novel-downloader 1.2.2__tar.gz → 1.3.1__tar.gz

{novel_downloader-1.2.2 → novel_downloader-1.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: novel-downloader
-Version: 1.2.2
+Version: 1.3.1
 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)

{novel_downloader-1.2.2 → novel_downloader-1.3.1}/README.md

@@ -22,13 +22,10 @@ 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
@@ -45,7 +42,6 @@ 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)
@@ -55,7 +51,10 @@ 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
@@ -69,8 +68,9 @@ 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)

{novel_downloader-1.2.2 → novel_downloader-1.3.1}/novel_downloader/__init__.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader
 ----------------
@@ -7,7 +6,7 @@ novel_downloader
 Core package for the Novel Downloader project.
 """
 
-__version__ = "1.2.2"
+__version__ = "1.3.1"
 
 __author__ = "Saudade Z"
 __email__ = "saudadez217@gmail.com"

{novel_downloader-1.2.2 → novel_downloader-1.3.1}/novel_downloader/cli/__init__.py

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

{novel_downloader-1.2.2 → novel_downloader-1.3.1}/novel_downloader/cli/clean.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.cli.clean
 -----------------------------
@@ -8,7 +7,6 @@ novel_downloader.cli.clean
 
 import shutil
 from pathlib import Path
-from typing import List, Optional
 
 import click
 
@@ -19,7 +17,6 @@ from novel_downloader.utils.constants import (
     LOGGER_DIR,
     MODEL_CACHE_DIR,
     REC_CHAR_MODEL_REPO,
-    STATE_DIR,
 )
 from novel_downloader.utils.i18n import t
 
@@ -35,7 +32,7 @@ def delete_path(p: Path) -> None:
         click.echo(f"[clean] {t('clean_not_found')}: {p}")
 
 
-def clean_model_repo_cache(repo_id: Optional[str] = None, all: bool = False) -> bool:
+def clean_model_repo_cache(repo_id: str | None = None, all: bool = False) -> bool:
     """
     Delete Hugging Face cache for a specific repo.
     """
@@ -61,7 +58,6 @@ def clean_model_repo_cache(repo_id: Optional[str] = None, all: bool = False) ->
 @click.command(name="clean", help=t("help_clean"))  # type: ignore
 @click.option("--logs", is_flag=True, help=t("clean_logs"))  # type: ignore
 @click.option("--cache", is_flag=True, help=t("clean_cache"))  # type: ignore
-@click.option("--state", is_flag=True, help=t("clean_state"))  # type: ignore
 @click.option("--data", is_flag=True, help=t("clean_data"))  # type: ignore
 @click.option("--config", is_flag=True, help=t("clean_config"))  # type: ignore
 @click.option("--models", is_flag=True, help=t("clean_models"))  # type: ignore
@@ -72,7 +68,6 @@ def clean_model_repo_cache(repo_id: Optional[str] = None, all: bool = False) ->
 def clean_cli(
     logs: bool,
     cache: bool,
-    state: bool,
     data: bool,
     config: bool,
     models: bool,
@@ -81,7 +76,7 @@ def clean_cli(
     all: bool,
     yes: bool,
 ) -> None:
-    targets: List[Path] = []
+    targets: list[Path] = []
 
     if all:
         if not yes:
@@ -92,7 +87,6 @@ def clean_cli(
         targets = [
             LOGGER_DIR,
             JS_SCRIPT_DIR,
-            STATE_DIR,
             DATA_DIR,
             CONFIG_DIR,
             MODEL_CACHE_DIR,
@@ -102,8 +96,6 @@ def clean_cli(
             targets.append(LOGGER_DIR)
         if cache:
             targets.append(JS_SCRIPT_DIR)
-        if state:
-            targets.append(STATE_DIR)
         if data:
             targets.append(DATA_DIR)
         if config:

{novel_downloader-1.2.2 → novel_downloader-1.3.1}/novel_downloader/cli/download.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.cli.download
 -----------------------------
@@ -8,7 +7,7 @@ Download full novels by book IDs
 (supports config files, site switching, and localization prompts).
 """
 
-from typing import List
+import asyncio
 
 import click
 from click import Context
@@ -41,7 +40,7 @@ from novel_downloader.utils.logger import setup_logging
     help=t("download_option_site", default="qidian"),
 )  # type: ignore
 @click.pass_context  # type: ignore
-def download_cli(ctx: Context, book_ids: List[str], site: str) -> None:
+def download_cli(ctx: Context, book_ids: list[str], site: str) -> None:
     """Download full novels by book IDs."""
     config_path = ctx.obj.get("config_path")
 
@@ -69,7 +68,7 @@ def download_cli(ctx: Context, book_ids: List[str], site: str) -> None:
 
     # Filter out placeholder/example IDs
     invalid_ids = {"0000000000"}
-    valid_book_ids = [bid for bid in book_ids if bid not in invalid_ids]
+    valid_book_ids = set(book_ids) - invalid_ids
 
     if not book_ids:
         click.echo(t("download_no_ids"))
@@ -82,21 +81,20 @@ def download_cli(ctx: Context, book_ids: List[str], site: str) -> None:
 
     # Initialize the requester, parser, saver, and downloader components
     if downloader_cfg.mode == "async":
-        import asyncio
-
-        async_requester = get_async_requester(site, requester_cfg)
-        async_parser = get_parser(site, parser_cfg)
-        async_saver = get_saver(site, saver_cfg)
         setup_logging()
-        async_downloader = get_async_downloader(
-            requester=async_requester,
-            parser=async_parser,
-            saver=async_saver,
-            site=site,
-            config=downloader_cfg,
-        )
 
         async def async_download_all() -> None:
+            async_requester = get_async_requester(site, requester_cfg)
+            async_parser = get_parser(site, parser_cfg)
+            async_saver = get_saver(site, saver_cfg)
+            async_downloader = get_async_downloader(
+                requester=async_requester,
+                parser=async_parser,
+                saver=async_saver,
+                site=site,
+                config=downloader_cfg,
+            )
+
             prepare = getattr(async_downloader, "prepare", None)
             if prepare and asyncio.iscoroutinefunction(prepare):
                 await prepare()
@@ -105,9 +103,7 @@ def download_cli(ctx: Context, book_ids: List[str], site: str) -> None:
                 click.echo(t("download_downloading", book_id=book_id, site=site))
                 await async_downloader.download_one(book_id)
 
-            if requester_cfg.auto_close:
-                input(t("download_prompt_parse"))
-                await async_requester.shutdown()
+            await async_requester.close()
 
         asyncio.run(async_download_all())
     else:
@@ -127,8 +123,6 @@ def download_cli(ctx: Context, book_ids: List[str], site: str) -> None:
             click.echo(t("download_downloading", book_id=book_id, site=site))
             sync_downloader.download_one(book_id)
 
-        if requester_cfg.auto_close:
-            input(t("download_prompt_parse"))
-            sync_requester.shutdown()
+        sync_requester.close()
 
     return

{novel_downloader-1.2.2 → novel_downloader-1.3.1}/novel_downloader/cli/interactive.py

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

{novel_downloader-1.2.2 → novel_downloader-1.3.1}/novel_downloader/cli/main.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.cli.main
 --------------------------
@@ -7,7 +6,6 @@ novel_downloader.cli.main
 Unified CLI entry point. Parses arguments and delegates to parser or interactive.
 """
 
-from typing import Optional
 
 import click
 from click import Context
@@ -24,7 +22,7 @@ from novel_downloader.utils.i18n import t
     help=t("help_config"),
 )  # type: ignore
 @click.pass_context  # type: ignore
-def cli_main(ctx: Context, config: Optional[str]) -> None:
+def cli_main(ctx: Context, config: str | None) -> None:
     """Novel Downloader CLI."""
     ctx.ensure_object(dict)
     ctx.obj["config_path"] = config

{novel_downloader-1.2.2 → novel_downloader-1.3.1}/novel_downloader/cli/settings.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.cli.settings
 -----------------------------
@@ -10,7 +9,6 @@ Commands to configure novel downloader settings.
 import shutil
 from importlib.resources import as_file
 from pathlib import Path
-from typing import Optional
 
 import click
 from click import Context
@@ -61,7 +59,7 @@ def init_settings(force: bool) -> None:
         except Exception as e:
             raise click.ClickException(
                 t("settings_init_error", filename=resource.name, err=e)
-            )
+            ) from e
 
 
 @settings_cli.command(name="set-lang", help=t("settings_set_lang_help"))  # type: ignore
@@ -81,7 +79,7 @@ def set_config(path: str) -> None:
         save_config_file(path)
         click.echo(t("settings_set_config", path=path))
     except Exception as e:
-        raise click.ClickException(t("settings_set_config_fail", err=e))
+        raise click.ClickException(t("settings_set_config_fail", err=e)) from e
 
 
 @settings_cli.command(name="update-rules", help=t("settings_update_rules_help"))  # type: ignore
@@ -92,7 +90,7 @@ def update_rules(path: str) -> None:
         save_rules_as_json(path)
         click.echo(t("settings_update_rules", path=path))
     except Exception as e:
-        raise click.ClickException(t("settings_update_rules_fail", err=e))
+        raise click.ClickException(t("settings_update_rules_fail", err=e)) from e
 
 
 @settings_cli.command(
@@ -120,7 +118,7 @@ def set_cookies(ctx: Context, site: str, cookies: str) -> None:
         state_mgr.set_cookies(site, cookies)
         click.echo(t("settings_set_cookies_success", site=site))
     except Exception as e:
-        raise click.ClickException(t("settings_set_cookies_fail", err=e))
+        raise click.ClickException(t("settings_set_cookies_fail", err=e)) from e
 
 
 @settings_cli.command(name="add-hash", help=t("settings_add_hash_help"))  # type: ignore
@@ -129,7 +127,7 @@ def set_cookies(ctx: Context, site: str, cookies: str) -> None:
     type=click.Path(exists=True, dir_okay=False),
     help=t("settings_add_hash_path_help"),
 )  # type: ignore
-def add_image_hashes(path: Optional[str]) -> None:
+def add_image_hashes(path: str | None) -> None:
     """
     Add image hashes to internal store for matching.
     Can be run in interactive mode (no --path), or with a JSON file.
@@ -142,7 +140,9 @@ def add_image_hashes(path: Optional[str]) -> None:
             img_hash_store.save()
             click.echo(t("settings_add_hash_loaded", path=path))
         except Exception as e:
-            raise click.ClickException(t("settings_add_hash_load_fail", err=str(e)))
+            raise click.ClickException(
+                t("settings_add_hash_load_fail", err=str(e))
+            ) from e
     else:
         click.echo(t("settings_add_hash_prompt_tip"))
         while True:

{novel_downloader-1.2.2 → novel_downloader-1.3.1}/novel_downloader/config/__init__.py

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

{novel_downloader-1.2.2 → novel_downloader-1.3.1}/novel_downloader/config/adapter.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
 novel_downloader.config.adapter
 -------------------------------
@@ -15,7 +14,9 @@ Supported mappings:
 - sites[site]       -> book_ids list
 """
 
-from typing import Any, Dict, List
+from typing import Any
+
+from novel_downloader.utils.constants import SUPPORTED_SITES
 
 from .models import (
     DownloaderConfig,
@@ -31,7 +32,7 @@ class ConfigAdapter:
     Adapter to map a raw config dict + site name into structured dataclass configs.
     """
 
-    def __init__(self, config: Dict[str, Any], site: str):
+    def __init__(self, config: dict[str, Any], site: str):
         """
         :param config: 完整加载的配置 dict
         :param site:   当前站点名称 (e.g. "qidian")
@@ -40,33 +41,33 @@ class ConfigAdapter:
         self._site = site
 
         site_rules = load_site_rules()  # -> Dict[str, SiteRules]
-        self._supported_sites = set(site_rules.keys())
+        self._supported_sites = set(site_rules.keys()) | SUPPORTED_SITES
 
-    def set_site(self, site: str) -> None:
-        """
-        切换当前适配的站点
-        """
-        self._site = site
+    @property
+    def site(self) -> str:
+        return self._site
+
+    @site.setter
+    def site(self, value: str) -> None:
+        self._site = value
 
-    def _get_site_cfg(self) -> Dict[str, Any]:
+    def _get_site_cfg(self, site: str | None = None) -> dict[str, Any]:
         """
-        统一获取站点配置:
+        获取指定站点的配置 (默认为当前适配站点)
 
-        1. 先尝试从 self._config["sites"][self._site] 取配置
-        2. 如果没有配置, 且 self._site 在 self._supported_sites 中, 则取 sites["common"]
+        1. 如果有 site-specific 配置, 优先返回它
+        2. 否则, 如果该站点在支持站点中, 尝试返回 'common' 配置
         3. 否则返回空 dict
         """
+        site = site or self._site
         sites_cfg = self._config.get("sites", {}) or {}
 
-        # 1. site-specific config
-        if self._site in sites_cfg:
-            return sites_cfg[self._site] or {}
+        if site in sites_cfg:
+            return sites_cfg[site] or {}
 
-        # 2. fallback to "common" only if site is supported
-        if self._site in self._supported_sites:
+        if site in self._supported_sites:
             return sites_cfg.get("common", {}) or {}
 
-        # 3. completely unsupported site
         return {}
 
     def get_requester_config(self) -> RequesterConfig:
@@ -77,10 +78,11 @@ class ConfigAdapter:
         req = self._config.get("requests", {})
         site_cfg = self._get_site_cfg()
         return RequesterConfig(
-            wait_time=req.get("wait_time", 5),
             retry_times=req.get("retry_times", 3),
-            retry_interval=req.get("retry_interval", 5),
-            timeout=req.get("timeout", 30),
+            backoff_factor=req.get("backoff_factor", 2.0),
+            timeout=req.get("timeout", 30.0),
+            max_connections=req.get("max_connections", 10),
+            max_rps=req.get("max_rps", None),
             headless=req.get("headless", True),
             user_data_folder=req.get("user_data_folder", "./user_data"),
             profile_name=req.get("profile_name", "Profile_1"),
@@ -88,7 +90,6 @@ class ConfigAdapter:
             disable_images=req.get("disable_images", True),
             mute_audio=req.get("mute_audio", True),
             mode=site_cfg.get("mode", "session"),
-            max_rps=site_cfg.get("max_rps", None),
         )
 
     def get_downloader_config(self) -> DownloaderConfig:
@@ -100,9 +101,9 @@ class ConfigAdapter:
         debug = gen.get("debug", {})
         site_cfg = self._get_site_cfg()
         return DownloaderConfig(
-            request_interval=gen.get("request_interval", 5),
+            request_interval=gen.get("request_interval", 5.0),
             raw_data_dir=gen.get("raw_data_dir", "./raw_data"),
-            cache_dir=gen.get("cache_dir", "./cache"),
+            cache_dir=gen.get("cache_dir", "./novel_cache"),
             download_workers=gen.get("download_workers", 4),
             parser_workers=gen.get("parser_workers", 4),
             use_process_pool=gen.get("use_process_pool", True),
@@ -110,6 +111,8 @@ class ConfigAdapter:
             login_required=site_cfg.get("login_required", False),
             save_html=debug.get("save_html", False),
             mode=site_cfg.get("mode", "session"),
+            storage_backend=gen.get("storage_backend", "json"),
+            storage_batch_size=gen.get("storage_batch_size", 1),
         )
 
     def get_parser_config(self) -> ParserConfig:
@@ -121,7 +124,7 @@ class ConfigAdapter:
         font_ocr = gen.get("font_ocr", {})
         site_cfg = self._get_site_cfg()
         return ParserConfig(
-            cache_dir=gen.get("cache_dir", "./cache"),
+            cache_dir=gen.get("cache_dir", "./novel_cache"),
             decode_font=font_ocr.get("decode_font", False),
             use_freq=font_ocr.get("use_freq", False),
             use_ocr=font_ocr.get("use_ocr", True),
@@ -149,6 +152,7 @@ class ConfigAdapter:
         return SaverConfig(
             raw_data_dir=gen.get("raw_data_dir", "./raw_data"),
             output_dir=gen.get("output_dir", "./downloads"),
+            storage_backend=gen.get("storage_backend", "json"),
             clean_text=out.get("clean_text", True),
             make_txt=fmt.get("make_txt", True),
             make_epub=fmt.get("make_epub", False),
@@ -158,9 +162,10 @@ class ConfigAdapter:
             filename_template=naming.get("filename_template", "{title}_{author}"),
             include_cover=epub_opts.get("include_cover", True),
             include_toc=epub_opts.get("include_toc", False),
+            include_picture=epub_opts.get("include_picture", False),
         )
 
-    def get_book_ids(self) -> List[str]:
+    def get_book_ids(self) -> list[str]:
         """
         从 config["sites"][site]["book_ids"] 中提取目标书籍列表
         """