novel-downloader 1.4.0__py3-none-any.whl → 1.4.2__py3-none-any.whl

novel_downloader/core/exporters/epub_utils/initializer.py

@@ -1,100 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.exporters.epub_utils.initializer
-------------------------------------------------------
-
-Initializes an epub.EpubBook object, sets metadata
-(identifier, title, author, language, description),
-adds a cover, and prepares the initial spine and TOC entries.
-"""
-
-import logging
-from pathlib import Path
-from typing import Any
-
-from ebooklib import epub
-
-from novel_downloader.utils.constants import (
-    EPUB_IMAGE_FOLDER,
-    EPUB_TEXT_FOLDER,
-    VOLUME_BORDER_IMAGE_PATH,
-)
-
-logger = logging.getLogger(__name__)
-
-
-def init_epub(
-    book_info: dict[str, Any],
-    book_id: str,
-    intro_html: str,
-    book_cover_path: Path | None = None,
-    include_toc: bool = False,
-) -> tuple[epub.EpubBook, list[Any], list[Any]]:
-    """
-    Initialize an EPUB book with metadata, optional cover, and intro page.
-
-    :param book_info: Dict with keys 'book_name', 'author', 'summary'.
-    :param book_id: Book identifier (numeric or string).
-    :param intro_html: Intro content in XHTML format.
-    :param book_cover_path: Optional Path to the cover image file.
-    :param include_toc: Whether to include the <nav> item in the spine.
-    :return: (book, spine, toc_list)
-    """
-    book = epub.EpubBook()
-    book.set_identifier(str(book_id))
-    book_name = book_info.get("book_name") or book_info.get("volume_name", "未找到书名")
-    book.set_title(book_name)
-    book.set_language("zh-CN")
-    book.add_author(book_info.get("author", "未找到作者"))
-    desc = book_info.get("summary") or book_info.get("volume_intro", "未找到作品简介")
-    book.add_metadata("DC", "description", desc)
-
-    spine = []
-
-    # cover
-    if book_cover_path:
-        try:
-            cover_bytes = book_cover_path.read_bytes()
-            ext = book_cover_path.suffix.lower()
-            ext = ext if ext in [".jpg", ".jpeg", ".png"] else ".jpeg"
-            filename = f"{EPUB_IMAGE_FOLDER}/cover{ext}"
-            book.set_cover(filename, cover_bytes)
-            spine.append("cover")
-        except FileNotFoundError:
-            logger.info(f"[epub] 封面图片不存在: {book_cover_path}")
-        except Exception as e:
-            logger.info(f"[epub] 读取封面失败: {book_cover_path}，错误：{e}")
-
-    # 导航菜单
-    if include_toc:
-        spine.append("nav")
-
-    # 简介页面
-    intro = epub.EpubHtml(
-        title="书籍简介",
-        file_name=f"{EPUB_TEXT_FOLDER}/intro.xhtml",
-        lang="zh-CN",
-        uid="intro",
-    )
-    intro.content = intro_html
-    intro.add_link(href="../Styles/main.css", rel="stylesheet", type="text/css")
-    book.add_item(intro)
-    spine.append(intro)
-
-    # 添加卷边框图像 (volume_border.png)
-    try:
-        border_bytes = VOLUME_BORDER_IMAGE_PATH.read_bytes()
-        border_item = epub.EpubItem(
-            uid="volume-border",
-            file_name=f"{EPUB_IMAGE_FOLDER}/volume_border.png",
-            media_type="image/png",
-            content=border_bytes,
-        )
-        book.add_item(border_item)
-    except FileNotFoundError:
-        logger.info(f"[epub] 卷边框图片不存在: {VOLUME_BORDER_IMAGE_PATH}")
-    except Exception as e:
-        logger.info(f"[epub] 读取卷边框失败: {VOLUME_BORDER_IMAGE_PATH}: {e}")
-
-    toc_list = [epub.Link(intro.file_name, "书籍简介", intro.id)]
-    return book, spine, toc_list

novel_downloader/core/exporters/epub_utils/text_to_html.py

@@ -1,178 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.exporters.epub_utils.text_to_html
--------------------------------------------------------
-
-Module for converting raw chapter text to formatted HTML,
-with automatic word correction and optional image/tag support.
-"""
-
-import json
-import logging
-import re
-from pathlib import Path
-from typing import Any
-
-from novel_downloader.utils.constants import (
-    EPUB_IMAGE_WRAPPER,
-    REPLACE_WORD_MAP_PATH,
-)
-from novel_downloader.utils.network import download_image
-from novel_downloader.utils.text_utils import diff_inline_display
-
-logger = logging.getLogger(__name__)
-
-_IMG_TAG_PATTERN = re.compile(
-    r'<img\s+[^>]*src=[\'"]([^\'"]+)[\'"][^>]*>', re.IGNORECASE
-)
-
-
-# Load and sort replacement map from JSON
-try:
-    replace_map_raw = REPLACE_WORD_MAP_PATH.read_text(encoding="utf-8")
-    REPLACE_WORDS_MAP = json.loads(replace_map_raw)
-    REPLACE_WORDS_MAP = dict(
-        sorted(REPLACE_WORDS_MAP.items(), key=lambda x: len(x[0]), reverse=True)
-    )
-except Exception as e:
-    REPLACE_WORDS_MAP = {}
-    logger.info(
-        f"[epub] Failed to load REPLACE_WORDS_MAP from {REPLACE_WORD_MAP_PATH}: {e}"
-    )
-
-
-def _check_and_correct_words(txt_str: str) -> str:
-    """
-    Perform word replacement using REPLACE_WORDS_MAP.
-
-    :param txt_str: Raw string of text.
-    :return: String with corrected words.
-    """
-    for k, v in REPLACE_WORDS_MAP.items():
-        txt_str = txt_str.replace(k, v)
-    return txt_str
-
-
-def chapter_txt_to_html(
-    chapter_title: str,
-    chapter_text: str,
-    author_say: str,
-) -> str:
-    """
-    Convert chapter text and author note to styled HTML.
-
-    :param chapter_title: Title of the chapter.
-    :param chapter_text: Main content of the chapter.
-    :param author_say: Optional author note content.
-    :return: Rendered HTML as a string.
-    """
-
-    def _render_lines(text: str) -> str:
-        parts = []
-        for line in text.strip().splitlines():
-            line = line.strip()
-            if not line:
-                continue
-
-            if (
-                line.startswith("<img")
-                and line.endswith("/>")
-                or line.startswith('<div class="duokan-image-single illus">')
-                and line.endswith("</div>")
-            ):
-                parts.append(line)
-            else:
-                corrected = _check_and_correct_words(line)
-                if corrected != line:
-                    diff = diff_inline_display(line, corrected)
-                    logger.info("[epub] Correction diff:\n%s", diff)
-                parts.append(f"<p>{corrected}</p>")
-        return "\n".join(parts)
-
-    html_parts = [f"<h2>{chapter_title}</h2>"]
-    html_parts.append(_render_lines(chapter_text))
-
-    if author_say.strip():
-        html_parts.extend(["<hr />", "<p>作者说:</p>", _render_lines(author_say)])
-
-    return "\n".join(html_parts)
-
-
-def inline_remote_images(
-    content: str,
-    image_dir: str | Path,
-) -> str:
-    """
-    Download every remote `<img src="...">` in `content` into `image_dir`,
-    and replace the original tag with EPUB_IMAGE_WRAPPER
-    pointing to the local filename.
-
-    :param content: HTML/text of the chapter containing <img> tags.
-    :param image_dir: Directory to save downloaded images into.
-    :return: Modified content with local image references.
-    """
-
-    def _replace(match: re.Match[str]) -> str:
-        url = match.group(1)
-        try:
-            # download_image returns a Path or None
-            local_path = download_image(
-                url, image_dir, target_name=None, on_exist="skip"
-            )
-            if not local_path:
-                logger.warning(
-                    "Failed to download image, leaving original tag: %s", url
-                )
-                return match.group(0)
-
-            # wrap with the EPUB_IMAGE_WRAPPER, inserting just the filename
-            return EPUB_IMAGE_WRAPPER.format(filename=local_path.name)
-        except Exception:
-            logger.exception("Error processing image URL: %s", url)
-            return match.group(0)
-
-    return _IMG_TAG_PATTERN.sub(_replace, content)
-
-
-def generate_book_intro_html(book_info: dict[str, Any]) -> str:
-    """
-    Generate HTML string for a book's information and summary.
-
-    This function takes a dictionary containing book details and formats
-    it into a styled HTML block, skipping any missing fields gracefully.
-
-    :param book_info: A dictionary containing keys like 'book_name'...
-
-    :return: An HTML-formatted string presenting the book's information.
-    """
-    book_name = book_info.get("book_name")
-    author = book_info.get("author")
-    serial_status = book_info.get("serial_status")
-    word_count = book_info.get("word_count")
-    summary = book_info.get("summary", "").strip()
-
-    # Start composing the HTML output
-    html_parts = ["<h1>书籍简介</h1>", '<div class="list">', "<ul>"]
-
-    if book_name:
-        html_parts.append(f"<li>书名: 《{book_name}》</li>")
-    if author:
-        html_parts.append(f"<li>作者: {author}</li>")
-
-    if word_count:
-        html_parts.append(f"<li>字数: {word_count}</li>")
-    if serial_status:
-        html_parts.append(f"<li>状态: {serial_status}</li>")
-
-    html_parts.append("</ul>")
-    html_parts.append("</div>")
-    html_parts.append('<p class="new-page-after"><br/></p>')
-
-    if summary:
-        html_parts.append("<h2>简介</h2>")
-        for paragraph in summary.split("\n"):
-            paragraph = paragraph.strip()
-            if paragraph:
-                html_parts.append(f"<p>{paragraph}</p>")
-
-    return "\n".join(html_parts)

novel_downloader/core/exporters/epub_utils/volume_intro.py

@@ -1,60 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.exporters.epub_utils.volume_intro
--------------------------------------------------------
-
-Responsible for generating HTML code for volume introduction pages,
-including two style variants and a unified entry point.
-"""
-
-
-from novel_downloader.utils.constants import EPUB_IMAGE_FOLDER
-
-
-def split_volume_title(volume_title: str) -> tuple[str, str]:
-    """
-    Split volume title into two parts for better display.
-
-    :param volume_title: Original volume title string.
-    :return: Tuple of (line1, line2)
-    """
-    if " " in volume_title:
-        parts = volume_title.split(" ")
-    elif "-" in volume_title:
-        parts = volume_title.split("-")
-    else:
-        return "", volume_title
-
-    return parts[0], "".join(parts[1:])
-
-
-def create_volume_intro(volume_title: str, volume_intro_text: str = "") -> str:
-    """
-    Generate the HTML snippet for a volume's introduction section.
-
-    :param volume_title: Title of the volume.
-    :param volume_intro_text: Optional introduction text for the volume.
-    :return: HTML string representing the volume's intro section.
-    """
-    line1, line2 = split_volume_title(volume_title)
-
-    def make_border_img(class_name: str) -> str:
-        return (
-            f'<div class="{class_name}">'
-            f'<img alt="" class="{class_name}" '
-            f'src="../{EPUB_IMAGE_FOLDER}/volume_border.png" />'
-            f"</div>"
-        )
-
-    html_parts = [make_border_img("border1")]
-
-    if line1:
-        html_parts.append(f'<h1 class="volume-title-line1">{line1}</h1>')
-
-    html_parts.append(f'<p class="volume-title-line2">{line2}</p>')
-    html_parts.append(make_border_img("border2"))
-
-    if volume_intro_text:
-        html_parts.append(f'<p class="intro">{volume_intro_text}</p>')
-
-    return "\n".join(html_parts)