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

novel_downloader/core/fetchers/registry.py

@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.registry
+---------------------------------------
+
+Registry and factory helpers for creating site-specific fetchers.
+"""
+
+__all__ = ["register_fetcher", "get_fetcher"]
+
+from collections.abc import Callable, Sequence
+from typing import TypeVar
+
+from novel_downloader.core.interfaces import FetcherProtocol
+from novel_downloader.models import FetcherConfig
+
+FetcherBuilder = Callable[[FetcherConfig], FetcherProtocol]
+
+F = TypeVar("F", bound=FetcherProtocol)
+_FETCHER_MAP: dict[str, FetcherBuilder] = {}
+
+
+def register_fetcher(
+    site_keys: Sequence[str],
+) -> Callable[[type[F]], type[F]]:
+    """
+    Decorator to register a fetcher class under given keys.
+
+    :param site_keys: Sequence of site identifiers
+    :param backends: Sequence of backend types
+    :return: A class decorator that populates _FETCHER_MAP.
+    """
+
+    def decorator(cls: type[F]) -> type[F]:
+        for site in site_keys:
+            site_lower = site.lower()
+            _FETCHER_MAP[site_lower] = cls
+        return cls
+
+    return decorator
+
+
+def get_fetcher(
+    site: str,
+    config: FetcherConfig,
+) -> FetcherProtocol:
+    """
+    Returns an FetcherProtocol for the given site.
+
+    :param site: Site name (e.g., 'qidian')
+    :param config: Configuration for the requester
+    :return: An instance of a requester class
+    """
+    site_key = site.lower()
+    try:
+        fetcher_cls = _FETCHER_MAP[site_key]
+    except KeyError as err:
+        raise ValueError(f"Unsupported site: {site!r}") from err
+
+    return fetcher_cls(config)

novel_downloader/core/fetchers/{sfacg/session.py → sfacg.py}

@@ -1,19 +1,23 @@
 #!/usr/bin/env python3
 """
-novel_downloader.core.fetchers.sfacg.session
---------------------------------------------
+novel_downloader.core.fetchers.sfacg
+------------------------------------
 
 """
 
 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, LoginField
 
 
+@register_fetcher(
+    site_keys=["sfacg"],
+)
 class SfacgSession(BaseSession):
     """
-    A session class for interacting with the Sfacg (m.sfacg.com) novel website.
+    A session class for interacting with the SF轻小说 (m.sfacg.com) novel website.
     """
 
     LOGIN_URL = "https://m.sfacg.com/login"
@@ -60,8 +64,10 @@ class SfacgSession(BaseSession):
         """
         Fetch the raw HTML of the book info page asynchronously.
 
+        Order: [info, catalog]
+
         :param book_id: The book identifier.
-        :return: The page content as a string.
+        :return: The page content as string list.
         """
         info_url = self.book_info_url(book_id=book_id)
         catalog_url = self.book_catalog_url(book_id=book_id)
@@ -82,7 +88,7 @@ class SfacgSession(BaseSession):
 
         :param book_id: The book identifier.
         :param chapter_id: The chapter identifier.
-        :return: The chapter content as a string.
+        :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)]
@@ -152,10 +158,6 @@ class SfacgSession(BaseSession):
         """
         return cls.CHAPTER_URL.format(chapter_id=chapter_id)
 
-    @property
-    def hostname(self) -> str:
-        return "m.sfacg.com"
-
     async def _check_login_status(self) -> bool:
         """
         Check whether the user is currently logged in by

novel_downloader/core/fetchers/shencou.py

@@ -0,0 +1,106 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.shencou
+--------------------------------------
+
+"""
+
+import asyncio
+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(
+    site_keys=["shencou"],
+)
+class ShencouSession(BaseSession):
+    """
+    A session class for interacting with the 神凑轻小说 (www.shencou.com) novel website.
+    """
+
+    BOOK_INFO_URL = "https://www.shencou.com/books/read_{book_id}.html"
+    BOOK_CATALOG_URL = "https://www.shencou.com/read/{book_id}/index.html"
+    CHAPTER_URL = "https://www.shencou.com/read/{book_id}/{chapter_id}.html"
+
+    def __init__(
+        self,
+        config: FetcherConfig,
+        cookies: dict[str, str] | None = None,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__("shencou", 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.
+
+        Order: [info, catalog]
+
+        :param book_id: The book identifier.
+        :return: The page content as string list.
+        """
+        book_id = book_id.replace("-", "/")
+        info_url = self.book_info_url(book_id=book_id)
+        catalog_url = self.book_catalog_url(book_id=book_id)
+
+        info_html, catalog_html = await asyncio.gather(
+            self.fetch(info_url, **kwargs),
+            self.fetch(catalog_url, **kwargs),
+        )
+        return [info_html, catalog_html]
+
+    async def get_book_chapter(
+        self,
+        book_id: str,
+        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)]
+
+    @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.
+        """
+        clean_id = book_id.rsplit("/", 1)[-1]
+        return cls.BOOK_INFO_URL.format(book_id=clean_id)
+
+    @classmethod
+    def book_catalog_url(cls, book_id: str) -> str:
+        """
+        Construct the URL for fetching a book's catalog page.
+
+        :param book_id: The identifier of the book.
+        :return: Fully qualified catalog page URL.
+        """
+        return cls.BOOK_CATALOG_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(book_id=book_id, chapter_id=chapter_id)

novel_downloader/core/fetchers/{common/browser.py → shuhaige.py}

@@ -1,31 +1,36 @@
 #!/usr/bin/env python3
 """
-novel_downloader.core.fetchers.common.browser
----------------------------------------------
+novel_downloader.core.fetchers.shuhaige
+---------------------------------------
 
 """
 
 from typing import Any
 
-from novel_downloader.core.fetchers.base import BaseBrowser
-from novel_downloader.models import FetcherConfig, SiteProfile
+from novel_downloader.core.fetchers.base import BaseSession
+from novel_downloader.core.fetchers.registry import register_fetcher
+from novel_downloader.models import FetcherConfig
 
 
-class CommonBrowser(BaseBrowser):
+@register_fetcher(
+    site_keys=["shuhaige"],
+)
+class ShuhaigeSession(BaseSession):
     """
-    A common async browser for handling site-specific HTTP requests.
+    A session class for interacting with the
+    书海阁小说网 (www.shuhaige.net) novel website.
     """
 
+    BOOK_INFO_URL = "https://www.shuhaige.net/{book_id}/"
+    CHAPTER_URL = "https://www.shuhaige.net/{book_id}/{chapter_id}.html"
+
     def __init__(
         self,
-        site: str,
-        profile: SiteProfile,
         config: FetcherConfig,
-        reuse_page: bool = False,
+        cookies: dict[str, str] | None = None,
         **kwargs: Any,
     ) -> None:
-        super().__init__(site, config, reuse_page, **kwargs)
-        self._profile = profile
+        super().__init__("shuhaige", config, cookies, **kwargs)
 
     async def get_book_info(
         self,
@@ -36,7 +41,7 @@ class CommonBrowser(BaseBrowser):
         Fetch the raw HTML of the book info page asynchronously.
 
         :param book_id: The book identifier.
-        :return: The page content as a string.
+        :return: The page content as string list.
         """
         url = self.book_info_url(book_id=book_id)
         return [await self.fetch(url, **kwargs)]
@@ -52,21 +57,23 @@ class CommonBrowser(BaseBrowser):
 
         :param book_id: The book identifier.
         :param chapter_id: The chapter identifier.
-        :return: The chapter content as a string.
+        :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)]
 
-    def book_info_url(self, book_id: str) -> str:
+    @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 self._profile["book_info_url"].format(book_id=book_id)
+        return cls.BOOK_INFO_URL.format(book_id=book_id)
 
-    def chapter_url(self, book_id: str, chapter_id: str) -> str:
+    @classmethod
+    def chapter_url(cls, book_id: str, chapter_id: str) -> str:
         """
         Construct the URL for fetching a specific chapter.
 
@@ -74,6 +81,4 @@ class CommonBrowser(BaseBrowser):
         :param chapter_id: The identifier of the chapter.
         :return: Fully qualified chapter URL.
         """
-        return self._profile["chapter_url"].format(
-            book_id=book_id, chapter_id=chapter_id
-        )
+        return cls.CHAPTER_URL.format(book_id=book_id, chapter_id=chapter_id)

novel_downloader/core/fetchers/tongrenquan.py

@@ -0,0 +1,84 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.tongrenquan
+------------------------------------------
+
+"""
+
+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(
+    site_keys=["tongrenquan"],
+)
+class TongrenquanSession(BaseSession):
+    """
+    A session class for interacting with the 同人圈 (www.tongrenquan.org) novel website.
+    """
+
+    BASE_URL = "https://www.tongrenquan.org"
+    BOOK_INFO_URL = "https://www.tongrenquan.org/tongren/{book_id}.html"
+    CHAPTER_URL = "https://www.tongrenquan.org/tongren/{book_id}/{chapter_id}.html"
+
+    def __init__(
+        self,
+        config: FetcherConfig,
+        cookies: dict[str, str] | None = None,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__("tongrenquan", 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)]
+
+    async def get_book_chapter(
+        self,
+        book_id: str,
+        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)]
+
+    @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(book_id=book_id, chapter_id=chapter_id)

novel_downloader/core/fetchers/ttkan.py

@@ -0,0 +1,95 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.ttkan
+------------------------------------
+
+"""
+
+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(
+    site_keys=["ttkan"],
+)
+class TtkanSession(BaseSession):
+    """
+    A session class for interacting with the 天天看小说 (www.ttkan.co) novel website.
+    """
+
+    BOOK_INFO_URL = "https://{lang}.ttkan.co/novel/chapters/{book_id}"
+    CHAPTER_URL = "https://{lang}.wa01.com/novel/pagea/{book_id}_{chapter_id}.html"
+
+    def __init__(
+        self,
+        config: FetcherConfig,
+        cookies: dict[str, str] | None = None,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__("ttkan", config, cookies, **kwargs)
+        self._lang = "cn" if config.locale_style == "simplified" else "tw"
+
+    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)]
+
+    async def get_book_chapter(
+        self,
+        book_id: str,
+        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,
+            lang=self._lang,
+        )
+        return [await self.fetch(url, **kwargs)]
+
+    @classmethod
+    def book_info_url(cls, book_id: str, lang: str = "cn") -> str:
+        """
+        Construct the URL for fetching a book's info page.
+
+        :param book_id: The identifier of the book.
+        :param lang: The language of the book. (cn / tw)
+        :return: Fully qualified URL for the book info page.
+        """
+        return cls.BOOK_INFO_URL.format(book_id=book_id, lang=lang)
+
+    @classmethod
+    def chapter_url(
+        cls,
+        book_id: str,
+        chapter_id: str,
+        lang: str = "cn",
+    ) -> str:
+        """
+        Construct the URL for fetching a specific chapter.
+
+        :param book_id: The identifier of the book.
+        :param chapter_id: The chapter identifier.
+        :param lang: The language of the book. (cn / tw)
+        :return: Fully qualified chapter URL.
+        """
+        return cls.CHAPTER_URL.format(book_id=book_id, chapter_id=chapter_id, lang=lang)

novel_downloader/core/fetchers/{common/session.py → wanbengo.py}

@@ -1,31 +1,35 @@
 #!/usr/bin/env python3
 """
-novel_downloader.core.fetchers.common.session
----------------------------------------------
+novel_downloader.core.fetchers.wanbengo
+---------------------------------------
 
 """
 
 from typing import Any
 
 from novel_downloader.core.fetchers.base import BaseSession
-from novel_downloader.models import FetcherConfig, SiteProfile
+from novel_downloader.core.fetchers.registry import register_fetcher
+from novel_downloader.models import FetcherConfig
 
 
-class CommonSession(BaseSession):
+@register_fetcher(
+    site_keys=["wanbengo"],
+)
+class WanbengoSession(BaseSession):
     """
-    A common async session for handling site-specific HTTP requests.
+    A session class for interacting with the 完本神站 (www.wanbengo.com) novel website.
     """
 
+    BOOK_INFO_URL = "https://www.wanbengo.com/{book_id}/"
+    CHAPTER_URL = "https://www.wanbengo.com/{book_id}/{chapter_id}.html"
+
     def __init__(
         self,
-        site: str,
-        profile: SiteProfile,
         config: FetcherConfig,
         cookies: dict[str, str] | None = None,
         **kwargs: Any,
     ) -> None:
-        super().__init__(site, config, cookies, **kwargs)
-        self._profile = profile
+        super().__init__("wanbengo", config, cookies, **kwargs)
 
     async def get_book_info(
         self,
@@ -36,7 +40,7 @@ class CommonSession(BaseSession):
         Fetch the raw HTML of the book info page asynchronously.
 
         :param book_id: The book identifier.
-        :return: The page content as a string.
+        :return: The page content as string list.
         """
         url = self.book_info_url(book_id=book_id)
         return [await self.fetch(url, **kwargs)]
@@ -52,21 +56,23 @@ class CommonSession(BaseSession):
 
         :param book_id: The book identifier.
         :param chapter_id: The chapter identifier.
-        :return: The chapter content as a string.
+        :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)]
 
-    def book_info_url(self, book_id: str) -> str:
+    @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 self._profile["book_info_url"].format(book_id=book_id)
+        return cls.BOOK_INFO_URL.format(book_id=book_id)
 
-    def chapter_url(self, book_id: str, chapter_id: str) -> str:
+    @classmethod
+    def chapter_url(cls, book_id: str, chapter_id: str) -> str:
         """
         Construct the URL for fetching a specific chapter.
 
@@ -74,6 +80,4 @@ class CommonSession(BaseSession):
         :param chapter_id: The identifier of the chapter.
         :return: Fully qualified chapter URL.
         """
-        return self._profile["chapter_url"].format(
-            book_id=book_id, chapter_id=chapter_id
-        )
+        return cls.CHAPTER_URL.format(book_id=book_id, chapter_id=chapter_id)

novel_downloader/core/fetchers/xiaoshuowu.py

@@ -0,0 +1,106 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.xiaoshuowu
+-----------------------------------------
+
+"""
+
+import asyncio
+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(
+    site_keys=["xiaoshuowu", "xiaoshuoge"],
+)
+class XiaoshuowuSession(BaseSession):
+    """
+    A session class for interacting with the 小说屋 (www.xiaoshuoge.info) novel.
+    """
+
+    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,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Fetch the raw HTML of the book info page asynchronously.
+
+        Order: [info, catalog]
+
+        :param book_id: The book identifier.
+        :return: The page content as string list.
+        """
+        book_id = book_id.replace("-", "/")
+        info_url = self.book_info_url(book_id=book_id)
+        catalog_url = self.book_catalog_url(book_id=book_id)
+
+        info_html, catalog_html = await asyncio.gather(
+            self.fetch(info_url, ssl=False, **kwargs),
+            self.fetch(catalog_url, ssl=False, **kwargs),
+        )
+        return [info_html, catalog_html]
+
+    async def get_book_chapter(
+        self,
+        book_id: str,
+        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)]
+
+    @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.
+        """
+        clean_id = book_id.rsplit("/", 1)[-1]
+        return cls.BOOK_INFO_URL.format(book_id=clean_id)
+
+    @classmethod
+    def book_catalog_url(cls, book_id: str) -> str:
+        """
+        Construct the URL for fetching a book's catalog page.
+
+        :param book_id: The identifier of the book.
+        :return: Fully qualified catalog page URL.
+        """
+        return cls.BOOK_CATALOG_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(book_id=book_id, chapter_id=chapter_id)