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

novel_downloader/core/fetchers/xiguashuwu.py

@@ -0,0 +1,177 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.xiguashuwu
+-----------------------------------------
+
+"""
+
+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(
+    site_keys=["xiguashuwu"],
+)
+class XiguashuwuSession(BaseSession):
+    """
+    A session class for interacting with the 西瓜书屋 (www.xiguashuwu.com) novel.
+    """
+
+    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,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Fetch the raw HTML of the book info page asynchronously.
+
+        Order: [info, catalogs1, ..., catalogsN]
+
+        :param book_id: The book identifier.
+        :return: The page content as string list.
+        """
+        info_url = self.book_info_url(book_id=book_id)
+        info_html = await self.fetch(info_url, **kwargs)
+
+        catalog_url = self.book_catalog_url(book_id=book_id)
+        catalog_pages: list[str] = []
+        idx = 1
+        while True:
+            suffix = "" if idx == 1 else f"{idx}.html"
+            full_url = catalog_url + suffix
+
+            try:
+                html = await self.fetch(full_url, **kwargs)
+            except Exception as exc:
+                self.logger.warning(
+                    "[async] get_book_catalog(%s page %d) failed: %s",
+                    book_id,
+                    idx,
+                    exc,
+                )
+                break
+
+            catalog_pages.append(html)
+            idx += 1
+            next_patterns = [
+                # f"javascript:readbook('{book_id}','{idx}');",
+                # f"javascript:gobook('{book_id}','{idx}');",
+                # f"javascript:runbook('{book_id}','{idx}');",
+                # f"javascript:gotochapter('{book_id}','{idx}');",
+                f"javascript:readbookjump('{book_id}','{idx}');",
+                f"javascript:gobookjump('{book_id}','{idx}');",
+                f"javascript:runbookjump('{book_id}','{idx}');",
+                f"javascript:gotojump('{book_id}','{idx}');",
+                f"javascript:gotochapterjump('{book_id}','{idx}');",
+                f"/book/{book_id}/catalog/{idx}.html",
+            ]
+            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,
+            )
+        return [info_html, *catalog_pages]
+
+    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.
+
+        Order: [page1, ..., pageN]
+
+        :param book_id: The book identifier.
+        :param chapter_id: The chapter identifier.
+        :return: The page content as string list.
+        """
+        html_pages: list[str] = []
+        idx = 1
+
+        while True:
+            chapter_suffix = chapter_id if idx == 1 else f"{chapter_id}_{idx}"
+            relative_path = self.relative_chapter_url(book_id, chapter_suffix)
+            if idx > 1 and relative_path not in html_pages[-1]:
+                break
+            full_url = self.BASE_URL + relative_path
+
+            try:
+                html = await self.fetch(full_url, **kwargs)
+            except Exception as exc:
+                self.logger.warning(
+                    "[async] get_book_chapter(%s page %d) failed: %s",
+                    chapter_id,
+                    idx,
+                    exc,
+                )
+                break
+
+            html_pages.append(html)
+            idx += 1
+            await async_jitter_sleep(
+                self.request_interval,
+                mul_spread=1.1,
+                max_sleep=self.request_interval + 2,
+            )
+
+        return html_pages
+
+    @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)
+
+    @classmethod
+    def relative_chapter_url(cls, book_id: str, chapter_id: str) -> str:
+        """
+        Return the relative URL path for a given chapter.
+        """
+        return f"/book/{book_id}/{chapter_id}.html"

novel_downloader/core/fetchers/xs63b.py

@@ -0,0 +1,171 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.xs63b
+------------------------------------
+
+"""
+
+import asyncio
+import base64
+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
+from novel_downloader.utils import async_jitter_sleep
+
+
+@register_fetcher(
+    site_keys=["xs63b"],
+)
+class Xs63bSession(BaseSession):
+    """
+    A session class for interacting with the 小说路上 (m.xs63b.com) novel website.
+    """
+
+    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"
+
+    _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,
+        **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.
+
+        Order: [page1, ..., pageN]
+
+        :param book_id: The book identifier.
+        :param chapter_id: The chapter identifier.
+        :return: The page content as string list.
+        """
+        book_id = book_id.replace("-", "/")
+        html_pages: list[str] = []
+        chapter_url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
+
+        while True:
+            try:
+                html = await self.fetch(chapter_url, **kwargs)
+            except Exception as exc:
+                self.logger.warning(
+                    "[async] get_book_chapter(%s page %d) failed: %s",
+                    chapter_url,
+                    exc,
+                )
+                break
+
+            html_pages.append(html)
+            if "/xs635/mobile/images/nextpage.png" not in html:
+                break
+
+            jsarr = self._parse_jsarr(html)
+            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,
+            )
+
+        return html_pages
+
+    @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)
+
+    @classmethod
+    def _parse_jsarr(cls, text: str) -> list[int]:
+        """
+        Extract jsarr from `var jsarr = [...];`.
+
+        Raises ValueError if not found.
+        """
+        m = cls._JSARR_PATTERN.search(text)
+        if not m:
+            raise ValueError("jsarr not found")
+        return [int(x) for x in m.group(1).split(",")]
+
+    @classmethod
+    def _parse_jsstr(cls, text: str) -> str:
+        """
+        Extract jsstr from `var jsstr = "...";`.
+
+        Raises ValueError if not found.
+        """
+        m = cls._JSSTR_PATTERN.search(text)
+        if not m:
+            raise ValueError("jsstr not found")
+        return m.group(1)
+
+    @staticmethod
+    def _build_chapter_url(book_id: str, jsarr: list[int], jsstr: str) -> str:
+        decoded = base64.b64decode(jsstr).decode("utf-8")
+        nnarr = list(decoded)
+        nnstr = "".join(nnarr[i] for i in jsarr)
+        return f"https://m.xs63b.com/{book_id}/{nnstr}.html"

novel_downloader/core/fetchers/xshbook.py

@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.xshbook
+--------------------------------------
+
+"""
+
+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=["xshbook"],
+)
+class XshbookSession(BaseSession):
+    """
+    A session class for interacting with the 小说虎 (www.xshbook.com) novel website.
+    """
+
+    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)]
+
+    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/{yamibo/session.py → yamibo.py}

@@ -1,22 +1,27 @@
 #!/usr/bin/env python3
 """
-novel_downloader.core.fetchers.yamibo.session
----------------------------------------------
+novel_downloader.core.fetchers.yamibo
+-------------------------------------
 
 """
 
+from collections.abc import Mapping
 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, LoginField
-from novel_downloader.utils.time_utils import async_sleep_with_random_delay
+from novel_downloader.utils import async_jitter_sleep
 
 
+@register_fetcher(
+    site_keys=["yamibo"],
+)
 class YamiboSession(BaseSession):
     """
-    A session class for interacting with the Yamibo (www.yamibo.com) novel website.
+    A session class for interacting with the 百合会 (www.yamibo.com) novel website.
     """
 
     BASE_URL = "https://www.yamibo.com"
@@ -64,7 +69,7 @@ class YamiboSession(BaseSession):
             ):
                 self._is_logged_in = True
                 return True
-            await async_sleep_with_random_delay(
+            await async_jitter_sleep(
                 self.backoff_factor,
                 mul_spread=1.1,
                 max_sleep=self.backoff_factor + 2,
@@ -82,7 +87,7 @@ class YamiboSession(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)]
@@ -98,7 +103,7 @@ class YamiboSession(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)]
@@ -166,10 +171,6 @@ class YamiboSession(BaseSession):
         """
         return cls.CHAPTER_URL.format(book_id=book_id, chapter_id=chapter_id)
 
-    @property
-    def hostname(self) -> str:
-        return "www.yamibo.com"
-
     async def _api_login(self, username: str, password: str) -> bool:
         """
         Login to the API using a 2-step token-based process.
@@ -227,3 +228,14 @@ class YamiboSession(BaseSession):
         if not resp_text:
             return False
         return not any(kw in resp_text[0] for kw in keywords)
+
+    @staticmethod
+    def _filter_cookies(
+        raw_cookies: list[Mapping[str, Any]],
+    ) -> dict[str, str]:
+        ALLOWED_DOMAINS = {"www.yamibo.com", "bbs.yamibo.com", ""}
+        return {
+            c["name"]: c["value"]
+            for c in raw_cookies
+            if c.get("domain", "") in ALLOWED_DOMAINS
+        }

novel_downloader/core/fetchers/yibige.py

@@ -0,0 +1,114 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.yibige
+-------------------------------------
+
+"""
+
+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=["yibige"],
+)
+class YibigeSession(BaseSession):
+    """
+    A session class for interacting with the 一笔阁 (www.yibige.org) novel website.
+    """
+
+    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,
+        **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.
+        """
+        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),
+            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.
+        """
+        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 book_catalog_url(cls, base_url: str, 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(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/interfaces/__init__.py

@@ -3,25 +3,19 @@
 novel_downloader.core.interfaces
 --------------------------------
 
-This package centralizes the protocol definitions used across the
-system to promote interface-based design and type-safe dependency
-injection.
-
-Included protocols:
-- DownloaderProtocol
-- FetcherProtocol
-- ParserProtocol
-- ExporterProtocol
+Protocol interfaces defining the contracts for core components.
 """
 
-from .downloader import DownloaderProtocol
-from .exporter import ExporterProtocol
-from .fetcher import FetcherProtocol
-from .parser import ParserProtocol
-
 __all__ = [
     "DownloaderProtocol",
     "ExporterProtocol",
     "FetcherProtocol",
     "ParserProtocol",
+    "SearcherProtocol",
 ]
+
+from .downloader import DownloaderProtocol
+from .exporter import ExporterProtocol
+from .fetcher import FetcherProtocol
+from .parser import ParserProtocol
+from .searcher import SearcherProtocol