novel-downloader 1.5.0__py3-none-any.whl → 2.0.1__py3-none-any.whl

novel_downloader/core/fetchers/hetushu.py

@@ -0,0 +1,92 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.hetushu
+--------------------------------------
+
+"""
+
+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=["hetushu"],
+)
+class HetushuSession(BaseSession):
+    """
+    A session class for interacting with the 和图书 (www.hetushu.com) novel website.
+    """
+
+    BOOK_INFO_URL = "https://{base_url}/book/{book_id}/index.html"
+    CHAPTER_URL = "https://{base_url}/book/{book_id}/{chapter_id}.html"
+
+    def __init__(
+        self,
+        config: FetcherConfig,
+        cookies: dict[str, str] | None = None,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__("hetushu", config, cookies, **kwargs)
+        self.base_url = (
+            "www.hetushu.com"
+            if config.locale_style == "simplified"
+            else "www.hetubook.com"
+        )
+
+    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(base_url=self.base_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(
+            base_url=self.base_url, book_id=book_id, chapter_id=chapter_id
+        )
+        return [await self.fetch(url, **kwargs)]
+
+    @classmethod
+    def book_info_url(cls, base_url: str, 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(base_url=base_url, book_id=book_id)
+
+    @classmethod
+    def chapter_url(cls, base_url: str, 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(
+            base_url=base_url, book_id=book_id, chapter_id=chapter_id
+        )

novel_downloader/core/fetchers/{qianbi/browser.py → i25zw.py}

@@ -1,42 +1,37 @@
 #!/usr/bin/env python3
 """
-novel_downloader.core.fetchers.qianbi.browser
----------------------------------------------
+novel_downloader.core.fetchers.i25zw
+------------------------------------
 
 """
 
+import asyncio
 from typing import Any
 
-from novel_downloader.core.fetchers.base import BaseBrowser
+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=["qianbi"],
-    backends=["browser"],
+    site_keys=["i25zw"],
 )
-class QianbiBrowser(BaseBrowser):
+class I25zwSession(BaseSession):
     """
-    A browser class for interacting with the Qianbi (www.23qb.com) novel website.
+    A session class for interacting with the 25中文网 (www.i25zw.com) novel website.
     """
 
-    BASE_URLS = [
-        "www.23qb.com",
-        "www.23qb.net",
-    ]
-
-    BOOK_INFO_URL = "https://www.23qb.com/book/{book_id}/"
-    BOOK_CATALOG_URL = "https://www.23qb.com/book/{book_id}/catalog"
-    CHAPTER_URL = "https://www.23qb.com/book/{book_id}/{chapter_id}.html"
+    BOOK_INFO_URL = "https://www.i25zw.com/book/{book_id}.html"
+    BOOK_CATALOG_URL = "https://www.i25zw.com/{book_id}/"
+    CHAPTER_URL = "https://www.i25zw.com/{book_id}/{chapter_id}.html"
 
     def __init__(
         self,
         config: FetcherConfig,
-        reuse_page: bool = False,
+        cookies: dict[str, str] | None = None,
         **kwargs: Any,
     ) -> None:
-        super().__init__("qianbi", config, reuse_page, **kwargs)
+        super().__init__("i25zw", config, cookies, **kwargs)
 
     async def get_book_info(
         self,
@@ -49,14 +44,15 @@ class QianbiBrowser(BaseBrowser):
         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)
 
-        info_html = await self.fetch(info_url, **kwargs)
-        catalog_html = await self.fetch(catalog_url, **kwargs)
-
+        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(
@@ -70,11 +66,10 @@ class QianbiBrowser(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.
         """
-        catalog_url = self.book_catalog_url(book_id=book_id)
         url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
-        return [await self.fetch(url, referer=catalog_url, **kwargs)]
+        return [await self.fetch(url, **kwargs)]
 
     @classmethod
     def book_info_url(cls, book_id: str) -> str:
@@ -106,7 +101,3 @@ class QianbiBrowser(BaseBrowser):
         :return: Fully qualified chapter URL.
         """
         return cls.CHAPTER_URL.format(book_id=book_id, chapter_id=chapter_id)
-
-    @property
-    def hostname(self) -> str:
-        return "www.23qb.com"

novel_downloader/core/fetchers/ixdzs8.py

@@ -0,0 +1,113 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.ixdzs8
+-------------------------------------
+
+"""
+
+import asyncio
+import re
+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=["ixdzs8"],
+)
+class Ixdzs8Session(BaseSession):
+    """
+    A session class for interacting with the 爱下电子书 (ixdzs8.com) novel website.
+    """
+
+    BOOK_INFO_URL = "https://ixdzs8.com/read/{book_id}/"
+    BOOK_CATALOG_URL = "https://ixdzs8.com/novel/clist/"
+    CHAPTER_URL = "https://ixdzs8.com/read/{book_id}/{chapter_id}.html"
+    _TOKEN_PATTERN = re.compile(r'let\s+token\s*=\s*"([^"]+)"')
+
+    def __init__(
+        self,
+        config: FetcherConfig,
+        cookies: dict[str, str] | None = None,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__("ixdzs8", 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.
+        """
+        url = self.book_info_url(book_id=book_id)
+        data = {"bid": book_id}
+        info_html, clist_response = await asyncio.gather(
+            self.fetch_verified_html(url, **kwargs),
+            self.post(self.BOOK_CATALOG_URL, data),
+        )
+        catalog_html = await clist_response.text()
+        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.
+        """
+        url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
+        return [await self.fetch_verified_html(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)
+
+    async def fetch_verified_html(self, url: str, **kwargs: Any) -> str:
+        """
+        Automatically solving the browser verification challenge if required.
+        """
+        resp = await self.fetch(url, **kwargs)
+
+        if "正在验证浏览器" not in resp:
+            return resp
+
+        token_match = self._TOKEN_PATTERN.search(resp)
+        if not token_match:
+            raise ValueError("Token not found in page HTML.")
+        token_value = token_match.group(1)
+
+        challenge_url = f"{url}?challenge={token_value}"
+        _ = await self.fetch(challenge_url, **kwargs)
+        return await self.fetch(url, **kwargs)

novel_downloader/core/fetchers/jpxs123.py

@@ -0,0 +1,101 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.jpxs123
+--------------------------------------
+
+"""
+
+from typing import Any
+
+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
+
+
+@register_fetcher(
+    site_keys=["jpxs123"],
+)
+class Jpxs123Session(BaseSession):
+    """
+    A session class for interacting with the 精品小说网 (www.jpxs123.com) novel website.
+    """
+
+    BASE_URL = "https://www.jpxs123.com"
+    BOOK_INFO_URL = "https://www.jpxs123.com/{book_id}.html"
+    CHAPTER_URL = "https://www.jpxs123.com/{book_id}/{chapter_id}.html"
+
+    def __init__(
+        self,
+        config: FetcherConfig,
+        cookies: dict[str, str] | None = None,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__("jpxs123", 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, download]
+
+        :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)
+        info_html = await self.fetch(url, **kwargs)
+        try:
+            info_tree = html.fromstring(info_html)
+            txt_link = info_tree.xpath(
+                '//div[@class="booktips"]//a[contains(text(), "txt下载")]/@href'
+            )
+            download_url = f"{self.BASE_URL}{txt_link[0]}" if txt_link else None
+        except Exception:
+            download_url = None
+
+        download_html = await self.fetch(download_url, **kwargs) if download_url else ""
+        return [info_html, download_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.
+        """
+        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/lewenn.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.lewenn
+-------------------------------------
+
+"""
+
+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=["lewenn", "lewen"],
+)
+class LewennSession(BaseSession):
+    """
+    A session class for interacting with the 乐文小说网 (www.lewenn.net) novel website.
+    """
+
+    BOOK_INFO_URL = "https://www.lewenn.net/{book_id}/"
+    CHAPTER_URL = "https://www.lewenn.net/{book_id}/{chapter_id}.html"
+
+    def __init__(
+        self,
+        config: FetcherConfig,
+        cookies: dict[str, str] | None = None,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__("lewenn", 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/{linovelib/session.py → linovelib.py}

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 """
-novel_downloader.core.fetchers.linovelib.session
-------------------------------------------------
+novel_downloader.core.fetchers.linovelib
+----------------------------------------
 
 """
 
@@ -11,16 +11,15 @@ 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_sleep_with_random_delay
+from novel_downloader.utils import async_jitter_sleep
 
 
 @register_fetcher(
     site_keys=["linovelib"],
-    backends=["session"],
 )
 class LinovelibSession(BaseSession):
     """
-    A session class for interacting with Linovelib (www.linovelib.com) novel website.
+    A session class for interacting with 哔哩轻小说 (www.linovelib.com) novel website.
     """
 
     BASE_URL = "https://www.linovelib.com"
@@ -47,8 +46,10 @@ class LinovelibSession(BaseSession):
         """
         Fetch the raw HTML of the book info page.
 
+        Order: [info, vol1_html, ..., volN_html]
+
         :param book_id: The book identifier.
-        :return: A list of HTML strings: [info_html, vol1_html, ..., volN_html]
+        :return: The page content as string list.
         """
         url = self.book_info_url(book_id=book_id)
         info_html = await self.fetch(url, **kwargs)
@@ -62,7 +63,7 @@ class LinovelibSession(BaseSession):
 
         vol_htmls = []
         for vol_id in vol_ids:
-            await async_sleep_with_random_delay(
+            await async_jitter_sleep(
                 self.request_interval,
                 mul_spread=1.1,
                 max_sleep=self.request_interval + 2,
@@ -98,9 +99,11 @@ class LinovelibSession(BaseSession):
         """
         Fetch the raw HTML of a single chapter asynchronously.
 
+        Order: [page1, ..., pageN]
+
         :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.
         """
         html_pages: list[str] = []
         idx = 1
@@ -126,7 +129,7 @@ class LinovelibSession(BaseSession):
 
             html_pages.append(html)
             idx += 1
-            await async_sleep_with_random_delay(
+            await async_jitter_sleep(
                 self.request_interval,
                 mul_spread=1.1,
                 max_sleep=self.request_interval + 2,
@@ -183,10 +186,6 @@ class LinovelibSession(BaseSession):
         """
         return f"/novel/{book_id}/{chapter_id}.html"
 
-    @property
-    def hostname(self) -> str:
-        return "www.linovelib.com"
-
     def _extract_vol_ids(self, html_str: str) -> list[str]:
         """
         Extract volume IDs (like 'vol_12345') from the info HTML.

novel_downloader/core/fetchers/piaotia.py

@@ -0,0 +1,105 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.piaotia
+--------------------------------------
+
+"""
+
+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=["piaotia"],
+)
+class PiaotiaSession(BaseSession):
+    """
+    A session class for interacting with the 飘天文学网 (www.piaotia.com) novel website.
+    """
+
+    BOOK_INFO_URL = "https://www.piaotia.com/bookinfo/{book_id}.html"
+    BOOK_CATALOG_URL = "https://www.piaotia.com/html/{book_id}/index.html"
+    CHAPTER_URL = "https://www.piaotia.com/html/{book_id}/{chapter_id}.html"
+
+    def __init__(
+        self,
+        config: FetcherConfig,
+        cookies: dict[str, str] | None = None,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__("piaotia", 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.
+        """
+        return cls.BOOK_INFO_URL.format(book_id=book_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)