novel-downloader 1.4.5__py3-none-any.whl → 2.0.0__py3-none-any.whl

novel_downloader/models/config.py

@@ -5,27 +5,11 @@ novel_downloader.models.config
 
 Defines structured configuration models using dataclasses for each
 major component in the novel_downloader pipeline.
-
-Each config section corresponds to a specific stage of the pipeline:
-- RequesterConfig: network settings for requests and DrissionPage
-- DownloaderConfig: chapter download behavior and local raw data paths
-- ParserConfig: font decoding, cache handling, and debug options
-- SaverConfig: output formatting, export formats, and filename templates
-
-These models are used to map loaded YAML or JSON config data into
-strongly typed Python objects for safer and cleaner access.
 """
 
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from typing import NotRequired, TypedDict
 
-from .types import (
-    BrowserType,
-    ModeType,
-    SplitMode,
-    StorageBackend,
-)
-
 
 @dataclass
 class FetcherConfig:
@@ -33,16 +17,12 @@ class FetcherConfig:
     retry_times: int = 3
     backoff_factor: float = 2.0
     timeout: float = 30.0
-    headless: bool = False
-    disable_images: bool = False
-    mode: ModeType = "session"
     max_connections: int = 10
-    max_rps: float | None = None  # Maximum requests per second
-    proxy: str | None = None
+    max_rps: float = 1000.0
     user_agent: str | None = None
     headers: dict[str, str] | None = None
-    browser_type: BrowserType = "chromium"
     verify_ssl: bool = True
+    locale_style: str = "simplified"
 
 
 @dataclass
@@ -52,17 +32,11 @@ class DownloaderConfig:
     backoff_factor: float = 2.0
     raw_data_dir: str = "./raw_data"
     cache_dir: str = "./novel_cache"
-    download_workers: int = 4
-    parser_workers: int = 4
+    workers: int = 4
     skip_existing: bool = True
     login_required: bool = False
     save_html: bool = False
-    mode: ModeType = "session"
-    storage_backend: StorageBackend = "json"
     storage_batch_size: int = 1
-    username: str = ""
-    password: str = ""
-    cookies: str = ""
 
 
 @dataclass
@@ -70,17 +44,17 @@ class ParserConfig:
     cache_dir: str = "./novel_cache"
     use_truncation: bool = True
     decode_font: bool = False
-    use_freq: bool = False
-    use_ocr: bool = True
-    use_vec: bool = False
-    ocr_version: str = "v1.0"
     batch_size: int = 32
-    gpu_mem: int = 500
-    gpu_id: int | None = None
-    ocr_weight: float = 0.6
-    vec_weight: float = 0.4
     save_font_debug: bool = False
-    mode: ModeType = "session"
+
+
+@dataclass
+class TextCleanerConfig:
+    remove_invisible: bool = True
+    title_remove_patterns: list[str] = field(default_factory=list)
+    title_replacements: dict[str, str] = field(default_factory=dict)
+    content_remove_patterns: list[str] = field(default_factory=list)
+    content_replacements: dict[str, str] = field(default_factory=dict)
 
 
 @dataclass
@@ -88,7 +62,6 @@ class ExporterConfig:
     cache_dir: str = "./novel_cache"
     raw_data_dir: str = "./raw_data"
     output_dir: str = "./downloads"
-    storage_backend: StorageBackend = "json"
     clean_text: bool = True
     make_txt: bool = True
     make_epub: bool = False
@@ -97,9 +70,9 @@ class ExporterConfig:
     append_timestamp: bool = True
     filename_template: str = "{title}_{author}"
     include_cover: bool = True
-    include_toc: bool = False
-    include_picture: bool = False
-    split_mode: SplitMode = "book"
+    include_picture: bool = True
+    split_mode: str = "book"
+    cleaner_cfg: TextCleanerConfig = field(default_factory=TextCleanerConfig)
 
 
 class BookConfig(TypedDict):

novel_downloader/models/login.py

@@ -13,7 +13,7 @@ from typing import Literal
 class LoginField:
     name: str
     label: str
-    type: Literal["text", "password", "cookie", "manual_login"]
+    type: Literal["text", "password", "cookie"]
     required: bool
     default: str = ""
     placeholder: str = ""

novel_downloader/models/search.py

@@ -0,0 +1,21 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.models.search
+------------------------------
+
+"""
+
+from typing import TypedDict
+
+
+class SearchResult(TypedDict, total=True):
+    site: str
+    book_id: str
+    book_url: str
+    cover_url: str
+    title: str
+    author: str
+    latest_chapter: str
+    update_date: str
+    word_count: str
+    priority: int

novel_downloader/resources/config/settings.toml

@@ -1,31 +1,18 @@
-# 网络请求层设置
-[requests]
+# 全局通用设置
+[general]
 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
-max_rps = 1.0                      # 最大请求速率 (requests per second), 如不设置则请注释掉或删掉本行
-# proxy = "http://127.0.0.1:1080"  # 如需使用代理, 填写完整的代理地址
-# user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36"
-# headers = {}
-browser_type = "chromium"
-verify_ssl = true
-
-# 浏览器设置
-headless = false                   # 是否以无头模式启动浏览器
-disable_images = false             # 是否禁用图片加载 (加速)
-
-# 全局通用设置
-[general]
+max_rps = 1.0                      # 最大请求速率 (requests per second), 如不设置则请设置一个较大的数或负数
 request_interval = 2.0             # 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 = 2               # 并发下载线程数
-parser_workers = 2                 # 并发解析线程数
+workers = 2                        # 工作协程数
 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
+storage_batch_size = 1             # SQLite 批量提交的章节数量
+locale_style = "simplified"        # simplified / traditional
 
 [general.debug]
 save_html = false                  # 是否将抓取到的原始 HTML 保留到磁盘
@@ -33,16 +20,8 @@ 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
+save_font_debug = false            # 是否保存字体解码调试数据
 
 # 各站点的特定配置
 [sites.qidian]  # 起点中文网
@@ -50,76 +29,33 @@ book_ids = [
   "0000000000",
   "0000000000"
 ]
-mode = "session"                   # browser / session
 login_required = true              # 是否需要登录才能访问
 use_truncation = true              # 是否基于章节长度截断以避免重复内容
 
-[sites.biquge]  # 笔趣阁
-book_ids = [
-  "0000000000",
-  "0000000000"
-]
-mode = "session"                   # browser / session
-login_required = false
-
-[sites.qianbi]  # 铅笔小说
-book_ids = [
-  "0000000000",
-  "0000000000"
-]
-mode = "session"                   # browser / session
-login_required = false
-
-[sites.sfacg]  # SF轻小说
-book_ids = [
-  "0000000000",
-  "0000000000"
-]
-mode = "session"                   # browser / session
-login_required = false
-
 [sites.esjzone]  # ESJ Zone
 book_ids = [
   "0000000000",
   "0000000000"
 ]
-mode = "session"                   # browser / session
 login_required = true
 # username = "youremail@domain.com"  # 登录邮箱
 # password = "yourpassword"          # 登录密码
 
-[sites.yamibo]  # 百合会
-book_ids = [
-  "0000000000",
-  "0000000000"
-]
-mode = "session"                   # browser / session
-login_required = false
-# username = "yourusername"          # 登录账户
-# password = "yourpassword"          # 登录密码
-
 [sites.linovelib]  # 哔哩轻小说
 book_ids = [
   "0000000000",
   "0000000000"
 ]
-mode = "session"
 split_mode = "book"                # 导出方式: book / volume
 login_required = false
 
 [sites.common]
-mode = "session"                   # browser / session
 login_required = false
 
 # 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)
+make_epub = true                   # 是否生成 EPUB
 
 [output.naming]
 append_timestamp = false           # 在文件名中追加时间戳
@@ -127,5 +63,34 @@ 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)
+include_picture = true             # 是否下载章节图片 (体积较大)
+
+[cleaner]
+clean_text = false                 # 是否对章节文本做清理
+remove_invisible = true
+
+[cleaner.title]
+remove_patterns = [
+  '【[^】]*?】',
+  '[(（][^()（）]*?求票[^()（）]*?[)）]',
+]
+
+[cleaner.title.replace]
+'：' = ':'
+
+[cleaner.title.external]
+enabled = false
+remove_patterns = "path/to/title-remove.json"
+replace         = "path/to/title-replace.json"
+
+[cleaner.content]
+remove_patterns = []
+
+[cleaner.content.replace]
+'li子' = '例子'
+'pinbi词' = '屏蔽词'
+
+[cleaner.content.external]
+enabled = false
+remove_patterns = "path/to/content-remove.json"
+replace         = "path/to/content-replace.json"

novel_downloader/resources/css_styles/intro.css

@@ -0,0 +1,83 @@
+body {
+  font-family: serif;
+  line-height: 1.5;
+  height: 95%;
+  margin: 2em;
+}
+
+h1 {
+  font-size: 2em;
+  text-align: center;
+  margin-bottom: 1em;
+}
+
+p.new-page-after {
+  page-break-after: always;
+  margin: 0;
+  padding: 0;
+}
+
+.intro-info {
+  list-style: none;
+  padding: 0;
+  margin: 0 0 2em;
+}
+.intro-info li {
+  margin: 0.5em 0;
+  font-size: 1.1em;
+}
+
+.intro-summary {
+  margin-top: 1em;
+  font-size: 1em;
+}
+
+.vol-header {
+  display: flex;
+  flex-direction: column;
+  justify-content: center;
+  align-items: center;
+  margin: 0;
+}
+
+.vol-border {
+  width: 100%;
+  text-align: center;
+  margin: 0 auto 0 auto;
+  text-indent: 0em;
+}
+.vol-border.flip {
+  transform: rotate(180deg);
+  -ms-transform: rotate(180deg);
+  -moz-transform: rotate(180deg);
+  -webkit-transform: rotate(180deg);
+  -o-transform: rotate(180deg);
+}
+
+.vol-title-main,
+.vol-title-sub {
+  font-weight: bold;
+  text-align: center;
+  text-indent: 0em;
+  color: #6e471c;
+  margin: 0.25em 0;
+  display: block;
+  color: #6e471c;
+  text-shadow: 1px 1px 2px rgba(255,255,255,0.8);
+}
+.vol-title-main {
+  font-size: 1.25rem;
+}
+.vol-title-sub {
+  font-size: 1rem;
+}
+
+.volume-intro-text {
+  margin: 1em 0;
+  padding: 0 1em;
+  text-align: justify;
+}
+.volume-intro-text p {
+  margin: 0.5em 0;
+  line-height: 1.6;
+}

novel_downloader/resources/css_styles/main.css

@@ -1,104 +1,45 @@
-html, body {
-    height: 95%;
-    padding: 0.5em;
+body {
+  font-family: serif;
+  height: 95%;
+  line-height: 1.6;
+  margin: 1em;
 }
 
-.images img {
-    width:100%; /*自适应*/
-}
-.color .images {
-    margin:0 0 1.5em;
-}
-.article .images {
-    margin:1.0em 0;
-    border:1px solid #000
-}
-
-.new-page-after {
-    page-break-after:always;
-}
-
-.cover {
-    width:100%;
-    padding:0px;
-}
-.center {
-    text-align: center;
-    margin-left: 0%;
-    margin-right: 0%;
-}
-.left {
-    text-align: center;
-    margin-left: 0%;
-    margin-right: 0%;
-}
-.right {
-    text-align: right;
-    margin-left: 0%;
-    margin-right: 0%;
+h2 {
+  font-size: 1.5em;
+  margin: 1.5em 0 0.75em;
+  text-align: center;
 }
 
-hr {
-    margin: 0;
-    border-style: dotted;
-    border-width: 1px 0 0 0;
-    margin-top: 0.5em;
-    margin-bottom: 0.5em;
-}
-
-h1 {
-    text-indent: 0;
-    duokan-text-indent: 0;
-    line-height: 110%;
-    text-align: center;
-    font-size: 1.2em;
-    margin-top: 0.4em;
-    margin-bottom: 0.4em;
-}
-
-h2, h3, h4, h5, h6 {
-    text-indent: 0;
-    duokan-text-indent: 0;
-    line-height: 110%;
-    font-size: 1.1em;
-    margin-top: 0.4em;
-    margin-bottom: 0.4em;
+p {
+  text-indent: 2em;
+  margin: 0.5em 0;
 }
 
-p {
-    text-align: justify;  /* 让文本两端对齐 */
-    text-indent: 2em;
-    duokan-text-indent: 2em;
-    line-height: 100%;
-    margin-top: 0.4em;
-    margin-bottom: 0.4em;
+p.new-page-after {
+  margin: 0;
+  padding: 0;
+  page-break-after: always;
 }
 
-div.list {
-    text-align: left;
-    font-size: 0.85em;
-    line-height: 130%;
+.duokan-image-single {
+  text-align: center;
+  margin: 1em 0;
 }
 
-span {
-    text-indent: 0;
-    duokan-text-indent: 0;
-    text-align: left;
-    font-size: 1em;
+.duokan-image-single img {
+  max-width: 100%;
+  height: auto;
+  display: inline-block;
 }
 
-ol {
-    text-align: left;
-    margin-top: 1.2em;
-    margin-bottom: 1.2em;
-    margin-left: 0;
-    list-style-type: none;
+hr {
+  border: none;
+  border-top: 1px solid #ccc;
+  margin: 1.5em 0;
 }
 
-li {
-    text-align: left;
-    margin-top: 0.4em;
-    margin-bottom: 0.4em;
-    margin-left: 0;
-    list-style-type: none;
+h3 {
+  font-size: 1.2em;
+  margin: 1em 0 0.5em;
 }