = _find_chapter_file(raw_base, chap_id)
-            if json_path is None:
-                logger.info(
+            chapter_data = saver._get_chapter(book_id, chap_id)
+            if not chapter_data:
+                saver.logger.info(
                     "%s Missing chapter file in: %s (%s), skipping.",
                     TAG,
                     chap_title,
@@ -113,12 +89,6 @@ def common_save_as_txt(
                 )
                 continue
 
-            try:
-                chapter_data = json.loads(json_path.read_text(encoding="utf-8"))
-            except Exception as e:
-                logger.error("%s Error reading %s: %s", TAG, json_path, e)
-                continue
-
             # Extract structured fields
             title = chapter_data.get("title", chap_title).strip()
             content = chapter_data.get("content", "").strip()
@@ -170,7 +140,7 @@ def common_save_as_txt(
     # --- Save final text ---
     try:
         save_as_txt(content=final_text, filepath=out_path)
-        logger.info("%s Novel saved to: %s", TAG, out_path)
+        saver.logger.info("%s Novel saved to: %s", TAG, out_path)
     except Exception as e:
-        logger.error("%s Failed to save file: %s", TAG, e)
+        saver.logger.error("%s Failed to save file: %s", TAG, e)
     return

novel_downloader/core/savers/epub_utils/__init__.py

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

novel_downloader/core/savers/epub_utils/css_builder.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.core.savers.epub_utils.css_builder
 
@@ -9,7 +8,7 @@ returning a list ready to be added to the EPUB.
 
 import logging
 from importlib.abc import Traversable
-from typing import Dict, List, Union
+from typing import TypedDict
 
 from ebooklib import epub
 
@@ -21,16 +20,23 @@ from novel_downloader.utils.constants import (
 logger = logging.getLogger(__name__)
 
 
+class CssConfig(TypedDict):
+    include: bool
+    path: Traversable
+    uid: str
+    file_name: str
+
+
 def create_css_items(
     include_main: bool = True,
     include_volume: bool = True,
-) -> List[epub.EpubItem]:
+) -> list[epub.EpubItem]:
     """
     :param include_main:   Whether to load the main stylesheet.
     :param include_volume: Whether to load the “volume intro” stylesheet.
     :returns: A list of epub.EpubItem ready to add to the book.
     """
-    css_config: List[Dict[str, Union[str, bool, Traversable]]] = [
+    css_config: list[CssConfig] = [
         {
             "include": include_main,
             "path": CSS_MAIN_PATH,
@@ -44,20 +50,20 @@ def create_css_items(
             "file_name": "Styles/volume-intro.css",
         },
     ]
-    css_items: List[epub.EpubItem] = []
+    css_items: list[epub.EpubItem] = []
 
     for css in css_config:
         if css["include"]:
             path = css["path"]
-            assert isinstance(path, Traversable)
             try:
                 content: str = path.read_text(encoding="utf-8")
+                content_bytes: bytes = content.encode("utf-8")
                 css_items.append(
                     epub.EpubItem(
                         uid=css["uid"],
                         file_name=css["file_name"],
                         media_type="text/css",
-                        content=content,
+                        content=content_bytes,
                     )
                 )
             except FileNotFoundError:

novel_downloader/core/savers/epub_utils/initializer.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.core.savers.epub_utils.initializer
 
@@ -10,7 +9,7 @@ adds a cover, and prepares the initial spine and TOC entries.
 
 import logging
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any
 
 from ebooklib import epub
 
@@ -24,12 +23,12 @@ logger = logging.getLogger(__name__)
 
 
 def init_epub(
-    book_info: Dict[str, Any],
+    book_info: dict[str, Any],
     book_id: str,
     intro_html: str,
-    book_cover_path: Optional[Path] = None,
+    book_cover_path: Path | None = None,
     include_toc: bool = False,
-) -> Tuple[epub.EpubBook, List[Any], List[Any]]:
+) -> tuple[epub.EpubBook, list[Any], list[Any]]:
     """
     Initialize an EPUB book with metadata, optional cover, and intro page.
 

novel_downloader/core/savers/epub_utils/text_to_html.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.core.savers.epub_utils.text_to_html
 
@@ -9,7 +8,7 @@ with automatic word correction and optional image/tag support.
 
 import json
 import logging
-from typing import Any, Dict
+from typing import Any
 
 from novel_downloader.utils.constants import REPLACE_WORD_MAP_PATH
 from novel_downloader.utils.text_utils import diff_inline_display
@@ -88,7 +87,7 @@ def chapter_txt_to_html(
     return "\n".join(html_parts)
 
 
-def generate_book_intro_html(book_info: Dict[str, Any]) -> str:
+def generate_book_intro_html(book_info: dict[str, Any]) -> str:
     """
     Generate HTML string for a book's information and summary.
 

novel_downloader/core/savers/epub_utils/volume_intro.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.core.savers.epub_utils.volume_intro
 
@@ -7,12 +6,11 @@ Responsible for generating HTML code for volume introduction pages,
 including two style variants and a unified entry point.
 """
 
-from typing import Tuple
 
 from novel_downloader.utils.constants import EPUB_IMAGE_FOLDER
 
 
-def split_volume_title(volume_title: str) -> Tuple[str, str]:
+def split_volume_title(volume_title: str) -> tuple[str, str]:
     """
     Split volume title into two parts for better display.
 

novel_downloader/core/savers/{qidian_saver.py → qidian.py}

@@ -1,8 +1,7 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
-novel_downloader.core.savers.qidian_saver
------------------------------------------
+novel_downloader.core.savers.qidian
+-----------------------------------
 
 This module provides the `QidianSaver` class for handling the saving process
 of novels sourced from Qidian (起点中文网). It implements the platform-specific
@@ -11,12 +10,19 @@ logic required to structure and export novel content into desired formats.
 
 from novel_downloader.config.models import SaverConfig
 
-from .common_saver import CommonSaver
+from .common import CommonSaver
 
 
 class QidianSaver(CommonSaver):
-    def __init__(self, config: SaverConfig):
-        super().__init__(config, site="qidian")
+    def __init__(
+        self,
+        config: SaverConfig,
+    ):
+        super().__init__(
+            config,
+            site="qidian",
+            chap_folders=["chapters", "encrypted_chapters"],
+        )
 
 
 __all__ = ["QidianSaver"]

novel_downloader/locales/en.json

@@ -3,7 +3,7 @@
   "help_config": "Path to config file",
   "help_download": "Download novels",
   "help_clean": "Clean cache and configuration files",
-  "main_no_command": "No command provided, entering interactive mode…",
+  "main_no_command": "No command provided, entering interactive mode...",
 
   "settings_help": "Configure downloader settings.",
   "settings_set_lang_help": "Switch language between Chinese and English.",
@@ -49,8 +49,8 @@
   "interactive_option_preview": "Preview chapters",
   "interactive_option_exit": "Exit",
   "interactive_prompt_choice": "Enter your choice",
-  "interactive_browse_start": "Starting interactive browser…",
-  "interactive_preview_start": "Previewing chapters…",
+  "interactive_browse_start": "Starting interactive browser...",
+  "interactive_preview_start": "Previewing chapters...",
   "interactive_exit": "Exiting.",
 
   "download_help": "Download full novels by book IDs.",
@@ -69,11 +69,15 @@
   "login_prompt_intro": "Manual login is required. Please switch to the browser and log in.",
   "login_prompt_press_enter": "Attempt {attempt}/{max_retries}: Press Enter after completing login in the browser...",
 
+  "session_login_prompt_intro": "Failed to restore login from saved cookies. Please log in via browser, then paste the cookie string below.",
+  "session_login_prompt_paste_cookie": "Attempt {attempt}/{max_retries}: Paste your browser cookie string and press Enter:",
+  "session_login_prompt_invalid_cookie": "Invalid cookie. Please copy and paste again.",
+
   "clean_logs": "Clean log directory",
   "clean_cache": "Clean scripts and browser cache",
   "clean_state": "Clean state files (state.json)",
   "clean_data": "Clean data files (e.g. image hashes, browser data)",
-  "clean_config": "Clean config files (e.g. settings.yaml, site rules)",
+  "clean_config": "Clean config files (e.g. settings.toml, site rules)",
   "clean_models": "Clean downloaded model cache",
   "clean_hf_cache": "Clear Hugging Face model cache",
   "clean_hf_cache_done": "Hugging Face cache cleared",

novel_downloader/locales/zh.json

@@ -69,11 +69,15 @@
   "login_prompt_intro": "需要手动登录, 请切换到浏览器窗口完成登录",
   "login_prompt_press_enter": "第 {attempt}/{max_retries} 次尝试: 请在浏览器中完成登录后按回车键...",
 
+  "session_login_prompt_intro": "尝试使用历史 Cookie 恢复登录失败, 请在浏览器登录后从开发者工具复制 Cookie 粘贴至下方",
+  "session_login_prompt_paste_cookie": "第 {attempt}/{max_retries} 次尝试, 请粘贴 Cookie 字符串并回车:",
+  "session_login_prompt_invalid_cookie": "Cookie 格式不正确, 请重新复制粘贴",
+
   "clean_logs": "清理日志目录",
   "clean_cache": "清理脚本和浏览器缓存",
   "clean_state": "清理状态文件 (state.json)",
   "clean_data": "清理数据文件 (如 image hashes, 浏览器数据)",
-  "clean_config": "清理配置文件 (如 settings.yaml 和规则)",
+  "clean_config": "清理配置文件 (如 settings.toml 和规则)",
   "clean_models": "清理模型缓存目录",
   "clean_hf_cache": "清理 Hugging Face 下载缓存",
   "clean_hf_cache_done": "已清除 Hugging Face 本地缓存",

novel_downloader/resources/config/settings.toml

@@ -0,0 +1,88 @@
+# 网络请求层设置
+[requests]
+retry_times = 3                    # 请求失败重试次数
+backoff_factor = 2.0
+timeout = 30.0                     # 页面加载超时时间 (秒)
+max_connections = 10               # 并发连接的最大数 (async)
+# max_rps =                        # 最大请求速率 (requests per second), 为空则不限制
+
+# DrissionPage 专用设置
+headless = false                   # 是否以无头模式启动浏览器
+user_data_folder = ""              # 浏览器用户数据目录: 为空则使用默认目录
+profile_name = ""                  # 使用的用户配置名称: 为空则使用默认配置
+auto_close = true                  # 页面抓取完是否自动关闭浏览器
+disable_images = false             # 是否禁用图片加载 (加速)
+mute_audio = true                  # 是否静音
+
+# 全局通用设置
+[general]
+request_interval = 5.0             # 同一本书各章节请求间隔 (秒)
+raw_data_dir = "./raw_data"        # 原始章节 JSON/DB 存放目录
+output_dir = "./downloads"         # 最终输出文件存放目录
+cache_dir = "./novel_cache"        # 本地缓存目录 (字体 / 图片等)
+download_workers = 4               # 并发下载线程数 (async)
+parser_workers = 4                 # 并发解析线程数
+use_process_pool = false           # 是否使用多进程池来处理任务
+skip_existing = true               # 是否跳过已存在章节
+storage_backend = "sqlite"         # 章节储存方法: json / sqlite
+storage_batch_size = 30            # SQLite 批量提交的章节数量
+
+[general.debug]
+save_html = false                  # 是否将抓取到的原始 HTML 保留到磁盘
+log_level = "INFO"                 # 日志级别: DEBUG, INFO, WARNING, ERROR
+
+[general.font_ocr]
+decode_font = false                # 是否尝试本地解码混淆字体
+use_freq = false                   # 是否使用频率分析
+ocr_version = "v2.0"               # "v1.0" / "v2.0"
+use_ocr = true                     # 是否使用 OCR 辅助识别文本
+use_vec = false                    # 是否使用 Vector 辅助识别文本
+save_font_debug = false            # 是否保存字体解码调试数据
+batch_size = 32
+gpu_mem = 500                      # GPU 显存限制 (MB)
+# gpu_id =                         # 使用哪个 GPU
+ocr_weight = 0.5
+vec_weight = 0.5
+
+# 各站点的特定配置
+[sites.qidian]
+# 小说 ID 列表
+# 例如: 访问 https://www.qidian.com/book/1010868264/
+# 该小说的 ID 就是 1010868264
+book_ids = [
+  "0000000000",
+  "0000000000"
+]
+mode = "browser"                   # browser / session
+login_required = true              # 是否需要登录才能访问
+
+[sites.biquge]
+book_ids = [
+  "0000000000",
+  "0000000000"
+]
+mode = "session"                   # async / session
+login_required = false             # 是否需要登录才能访问
+
+[sites.common]
+mode = "session"                   # async / session
+login_required = false             # 是否需要登录才能访问
+
+# 输出文件格式及相关选项
+[output]
+clean_text = true                  # 是否对章节文本做清理
+
+[output.formats]
+make_txt = true                    # 是否生成完整 TXT 文件
+make_epub = false                  # 是否生成 EPUB
+make_md = false                    # 是否生成 Markdown (未实现)
+make_pdf = false                   # 可能支持 PDF 输出 (未实现)
+
+[output.naming]
+append_timestamp = false           # 在文件名中追加时间戳
+filename_template = "{title}_{author}"  # 文件命名规则
+
+[output.epub]
+include_cover = true               # 是否在 EPUB 中包含封面
+include_toc = false                # 是否自动生成目录
+include_picture = false            # 是否下载章节图片 (体积较大)

novel_downloader/utils/cache.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.utils.cache
 ----------------------------
@@ -8,8 +7,9 @@ Provides decorators for caching function results,
 specifically optimized for configuration loading functions.
 """
 
+from collections.abc import Callable
 from functools import lru_cache, wraps
-from typing import Any, Callable, TypeVar, cast
+from typing import Any, TypeVar, cast
 
 T = TypeVar("T", bound=Callable[..., Any])