novel-downloader 1.3.2__py3-none-any.whl → 1.4.0__py3-none-any.whl

novel_downloader/core/interfaces/sync_downloader.py

@@ -1,36 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.interfaces.sync_downloader
-------------------------------------------------
-
-This module defines the SyncDownloaderProtocol, a structural interface
-that outlines the expected behavior of any downloader class.
-"""
-
-from typing import Protocol
-
-
-class SyncDownloaderProtocol(Protocol):
-    """
-    Protocol for downloader classes.
-
-    Defines the expected interface for any downloader implementation,
-    including both batch and single book downloads,
-    as well as optional pre-download hooks.
-    """
-
-    def download(self, book_ids: list[str]) -> None:
-        """
-        Batch download entry point.
-
-        :param book_ids: List of book IDs to download.
-        """
-        ...
-
-    def download_one(self, book_id: str) -> None:
-        """
-        Download logic for a single book.
-
-        :param book_id: The identifier of the book.
-        """
-        ...

novel_downloader/core/interfaces/sync_requester.py

@@ -1,82 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.interfaces.sync_requester
------------------------------------------------
-
-Defines the RequesterProtocol interface for fetching raw HTML or JSON
-for book info pages, individual chapters, managing request lifecycle,
-and optionally retrieving a user's authenticated bookcase.
-"""
-
-from typing import Any, Literal, Protocol, runtime_checkable
-
-
-@runtime_checkable
-class SyncRequesterProtocol(Protocol):
-    """
-    A requester must be able to fetch raw HTML/data for:
-      - a book's info page,
-      - a specific chapter page.
-    """
-
-    def is_async(self) -> Literal[False]:
-        ...
-
-    def login(
-        self,
-        username: str = "",
-        password: str = "",
-        manual_login: bool = False,
-        **kwargs: Any,
-    ) -> bool:
-        """
-        Attempt to log in
-        """
-        ...
-
-    def get_book_info(
-        self,
-        book_id: str,
-        **kwargs: Any,
-    ) -> list[str]:
-        """
-        Fetch the raw HTML (or JSON) of the book info page.
-
-        :param book_id: The book identifier.
-        :return: The page content as a string.
-        """
-        ...
-
-    def get_book_chapter(
-        self,
-        book_id: str,
-        chapter_id: str,
-        **kwargs: Any,
-    ) -> list[str]:
-        """
-        Fetch the raw HTML (or JSON) of a single chapter.
-
-        :param book_id: The book identifier.
-        :param chapter_id: The chapter identifier.
-        :return: The chapter content as a string.
-        """
-        ...
-
-    def get_bookcase(
-        self,
-        page: int = 1,
-        **kwargs: Any,
-    ) -> list[str]:
-        """
-        Optional: Retrieve the HTML content of the authenticated user's bookcase page.
-
-        :param page: Page idx
-        :return: The HTML markup of the bookcase page.
-        """
-        ...
-
-    def close(self) -> None:
-        """
-        Shutdown and cleans up resources.
-        """
-        ...

novel_downloader/core/parsers/qidian/browser/__init__.py

@@ -1,12 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.parsers.qidian.browser
---------------------------------------------
-
-This package provides parsing components for handling Qidian
-pages that have been rendered by a browser engine.
-"""
-
-from .main_parser import QidianBrowserParser
-
-__all__ = ["QidianBrowserParser"]

novel_downloader/core/parsers/qidian/browser/chapter_normal.py

@@ -1,93 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.parsers.qidian.browser.chapter_normal
------------------------------------------------------------
-
-Parser logic for extracting readable text from Qidian chapters
-that use plain (non-encrypted) browser-rendered HTML.
-"""
-
-import logging
-
-from bs4 import BeautifulSoup
-
-from novel_downloader.utils.chapter_storage import ChapterDict
-
-from ..shared import (
-    extract_chapter_info,
-    find_ssr_page_context,
-)
-
-logger = logging.getLogger(__name__)
-
-
-def parse_normal_chapter(
-    soup: BeautifulSoup,
-    chapter_id: str,
-) -> ChapterDict | None:
-    """
-    Extract and format the chapter text from a normal Qidian page.
-    Returns empty string if VIP/encrypted.
-
-    This method performs the following steps:
-      1. Parses HTML into soup.
-      2. Skips parsing if VIP or encrypted.
-      3. Locates main content container.
-      4. Extracts SSR-rendered chapter info (title, author note).
-      5. Removes review spans.
-      6. Extracts paragraph texts and formats them.
-
-    :param html_str: Raw HTML content of the chapter page.
-    :return: Formatted chapter text or empty string if not parsable.
-    """
-    try:
-        main = soup.select_one("div#app div#reader-content main")
-        if not main:
-            logger.warning("[Parser] Main content not found for chapter")
-            return None
-
-        ssr_data = find_ssr_page_context(soup)
-        chapter_info = extract_chapter_info(ssr_data)
-        if not chapter_info:
-            logger.warning(
-                "[Parser] ssr_chapterInfo not found for chapter '%s'", chapter_id
-            )
-            return None
-
-        title = chapter_info.get("chapterName", "Untitled")
-        chapter_id = chapter_info.get("chapterId", "")
-        author_say = chapter_info.get("authorSay", "")
-        update_time = chapter_info.get("updateTime", "")
-        update_timestamp = chapter_info.get("updateTimestamp", 0)
-        modify_time = chapter_info.get("modifyTime", 0)
-        word_count = chapter_info.get("wordsCount", 0)
-        seq = chapter_info.get("seq", None)
-        volume = chapter_info.get("extra", {}).get("volumeName", "")
-
-        # remove review spans
-        for span in main.select("span.review"):
-            span.decompose()
-
-        paras = [p.get_text(strip=True) for p in main.find_all("p")]
-        chapter_text = "\n\n".join(paras)
-
-        return {
-            "id": str(chapter_id),
-            "title": title,
-            "content": chapter_text,
-            "extra": {
-                "author_say": author_say.strip() if author_say else "",
-                "updated_at": update_time,
-                "update_timestamp": update_timestamp,
-                "modify_time": modify_time,
-                "word_count": word_count,
-                "seq": seq,
-                "volume": volume,
-            },
-        }
-
-    except Exception as e:
-        logger.warning(
-            "[Parser] parse error for normal chapter '%s': %s", chapter_id, e
-        )
-    return None

novel_downloader/core/parsers/qidian/browser/chapter_router.py

@@ -1,71 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.parsers.qidian.browser.chapter_router
------------------------------------------------------------
-
-Routing logic for selecting the correct chapter parser for Qidian browser pages.
-
-This module acts as a dispatcher that analyzes a chapter's HTML content and
-routes the parsing task to either the encrypted or normal chapter parser.
-"""
-
-from __future__ import annotations
-
-import logging
-from typing import TYPE_CHECKING
-
-from novel_downloader.utils.chapter_storage import ChapterDict
-
-from ..shared import (
-    can_view_chapter,
-    html_to_soup,
-    is_encrypted,
-)
-from .chapter_normal import parse_normal_chapter
-
-if TYPE_CHECKING:
-    from .main_parser import QidianBrowserParser
-
-logger = logging.getLogger(__name__)
-
-
-def parse_chapter(
-    parser: QidianBrowserParser,
-    html_str: str,
-    chapter_id: str,
-) -> ChapterDict | None:
-    """
-    Extract and return the formatted textual content of chapter.
-
-    :param parser: Instance of QidianBrowserParser.
-    :param html_str: Raw HTML content of the chapter page.
-    :param chapter_id: Identifier of the chapter being parsed.
-    :return: Formatted chapter text or empty string if not parsable.
-    """
-    try:
-        soup = html_to_soup(html_str)
-
-        if not can_view_chapter(soup):
-            logger.warning(
-                "[Parser] Chapter '%s' is not purchased or inaccessible.", chapter_id
-            )
-            return None
-
-        if is_encrypted(soup):
-            if not parser._decode_font:
-                return None
-            try:
-                from .chapter_encrypted import parse_encrypted_chapter
-
-                return parse_encrypted_chapter(parser, soup, chapter_id)
-            except ImportError:
-                logger.warning(
-                    "[Parser] Encrypted chapter '%s' requires extra dependencies.",
-                    chapter_id,
-                )
-                return None
-
-        return parse_normal_chapter(soup, chapter_id)
-    except Exception as e:
-        logger.warning("[Parser] parse error for chapter '%s': %s", chapter_id, e)
-    return None

novel_downloader/core/parsers/qidian/session/__init__.py

@@ -1,12 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.parsers.qidian.session
---------------------------------------------
-
-This package provides parsing components for handling Qidian
-pages that have been rendered by a session.
-"""
-
-from .main_parser import QidianSessionParser
-
-__all__ = ["QidianSessionParser"]