novel-downloader 1.3.1__py3-none-any.whl → 1.3.2__py3-none-any.whl

novel_downloader/core/requesters/yamibo/session.py

@@ -0,0 +1,237 @@
+"""
+novel_downloader.core.requesters.yamibo.session
+-----------------------------------------------
+
+"""
+
+from typing import Any
+
+from lxml import etree
+
+from novel_downloader.config.models import RequesterConfig
+from novel_downloader.core.requesters.base import BaseSession
+from novel_downloader.utils.i18n import t
+from novel_downloader.utils.state import state_mgr
+from novel_downloader.utils.time_utils import sleep_with_random_delay
+
+
+class YamiboSession(BaseSession):
+    """
+    A session class for interacting with the
+    yamibo (www.yamibo.com) novel website.
+    """
+
+    BASE_URL = "https://www.yamibo.com"
+    BOOKCASE_URL = "https://www.yamibo.com/my/fav"
+    BOOK_INFO_URL = "https://www.yamibo.com/novel/{book_id}"
+    CHAPTER_URL = "https://www.yamibo.com/novel/view-chapter?id={chapter_id}"
+
+    LOGIN_URL = "https://www.yamibo.com/user/login"
+
+    def __init__(
+        self,
+        config: RequesterConfig,
+    ):
+        super().__init__(config)
+        self._logged_in: bool = False
+        self._request_interval = config.backoff_factor
+        self._retry_times = config.retry_times
+        self._username = config.username
+        self._password = config.password
+
+    def login(
+        self,
+        username: str = "",
+        password: str = "",
+        manual_login: bool = False,
+        **kwargs: Any,
+    ) -> bool:
+        """
+        Restore cookies persisted by the session-based workflow.
+        """
+        cookies: dict[str, str] = state_mgr.get_cookies("yamibo")
+        username = username or self._username
+        password = password or self._password
+
+        self.update_cookies(cookies)
+        for _ in range(self._retry_times):
+            if self._check_login_status():
+                self.logger.debug("[auth] Already logged in.")
+                self._logged_in = True
+                return True
+            if username and password and not self._api_login(username, password):
+                print(t("session_login_failed", site="esjzone"))
+            sleep_with_random_delay(
+                self._request_interval,
+                mul_spread=1.1,
+                max_sleep=self._request_interval + 2,
+            )
+
+        self._logged_in = self._check_login_status()
+        return self._logged_in
+
+    def get_book_info(
+        self,
+        book_id: str,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Fetch the raw HTML of the book info and catalog pages.
+
+        Order: [info, catalog]
+
+        :param book_id: The book identifier.
+        :return: The page content as a string.
+        """
+        url = self.book_info_url(book_id=book_id)
+        try:
+            resp = self.get(url, **kwargs)
+            resp.raise_for_status()
+            return [resp.text]
+        except Exception as exc:
+            self.logger.warning(
+                "[session] get_book_info(%s) failed: %s",
+                book_id,
+                exc,
+            )
+        return []
+
+    def get_book_chapter(
+        self,
+        book_id: str,
+        chapter_id: str,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Fetch the HTML of a single chapter.
+
+        :param book_id: The book identifier.
+        :param chapter_id: The chapter identifier.
+        :return: The chapter content as a string.
+        """
+        url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
+        try:
+            resp = self.get(url, **kwargs)
+            resp.raise_for_status()
+            return [resp.text]
+        except Exception as exc:
+            self.logger.warning(
+                "[session] get_book_chapter(%s) failed: %s",
+                book_id,
+                exc,
+            )
+        return []
+
+    def get_bookcase(
+        self,
+        page: int = 1,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Retrieve the user's *bookcase* page.
+
+        :return: The HTML markup of the bookcase page.
+        """
+        url = self.bookcase_url()
+        try:
+            resp = self.get(url, **kwargs)
+            resp.raise_for_status()
+            return [resp.text]
+        except Exception as exc:
+            self.logger.warning(
+                "[session] get_bookcase failed: %s",
+                exc,
+            )
+        return []
+
+    @classmethod
+    def bookcase_url(cls) -> str:
+        """
+        Construct the URL for the user's bookcase page.
+
+        :return: Fully qualified URL of the bookcase.
+        """
+        return cls.BOOKCASE_URL
+
+    @classmethod
+    def book_info_url(cls, book_id: str) -> str:
+        """
+        Construct the URL for fetching a book's info page.
+
+        :param book_id: The identifier of the book.
+        :return: Fully qualified URL for the book info page.
+        """
+        return cls.BOOK_INFO_URL.format(book_id=book_id)
+
+    @classmethod
+    def chapter_url(cls, book_id: str, chapter_id: str) -> str:
+        """
+        Construct the URL for fetching a specific chapter.
+
+        :param book_id: The identifier of the book.
+        :param chapter_id: The identifier of the chapter.
+        :return: Fully qualified chapter URL.
+        """
+        return cls.CHAPTER_URL.format(chapter_id=chapter_id)
+
+    def _api_login(self, username: str, password: str) -> bool:
+        """
+        Login to the API using a 2-step token-based process.
+
+        Step 1: Get token `_csrf-frontend`.
+        Step 2: Use token and credentials to perform login.
+        Return True if login succeeds, False otherwise.
+        """
+        try:
+            resp_1 = self.get(self.LOGIN_URL)
+            resp_1.raise_for_status()
+            tree = etree.HTML(resp_1.text)
+            csrf_value = tree.xpath('//input[@name="_csrf-frontend"]/@value')
+            csrf_value = csrf_value[0] if csrf_value else ""
+            if not csrf_value:
+                self.logger.warning("[session] _api_login: CSRF token not found.")
+                return False
+        except Exception as exc:
+            self.logger.warning("[session] _api_login failed at step 1: %s", exc)
+            return False
+
+        data_2 = {
+            "_csrf-frontend": csrf_value,
+            "LoginForm[username]": username,
+            "LoginForm[password]": password,
+            # "LoginForm[rememberMe]": 0,
+            "LoginForm[rememberMe]": 1,
+            "login-button": "",
+        }
+        temp_headers = dict(self.headers)
+        temp_headers["Origin"] = self.BASE_URL
+        temp_headers["Referer"] = self.LOGIN_URL
+        try:
+            resp_2 = self.post(self.LOGIN_URL, data=data_2, headers=temp_headers)
+            resp_2.raise_for_status()
+            return "登录成功" in resp_2.text
+        except Exception as exc:
+            self.logger.warning("[session] _api_login failed at step 2: %s", exc)
+        return False
+
+    def _check_login_status(self) -> bool:
+        """
+        Check whether the user is currently logged in by
+        inspecting the bookcase page content.
+
+        :return: True if the user is logged in, False otherwise.
+        """
+        keywords = [
+            "登录 - 百合会",
+            "用户名/邮箱",
+        ]
+        resp_text = self.get_bookcase()
+        if not resp_text:
+            return False
+        return not any(kw in resp_text[0] for kw in keywords)
+
+    def _on_close(self) -> None:
+        """
+        Save cookies to the state manager before closing.
+        """
+        state_mgr.set_cookies("yamibo", self.cookies)

novel_downloader/core/savers/__init__.py

@@ -6,17 +6,29 @@ novel_downloader.core.savers
 This module defines saver classes for different novel platforms.
 
 Currently supported platforms:
-- Biquge (笔趣阁)
-- Qidian (起点中文网)
-- CommonSaver (通用)
+- biquge (笔趣阁)
+- esjzone (ESJ Zone)
+- qianbi (铅笔小说)
+- qidian (起点中文网)
+- sfacg (SF轻小说)
+- yamibo (百合会)
+- common (通用架构)
 """
 
 from .biquge import BiqugeSaver
 from .common import CommonSaver
+from .esjzone import EsjzoneSaver
+from .qianbi import QianbiSaver
 from .qidian import QidianSaver
+from .sfacg import SfacgSaver
+from .yamibo import YamiboSaver
 
 __all__ = [
     "BiqugeSaver",
     "CommonSaver",
+    "EsjzoneSaver",
+    "QianbiSaver",
     "QidianSaver",
+    "SfacgSaver",
+    "YamiboSaver",
 ]

novel_downloader/core/savers/base.py

@@ -39,6 +39,7 @@ class BaseSaver(SaverProtocol, abc.ABC):
         """
         self._config = config
 
+        self._base_cache_dir = Path(config.cache_dir)
         self._raw_data_dir = Path(config.raw_data_dir)
         self._output_dir = Path(config.output_dir)
         self._raw_data_dir.mkdir(parents=True, exist_ok=True)

novel_downloader/core/savers/esjzone.py

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

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/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
@@ -60,4 +61,45 @@ def sleep_with_random_delay(
     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.info("[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-1.3.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: novel-downloader
-Version: 1.3.1
+Version: 1.3.2
 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
@@ -80,9 +80,26 @@ Dynamic: license-file
 - 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。
+- 若配置 `login_required: true`, 程序会在运行时自动检查登录状态, 支持自动重用历史 Cookie, 仅在首次登录或 Cookie 失效时需要人工介入:
+  - 若使用 `browser` 模式, 请在程序打开的浏览器窗口登录, 登录后回车继续
+  - 若使用 `session` 模式, 请根据程序提示粘贴浏览器中登录成功后的 Cookie ([复制 Cookies](https://github.com/BowenZ217/novel-downloader/blob/main/docs/copy-cookies.md))
 
-**快速开始**
+## 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)
+- 爬取部分小说网站
+- 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
+
+---
+
+## 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)