novel-downloader 1.5.0__py3-none-any.whl → 2.0.0__py3-none-any.whl

novel_downloader/core/fetchers/shuhaige.py

@@ -0,0 +1,84 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.shuhaige
+---------------------------------------
+
+"""
+
+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=["shuhaige"],
+)
+class ShuhaigeSession(BaseSession):
+    """
+    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,
+        config: FetcherConfig,
+        cookies: dict[str, str] | None = None,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__("shuhaige", 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/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/wanbengo.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.wanbengo
+---------------------------------------
+
+"""
+
+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=["wanbengo"],
+)
+class WanbengoSession(BaseSession):
+    """
+    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,
+        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)]
+
+    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/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)

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"