novel-downloader 1.3.1__py3-none-any.whl → 1.3.3__py3-none-any.whl

novel_downloader/core/savers/qianbi.py

@@ -0,0 +1,25 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.savers.qianbi
+-----------------------------------
+
+"""
+
+from novel_downloader.config.models import SaverConfig
+
+from .common import CommonSaver
+
+
+class QianbiSaver(CommonSaver):
+    def __init__(
+        self,
+        config: SaverConfig,
+    ):
+        super().__init__(
+            config,
+            site="qianbi",
+            chap_folders=["chapters"],
+        )
+
+
+__all__ = ["QianbiSaver"]

novel_downloader/core/savers/sfacg.py

@@ -0,0 +1,25 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.savers.sfacg
+----------------------------------
+
+"""
+
+from novel_downloader.config.models import SaverConfig
+
+from .common import CommonSaver
+
+
+class SfacgSaver(CommonSaver):
+    def __init__(
+        self,
+        config: SaverConfig,
+    ):
+        super().__init__(
+            config,
+            site="sfacg",
+            chap_folders=["chapters"],
+        )
+
+
+__all__ = ["SfacgSaver"]

novel_downloader/core/savers/yamibo.py

@@ -0,0 +1,25 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.savers.yamibo
+-----------------------------------
+
+"""
+
+from novel_downloader.config.models import SaverConfig
+
+from .common import CommonSaver
+
+
+class YamiboSaver(CommonSaver):
+    def __init__(
+        self,
+        config: SaverConfig,
+    ):
+        super().__init__(
+            config,
+            site="yamibo",
+            chap_folders=["chapters"],
+        )
+
+
+__all__ = ["YamiboSaver"]

novel_downloader/locales/en.json

@@ -72,6 +72,7 @@
   "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.",
+  "session_login_failed": "Login to {site} failed. Please check your credentials or try again later.",
 
   "clean_logs": "Clean log directory",
   "clean_cache": "Clean scripts and browser cache",

novel_downloader/locales/zh.json

@@ -72,6 +72,7 @@
   "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",
+  "session_login_failed": "登录 {site} 失败, 请检查账号或稍后再试",
 
   "clean_logs": "清理日志目录",
   "clean_cache": "清理脚本和浏览器缓存",

novel_downloader/resources/config/settings.toml

@@ -45,7 +45,7 @@ ocr_weight = 0.5
 vec_weight = 0.5
 
 # 各站点的特定配置
-[sites.qidian]
+[sites.qidian]  # 起点中文网
 # 小说 ID 列表
 # 例如: 访问 https://www.qidian.com/book/1010868264/
 # 该小说的 ID 就是 1010868264
@@ -56,17 +56,53 @@ book_ids = [
 mode = "browser"                   # browser / session
 login_required = true              # 是否需要登录才能访问
 
-[sites.biquge]
+[sites.biquge]  # 笔趣阁
 book_ids = [
   "0000000000",
   "0000000000"
 ]
 mode = "session"                   # async / session
-login_required = false             # 是否需要登录才能访问
+login_required = false
+
+[sites.qianbi]  # 铅笔小说
+book_ids = [
+  "0000000000",
+  "0000000000"
+]
+mode = "session"                   # async / session
+login_required = false
+
+[sites.sfacg]  # SF轻小说
+book_ids = [
+  "0000000000",
+  "0000000000"
+]
+mode = "session"                   # async / session
+login_required = false
+
+[sites.esjzone]  # ESJ Zone
+book_ids = [
+  "0000000000",
+  "0000000000"
+]
+mode = "session"                   # async / 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"                   # async / session
+login_required = false
+username = "yourusername"          # 登录账户
+password = "yourpassword"          # 登录密码
 
 [sites.common]
 mode = "session"                   # async / session
-login_required = false             # 是否需要登录才能访问
+login_required = false
 
 # 输出文件格式及相关选项
 [output]

novel_downloader/utils/constants.py

@@ -116,6 +116,10 @@ BLACKLIST_PATH = files("novel_downloader.resources.text").joinpath("blacklist.tx
 EPUB_IMAGE_FOLDER = "Images"
 EPUB_TEXT_FOLDER = "Text"
 
+EPUB_IMAGE_WRAPPER = (
+    '<div class="duokan-image-single illus"><img src="../Images/{filename}" /></div>'
+)
+
 EPUB_OPTIONS = {
     # guide 是 EPUB 2 的一个部分, 包含封面, 目录, 索引等重要导航信息
     "epub2_guide": True,

novel_downloader/utils/file_utils/io.py

@@ -103,7 +103,7 @@ def _write_file(
             tmp.write(content_to_write)
             tmp_path = Path(tmp.name)
         tmp_path.replace(path)
-        logger.info("[file] '%s' written successfully", path)
+        logger.debug("[file] '%s' written successfully", path)
         return True
     except Exception as exc:
         logger.warning("[file] Error writing %r: %s", path, exc)

novel_downloader/utils/network.py

@@ -16,7 +16,7 @@ from urllib.parse import unquote, urlparse
 import requests
 
 from .constants import DEFAULT_HEADERS, DEFAULT_IMAGE_SUFFIX
-from .file_utils.io import _get_non_conflicting_path, _write_file, read_binary_file
+from .file_utils.io import _get_non_conflicting_path, _write_file
 
 logger = logging.getLogger(__name__)
 
@@ -84,28 +84,28 @@ def image_url_to_filename(url: str) -> str:
     return filename
 
 
-def download_image_as_bytes(
+def download_image(
     url: str,
     target_folder: str | Path | None = None,
+    target_name: str | None = None,
     *,
     timeout: int = 10,
     retries: int = 3,
     backoff: float = 0.5,
     on_exist: Literal["overwrite", "skip", "rename"] = "overwrite",
-) -> bytes | None:
+) -> Path | None:
     """
-    Download an image from a given URL and return its content as bytes.
-
-    If on_exist='skip' and the file already exists, it will be read from disk
-    instead of being downloaded again.
+    Download an image from `url` and save it to `target_folder`, returning the Path.
+    Can override the filename via `target_name`.
 
     :param url: Image URL. Can start with 'http', '//', or without protocol.
-    :param target_folder: Optional folder to save the image (str or Path).
+    :param target_folder: Directory to save into (defaults to cwd).
+    :param target_name: Optional filename (with or without extension).
     :param timeout: Request timeout in seconds.
     :param retries: Number of retry attempts.
     :param backoff: Base delay between retries (exponential backoff).
     :param on_exist: What to do if file exists: 'overwrite', 'skip', or 'rename'.
-    :return: Image content as bytes, or None if failed.
+    :return: Path to the saved image, or `None` on any failure.
     """
     # Normalize URL
     if url.startswith("//"):
@@ -113,21 +113,28 @@ def download_image_as_bytes(
     elif not url.startswith("http"):
         url = "https://" + url
 
-    save_path = None
-    if target_folder:
-        target_folder = Path(target_folder)
-        filename = image_url_to_filename(url)
-        save_path = target_folder / filename
-
-        if on_exist == "skip" and save_path.exists():
-            logger.info(
-                "[image] '%s' exists, skipping download and reading from disk.",
-                save_path,
-            )
-            return read_binary_file(save_path)
+    folder = Path(target_folder) if target_folder else Path.cwd()
+    folder.mkdir(parents=True, exist_ok=True)
+
+    if target_name:
+        name = target_name
+        if not Path(name).suffix:
+            # infer ext from URL-derived name
+            name += Path(image_url_to_filename(url)).suffix
+    else:
+        name = image_url_to_filename(url)
+    save_path = folder / name
+
+    # Handle existing file
+    if save_path.exists():
+        if on_exist == "skip":
+            logger.debug("Skipping download; file exists: %s", save_path)
+            return save_path
+        if on_exist == "rename":
+            save_path = _get_non_conflicting_path(save_path)
 
     # Proceed with download
-    response = http_get_with_retry(
+    resp = http_get_with_retry(
         url,
         retries=retries,
         timeout=timeout,
@@ -136,19 +143,25 @@ def download_image_as_bytes(
         stream=False,
     )
 
-    if response and response.ok:
-        content = response.content
-
-        if save_path:
-            _write_file(
-                content=content,
-                filepath=save_path,
-                mode="wb",
-                on_exist=on_exist,
-            )
-
-        return content
+    if not (resp and resp.ok):
+        logger.warning(
+            "Failed to download %s (status=%s)",
+            url,
+            getattr(resp, "status_code", None),
+        )
+        return None
 
+    # Write to disk
+    try:
+        _write_file(
+            content=resp.content,
+            filepath=save_path,
+            mode="wb",
+            on_exist=on_exist,
+        )
+        return save_path
+    except Exception:
+        logger.exception("Error saving image to %s", save_path)
     return None
 
 
@@ -191,7 +204,7 @@ def download_font_file(
 
     # If skip and file exists -> return immediately
     if on_exist == "skip" and font_path.exists():
-        logger.info("[font] File exists, skipping download: %s", font_path)
+        logger.debug("[font] File exists, skipping download: %s", font_path)
         return font_path
 
     # Retry download with exponential backoff
@@ -214,7 +227,7 @@ def download_font_file(
                     if chunk:
                         f.write(chunk)
 
-            logger.info("[font] Font saved to: %s", font_path)
+            logger.debug("[font] Font saved to: %s", font_path)
             return font_path
 
         except Exception as e:
@@ -258,7 +271,7 @@ def download_js_file(
     save_path = target_folder / filename
 
     if on_exist == "skip" and save_path.exists():
-        logger.info("[js] File exists, skipping download: %s", save_path)
+        logger.debug("[js] File exists, skipping download: %s", save_path)
         return save_path
 
     response = http_get_with_retry(
@@ -278,7 +291,7 @@ def download_js_file(
 
         try:
             _write_file(content=content, filepath=save_path, mode="wb")
-            logger.info("[js] JS file saved to: %s", save_path)
+            logger.debug("[js] JS file saved to: %s", save_path)
             return save_path
         except Exception as e:
             logger.error("[js] Error writing JS to disk: %s", e)

novel_downloader/utils/time_utils/__init__.py

@@ -13,9 +13,10 @@ Includes:
 """
 
 from .datetime_utils import calculate_time_difference
-from .sleep_utils import sleep_with_random_delay
+from .sleep_utils import async_sleep_with_random_delay, sleep_with_random_delay
 
 __all__ = [
     "calculate_time_difference",
+    "async_sleep_with_random_delay",
     "sleep_with_random_delay",
 ]

novel_downloader/utils/time_utils/datetime_utils.py

@@ -24,6 +24,8 @@ _DATETIME_FORMATS = [
     (r"\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}[+-]\d{2}:\d{2}", "%Y-%m-%dT%H:%M:%S%z"),
     # 完整年月日+时分秒 空格格式
     (r"\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}", "%Y-%m-%d %H:%M:%S"),
+    (r"\d{4}-\d{2}-\d{2} \d{2}:\d{2}", "%Y-%m-%d %H:%M"),
+    (r"\d{2}-\d{2}-\d{2} \d{2}:\d{2}", "%y-%m-%d %H:%M"),
     # 年月日 (无时间)
     (r"\d{4}-\d{2}-\d{2}", "%Y-%m-%d"),
     # Slashes 分隔
@@ -136,7 +138,7 @@ def calculate_time_difference(
 
     except Exception as e:
         logger.warning("[time] Failed to calculate time difference: %s", e)
-        return 0, 0, 0, 0
+        return 999, 23, 59, 59
 
 
 __all__ = [

novel_downloader/utils/time_utils/sleep_utils.py

@@ -10,6 +10,7 @@ Includes:
   optionally capped with a max_sleep limit.
 """
 
+import asyncio
 import logging
 import random
 import time
@@ -55,9 +56,50 @@ def sleep_with_random_delay(
     if max_sleep is not None:
         duration = min(duration, max_sleep)
 
-    logger.info("[time] Sleeping for %.2f seconds", duration)
+    logger.debug("[time] Sleeping for %.2f seconds", duration)
     time.sleep(duration)
     return
 
 
-__all__ = ["sleep_with_random_delay"]
+async def async_sleep_with_random_delay(
+    base: float,
+    add_spread: float = 0.0,
+    mul_spread: float = 1.0,
+    *,
+    max_sleep: float | None = None,
+) -> None:
+    """
+    Async sleep for a random duration by combining multiplicative and additive jitter.
+
+    The total sleep time is computed as:
+
+        duration = base * uniform(1.0, mul_spread) + uniform(0, add_spread)
+
+    If `max_sleep` is provided, the duration will be capped at that value.
+
+    :param base: Base sleep time in seconds. Must be >= 0.
+    :param add_spread: Maximum extra seconds to add after scaling base.
+    :param mul_spread: Maximum multiplier factor for base; drawn from [1.0, mul_spread].
+    :param max_sleep: Optional upper limit for the final sleep duration.
+    """
+    if base < 0 or add_spread < 0 or mul_spread < 0:
+        logger.warning(
+            "[async sleep] Invalid parameters: base=%s, add_spread=%s, mul_spread=%s",
+            base,
+            add_spread,
+            mul_spread,
+        )
+        return
+
+    multiplicative_jitter = random.uniform(1.0, mul_spread)
+    additive_jitter = random.uniform(0, add_spread)
+    duration = base * multiplicative_jitter + additive_jitter
+
+    if max_sleep is not None:
+        duration = min(duration, max_sleep)
+
+    logger.debug("[async time] Sleeping for %.2f seconds", duration)
+    await asyncio.sleep(duration)
+
+
+__all__ = ["sleep_with_random_delay", "async_sleep_with_random_delay"]

{novel_downloader-1.3.1.dist-info → novel_downloader-1.3.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: novel-downloader
-Version: 1.3.1
+Version: 1.3.3
 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
@@ -69,20 +69,37 @@ Dynamic: license-file
 
 # novel-downloader
 
-一个基于 [DrissionPage](https://www.drissionpage.cn) 和 [requests](https://github.com/psf/requests) 的小说下载器。
+一个基于 [DrissionPage](https://www.drissionpage.cn) 和 [requests](https://github.com/psf/requests) 的小说下载工具/库。
 
 ---
 
 ## 项目简介
 
-**novel-downloader** 是一个通用的小说下载库 / CLI 工具,
-- 大多数支持的站点仅依赖 [`requests`](https://github.com/psf/requests) 进行 HTTP 抓取
+**novel-downloader** 支持多种小说网站的章节抓取与合并导出,
+- **轻量化抓取**: 绝大多数站点仅依赖 `requests` 实现 HTTP 请求, 无需额外浏览器驱动
 - 对于起点中文网 (Qidian), 可在配置中选择:
   - `mode: session` : 纯 Requests 模式
-  - `mode: browser`  : 基于 DrissionPage 驱动 Chrome 的浏览器模式 (可处理更复杂的 JS/加密)。
-- 如果在 `browser` 模式下且 `login_required: true`, 首次运行会自动打开浏览器, 请完成登录后继续。
+  - `mode: browser`  : 基于 `DrissionPage` 驱动 Chrome 的浏览器模式 (可处理更复杂的 JS/加密)。
+- **自动登录** (可选)
+  - 配置 `login_required: true` 后自动检测并重用历史 Cookie
+  - 首次登录或 Cookie 失效时:
+    - **browser** 模式: 在程序打开的浏览器窗口登录, 登录后回车继续
+    - **session** 模式: 根据提示粘贴浏览器中已登录的 Cookie (参考 [复制 Cookies](https://github.com/BowenZ217/novel-downloader/blob/main/docs/copy-cookies.md))
 
-**快速开始**
+## 功能特性
+
+- 抓取起点中文网免费及已订阅章节内容
+- 支持断点续爬, 自动续传未完成任务
+- 自动整合所有章节并导出为:
+  - TXT
+  - EPUB (可选包含章节插图)
+- 支持活动广告过滤:
+  - [x] 章节标题
+  - [ ] 章节正文
+
+---
+
+## 快速开始
 
 ```bash
 # 克隆 + 安装
@@ -101,7 +118,10 @@ novel-cli settings init
 novel-cli download 123456
 ```
 
-**从 GitHub 安装 (开发版)**
+- 详细可见: [支持站点列表](https://github.com/BowenZ217/novel-downloader/blob/main/docs/6-supported-sites.md)
+- 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)
+
+## 从 GitHub 安装 (开发版)
 
 如需体验开发中的最新功能, 可通过 GitHub 安装:
 
@@ -113,22 +133,6 @@ pip install .
 # pip install .[font-recovery]
 ```
 
-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)
-
----
-
-## 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)
-- 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
-  - [ ] 作者说
-
 ---
 
 ## 文档结构
@@ -140,6 +144,7 @@ pip install .
 - [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)
+- [复制 Cookies](https://github.com/BowenZ217/novel-downloader/blob/main/docs/copy-cookies.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)