novel-downloader 1.3.3__py3-none-any.whl → 1.4.0__py3-none-any.whl

novel_downloader/core/exporters/linovelib/epub.py

@@ -0,0 +1,449 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.exporters.linovelib.epub
+----------------------------------------------
+
+Contains the logic for exporting novel content as a single `.epub` file.
+"""
+
+from __future__ import annotations
+
+import html
+import json
+import re
+from pathlib import Path
+from typing import TYPE_CHECKING, Any
+
+from ebooklib import epub
+
+from novel_downloader.core.exporters.epub_utils import (
+    add_images_from_dir,
+    add_images_from_list,
+    chapter_txt_to_html,
+    create_css_items,
+    create_volume_intro,
+    init_epub,
+)
+from novel_downloader.utils.constants import (
+    DEFAULT_HEADERS,
+    EPUB_IMAGE_FOLDER,
+    EPUB_IMAGE_WRAPPER,
+    EPUB_OPTIONS,
+    EPUB_TEXT_FOLDER,
+)
+from novel_downloader.utils.file_utils import sanitize_filename
+from novel_downloader.utils.network import download_image
+
+if TYPE_CHECKING:
+    from .main_exporter import LinovelibExporter
+
+_IMG_TAG_PATTERN = re.compile(
+    r'<img\s+[^>]*src=[\'"]([^\'"]+)[\'"][^>]*>', re.IGNORECASE
+)
+_IMG_HEADERS = DEFAULT_HEADERS.copy()
+_IMG_HEADERS["Referer"] = "https://www.linovelib.com/"
+
+
+def export_whole_book(
+    exporter: LinovelibExporter,
+    book_id: str,
+) -> None:
+    """
+    Export a single novel (identified by `book_id`) to an EPUB file.
+
+    This function will:
+      1. Load `book_info.json` for metadata.
+      2. Generate introductory HTML and optionally include the cover image.
+      3. Initialize the EPUB container.
+      4. Iterate through volumes and chapters, convert each to XHTML.
+      5. Assemble the spine, TOC, CSS and write out the final `.epub`.
+
+    :param book_id: Identifier of the novel (used as subdirectory name).
+    """
+    TAG = "[exporter]"
+    config = exporter._config
+    # --- Paths & options ---
+    raw_base = exporter._raw_data_dir / book_id
+    img_dir = exporter._cache_dir / book_id / "images"
+    out_dir = exporter.output_dir
+    img_dir.mkdir(parents=True, exist_ok=True)
+    out_dir.mkdir(parents=True, exist_ok=True)
+
+    # --- Load book_info.json ---
+    info_path = raw_base / "book_info.json"
+    try:
+        info_text = info_path.read_text(encoding="utf-8")
+        book_info = json.loads(info_text)
+    except Exception as e:
+        exporter.logger.error("%s Failed to load %s: %s", TAG, info_path, e)
+        return
+
+    book_name = book_info.get("book_name", book_id)
+    exporter.logger.info(
+        "%s Starting EPUB generation: %s (ID: %s)", TAG, book_name, book_id
+    )
+
+    # --- Generate intro + cover ---
+    intro_html = _generate_intro_html(book_info)
+    cover_path: Path | None = None
+    cover_url = book_info.get("cover_url", "")
+    if config.include_cover and cover_url:
+        cover_path = download_image(
+            cover_url,
+            raw_base,
+            target_name="cover",
+            headers=_IMG_HEADERS,
+            on_exist="overwrite",
+        )
+        if not cover_path:
+            exporter.logger.warning("Failed to download cover from %s", cover_url)
+
+    # --- Initialize EPUB ---
+    book, spine, toc_list = init_epub(
+        book_info=book_info,
+        book_id=book_id,
+        intro_html=intro_html,
+        book_cover_path=cover_path,
+        include_toc=config.include_toc,
+    )
+    for css in create_css_items(
+        include_main=True,
+        include_volume=True,
+    ):
+        book.add_item(css)
+
+    # --- Compile chapters ---
+    volumes = book_info.get("volumes", [])
+    for vol_index, vol in enumerate(volumes, start=1):
+        vol_name = vol.get("volume_name", "").strip() or f"Unknown Volume {vol_index}"
+        vol_name = vol_name.replace(book_name, "").strip()
+        vol_cover_path: Path | None = None
+        vol_cover_url = vol.get("volume_cover", "")
+        if config.include_cover and vol_cover_url:
+            vol_cover_path = download_image(
+                vol_cover_url,
+                img_dir,
+                headers=_IMG_HEADERS,
+                on_exist="skip",
+            )
+
+        exporter.logger.info("Processing volume %d: %s", vol_index, vol_name)
+
+        # Volume intro
+        vol_intro = epub.EpubHtml(
+            title=vol_name,
+            file_name=f"{EPUB_TEXT_FOLDER}/volume_intro_{vol_index}.xhtml",
+            lang="zh",
+        )
+        vol_intro.content = _generate_vol_intro_html(
+            vol_name,
+            vol.get("volume_intro", ""),
+            vol_cover_path,
+        )
+        vol_intro.add_link(
+            href="../Styles/volume-intro.css",
+            rel="stylesheet",
+            type="text/css",
+        )
+        book.add_item(vol_intro)
+        spine.append(vol_intro)
+
+        section = epub.Section(vol_name, vol_intro.file_name)
+        chapter_items: list[epub.EpubHtml] = []
+
+        for chap in vol.get("chapters", []):
+            chap_id = chap.get("chapterId")
+            chap_title = chap.get("title", "")
+            if not chap_id:
+                exporter.logger.warning("%s Missing chapterId, skipping: %s", TAG, chap)
+                continue
+
+            chapter_data = exporter._get_chapter(book_id, chap_id)
+            if not chapter_data:
+                exporter.logger.info(
+                    "%s Missing chapter file: %s (%s), skipping.",
+                    TAG,
+                    chap_title,
+                    chap_id,
+                )
+                continue
+
+            title = chapter_data.get("title", "") or chap_id
+            content: str = chapter_data.get("content", "")
+            content, _ = _inline_remote_images(content, img_dir)
+            chap_html = chapter_txt_to_html(
+                chapter_title=title,
+                chapter_text=content,
+                author_say="",
+            )
+
+            chap_path = f"{EPUB_TEXT_FOLDER}/{chap_id}.xhtml"
+            item = epub.EpubHtml(title=chap_title, file_name=chap_path, lang="zh")
+            item.content = chap_html
+            item.add_link(
+                href="../Styles/main.css",
+                rel="stylesheet",
+                type="text/css",
+            )
+            book.add_item(item)
+            spine.append(item)
+            chapter_items.append(item)
+
+        toc_list.append((section, chapter_items))
+
+    book = add_images_from_dir(book, img_dir)
+
+    # --- 5. Finalize EPUB ---
+    exporter.logger.info("%s Building TOC and spine...", TAG)
+    book.toc = toc_list
+    book.spine = spine
+    book.add_item(epub.EpubNcx())
+    book.add_item(epub.EpubNav())
+
+    out_name = exporter.get_filename(
+        title=book_name,
+        author=book_info.get("author"),
+        ext="epub",
+    )
+    out_path = out_dir / sanitize_filename(out_name)
+
+    try:
+        epub.write_epub(out_path, book, EPUB_OPTIONS)
+        exporter.logger.info("%s EPUB successfully written to %s", TAG, out_path)
+    except Exception as e:
+        exporter.logger.error("%s Failed to write EPUB to %s: %s", TAG, out_path, e)
+    return
+
+
+def export_by_volume(
+    exporter: LinovelibExporter,
+    book_id: str,
+) -> None:
+    """
+    Export a single novel (identified by `book_id`) to multi EPUB file.
+
+    :param book_id: Identifier of the novel (used as subdirectory name).
+    """
+    TAG = "[exporter]"
+    config = exporter._config
+    # --- Paths & options ---
+    raw_base = exporter._raw_data_dir / book_id
+    img_dir = exporter._cache_dir / book_id / "images"
+    out_dir = exporter.output_dir
+    img_dir.mkdir(parents=True, exist_ok=True)
+    out_dir.mkdir(parents=True, exist_ok=True)
+
+    # --- Load book_info.json ---
+    info_path = raw_base / "book_info.json"
+    try:
+        info_text = info_path.read_text(encoding="utf-8")
+        book_info = json.loads(info_text)
+    except Exception as e:
+        exporter.logger.error("%s Failed to load %s: %s", TAG, info_path, e)
+        return
+
+    book_name = book_info.get("book_name", book_id)
+    exporter.logger.info(
+        "%s Starting EPUB generation: %s (ID: %s)", TAG, book_name, book_id
+    )
+    css_items = create_css_items(
+        include_main=True,
+        include_volume=True,
+    )
+
+    # --- Compile columes ---
+    volumes = book_info.get("volumes", [])
+    for vol_index, vol in enumerate(volumes, start=1):
+        vol_name = vol.get("volume_name", "").strip() or f"Unknown Volume {vol_index}"
+        vol_cover_path: Path | None = None
+        vol_cover_url = vol.get("volume_cover", "")
+        if config.include_cover and vol_cover_url:
+            vol_cover_path = download_image(
+                vol_cover_url,
+                img_dir,
+                headers=_IMG_HEADERS,
+                on_exist="skip",
+            )
+        intro_html = _generate_intro_html(vol)
+
+        book, spine, toc_list = init_epub(
+            book_info=vol,
+            book_id=f"{book_id}_{vol_index}",
+            intro_html=intro_html,
+            book_cover_path=vol_cover_path,
+            include_toc=config.include_toc,
+        )
+        for css in css_items:
+            book.add_item(css)
+
+        for chap in vol.get("chapters", []):
+            chap_id = chap.get("chapterId")
+            chap_title = chap.get("title", "")
+            if not chap_id:
+                exporter.logger.warning("%s Missing chapterId, skipping: %s", TAG, chap)
+                continue
+
+            chapter_data = exporter._get_chapter(book_id, chap_id)
+            if not chapter_data:
+                exporter.logger.info(
+                    "%s Missing chapter file: %s (%s), skipping.",
+                    TAG,
+                    chap_title,
+                    chap_id,
+                )
+                continue
+
+            title = chapter_data.get("title", "") or chap_id
+            content: str = chapter_data.get("content", "")
+            content, imgs = _inline_remote_images(content, img_dir)
+            chap_html = chapter_txt_to_html(
+                chapter_title=title,
+                chapter_text=content,
+                author_say="",
+            )
+            add_images_from_list(book, imgs)
+
+            chap_path = f"{EPUB_TEXT_FOLDER}/{chap_id}.xhtml"
+            item = epub.EpubHtml(title=chap_title, file_name=chap_path, lang="zh")
+            item.content = chap_html
+            item.add_link(
+                href="../Styles/main.css",
+                rel="stylesheet",
+                type="text/css",
+            )
+            book.add_item(item)
+            spine.append(item)
+            toc_list.append(item)
+
+        book.toc = toc_list
+        book.spine = spine
+        book.add_item(epub.EpubNcx())
+        book.add_item(epub.EpubNav())
+
+        out_name = exporter.get_filename(
+            title=vol_name,
+            author=book_info.get("author"),
+            ext="epub",
+        )
+        out_path = out_dir / sanitize_filename(out_name)
+
+        try:
+            epub.write_epub(out_path, book, EPUB_OPTIONS)
+            exporter.logger.info("%s EPUB successfully written to %s", TAG, out_path)
+        except Exception as e:
+            exporter.logger.error("%s Failed to write EPUB to %s: %s", TAG, out_path, e)
+    return
+
+
+def _generate_intro_html(
+    info: dict[str, Any],
+    default_author: str = "",
+) -> str:
+    """
+    Generate an HTML snippet containing book metadata and summary.
+
+    :param info: A dict that may contain book info
+    :param default_author: Fallback author name.
+
+    :return: An HTML-formatted string.
+    """
+    title = info.get("book_name") or info.get("volume_name")
+    author = info.get("author") or default_author
+    status = info.get("serial_status")
+    words = info.get("word_count")
+    raw_summary = (info.get("summary") or info.get("volume_intro") or "").strip()
+
+    html_parts = [
+        "<h1>书籍简介</h1>",
+        '<div class="list">',
+        "<ul>",
+    ]
+    metadata = [
+        ("书名", title),
+        ("作者", author),
+        ("状态", status),
+        ("字数", words),
+    ]
+    for label, value in metadata:
+        if value is not None and str(value).strip():
+            safe = html.escape(str(value))
+            if label == "书名":
+                safe = f"《{safe}》"
+            html_parts.append(f"<li>{label}: {safe}</li>")
+
+    html_parts.extend(["</ul>", "</div>"])
+
+    if raw_summary:
+        html_parts.append('<p class="new-page-after"><br/></p>')
+        html_parts.append("<h2>简介</h2>")
+        for para in filter(None, (p.strip() for p in raw_summary.split("\n\n"))):
+            safe_para = html.escape(para).replace("\n", "<br/>")
+            html_parts.append(f"<p>{safe_para}</p>")
+
+    return "\n".join(html_parts)
+
+
+def _generate_vol_intro_html(
+    title: str,
+    intro: str = "",
+    cover_path: Path | None = None,
+) -> str:
+    """
+    Generate the HTML snippet for a volume's introduction section.
+
+    :param title: Title of the volume.
+    :param intro: Optional introduction text for the volume.
+    :param cover_path: Path of the volume cover.
+    :return: HTML string representing the volume's intro section.
+    """
+    if cover_path is None:
+        return create_volume_intro(title, intro)
+
+    html_parts = [
+        f'<h1 class="volume-title-line1">{title}</h1>',
+        f'<img class="width100" src="../{EPUB_IMAGE_FOLDER}/{cover_path.name}" />',
+        '<p class="new-page-after"><br/></p>',
+    ]
+
+    if intro.strip():
+        html_parts.append(f'<p class="intro">{intro}</p>')
+
+    return "\n".join(html_parts)
+
+
+def _inline_remote_images(
+    content: str,
+    image_dir: str | Path,
+) -> tuple[str, list[Path]]:
+    """
+    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: A tuple (modified_content, list_of_downloaded_image_paths).
+    """
+    downloaded_images: list[Path] = []
+
+    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,
+                headers=_IMG_HEADERS,
+                on_exist="skip",
+            )
+            if not local_path:
+                return match.group(0)
+
+            downloaded_images.append(local_path)
+            return EPUB_IMAGE_WRAPPER.format(filename=local_path.name)
+        except Exception:
+            return match.group(0)
+
+    modified_content = _IMG_TAG_PATTERN.sub(_replace, content)
+    return modified_content, downloaded_images

novel_downloader/core/exporters/linovelib/main_exporter.py

@@ -0,0 +1,127 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.exporters.linovelib.main_exporter
+-------------------------------------------------------
+
+"""
+
+from collections.abc import Mapping
+from typing import Any
+
+from novel_downloader.core.exporters.base import BaseExporter
+from novel_downloader.models import ExporterConfig
+from novel_downloader.utils.chapter_storage import ChapterStorage
+
+from .txt import linovelib_export_as_txt
+
+
+class LinovelibExporter(BaseExporter):
+    """"""
+
+    def __init__(
+        self,
+        config: ExporterConfig,
+    ):
+        """
+        Initialize the linovelib exporter.
+
+        :param config: A ExporterConfig object that defines
+                        save paths, formats, and options.
+        """
+        super().__init__(config, "linovelib")
+        self._chapter_storage_cache: dict[str, list[ChapterStorage]] = {}
+        self._chap_folders: list[str] = ["chapters"]
+
+    def export_as_txt(self, book_id: str) -> None:
+        """
+        Compile and export a novel as a single .txt file.
+
+        :param book_id: The book identifier (used to locate raw data)
+        """
+        self._init_chapter_storages(book_id)
+        return linovelib_export_as_txt(self, book_id)
+
+    def export_as_epub(self, book_id: str) -> None:
+        """
+        Persist the assembled book as a EPUB (.epub) file.
+
+        :param book_id: The book identifier.
+        :raises NotImplementedError: If the method is not overridden.
+        """
+        try:
+            from .epub import (
+                export_by_volume,
+                export_whole_book,
+            )
+        except ImportError as err:
+            raise NotImplementedError(
+                "EPUB export not supported. Please install 'ebooklib'"
+            ) from err
+
+        self._init_chapter_storages(book_id)
+
+        exporters = {
+            "volume": export_by_volume,
+            "book": export_whole_book,
+        }
+        try:
+            export_fn = exporters[self._config.split_mode]
+        except KeyError as err:
+            raise ValueError(
+                f"Unsupported split_mode: {self._config.split_mode!r}"
+            ) from err
+        return export_fn(self, book_id)
+
+    @property
+    def site(self) -> str:
+        """
+        Get the site identifier.
+
+        :return: The site string.
+        """
+        return self._site
+
+    @site.setter
+    def site(self, value: str) -> None:
+        """
+        Set the site identifier.
+
+        :param value: New site string to set.
+        """
+        self._site = value
+
+    def _get_chapter(
+        self,
+        book_id: str,
+        chap_id: str,
+    ) -> Mapping[str, Any]:
+        for storage in self._chapter_storage_cache[book_id]:
+            data = storage.get(chap_id)
+            if data:
+                return data
+        return {}
+
+    def _init_chapter_storages(self, book_id: str) -> None:
+        if book_id in self._chapter_storage_cache:
+            return
+        raw_base = self._raw_data_dir / book_id
+        self._chapter_storage_cache[book_id] = [
+            ChapterStorage(
+                raw_base=raw_base,
+                namespace=ns,
+                backend_type=self._config.storage_backend,
+            )
+            for ns in self._chap_folders
+        ]
+
+    def _on_close(self) -> None:
+        """
+        Close all ChapterStorage connections in the cache.
+        """
+        for storages in self._chapter_storage_cache.values():
+            for storage in storages:
+                try:
+                    storage.close()
+                except Exception as e:
+                    self.logger.warning("Failed to close storage %s: %s", storage, e)
+        self._chapter_storage_cache.clear()

novel_downloader/core/exporters/linovelib/txt.py

@@ -0,0 +1,129 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.exporters.linovelib.txt
+---------------------------------------------
+
+Contains the logic for exporting novel content as a single `.txt` file.
+
+This module defines `linovelib_export_as_txt` function, which assembles and formats
+a novel based on metadata and chapter files found in the raw data directory.
+It is intended to be used by `LinovelibExporter` as part of the save/export process.
+"""
+
+from __future__ import annotations
+
+import json
+from typing import TYPE_CHECKING
+
+from novel_downloader.utils.file_utils import save_as_txt
+from novel_downloader.utils.text_utils import (
+    format_chapter,
+)
+
+if TYPE_CHECKING:
+    from .main_exporter import LinovelibExporter
+
+
+def linovelib_export_as_txt(
+    exporter: LinovelibExporter,
+    book_id: str,
+) -> None:
+    """
+    将 save_path 文件夹中该小说的所有章节 json 文件合并保存为一个完整的 txt 文件,
+    并保存到 out_path 下
+
+    处理流程：
+      1. 从 book_info.json 中加载书籍信息 (包含书名、作者、简介及卷章节列表)
+      2. 遍历各卷, 每个卷先追加卷标题, 然后依次追加该卷下各章节的标题和内容
+      3. 将书籍元信息 (书名、作者、原文截至、内容简介) 与所有章节内容拼接
+      4. 将最终结果保存到 out_path 下 (例如：`{book_name}.txt`)
+
+    :param book_id: Identifier of the novel (used as subdirectory name).
+    """
+    TAG = "[exporter]"
+    # --- Paths & options ---
+    raw_base = exporter._raw_data_dir / book_id
+    out_dir = exporter.output_dir
+    out_dir.mkdir(parents=True, exist_ok=True)
+
+    # --- Load book_info.json ---
+    info_path = raw_base / "book_info.json"
+    try:
+        info_text = info_path.read_text(encoding="utf-8")
+        book_info = json.loads(info_text)
+    except Exception as e:
+        exporter.logger.error("%s Failed to load %s: %s", TAG, info_path, e)
+        return
+
+    # --- Compile chapters ---
+    parts: list[str] = []
+    volumes = book_info.get("volumes", [])
+
+    for vol in volumes:
+        vol_name = vol.get("volume_name", "").strip()
+        vol_intro = vol.get("volume_intro", "").strip()
+        if vol_name:
+            volume_header = f"\n\n{'=' * 6} {vol_name} {'=' * 6}\n\n"
+            parts.append(volume_header)
+            exporter.logger.info("%s Processing volume: %s", TAG, vol_name)
+        if vol_intro:
+            parts.append(f"{vol_intro}\n\n")
+        for chap in vol.get("chapters", []):
+            chap_id = chap.get("chapterId")
+            chap_title = chap.get("title", "")
+            if not chap_id:
+                exporter.logger.warning("%s Missing chapterId, skipping: %s", TAG, chap)
+                continue
+
+            chapter_data = exporter._get_chapter(book_id, chap_id)
+            if not chapter_data:
+                exporter.logger.info(
+                    "%s Missing chapter file in: %s (%s), skipping.",
+                    TAG,
+                    chap_title,
+                    chap_id,
+                )
+                continue
+
+            # Extract structured fields
+            title = chapter_data.get("title", chap_title).strip()
+            content = chapter_data.get("content", "").strip()
+
+            parts.append(format_chapter(title, content, ""))
+
+    # --- Build header ---
+    name = book_info.get("book_name")
+    author = book_info.get("author")
+    words = book_info.get("word_count")
+    updated = book_info.get("update_time")
+    summary = book_info.get("summary")
+
+    fields = [
+        ("书名", name),
+        ("作者", author),
+        ("总字数", words),
+        ("更新日期", updated),
+    ]
+    header_lines = [f"{label}: {value}" for label, value in fields if value]
+
+    if summary:
+        header_lines.append("内容简介:")
+        header_lines.append(summary)
+
+    header_lines += ["", "-" * 10, ""]
+
+    header = "\n".join(header_lines)
+
+    final_text = header + "\n\n" + "\n\n".join(parts).strip()
+
+    # --- Determine output file path ---
+    out_name = exporter.get_filename(title=name, author=author, ext="txt")
+    out_path = out_dir / out_name
+
+    # --- Save final text ---
+    try:
+        save_as_txt(content=final_text, filepath=out_path)
+        exporter.logger.info("%s Novel saved to: %s", TAG, out_path)
+    except Exception as e:
+        exporter.logger.error("%s Failed to save file: %s", TAG, e)
+    return