novel-downloader 2.0.1__py3-none-any.whl → 2.0.2__py3-none-any.whl

novel_downloader/core/fetchers/wanbengo.py

@@ -9,7 +9,6 @@ from typing import Any
 
 from novel_downloader.core.fetchers.base import BaseSession
 from novel_downloader.core.fetchers.registry import register_fetcher
-from novel_downloader.models import FetcherConfig
 
 
 @register_fetcher(
@@ -20,28 +19,16 @@ class WanbengoSession(BaseSession):
     A session class for interacting with the 完本神站 (www.wanbengo.com) novel website.
     """
 
+    site_name: str = "wanbengo"
+
     BOOK_INFO_URL = "https://www.wanbengo.com/{book_id}/"
     CHAPTER_URL = "https://www.wanbengo.com/{book_id}/{chapter_id}.html"
 
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("wanbengo", config, cookies, **kwargs)
-
     async def get_book_info(
         self,
         book_id: str,
         **kwargs: Any,
     ) -> list[str]:
-        """
-        Fetch the raw HTML of the book info page asynchronously.
-
-        :param book_id: The book identifier.
-        :return: The page content as string list.
-        """
         url = self.book_info_url(book_id=book_id)
         return [await self.fetch(url, **kwargs)]
 
@@ -51,13 +38,6 @@ class WanbengoSession(BaseSession):
         chapter_id: str,
         **kwargs: Any,
     ) -> list[str]:
-        """
-        Fetch the raw HTML of a single chapter asynchronously.
-
-        :param book_id: The book identifier.
-        :param chapter_id: The chapter identifier.
-        :return: The page content as string list.
-        """
         url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
         return [await self.fetch(url, **kwargs)]
 

novel_downloader/core/fetchers/xiaoshuowu.py

@@ -10,7 +10,6 @@ from typing import Any
 
 from novel_downloader.core.fetchers.base import BaseSession
 from novel_downloader.core.fetchers.registry import register_fetcher
-from novel_downloader.models import FetcherConfig
 
 
 @register_fetcher(
@@ -21,18 +20,12 @@ class XiaoshuowuSession(BaseSession):
     A session class for interacting with the 小说屋 (www.xiaoshuoge.info) novel.
     """
 
+    site_name: str = "xiaoshuowu"
+
     BOOK_INFO_URL = "http://www.xiaoshuoge.info/book/{book_id}/"
     BOOK_CATALOG_URL = "http://www.xiaoshuoge.info/html/{book_id}/"
     CHAPTER_URL = "http://www.xiaoshuoge.info/html/{book_id}/{chapter_id}.html"
 
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("xiaoshuowu", config, cookies, **kwargs)
-
     async def get_book_info(
         self,
         book_id: str,
@@ -62,13 +55,6 @@ class XiaoshuowuSession(BaseSession):
         chapter_id: str,
         **kwargs: Any,
     ) -> list[str]:
-        """
-        Fetch the raw HTML of a single chapter asynchronously.
-
-        :param book_id: The book identifier.
-        :param chapter_id: The chapter identifier.
-        :return: The page content as string list.
-        """
         book_id = book_id.replace("-", "/")
         url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
         return [await self.fetch(url, ssl=False, **kwargs)]

novel_downloader/core/fetchers/xiguashuwu.py

@@ -9,8 +9,6 @@ from typing import Any
 
 from novel_downloader.core.fetchers.base import BaseSession
 from novel_downloader.core.fetchers.registry import register_fetcher
-from novel_downloader.models import FetcherConfig
-from novel_downloader.utils import async_jitter_sleep
 
 
 @register_fetcher(
@@ -21,19 +19,13 @@ class XiguashuwuSession(BaseSession):
     A session class for interacting with the 西瓜书屋 (www.xiguashuwu.com) novel.
     """
 
+    site_name: str = "xiguashuwu"
+
     BASE_URL = "https://www.xiguashuwu.com"
     BOOK_INFO_URL = "https://www.xiguashuwu.com/book/{book_id}/iszip/0/"
     BOOK_CATALOG_URL = "https://www.xiguashuwu.com/book/{book_id}/catalog/"
     CHAPTER_URL = "https://www.xiguashuwu.com/book/{book_id}/{chapter_id}.html"
 
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("xiguashuwu", config, cookies, **kwargs)
-
     async def get_book_info(
         self,
         book_id: str,
@@ -85,11 +77,7 @@ class XiguashuwuSession(BaseSession):
             if not any(pat in html for pat in next_patterns):
                 break
 
-            await async_jitter_sleep(
-                self.request_interval,
-                mul_spread=1.1,
-                max_sleep=self.request_interval + 2,
-            )
+            await self._sleep()
         return [info_html, *catalog_pages]
 
     async def get_book_chapter(
@@ -130,11 +118,7 @@ class XiguashuwuSession(BaseSession):
 
             html_pages.append(html)
             idx += 1
-            await async_jitter_sleep(
-                self.request_interval,
-                mul_spread=1.1,
-                max_sleep=self.request_interval + 2,
-            )
+            await self._sleep()
 
         return html_pages
 

novel_downloader/core/fetchers/xs63b.py

@@ -12,8 +12,6 @@ from typing import Any
 
 from novel_downloader.core.fetchers.base import BaseSession
 from novel_downloader.core.fetchers.registry import register_fetcher
-from novel_downloader.models import FetcherConfig
-from novel_downloader.utils import async_jitter_sleep
 
 
 @register_fetcher(
@@ -24,6 +22,8 @@ class Xs63bSession(BaseSession):
     A session class for interacting with the 小说路上 (m.xs63b.com) novel website.
     """
 
+    site_name: str = "xs63b"
+
     BOOK_INFO_URL = "https://m.xs63b.com/{book_id}/"
     BOOK_CATALOG_URL = "https://www.xs63b.com/{book_id}/"
     CHAPTER_URL = "https://m.xs63b.com/{book_id}/{chapter_id}.html"
@@ -31,14 +31,6 @@ class Xs63bSession(BaseSession):
     _JSARR_PATTERN = re.compile(r"var\s+jsarr\s*=\s*\[([^\]]+)\]")
     _JSSTR_PATTERN = re.compile(r"var\s+jsstr\s*=\s*\"([^\"]+)\";")
 
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("xs63b", config, cookies, **kwargs)
-
     async def get_book_info(
         self,
         book_id: str,
@@ -100,11 +92,7 @@ class Xs63bSession(BaseSession):
             jsstr = self._parse_jsstr(html)
             chapter_url = self._build_chapter_url(book_id, jsarr, jsstr)
 
-            await async_jitter_sleep(
-                self.request_interval,
-                mul_spread=1.1,
-                max_sleep=self.request_interval + 2,
-            )
+            await self._sleep()
 
         return html_pages
 

novel_downloader/core/fetchers/xshbook.py

@@ -9,7 +9,6 @@ from typing import Any
 
 from novel_downloader.core.fetchers.base import BaseSession
 from novel_downloader.core.fetchers.registry import register_fetcher
-from novel_downloader.models import FetcherConfig
 
 
 @register_fetcher(
@@ -20,28 +19,16 @@ class XshbookSession(BaseSession):
     A session class for interacting with the 小说虎 (www.xshbook.com) novel website.
     """
 
+    site_name: str = "xshbook"
+
     BOOK_INFO_URL = "https://www.xshbook.com/{book_id}/"
     CHAPTER_URL = "https://www.xshbook.com/{book_id}/{chapter_id}.html"
 
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("xshbook", config, cookies, **kwargs)
-
     async def get_book_info(
         self,
         book_id: str,
         **kwargs: Any,
     ) -> list[str]:
-        """
-        Fetch the raw HTML of the book info page asynchronously.
-
-        :param book_id: The book identifier.
-        :return: The page content as string list.
-        """
         book_id = book_id.replace("-", "/")
         url = self.book_info_url(book_id=book_id)
         return [await self.fetch(url, **kwargs)]
@@ -52,13 +39,6 @@ class XshbookSession(BaseSession):
         chapter_id: str,
         **kwargs: Any,
     ) -> list[str]:
-        """
-        Fetch the raw HTML of a single chapter asynchronously.
-
-        :param book_id: The book identifier.
-        :param chapter_id: The chapter identifier.
-        :return: The page content as string list.
-        """
         book_id = book_id.replace("-", "/")
         url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
         return [await self.fetch(url, **kwargs)]

novel_downloader/core/fetchers/yamibo.py

@@ -12,8 +12,7 @@ from lxml import html
 
 from novel_downloader.core.fetchers.base import BaseSession
 from novel_downloader.core.fetchers.registry import register_fetcher
-from novel_downloader.models import FetcherConfig, LoginField
-from novel_downloader.utils import async_jitter_sleep
+from novel_downloader.models import LoginField
 
 
 @register_fetcher(
@@ -24,6 +23,8 @@ class YamiboSession(BaseSession):
     A session class for interacting with the 百合会 (www.yamibo.com) novel website.
     """
 
+    site_name: str = "yamibo"
+
     BASE_URL = "https://www.yamibo.com"
     BOOKCASE_URL = "https://www.yamibo.com/my/fav"
     BOOK_INFO_URL = "https://www.yamibo.com/novel/{book_id}"
@@ -31,14 +32,6 @@ class YamiboSession(BaseSession):
 
     LOGIN_URL = "https://www.yamibo.com/user/login"
 
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("yamibo", config, cookies, **kwargs)
-
     async def login(
         self,
         username: str = "",
@@ -69,11 +62,7 @@ class YamiboSession(BaseSession):
             ):
                 self._is_logged_in = True
                 return True
-            await async_jitter_sleep(
-                self.backoff_factor,
-                mul_spread=1.1,
-                max_sleep=self.backoff_factor + 2,
-            )
+            await self._sleep()
 
         self._is_logged_in = False
         return False
@@ -83,12 +72,6 @@ class YamiboSession(BaseSession):
         book_id: str,
         **kwargs: Any,
     ) -> list[str]:
-        """
-        Fetch the raw HTML of the book info page asynchronously.
-
-        :param book_id: The book identifier.
-        :return: The page content as string list.
-        """
         url = self.book_info_url(book_id=book_id)
         return [await self.fetch(url, **kwargs)]
 
@@ -98,13 +81,6 @@ class YamiboSession(BaseSession):
         chapter_id: str,
         **kwargs: Any,
     ) -> list[str]:
-        """
-        Fetch the raw HTML of a single chapter asynchronously.
-
-        :param book_id: The book identifier.
-        :param chapter_id: The chapter identifier.
-        :return: The page content as string list.
-        """
         url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
         return [await self.fetch(url, **kwargs)]
 

novel_downloader/core/fetchers/yibige.py

@@ -10,7 +10,6 @@ from typing import Any
 
 from novel_downloader.core.fetchers.base import BaseSession
 from novel_downloader.core.fetchers.registry import register_fetcher
-from novel_downloader.models import FetcherConfig
 
 
 @register_fetcher(
@@ -21,25 +20,20 @@ class YibigeSession(BaseSession):
     A session class for interacting with the 一笔阁 (www.yibige.org) novel website.
     """
 
+    site_name: str = "yibige"
+    BASE_URL_MAP: dict[str, str] = {
+        "simplified": "www.yibige.org",  # 主站
+        "traditional": "tw.yibige.org",
+        "singapore": "sg.yibige.org",  # 新加坡
+        "taiwan": "tw.yibige.org",  # 臺灣正體
+        "hongkong": "hk.yibige.org",  # 香港繁體
+    }
+    DEFAULT_BASE_URL: str = "www.yibige.org"
+
     BOOK_INFO_URL = "https://{base_url}/{book_id}/"
     BOOK_CATALOG_URL = "https://{base_url}/{book_id}/index.html"
     CHAPTER_URL = "https://{base_url}/{book_id}/{chapter_id}.html"
 
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("yibige", config, cookies, **kwargs)
-        self.base_url = (
-            "www.yibige.org" if config.locale_style == "simplified" else "tw.yibige.org"
-        )
-        # 主站: www.yibige.org
-        # 新加坡: sg.yibige.org
-        # 臺灣正體: tw.yibige.org
-        # 香港繁體: hk.yibige.org
-
     async def get_book_info(
         self,
         book_id: str,
@@ -53,8 +47,8 @@ class YibigeSession(BaseSession):
         :param book_id: The book identifier.
         :return: The page content as string list.
         """
-        info_url = self.book_info_url(base_url=self.base_url, book_id=book_id)
-        catalog_url = self.book_catalog_url(base_url=self.base_url, book_id=book_id)
+        info_url = self.book_info_url(base_url=self._base_url, book_id=book_id)
+        catalog_url = self.book_catalog_url(base_url=self._base_url, book_id=book_id)
 
         info_html, catalog_html = await asyncio.gather(
             self.fetch(info_url, **kwargs),
@@ -68,15 +62,8 @@ class YibigeSession(BaseSession):
         chapter_id: str,
         **kwargs: Any,
     ) -> list[str]:
-        """
-        Fetch the raw HTML of a single chapter asynchronously.
-
-        :param book_id: The book identifier.
-        :param chapter_id: The chapter identifier.
-        :return: The page content as string list.
-        """
         url = self.chapter_url(
-            base_url=self.base_url, book_id=book_id, chapter_id=chapter_id
+            base_url=self._base_url, book_id=book_id, chapter_id=chapter_id
         )
         return [await self.fetch(url, **kwargs)]
 

novel_downloader/core/interfaces/exporter.py

@@ -6,18 +6,13 @@ novel_downloader.core.interfaces.exporter
 Protocol defining the interface for exporting books to text, EPUB, and other formats.
 """
 
+import types
 from pathlib import Path
-from typing import Protocol, runtime_checkable
+from typing import Protocol, Self, runtime_checkable
 
 
 @runtime_checkable
 class ExporterProtocol(Protocol):
-    """
-    A exporter must implement a method to persist a completed book as plain text.
-
-    It may also optionally implement an EPUB (or other format) exporter.
-    """
-
     def export(self, book_id: str) -> dict[str, Path]:
         """
         Export the book in the formats specified in config.
@@ -58,3 +53,20 @@ class ExporterProtocol(Protocol):
         :param book_id: The book identifier.
         """
         ...
+
+    def close(self) -> None:
+        """
+        Shutdown and clean up the exporter.
+        """
+        ...
+
+    def __enter__(self) -> Self:
+        ...
+
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc_val: BaseException | None,
+        tb: types.TracebackType | None,
+    ) -> None:
+        ...

novel_downloader/core/interfaces/fetcher.py

@@ -21,6 +21,24 @@ class FetcherProtocol(Protocol):
     and manage login/shutdown asynchronously.
     """
 
+    async def init(
+        self,
+        **kwargs: Any,
+    ) -> None:
+        """
+        Perform async initialization, such as creating a session.
+
+        This should be called before using any other method
+        if initialization is required.
+        """
+        ...
+
+    async def close(self) -> None:
+        """
+        Shutdown and clean up any resources.
+        """
+        ...
+
     async def login(
         self,
         username: str = "",
@@ -64,50 +82,6 @@ class FetcherProtocol(Protocol):
         """
         ...
 
-    async def get_bookcase(
-        self,
-        **kwargs: Any,
-    ) -> list[str]:
-        """
-        Optional: Retrieve the HTML content of the authenticated
-        user's bookcase page asynchronously.
-
-        :return: The HTML markup of the bookcase page.
-        """
-        ...
-
-    async def fetch(
-        self,
-        url: str,
-        **kwargs: Any,
-    ) -> str:
-        """
-        Perform a generic HTTP request and return the response body as text.
-
-        :param url: The URL to request.
-        :return: The response content as a string (HTML or JSON or plain text).
-        """
-        ...
-
-    async def init(
-        self,
-        **kwargs: Any,
-    ) -> None:
-        """
-        Perform async initialization, such as
-        launching a browser or creating a session.
-
-        This should be called before using any other method
-        if initialization is required.
-        """
-        ...
-
-    async def close(self) -> None:
-        """
-        Shutdown and clean up any resources.
-        """
-        ...
-
     async def load_state(self) -> bool:
         """
         Restore session state from a persistent storage,
@@ -137,6 +111,9 @@ class FetcherProtocol(Protocol):
     def login_fields(self) -> list[LoginField]:
         ...
 
+    async def __aenter__(self) -> Self:
+        ...
+
     async def __aexit__(
         self,
         exc_type: type[BaseException] | None,
@@ -144,6 +121,3 @@ class FetcherProtocol(Protocol):
         tb: types.TracebackType | None,
     ) -> None:
         ...
-
-    async def __aenter__(self) -> Self:
-        ...

novel_downloader/core/parsers/__init__.py

@@ -13,7 +13,6 @@ __all__ = [
     "BiqugeParser",
     "BiquyueduParser",
     "DxmwxParser",
-    "EightnovelParser",
     "EsjzoneParser",
     "GuidayeParser",
     "HetushuParser",
@@ -22,10 +21,12 @@ __all__ = [
     "Jpxs123Parser",
     "LewennParser",
     "LinovelibParser",
+    "N8novelParser",
     "PiaotiaParser",
     "QbtrParser",
     "QianbiParser",
     "QidianParser",
+    "QqbookParser",
     "Quanben5Parser",
     "SfacgParser",
     "ShencouParser",
@@ -45,7 +46,6 @@ from .aaatxt import AaatxtParser
 from .b520 import BiqugeParser
 from .biquyuedu import BiquyueduParser
 from .dxmwx import DxmwxParser
-from .eightnovel import EightnovelParser
 from .esjzone import EsjzoneParser
 from .guidaye import GuidayeParser
 from .hetushu import HetushuParser
@@ -54,10 +54,12 @@ from .ixdzs8 import Ixdzs8Parser
 from .jpxs123 import Jpxs123Parser
 from .lewenn import LewennParser
 from .linovelib import LinovelibParser
+from .n8novel import N8novelParser
 from .piaotia import PiaotiaParser
 from .qbtr import QbtrParser
 from .qianbi import QianbiParser
 from .qidian import QidianParser
+from .qqbook import QqbookParser
 from .quanben5 import Quanben5Parser
 from .registry import get_parser
 from .sfacg import SfacgParser

novel_downloader/core/parsers/b520.py

@@ -20,7 +20,7 @@ from novel_downloader.models import (
 
 
 @register_parser(
-    site_keys=["biquge", "bqg", "b520"],
+    site_keys=["biquge", "b520"],
 )
 class BiqugeParser(BaseParser):
     """
@@ -112,5 +112,5 @@ class BiqugeParser(BaseParser):
             "id": chapter_id,
             "title": title,
             "content": content,
-            "extra": {"site": "biquge"},
+            "extra": {"site": "b520"},
         }

novel_downloader/core/parsers/base.py

@@ -12,18 +12,14 @@ from collections.abc import Iterable
 from pathlib import Path
 from typing import Any
 
-from novel_downloader.core.interfaces import ParserProtocol
 from novel_downloader.models import BookInfoDict, ChapterDict, ParserConfig
 
 
-class BaseParser(ParserProtocol, abc.ABC):
+class BaseParser(abc.ABC):
     """
     BaseParser defines the interface for extracting book metadata and chapter content
     from raw HTML.
 
-    This base class manages internal book state (e.g. current book ID) and supports
-    configuration-driven behavior such as content cleaning or formatting.
-
     Subclasses must implement actual parsing logic for specific sites.
     """
 
@@ -31,23 +27,20 @@ class BaseParser(ParserProtocol, abc.ABC):
 
     _SPACE_RE = re.compile(r"\s+")
 
-    def __init__(
-        self,
-        config: ParserConfig,
-    ):
+    def __init__(self, config: ParserConfig):
         """
         Initialize the parser with a configuration object.
 
         :param config: ParserConfig object controlling parsing behavior.
         """
-        self._config = config
         self._book_id: str | None = None
 
+        self._fontocr_cfg = config.fontocr_cfg
         self._save_font_debug = config.save_font_debug
         self._decode_font: bool = config.decode_font
+        self._batch_size = config.batch_size
         self._use_truncation = config.use_truncation
         self._base_cache_dir = Path(config.cache_dir)
-        self._cache_dir = self._base_cache_dir
 
         self._ad_pattern = self._compile_ads_pattern()
 
@@ -81,34 +74,6 @@ class BaseParser(ParserProtocol, abc.ABC):
         """
         ...
 
-    @property
-    def book_id(self) -> str | None:
-        """
-        Current book ID in context.
-
-        :return: The current book identifier.
-        """
-        return self._book_id
-
-    @book_id.setter
-    def book_id(self, value: str) -> None:
-        """
-        Set current book ID and update debug paths if needed.
-
-        :param value: Book identifier.
-        """
-        self._book_id = value
-        self._cache_dir = self._base_cache_dir / value
-        self._on_book_id_set()
-
-    def _on_book_id_set(self) -> None:
-        """
-        Hook called when a new book ID is set.
-        Subclasses can override this to initialize
-        book-related folders or states.
-        """
-        pass
-
     def _compile_ads_pattern(self) -> re.Pattern[str] | None:
         """
         Compile a regex pattern from the ADS list, or return None if no ADS.