novel-downloader 1.1.0__py3-none-any.whl

novel_downloader/core/savers/epub_utils/css_builder.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+novel_downloader.core.savers.epub_utils.css_builder
+
+Reads local CSS files and wraps them into epub.EpubItem objects,
+returning a list ready to be added to the EPUB.
+"""
+
+import logging
+from importlib.abc import Traversable
+from typing import Dict, List, Union
+
+from ebooklib import epub
+
+from novel_downloader.utils.constants import (
+    CSS_MAIN_PATH,
+    CSS_VOLUME_INTRO_PATH,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def create_css_items(
+    include_main: bool = True,
+    include_volume: bool = True,
+) -> 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]]] = [
+        {
+            "include": include_main,
+            "path": CSS_MAIN_PATH,
+            "uid": "style",
+            "file_name": "Styles/main.css",
+        },
+        {
+            "include": include_volume,
+            "path": CSS_VOLUME_INTRO_PATH,
+            "uid": "volume_style",
+            "file_name": "Styles/volume-intro.css",
+        },
+    ]
+    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")
+                css_items.append(
+                    epub.EpubItem(
+                        uid=css["uid"],
+                        file_name=css["file_name"],
+                        media_type="text/css",
+                        content=content,
+                    )
+                )
+            except FileNotFoundError:
+                logger.info(f"[epub] CSS 文件不存在: {css['path']}")
+            except UnicodeDecodeError:
+                logger.info(f"[epub] 无法解码文件: {css['path']}")
+
+    return css_items

novel_downloader/core/savers/epub_utils/initializer.py

@@ -0,0 +1,98 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+novel_downloader.core.savers.epub_utils.initializer
+
+Initializes an epub.EpubBook object, sets metadata
+(identifier, title, author, language, description),
+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 ebooklib import epub
+
+from novel_downloader.utils.constants import (
+    EPUB_IMAGE_FOLDER,
+    EPUB_TEXT_FOLDER,
+    VOLUME_BORDER_IMAGE_PATH,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def init_epub(
+    book_info: Dict[str, Any],
+    book_id: str,
+    intro_html: str,
+    book_cover_path: Optional[Path] = None,
+    include_toc: bool = False,
+) -> Tuple[epub.EpubBook, List[Any], List[Any]]:
+    """
+    Initialize an EPUB book with metadata, optional cover, and intro page.
+
+    :param book_info: Dict with keys 'book_name', 'author', 'summary'.
+    :param book_id: Book identifier (numeric or string).
+    :param intro_html: Intro content in XHTML format.
+    :param book_cover_path: Optional Path to the cover image file.
+    :param include_toc: Whether to include the <nav> item in the spine.
+    :return: (book, spine, toc_list)
+    """
+    book = epub.EpubBook()
+    book.set_identifier(str(book_id))
+    book.set_title(book_info.get("book_name", "未找到书名"))
+    book.set_language("zh-CN")
+    book.add_author(book_info.get("author", "未找到作者"))
+    book.add_metadata("DC", "description", book_info.get("summary", "未找到作品简介"))
+
+    spine = []
+
+    # cover
+    if book_cover_path:
+        try:
+            cover_bytes = book_cover_path.read_bytes()
+            ext = book_cover_path.suffix.lower()
+            ext = ext if ext in [".jpg", ".jpeg", ".png"] else ".jpeg"
+            filename = f"{EPUB_IMAGE_FOLDER}/cover{ext}"
+            book.set_cover(filename, cover_bytes)
+            spine.append("cover")
+        except FileNotFoundError:
+            logger.info(f"[epub] 封面图片不存在: {book_cover_path}")
+        except Exception as e:
+            logger.info(f"[epub] 读取封面失败: {book_cover_path}，错误：{e}")
+
+    # 导航菜单
+    if include_toc:
+        spine.append("nav")
+
+    # 简介页面
+    intro = epub.EpubHtml(
+        title="书籍简介",
+        file_name=f"{EPUB_TEXT_FOLDER}/intro.xhtml",
+        lang="zh-CN",
+        uid="intro",
+    )
+    intro.content = intro_html
+    intro.add_link(href="../Styles/main.css", rel="stylesheet", type="text/css")
+    book.add_item(intro)
+    spine.append(intro)
+
+    # 添加卷边框图像 (volume_border.png)
+    try:
+        border_bytes = VOLUME_BORDER_IMAGE_PATH.read_bytes()
+        border_item = epub.EpubItem(
+            uid="volume-border",
+            file_name=f"{EPUB_IMAGE_FOLDER}/volume_border.png",
+            media_type="image/png",
+            content=border_bytes,
+        )
+        book.add_item(border_item)
+    except FileNotFoundError:
+        logger.info(f"[epub] 卷边框图片不存在: {VOLUME_BORDER_IMAGE_PATH}")
+    except Exception as e:
+        logger.info(f"[epub] 读取卷边框失败: {VOLUME_BORDER_IMAGE_PATH}: {e}")
+
+    toc_list = [epub.Link(intro.file_name, "书籍简介", intro.id)]
+    return book, spine, toc_list

novel_downloader/core/savers/epub_utils/text_to_html.py

@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+novel_downloader.core.savers.epub_utils.text_to_html
+
+Module for converting raw chapter text to formatted HTML,
+with automatic word correction and optional image/tag support.
+"""
+
+import json
+import logging
+from typing import Any, Dict
+
+from novel_downloader.utils.constants import REPLACE_WORD_MAP_PATH
+from novel_downloader.utils.text_utils import diff_inline_display
+
+logger = logging.getLogger(__name__)
+
+
+# Load and sort replacement map from JSON
+try:
+    replace_map_raw = REPLACE_WORD_MAP_PATH.read_text(encoding="utf-8")
+    REPLACE_WORDS_MAP = json.loads(replace_map_raw)
+    REPLACE_WORDS_MAP = dict(
+        sorted(REPLACE_WORDS_MAP.items(), key=lambda x: len(x[0]), reverse=True)
+    )
+except Exception as e:
+    REPLACE_WORDS_MAP = {}
+    logger.info(
+        f"[epub] Failed to load REPLACE_WORDS_MAP from {REPLACE_WORD_MAP_PATH}: {e}"
+    )
+
+
+def _check_and_correct_words(txt_str: str) -> str:
+    """
+    Perform word replacement using REPLACE_WORDS_MAP.
+
+    :param txt_str: Raw string of text.
+    :return: String with corrected words.
+    """
+    for k, v in REPLACE_WORDS_MAP.items():
+        txt_str = txt_str.replace(k, v)
+    return txt_str
+
+
+def chapter_txt_to_html(
+    chapter_title: str,
+    chapter_text: str,
+    author_say: str,
+) -> str:
+    """
+    Convert chapter text and author note to styled HTML.
+
+    :param chapter_title: Title of the chapter.
+    :param chapter_text: Main content of the chapter.
+    :param author_say: Optional author note content.
+    :return: Rendered HTML as a string.
+    """
+
+    def _render_lines(text: str) -> str:
+        parts = []
+        for line in text.strip().splitlines():
+            line = line.strip()
+            if not line:
+                continue
+
+            if (
+                line.startswith("<img")
+                and line.endswith("/>")
+                or line.startswith('<div class="duokan-image-single illus">')
+                and line.endswith("</div>")
+            ):
+                parts.append(line)
+            else:
+                corrected = _check_and_correct_words(line)
+                if corrected != line:
+                    diff = diff_inline_display(line, corrected)
+                    logger.info("[epub] Correction diff:\n%s", diff)
+                parts.append(f"<p>{corrected}</p>")
+        return "\n".join(parts)
+
+    html_parts = [f"<h2>{chapter_title}</h2>"]
+    html_parts.append(_render_lines(chapter_text))
+
+    if author_say.strip():
+        html_parts.extend(["<hr />", "<p>作者说:</p>", _render_lines(author_say)])
+
+    return "\n".join(html_parts)
+
+
+def generate_book_intro_html(book_info: Dict[str, Any]) -> str:
+    """
+    Generate HTML string for a book's information and summary.
+
+    This function takes a dictionary containing book details and formats
+    it into a styled HTML block, skipping any missing fields gracefully.
+
+    :param book_info: A dictionary containing keys like 'book_name'...
+
+    :return: An HTML-formatted string presenting the book's information.
+    """
+    book_name = book_info.get("book_name")
+    author = book_info.get("author")
+    serial_status = book_info.get("serial_status")
+    word_count = book_info.get("word_count")
+    summary = book_info.get("summary", "").strip()
+
+    # Start composing the HTML output
+    html_parts = ["<h1>书籍简介</h1>", '<div class="list">', "<ul>"]
+
+    if book_name:
+        html_parts.append(f"<li>书名: 《{book_name}》</li>")
+    if author:
+        html_parts.append(f"<li>作者: {author}</li>")
+
+    if word_count:
+        html_parts.append(f"<li>字数: {word_count}</li>")
+    if serial_status:
+        html_parts.append(f"<li>状态: {serial_status}</li>")
+
+    html_parts.append("</ul>")
+    html_parts.append("</div>")
+    html_parts.append('<p class="new-page-after"><br/></p>')
+
+    if summary:
+        html_parts.append("<h2>简介</h2>")
+        for paragraph in summary.split("\n"):
+            paragraph = paragraph.strip()
+            if paragraph:
+                html_parts.append(f"<p>{paragraph}</p>")
+
+    return "\n".join(html_parts)

novel_downloader/core/savers/epub_utils/volume_intro.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+novel_downloader.core.savers.epub_utils.volume_intro
+
+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]:
+    """
+    Split volume title into two parts for better display.
+
+    :param volume_title: Original volume title string.
+    :return: Tuple of (line1, line2)
+    """
+    if " " in volume_title:
+        parts = volume_title.split(" ")
+    elif "-" in volume_title:
+        parts = volume_title.split("-")
+    else:
+        return "", volume_title
+
+    return parts[0], "".join(parts[1:])
+
+
+def create_volume_intro(volume_title: str, volume_intro_text: str = "") -> str:
+    """
+    Generate the HTML snippet for a volume's introduction section.
+
+    :param volume_title: Title of the volume.
+    :param volume_intro_text: Optional introduction text for the volume.
+    :return: HTML string representing the volume's intro section.
+    """
+    line1, line2 = split_volume_title(volume_title)
+
+    def make_border_img(class_name: str) -> str:
+        return (
+            f'<div class="{class_name}">'
+            f'<img alt="" class="{class_name}" '
+            f'src="../{EPUB_IMAGE_FOLDER}/volume_border.png" />'
+            f"</div>"
+        )
+
+    html_parts = [make_border_img("border1")]
+
+    if line1:
+        html_parts.append(f'<h1 class="volume-title-line1">{line1}</h1>')
+
+    html_parts.append(f'<p class="volume-title-line2">{line2}</p>')
+    html_parts.append(make_border_img("border2"))
+
+    if volume_intro_text:
+        html_parts.append(f'<p class="intro">{volume_intro_text}</p>')
+
+    return "\n".join(html_parts)

novel_downloader/core/savers/qidian_saver.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+novel_downloader.core.savers.qidian_saver
+-----------------------------------------
+
+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
+logic required to structure and export novel content into desired formats.
+"""
+
+from novel_downloader.config.models import SaverConfig
+
+from .common_saver import CommonSaver
+
+
+class QidianSaver(CommonSaver):
+    def __init__(self, config: SaverConfig):
+        super().__init__(config, site="qidian")
+
+
+__all__ = ["QidianSaver"]

novel_downloader/locales/en.json

@@ -0,0 +1,91 @@
+{
+  "cli_help": "Novel Downloader CLI tool.",
+  "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…",
+
+  "settings_help": "Configure downloader settings.",
+  "settings_set_lang_help": "Switch language between Chinese and English.",
+  "settings_set_config_help": "Set and save a custom YAML configuration file.",
+  "settings_update_rules_help": "Update site rules from a TOML/YAML/JSON file.",
+  "settings_init_help": "Initialize default config and rule files in the current directory.",
+  "settings_init_force_help": "Force overwrite if file already exists.",
+  "settings_init_exists": "File already exists: {filename}",
+  "settings_init_confirm_overwrite": "Do you want to overwrite {filename}?",
+  "settings_init_skip": "Skipped: {filename}",
+  "settings_init_copy": "Copied: {filename}",
+  "settings_init_overwrite": "Overwriting existing file: {filename}",
+  "settings_init_error": "Failed to copy {filename}: {err}",
+  "settings_set_lang": "Language switched to {lang}",
+  "settings_set_config": "Configuration file saved from {path}",
+  "settings_set_config_fail": "Failed to save config file: {err}",
+  "settings_update_rules": "Site rules updated from {path}",
+  "settings_update_rules_fail": "Failed to update site rules: {err}",
+  "settings_set_cookies_help": "Set cookies for a specific site.",
+  "settings_set_cookies_prompt_site": "Site identifier (e.g. 'qidian')",
+  "settings_set_cookies_prompt_payload": "Cookie payload (JSON or 'k=v; k2=v2')",
+  "settings_set_cookies_success": "Cookies for site '{site}' have been updated.",
+  "settings_set_cookies_fail": "Failed to set cookies: {err}",
+  "settings_add_hash_help": "Add image hashes manually or from file",
+  "settings_add_hash_path_help": "JSON path mapping image to label",
+  "settings_add_hash_prompt_img": "Image path",
+  "settings_add_hash_prompt_label": "Label for image",
+  "settings_add_hash_prompt_tip": "Enter image path and label. Leave blank or type 'exit' to finish.",
+  "settings_add_hash_path_invalid": "Path does not exist. Try again.",
+  "settings_add_hash_added": "Added image '{img}' under label '{label}'",
+  "settings_add_hash_failed": "Failed to add image: {err}",
+  "settings_add_hash_loaded": "Added images from mapping file: {path}",
+  "settings_add_hash_load_fail": "Failed to load image map: {err}",
+  "settings_add_hash_saved": "Image hash store saved",
+
+  "interactive_help": "Interactive mode for novel selection and preview.",
+  "interactive_option_download": "Download novels",
+  "interactive_browse_help": "Browse available novels interactively.",
+  "interactive_prompt_book_ids": "Enter book IDs to download, separated by spaces",
+  "interactive_preview_help": "Preview chapters before downloading.",
+  "interactive_no_sub": "No subcommand provided. Please select an action:",
+  "interactive_option_browse": "Browse novels",
+  "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_exit": "Exiting.",
+
+  "download_help": "Download full novels by book IDs.",
+  "download_short_help": "Download novels",
+  "download_option_site": "Website source, default is '{default}'.",
+  "download_using_config": "Using config: {path}",
+  "download_site_info": "Site: {site}",
+  "download_no_ids": "No book IDs provided. Exiting.",
+  "download_fail_get_ids": "Failed to get book IDs from config: {err}",
+  "download_only_example": "Only example book IDs found (e.g. '{example}').",
+  "download_edit_config": "Please edit your config and replace them with real book IDs.",
+  "download_downloading": "Downloading book {book_id} from {site}...",
+  "download_prompt_parse": "Parse...",
+
+  "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_models": "Clean downloaded model cache",
+  "clean_hf_cache": "Clear Hugging Face model cache",
+  "clean_hf_cache_done": "Hugging Face cache cleared",
+  "clean_hf_cache_fail": "Failed to clear Hugging Face cache: {err}",
+  "clean_hf_model": "Clear cached model from Hugging Face",
+  "clean_hf_model_done": "Cache for model '{repo}' has been cleared",
+  "clean_hf_model_not_found": "No local cache found for model '{repo}'",
+  "clean_hf_model_fail": "Failed to clear model cache: {err}",
+  "clean_hf_cache_all": "Clear all Hugging Face model and dataset cache",
+  "clean_hf_cache_all_done": "All Hugging Face cache cleared",
+  "clean_hf_cache_all_fail": "Failed to clear Hugging Face cache: {err}",
+  "clean_all": "Clean all settings, cache, and state files",
+  "clean_yes": "Skip confirmation prompt",
+  "clean_confirm": "Are you sure you want to delete all local data? (y/N)",
+  "clean_nothing": "No clean option specified",
+  "clean_deleted": "Deleted",
+  "clean_not_found": "Not found",
+  "clean_cancelled": "Clean operation cancelled"
+}

novel_downloader/locales/zh.json

@@ -0,0 +1,91 @@
+{
+  "cli_help": "小说下载器 CLI 工具",
+  "help_config": "配置文件路径",
+  "help_download": "下载小说",
+  "help_clean": "清理缓存和配置文件",
+  "main_no_command": "未提供命令, 进入交互模式...",
+
+  "settings_help": "配置下载器设置",
+  "settings_set_lang_help": "在中文和英文之间切换语言",
+  "settings_set_config_help": "设置并保存自定义 YAML 配置文件",
+  "settings_update_rules_help": "从 TOML/YAML/JSON 文件更新站点规则",
+  "settings_init_help": "在当前目录初始化默认配置和规则文件",
+  "settings_init_force_help": "如果文件已存在则强制覆盖",
+  "settings_init_exists": "文件已存在: {filename}",
+  "settings_init_confirm_overwrite": "你确定要覆盖 {filename} 吗?",
+  "settings_init_skip": "文件已存在: {filename}, 已跳过",
+  "settings_init_copy": "已复制默认文件: {filename}",
+  "settings_init_overwrite": "已覆盖现有文件: {filename}",
+  "settings_init_error": "复制 {filename} 失败: {err}",
+  "settings_set_lang": "语言已切换为 {lang}",
+  "settings_set_config": "已从 {path} 保存配置文件",
+  "settings_set_config_fail": "保存配置文件失败: {err}",
+  "settings_update_rules": "已从 {path} 更新站点规则",
+  "settings_update_rules_fail": "更新站点规则失败: {err}",
+  "settings_set_cookies_help": "为特定站点设置 Cookie",
+  "settings_set_cookies_prompt_site": "站点标识 (例如 'qidian')",
+  "settings_set_cookies_prompt_payload": "Cookie 内容 (JSON 或 'k=v; k2=v2')",
+  "settings_set_cookies_success": "已更新站点 '{site}' 的 Cookie",
+  "settings_set_cookies_fail": "设置 Cookie 失败: {err}",
+  "settings_add_hash_help": "手动或通过文件添加图像哈希",
+  "settings_add_hash_path_help": "映射图片路径到标签的 JSON 文件路径",
+  "settings_add_hash_prompt_img": "图片路径",
+  "settings_add_hash_prompt_label": "该图片对应的标签",
+  "settings_add_hash_prompt_tip": "请输入图片路径和标签, 输入空行或 'exit' 退出",
+  "settings_add_hash_path_invalid": "路径不存在, 请重试",
+  "settings_add_hash_added": "已添加图片 '{img}', 标签为 '{label}'",
+  "settings_add_hash_failed": "添加图片失败: {err}",
+  "settings_add_hash_loaded": "已从映射文件导入图片: {path}",
+  "settings_add_hash_load_fail": "加载映射文件失败: {err}",
+  "settings_add_hash_saved": "图像哈希库已保存",
+
+  "interactive_help": "小说选择和预览的交互式模式",
+  "interactive_option_download": "下载小说",
+  "interactive_browse_help": "以交互方式浏览可用小说",
+  "interactive_prompt_book_ids": "请输入要下载的书籍 ID, 用空格分隔",
+  "interactive_preview_help": "下载前预览章节",
+  "interactive_no_sub": "未提供子命令请选择一项操作:",
+  "interactive_option_browse": "浏览小说",
+  "interactive_option_preview": "预览章节",
+  "interactive_option_exit": "退出",
+  "interactive_prompt_choice": "请输入你的选择",
+  "interactive_browse_start": "启动交互式浏览器...",
+  "interactive_preview_start": "正在预览章节...",
+  "interactive_exit": "正在退出",
+
+  "download_help": "按书籍 ID 下载完整小说",
+  "download_short_help": "下载小说",
+  "download_option_site": "网站来源, 默认为 '{default}'",
+  "download_using_config": "使用配置: {path}",
+  "download_site_info": "站点: {site}",
+  "download_no_ids": "未提供书籍 ID, 正在退出",
+  "download_fail_get_ids": "从配置获取书籍 ID 失败: {err}",
+  "download_only_example": "只发现示例书籍 ID (例如 '{example}')",
+  "download_edit_config": "请编辑配置并将示例 ID 替换为真实书籍 ID",
+  "download_downloading": "正在从 {site} 下载书籍 {book_id}...",
+  "download_prompt_parse": "结束...",
+
+  "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_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",
+  "clean_hf_cache_fail": "清除 Hugging Face 缓存失败: {err}",
+  "clean_hf_model": "清理 Hugging Face 中模型缓存",
+  "clean_hf_model_done": "已清除模型 '{repo}' 的缓存",
+  "clean_hf_model_not_found": "未发现模型 '{repo}' 的本地缓存",
+  "clean_hf_model_fail": "清理模型缓存失败: {err}",
+  "clean_hf_cache_all": "清理所有 Hugging Face 模型与数据集缓存",
+  "clean_hf_cache_all_done": "已清除所有 Hugging Face 缓存",
+  "clean_hf_cache_all_fail": "清除 Hugging Face 缓存失败: {err}",
+  "clean_all": "清理所有配置, 缓存与状态",
+  "clean_yes": "跳过确认提示",
+  "clean_confirm": "确认要删除所有本地数据? (y/N)",
+  "clean_nothing": "未指定任何要清理的内容",
+  "clean_deleted": "已删除",
+  "clean_not_found": "未找到",
+  "clean_cancelled": "已取消清理操作"
+}