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

novel_downloader/core/fetchers/sfacg/browser.py

@@ -1,194 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.fetchers.sfacg.browser
---------------------------------------------
-
-"""
-
-from typing import Any
-
-from novel_downloader.core.fetchers.base import BaseBrowser
-from novel_downloader.core.fetchers.registry import register_fetcher
-from novel_downloader.models import FetcherConfig, LoginField
-from novel_downloader.utils.i18n import t
-
-
-@register_fetcher(
-    site_keys=["sfacg"],
-    backends=["browser"],
-)
-class SfacgBrowser(BaseBrowser):
-    """
-    A browser class for interacting with the Sfacg (m.sfacg.com) novel website.
-    """
-
-    LOGIN_URL = "https://m.sfacg.com/login"
-    BOOKCASE_URL = "https://m.sfacg.com/sheets/"
-    BOOK_INFO_URL = "https://m.sfacg.com/b/{book_id}/"
-    BOOK_CATALOG_URL = "https://m.sfacg.com/i/{book_id}/"
-    CHAPTER_URL = "https://m.sfacg.com/c/{chapter_id}/"
-
-    def __init__(
-        self,
-        config: FetcherConfig,
-        reuse_page: bool = False,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("sfacg", config, reuse_page, **kwargs)
-
-    async def login(
-        self,
-        username: str = "",
-        password: str = "",
-        cookies: dict[str, str] | None = None,
-        attempt: int = 1,
-        **kwargs: Any,
-    ) -> bool:
-        self._is_logged_in = await self._check_login_status()
-        return self._is_logged_in
-
-    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 a string.
-        """
-        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)
-
-        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 chapter content as a string.
-        """
-        url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
-        return [await self.fetch(url, **kwargs)]
-
-    async def get_bookcase(
-        self,
-        **kwargs: Any,
-    ) -> list[str]:
-        """
-        Retrieve the user's *bookcase* page.
-
-        :return: The HTML markup of the bookcase page.
-        """
-        url = self.bookcase_url()
-        return [await self.fetch(url, **kwargs)]
-
-    async def set_interactive_mode(self, enable: bool) -> bool:
-        """
-        Enable or disable interactive mode for manual login.
-
-        :param enable: True to enable, False to disable interactive mode.
-        :return: True if operation or login check succeeded, False otherwise.
-        """
-        if enable:
-            if self.headless:
-                await self._restart_browser(headless=False)
-            if self._manual_page is None:
-                self._manual_page = await self.context.new_page()
-            await self._manual_page.goto(self.LOGIN_URL)
-            return True
-
-        # restore
-        if self._manual_page:
-            await self._manual_page.close()
-        self._manual_page = None
-        if self.headless:
-            await self._restart_browser(headless=True)
-            self._is_logged_in = await self._check_login_status()
-        return self.is_logged_in
-
-    @property
-    def login_fields(self) -> list[LoginField]:
-        return [
-            LoginField(
-                name="manual_login",
-                label="手动登录",
-                type="manual_login",
-                required=True,
-                description=t("login_prompt_intro"),
-            )
-        ]
-
-    @classmethod
-    def bookcase_url(cls) -> str:
-        """
-        Construct the URL for the user's bookcase page.
-
-        :return: Fully qualified URL of the bookcase.
-        """
-        return cls.BOOKCASE_URL
-
-    @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(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
-        inspecting the bookcase page content.
-
-        :return: True if the user is logged in, False otherwise.
-        """
-        keywords = [
-            "请输入用户名和密码",
-            "用户未登录",
-            "可输入用户名",
-        ]
-        resp_text = await self.get_bookcase()
-        if not resp_text:
-            return False
-        return not any(kw in resp_text[0] for kw in keywords)

novel_downloader/core/fetchers/yamibo/__init__.py

@@ -1,14 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.fetchers.yamibo
--------------------------------------
-
-"""
-
-__all__ = [
-    "YamiboBrowser",
-    "YamiboSession",
-]
-
-from .browser import YamiboBrowser
-from .session import YamiboSession

novel_downloader/core/fetchers/yamibo/browser.py

@@ -1,234 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.fetchers.yamibo.browser
----------------------------------------------
-
-"""
-
-from typing import Any
-
-from novel_downloader.core.fetchers.base import BaseBrowser
-from novel_downloader.core.fetchers.registry import register_fetcher
-from novel_downloader.models import FetcherConfig, LoginField
-
-
-@register_fetcher(
-    site_keys=["yamibo"],
-    backends=["browser"],
-)
-class YamiboBrowser(BaseBrowser):
-    """
-    A browser class for interacting with the Yamibo (www.yamibo.com) novel website.
-    """
-
-    BASE_URL = "https://www.yamibo.com"
-    BOOKCASE_URL = "https://www.yamibo.com/my/fav"
-    BOOK_INFO_URL = "https://www.yamibo.com/novel/{book_id}"
-    CHAPTER_URL = "https://www.yamibo.com/novel/view-chapter?id={chapter_id}"
-
-    LOGIN_URL = "https://www.yamibo.com/user/login"
-
-    def __init__(
-        self,
-        config: FetcherConfig,
-        reuse_page: bool = False,
-        **kwargs: Any,
-    ) -> None:
-        super().__init__("yamibo", config, reuse_page, **kwargs)
-
-    async def login(
-        self,
-        username: str = "",
-        password: str = "",
-        cookies: dict[str, str] | None = None,
-        attempt: int = 1,
-        **kwargs: Any,
-    ) -> bool:
-        self._is_logged_in = await self._check_login_status()
-        if self._is_logged_in:
-            return True
-
-        if not (username and password):
-            self.logger.warning("[auth] No credentials provided.")
-            return False
-
-        for i in range(1, attempt + 1):
-            login_page = await self.context.new_page()
-            try:
-                await login_page.goto(self.LOGIN_URL, wait_until="networkidle")
-
-                await login_page.fill("#loginform-username", username)
-                await login_page.fill("#loginform-password", password)
-
-                before_url = login_page.url
-                await login_page.click('button[name="login-button"]')
-
-                try:
-                    await login_page.wait_for_url(
-                        lambda url, before_url=before_url: url_changed(url, before_url),
-                        timeout=15000,
-                    )
-                except Exception as e:
-                    self.logger.debug(
-                        f"[auth] No URL change after login attempt {i}: {e}"
-                    )
-
-                self._is_logged_in = await self._check_login_status()
-                if self._is_logged_in:
-                    self.logger.info(f"[auth] Login successful on attempt {i}.")
-                    return True
-                else:
-                    self.logger.warning(
-                        f"[auth] Login check failed after attempt {i}. Retrying..."
-                    )
-
-            except Exception as e:
-                self.logger.error(
-                    f"[auth] Unexpected error during login attempt {i}: {e}"
-                )
-            finally:
-                await login_page.close()
-
-        self.logger.error(f"[auth] Login failed after {attempt} attempt(s).")
-        return False
-
-    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 a string.
-        """
-        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 chapter content as a string.
-        """
-        url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
-        return [await self.fetch(url, **kwargs)]
-
-    async def get_bookcase(
-        self,
-        **kwargs: Any,
-    ) -> list[str]:
-        """
-        Retrieve the user's *bookcase* page.
-
-        :return: The HTML markup of the bookcase page.
-        """
-        url = self.bookcase_url()
-        return [await self.fetch(url, **kwargs)]
-
-    async def set_interactive_mode(self, enable: bool) -> bool:
-        """
-        Enable or disable interactive mode for manual login.
-
-        :param enable: True to enable, False to disable interactive mode.
-        :return: True if operation or login check succeeded, False otherwise.
-        """
-        if enable:
-            if self.headless:
-                await self._restart_browser(headless=False)
-            if self._manual_page is None:
-                self._manual_page = await self.context.new_page()
-            await self._manual_page.goto(self.LOGIN_URL)
-            return True
-
-        # restore
-        if self._manual_page:
-            await self._manual_page.close()
-        self._manual_page = None
-        if self.headless:
-            await self._restart_browser(headless=True)
-            self._is_logged_in = await self._check_login_status()
-        return self.is_logged_in
-
-    @property
-    def login_fields(self) -> list[LoginField]:
-        return [
-            LoginField(
-                name="username",
-                label="用户名",
-                type="text",
-                required=True,
-                placeholder="请输入你的用户名",
-                description="用于登录 www.yamibo.com 的用户名",
-            ),
-            LoginField(
-                name="password",
-                label="密码",
-                type="password",
-                required=True,
-                placeholder="请输入你的密码",
-                description="用于登录 www.yamibo.com 的密码",
-            ),
-        ]
-
-    @classmethod
-    def bookcase_url(cls) -> str:
-        """
-        Construct the URL for the user's bookcase page.
-
-        :return: Fully qualified URL of the bookcase.
-        """
-        return cls.BOOKCASE_URL
-
-    @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)
-
-    @property
-    def hostname(self) -> str:
-        return "www.yamibo.com"
-
-    async def _check_login_status(self) -> bool:
-        """
-        Check whether the user is currently logged in by
-        inspecting the bookcase page content.
-
-        :return: True if the user is logged in, False otherwise.
-        """
-        keywords = [
-            "登录 - 百合会",
-            "用户名/邮箱",
-        ]
-        resp_text = await self.get_bookcase()
-        if not resp_text:
-            return False
-        return not any(kw in resp_text[0] for kw in keywords)
-
-
-def url_changed(url: str, before: str) -> bool:
-    return url != before

novel_downloader/core/parsers/biquge.py

@@ -1,139 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.parsers.biquge
-------------------------------------
-
-"""
-
-import re
-from typing import Any
-
-from lxml import html
-
-from novel_downloader.core.parsers.base import BaseParser
-from novel_downloader.core.parsers.registry import register_parser
-from novel_downloader.models import ChapterDict
-
-
-@register_parser(
-    site_keys=["biquge", "bqg"],
-    backends=["session", "browser"],
-)
-class BiqugeParser(BaseParser):
-    """ """
-
-    def parse_book_info(
-        self,
-        html_list: list[str],
-        **kwargs: Any,
-    ) -> dict[str, Any]:
-        """
-        Parse a book info page and extract metadata and chapter structure.
-
-        :param html_list: Raw HTML of the book info page.
-        :return: Parsed metadata and chapter structure as a dictionary.
-        """
-        if not html_list:
-            return {}
-        tree = html.fromstring(html_list[0])
-        result: dict[str, Any] = {}
-
-        def extract_text(elem: html.HtmlElement | None) -> str:
-            if elem is None:
-                return ""
-            return "".join(elem.itertext(tag=None)).strip()
-
-        # 书名
-        book_name_elem = tree.xpath('//div[@id="info"]/h1')
-        result["book_name"] = extract_text(book_name_elem[0]) if book_name_elem else ""
-
-        # 作者
-        author_elem = tree.xpath('//div[@id="info"]/p[1]')
-        if author_elem:
-            author_text = extract_text(author_elem[0]).replace("\u00a0", "")
-            match = re.search(r"作\s*者[:：]?\s*(\S+)", author_text)
-            result["author"] = match.group(1).strip() if match else ""
-        else:
-            result["author"] = ""
-
-        # 封面
-        cover_elem = tree.xpath('//div[@id="fmimg"]/img/@src')
-        result["cover_url"] = cover_elem[0].strip() if cover_elem else ""
-
-        # 最后更新时间
-        update_elem = tree.xpath('//div[@id="info"]/p[3]')
-        if update_elem:
-            update_text = extract_text(update_elem[0])
-            match = re.search(r"最后更新[:：]\s*(\S+)", update_text)
-            result["update_time"] = match.group(1).strip() if match else ""
-        else:
-            result["update_time"] = ""
-
-        # 简介
-        intro_elem = tree.xpath('//div[@id="intro"]')
-        result["summary"] = extract_text(intro_elem[0]) if intro_elem else ""
-
-        # 卷和章节
-        chapters = []
-        in_main_volume = False
-
-        list_dl = tree.xpath('//div[@id="list"]/dl')[0]
-        for elem in list_dl:
-            if elem.tag == "dt":
-                text = "".join(elem.itertext()).strip()
-                in_main_volume = "正文" in text
-            elif in_main_volume and elem.tag == "dd":
-                a: list[html.HtmlElement] = elem.xpath("./a")
-                if a:
-                    title = "".join(a[0].itertext(tag=None)).strip()
-                    url = a[0].get("href", "").strip()
-                    href_cleaned = url.replace(".html", "")
-                    chapter_id_match = re.search(r"/(\d+)$", href_cleaned)
-                    chapter_id = chapter_id_match.group(1) if chapter_id_match else ""
-                    chapters.append(
-                        {"title": title, "url": url, "chapterId": chapter_id}
-                    )
-
-        result["volumes"] = [{"volume_name": "正文", "chapters": chapters}]
-
-        return result
-
-    def parse_chapter(
-        self,
-        html_list: list[str],
-        chapter_id: str,
-        **kwargs: Any,
-    ) -> ChapterDict | None:
-        """
-        Parse a single chapter page and extract clean text or simplified HTML.
-
-        :param html_list: Raw HTML of the chapter page.
-        :param chapter_id: Identifier of the chapter being parsed.
-        :return: Cleaned chapter content as plain text or minimal HTML.
-        """
-        if not html_list:
-            return None
-        tree = html.fromstring(html_list[0], parser=None)
-
-        # 提取标题
-        title_elem = tree.xpath('//div[@class="bookname"]/h1')
-        title = "".join(title_elem[0].itertext()).strip() if title_elem else ""
-        if not title:
-            title = f"第 {chapter_id} 章"
-
-        # 提取内容
-        content_elem = tree.xpath('//div[@id="content"]')
-        paragraphs = content_elem[0].xpath(".//p") if content_elem else []
-        paragraph_texts = [
-            "".join(p.itertext()).strip() for p in paragraphs if p is not None
-        ]
-        content = "\n\n".join([p for p in paragraph_texts if p])
-        if not content.strip():
-            return None
-
-        return {
-            "id": chapter_id,
-            "title": title,
-            "content": content,
-            "extra": {"site": "biquge"},
-        }

novel_downloader/core/parsers/qidian/book_info_parser.py

@@ -1,90 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.parsers.qidian.book_info_parser
------------------------------------------------------
-
-This module provides parsing of Qidian book info pages.
-
-It extracts metadata such as title, author, cover URL, update
-time, status, word count, summary, and volume-chapter structure.
-"""
-
-import logging
-import re
-from datetime import datetime
-from typing import Any
-
-from lxml import html
-
-logger = logging.getLogger(__name__)
-
-
-def _chapter_url_to_id(url: str) -> str:
-    return url.rstrip("/").split("/")[-1]
-
-
-def parse_book_info(html_str: str) -> dict[str, Any]:
-    """
-    Extract metadata: title, author, cover_url, update_time, status,
-    word_count, summary, and volumes with chapters.
-
-    :param html_str: Raw HTML of the book info page.
-    :return: A dict containing book metadata.
-    """
-    info: dict[str, Any] = {}
-    try:
-        doc = html.fromstring(html_str)
-
-        info["book_name"] = doc.xpath('string(//h1[@id="bookName"])').strip()
-
-        info["author"] = doc.xpath('string(//a[@class="writer-name"])').strip()
-
-        book_id = doc.xpath('//a[@id="bookImg"]/@data-bid')[0]
-        info[
-            "cover_url"
-        ] = f"https://bookcover.yuewen.com/qdbimg/349573/{book_id}/600.webp"
-
-        ut = (
-            doc.xpath('string(//span[@class="update-time"])')
-            .replace("更新时间:", "")
-            .strip()
-        )
-        if re.match(r"^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}$", ut):
-            info["update_time"] = ut
-        else:
-            info["update_time"] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-
-        info["serial_status"] = doc.xpath(
-            'string(//p[@class="book-attribute"]/span[1])'
-        ).strip()
-
-        tags = doc.xpath('//p[contains(@class,"all-label")]//a/text()')
-        info["tags"] = [t.strip() for t in tags if t.strip()]
-
-        info["word_count"] = doc.xpath('string(//p[@class="count"]/em[1])').strip()
-
-        summary = doc.xpath('string(//p[@class="intro"])').strip()
-        info["summary_brief"] = summary
-
-        raw = doc.xpath('//p[@id="book-intro-detail"]//text()')
-        info["summary"] = "\n".join(line.strip() for line in raw if line.strip())
-
-        volumes = []
-        for vol in doc.xpath('//div[@id="allCatalog"]//div[@class="catalog-volume"]'):
-            vol_name = vol.xpath('string(.//h3[@class="volume-name"])').strip()
-            vol_name = vol_name.split(chr(183))[0].strip()
-            chapters = []
-            for li in vol.xpath('.//ul[contains(@class,"volume-chapters")]/li'):
-                a = li.xpath('.//a[@class="chapter-name"]')[0]
-                title = a.text.strip()
-                url = a.get("href")
-                chapters.append(
-                    {"title": title, "url": url, "chapterId": _chapter_url_to_id(url)}
-                )
-            volumes.append({"volume_name": vol_name, "chapters": chapters})
-        info["volumes"] = volumes
-
-    except Exception as e:
-        logger.warning("[Parser] Error parsing book info: %s", e)
-
-    return info