novel-downloader 2.0.0__py3-none-any.whl → 2.0.2__py3-none-any.whl

novel_downloader/core/fetchers/esjzone.py

@@ -11,8 +11,7 @@ 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
-from novel_downloader.utils import async_jitter_sleep
+from novel_downloader.models import LoginField
 
 
 @register_fetcher(
@@ -23,6 +22,8 @@ class EsjzoneSession(BaseSession):
     A session class for interacting with the ESJ Zone (www.esjzone.cc) novel website.
     """
 
+    site_name: str = "esjzone"
+
     BOOKCASE_URL = "https://www.esjzone.cc/my/favorite"
     BOOK_INFO_URL = "https://www.esjzone.cc/detail/{book_id}.html"
     CHAPTER_URL = "https://www.esjzone.cc/forum/{book_id}/{chapter_id}.html"
@@ -30,13 +31,7 @@ class EsjzoneSession(BaseSession):
     API_LOGIN_URL_1 = "https://www.esjzone.cc/my/login"
     API_LOGIN_URL_2 = "https://www.esjzone.cc/inc/mem_login.php"
 
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("esjzone", config, cookies, **kwargs)
+    _TOKEN_RE = re.compile(r"<JinJing>(.*?)</JinJing>")
 
     async def login(
         self,
@@ -68,11 +63,7 @@ class EsjzoneSession(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
@@ -82,12 +73,6 @@ class EsjzoneSession(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)]
 
@@ -97,13 +82,6 @@ class EsjzoneSession(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)]
 
@@ -228,8 +206,7 @@ class EsjzoneSession(BaseSession):
         return not any(kw in resp_text[0] for kw in keywords)
 
     def _extract_token(self, text: str) -> str:
-        match = re.search(r"<JinJing>(.+?)</JinJing>", text)
-        return match.group(1) if match else ""
+        return m.group(1) if (m := self._TOKEN_RE.search(text)) else ""
 
     @staticmethod
     def _filter_cookies(

novel_downloader/core/fetchers/guidaye.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 GuidayeSession(BaseSession):
     A session class for interacting with the 名著阅读 (b.guidaye.com) novel website.
     """
 
+    site_name: str = "guidaye"
+
     BOOK_INFO_URL = "https://b.guidaye.com/{book_id}/"
     CHAPTER_URL = "https://b.guidaye.com/{book_id}/{chapter_id}.html"
 
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("guidaye", 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 GuidayeSession(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/hetushu.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(
@@ -20,34 +19,22 @@ class HetushuSession(BaseSession):
     A session class for interacting with the 和图书 (www.hetushu.com) novel website.
     """
 
+    site_name: str = "hetushu"
+    BASE_URL_MAP: dict[str, str] = {
+        "simplified": "www.hetushu.com",
+        "traditional": "www.hetubook.com",
+    }
+    DEFAULT_BASE_URL: str = "www.hetushu.com"
+
     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)
+        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(
@@ -56,15 +43,8 @@ class HetushuSession(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/fetchers/i25zw.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 I25zwSession(BaseSession):
     A session class for interacting with the 25中文网 (www.i25zw.com) novel website.
     """
 
+    site_name: str = "i25zw"
+
     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,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("i25zw", config, cookies, **kwargs)
-
     async def get_book_info(
         self,
         book_id: str,
@@ -61,13 +54,6 @@ class I25zwSession(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/ixdzs8.py

@@ -11,7 +11,6 @@ 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(
@@ -22,19 +21,13 @@ class Ixdzs8Session(BaseSession):
     A session class for interacting with the 爱下电子书 (ixdzs8.com) novel website.
     """
 
+    site_name: str = "ixdzs8"
+
     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,
@@ -63,13 +56,6 @@ class Ixdzs8Session(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_verified_html(url, **kwargs)]
 

novel_downloader/core/fetchers/jpxs123.py

@@ -11,7 +11,6 @@ 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(
@@ -22,18 +21,12 @@ class Jpxs123Session(BaseSession):
     A session class for interacting with the 精品小说网 (www.jpxs123.com) novel website.
     """
 
+    site_name: str = "jpxs123"
+
     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,
@@ -68,13 +61,6 @@ class Jpxs123Session(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/lewenn.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 LewennSession(BaseSession):
     A session class for interacting with the 乐文小说网 (www.lewenn.net) novel website.
     """
 
+    site_name: str = "lewenn"
+
     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)]
 
@@ -51,13 +38,6 @@ class LewennSession(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/linovelib.py

@@ -10,8 +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
-from novel_downloader.utils import async_jitter_sleep
 
 
 @register_fetcher(
@@ -22,6 +20,8 @@ class LinovelibSession(BaseSession):
     A session class for interacting with 哔哩轻小说 (www.linovelib.com) novel website.
     """
 
+    site_name: str = "linovelib"
+
     BASE_URL = "https://www.linovelib.com"
     BOOK_INFO_URL = "https://www.linovelib.com/novel/{book_id}.html"
     BOOK_CATALOG_UTL = "https://www.linovelib.com/novel/{book_id}/catalog"
@@ -30,14 +30,6 @@ class LinovelibSession(BaseSession):
 
     _VOL_ID_PATTERN: re.Pattern[str] = re.compile(r"/novel/\d+/(vol_\d+)\.html")
 
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("linovelib", config, cookies, **kwargs)
-
     async def get_book_info(
         self,
         book_id: str,
@@ -63,11 +55,7 @@ class LinovelibSession(BaseSession):
 
         vol_htmls = []
         for vol_id in vol_ids:
-            await async_jitter_sleep(
-                self.request_interval,
-                mul_spread=1.1,
-                max_sleep=self.request_interval + 2,
-            )
+            await self._sleep()
             html = await self.get_book_volume(book_id, vol_id, **kwargs)
             if html:
                 vol_htmls.append(html)
@@ -129,11 +117,7 @@ class LinovelibSession(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/{eightnovel.py → n8novel.py}

@@ -1,57 +1,42 @@
 #!/usr/bin/env python3
 """
-novel_downloader.core.fetchers.eightnovel
------------------------------------------
+novel_downloader.core.fetchers.n8novel
+--------------------------------------
 
 """
 
 import re
-from re import Pattern
 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=["8novel", "eightnovel"],
+    site_keys=["8novel", "n8novel"],
 )
-class EightnovelSession(BaseSession):
+class N8novelSession(BaseSession):
     """
     A session class for interacting with the 无限轻小说 (www.8novel.com) novel website.
     """
 
+    site_name: str = "n8novel"
+
     BOOK_INFO_URL = "https://www.8novel.com/novelbooks/{book_id}/"
     CHAPTER_URL = "https://article.8novel.com/read/{book_id}/?{chapter_id}"
     CHAPTER_CONTENT_URL = (
         "https://article.8novel.com/txt/1/{book_id}/{chapter_id}{seed_segment}.html"
     )
 
-    _SPLIT_STR_PATTERN = re.compile(
-        r'["\']([^"\']+)["\']\s*\.split\s*\(\s*["\']\s*,\s*["\']\s*\)', re.DOTALL
+    _SPLIT_DIGITS_PATTERN = re.compile(
+        r'["\'](\d+(?:,\d+)*)["\']\s*\.split\s*\(\s*["\']\s*,\s*["\']\s*\)', re.DOTALL
     )
-    _DIGIT_LIST_PATTERN: Pattern[str] = re.compile(r"^\d+(?:,\d+)*$")
-
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("eightnovel", 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)]
 
@@ -84,12 +69,6 @@ class EightnovelSession(BaseSession):
 
     @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
@@ -110,17 +89,10 @@ class EightnovelSession(BaseSession):
         of the form "...".split(","), pick the ones that may contain seed,
         and return the last value.
         """
-        split_literals: list[str] = cls._SPLIT_STR_PATTERN.findall(html_str)
-
-        numeric_lists = [
-            lit for lit in split_literals if cls._DIGIT_LIST_PATTERN.fullmatch(lit)
-        ]
-
-        if not numeric_lists:
-            return ""
-
-        last_list = numeric_lists[-1]
-        return last_list.split(",")[-1]
+        matches: list[str] = cls._SPLIT_DIGITS_PATTERN.findall(html_str)
+        if not matches:
+            raise ValueError("No digit lists found in HTML.")
+        return matches[-1].split(",")[-1]
 
     @classmethod
     def _build_chapter_content_url(

novel_downloader/core/fetchers/piaotia.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 PiaotiaSession(BaseSession):
     A session class for interacting with the 飘天文学网 (www.piaotia.com) novel website.
     """
 
+    site_name: str = "piaotia"
+
     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,
@@ -62,13 +55,6 @@ class PiaotiaSession(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/qbtr.py

@@ -11,7 +11,6 @@ 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(
@@ -22,18 +21,12 @@ class QbtrSession(BaseSession):
     A session class for interacting with the 全本同人小说 (www.qbtr.cc) novel website.
     """
 
+    site_name: str = "qbtr"
+
     BASE_URL = "https://www.qbtr.cc"
     BOOK_INFO_URL = "https://www.qbtr.cc/{book_id}.html"
     CHAPTER_URL = "https://www.qbtr.cc/{book_id}/{chapter_id}.html"
 
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("qbtr", config, cookies, **kwargs)
-
     async def get_book_info(
         self,
         book_id: str,
@@ -68,13 +61,6 @@ class QbtrSession(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/qianbi.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(
@@ -21,23 +20,12 @@ class QianbiSession(BaseSession):
     A session class for interacting with the 铅笔小说 (www.23qb.com) novel website.
     """
 
-    BASE_URLS = [
-        "www.23qb.com",
-        "www.23qb.net",
-    ]
+    site_name: str = "qianbi"
 
     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"
 
-    def __init__(
-        self,
-        config: FetcherConfig,
-        cookies: dict[str, str] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("qianbi", config, cookies, **kwargs)
-
     async def get_book_info(
         self,
         book_id: str,
@@ -66,13 +54,6 @@ class QianbiSession(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)]