novel-downloader 2.0.1__py3-none-any.whl → 2.0.2__py3-none-any.whl

novel_downloader/core/exporters/common/txt.py

@@ -1,146 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.exporters.common.txt
-------------------------------------------
-
-Defines `common_export_as_txt` to assemble and export a novel
-into a single `.txt` file. Intended for use by `CommonExporter`.
-"""
-
-from __future__ import annotations
-
-from pathlib import Path
-from typing import TYPE_CHECKING
-
-from novel_downloader.core.exporters.txt_util import (
-    build_txt_chapter,
-    build_txt_header,
-)
-from novel_downloader.utils import get_cleaner, write_file
-
-if TYPE_CHECKING:
-    from .main_exporter import CommonExporter
-
-
-def common_export_as_txt(
-    exporter: CommonExporter,
-    book_id: str,
-) -> Path | None:
-    """
-    Export a novel as a single text file by merging all chapter data.
-
-    Steps:
-      1. Load book metadata.
-      2. For each volume:
-         a. Append the volume title.
-         b. Batch-fetch all chapters in that volume to minimize SQLite calls.
-         c. Append each chapter's title, content, and optional author note.
-      3. Build a header with book metadata and the latest chapter title.
-      4. Concatenate header and all chapter contents.
-      5. Save the resulting .txt file to the output directory
-         (e.g., '{book_name}.txt').
-
-    :param exporter: The CommonExporter instance managing paths and config.
-    :param book_id: Identifier of the novel (subdirectory under raw data).
-    """
-    TAG = "[Exporter]"
-    # --- Paths & options ---
-    out_dir = exporter.output_dir
-    out_dir.mkdir(parents=True, exist_ok=True)
-    cleaner = get_cleaner(
-        enabled=exporter._config.clean_text,
-        config=exporter._config.cleaner_cfg,
-    )
-
-    # --- Load book_info.json ---
-    book_info = exporter._load_book_info(book_id)
-    if not book_info:
-        return None
-
-    # --- Compile chapters ---
-    parts: list[str] = []
-    latest_chapter_title: str = ""
-
-    for vol in book_info.get("volumes", []):
-        vol_name = cleaner.clean_title(vol.get("volume_name", ""))
-        if vol_name:
-            # e.g. "\n\n====== 第三卷 ======\n\n"
-            parts.append(f"\n\n{'=' * 6} {vol_name} {'=' * 6}\n\n")
-            exporter.logger.info("%s Processing volume: %s", TAG, vol_name)
-
-        # Batch-fetch chapters for this volume
-        chap_ids = [
-            chap["chapterId"]
-            for chap in vol.get("chapters", [])
-            if chap.get("chapterId")
-        ]
-        chap_map = exporter._get_chapters(book_id, chap_ids)
-
-        for chap_meta in vol.get("chapters", []):
-            chap_id = chap_meta.get("chapterId")
-            if not chap_id:
-                exporter.logger.warning(
-                    "%s Missing chapterId, skipping: %s", TAG, chap_meta
-                )
-                continue
-
-            chap_title = chap_meta.get("title", "")
-            data = chap_map.get(chap_id)
-            if not data:
-                exporter.logger.info(
-                    "%s Missing chapter: %s (%s), skipping.",
-                    TAG,
-                    chap_title,
-                    chap_id,
-                )
-                continue
-
-            # Extract and clean fields
-            title = cleaner.clean_title(data.get("title", chap_title))
-            content = cleaner.clean_content(data.get("content", ""))
-            extra = data.get("extra", {})
-            author_note = cleaner.clean_content(extra.get("author_say", ""))
-
-            extras = {"作者说": author_note} if author_note else {}
-            parts.append(
-                build_txt_chapter(title=title, paragraphs=content, extras=extras)
-            )
-
-            latest_chapter_title = title
-
-    # --- Build header ---
-    name = book_info.get("book_name") or ""
-    author = book_info.get("author") or ""
-    words = book_info.get("word_count") or ""
-    updated = book_info.get("update_time") or ""
-    summary = book_info.get("summary") or ""
-
-    header_fields = [
-        ("书名", name),
-        ("作者", author),
-        ("总字数", words),
-        ("更新日期", updated),
-        ("原文截至", latest_chapter_title),
-        ("内容简介", summary),
-    ]
-
-    header = build_txt_header(header_fields)
-
-    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:
-        result = write_file(
-            content=final_text,
-            filepath=out_path,
-            on_exist="overwrite",
-        )
-        exporter.logger.info("%s Novel saved to: %s", TAG, out_path)
-    except Exception as e:
-        exporter.logger.error("%s Failed to write novel to %s: %s", TAG, out_path, e)
-        return None
-    return result

novel_downloader/core/exporters/epub_util.py

@@ -1,215 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.exporters.epub_util
------------------------------------------
-
-Utilities for preparing and formatting chapter HTML for EPUB exports.
-"""
-
-__all__ = [
-    "download_cover",
-    "prepare_builder",
-    "finalize_export",
-    "inline_remote_images",
-    "remove_all_images",
-    "build_epub_chapter",
-]
-
-import logging
-import re
-from html import escape
-from pathlib import Path
-
-from novel_downloader.utils import download, sanitize_filename
-from novel_downloader.utils.constants import (
-    CSS_MAIN_PATH,
-    DEFAULT_HEADERS,
-    DEFAULT_IMAGE_SUFFIX,
-)
-from novel_downloader.utils.epub import EpubBuilder, StyleSheet
-
-_IMAGE_WRAPPER = '<div class="duokan-image-single illus">{img}</div>'
-_IMG_TAG_RE = re.compile(r"<img[^>]*>", re.IGNORECASE)
-_IMG_SRC_RE = re.compile(
-    r'<img[^>]*\bsrc=["\'](https?://[^"\']+)["\'][^>]*>',
-    re.IGNORECASE,
-)
-
-
-def download_cover(
-    cover_url: str,
-    raw_base: Path,
-    include_cover: bool,
-    logger: logging.Logger,
-    tag: str,
-    headers: dict[str, str] | None = None,
-) -> Path | None:
-    if include_cover and cover_url:
-        path = download(
-            cover_url,
-            raw_base,
-            filename="cover",
-            headers=headers or DEFAULT_HEADERS,
-            on_exist="overwrite",
-            default_suffix=DEFAULT_IMAGE_SUFFIX,
-        )
-        if not path:
-            logger.warning("%s Failed to download cover from %s", tag, cover_url)
-        return path
-    return None
-
-
-def prepare_builder(
-    site_name: str,
-    book_id: str,
-    title: str,
-    author: str,
-    description: str,
-    subject: list[str],
-    serial_status: str,
-    word_count: str,
-    cover_path: Path | None,
-) -> tuple[EpubBuilder, StyleSheet]:
-    book = EpubBuilder(
-        title=title,
-        author=author,
-        description=description,
-        cover_path=cover_path,
-        subject=subject,
-        serial_status=serial_status,
-        word_count=word_count,
-        uid=f"{site_name}_{book_id}",
-    )
-    css_text = CSS_MAIN_PATH.read_text(encoding="utf-8")
-    main_css = StyleSheet(id="main_style", content=css_text, filename="main.css")
-    book.add_stylesheet(main_css)
-    return book, main_css
-
-
-def finalize_export(
-    book: EpubBuilder,
-    out_dir: Path,
-    filename: str,
-    logger: logging.Logger,
-    tag: str,
-) -> Path | None:
-    out_path = out_dir / sanitize_filename(filename)
-    try:
-        book.export(out_path)
-        logger.info("%s EPUB successfully written to %s", tag, out_path)
-        return out_path
-    except OSError as e:
-        logger.error("%s Failed to write EPUB to %s: %s", tag, out_path, e)
-        return None
-
-
-def inline_remote_images(
-    book: EpubBuilder,
-    content: str,
-    image_dir: Path,
-    headers: dict[str, str] | None = None,
-) -> str:
-    """
-    Download every remote `<img src="...">` in `content` into `image_dir`,
-    and replace the original url with local path.
-
-    :param content: HTML/text of the chapter containing <img> tags.
-    :param image_dir: Directory to save downloaded images into.
-    :return: modified_content.
-    """
-
-    def _replace(m: re.Match[str]) -> str:
-        url = m.group(1)
-        try:
-            local_path = download(
-                url,
-                image_dir,
-                headers=headers or DEFAULT_HEADERS,
-                on_exist="skip",
-                default_suffix=DEFAULT_IMAGE_SUFFIX,
-            )
-            if not local_path:
-                return m.group(0)
-            filename = book.add_image(local_path)
-            return f'<img src="../Images/{filename}" />'
-        except Exception:
-            return m.group(0)
-
-    return _IMG_SRC_RE.sub(_replace, content)
-
-
-def remove_all_images(content: str) -> str:
-    """
-    Remove all <img> tags from the given content.
-
-    :param content: HTML/text of the chapter containing <img> tags.
-    """
-    return _IMG_TAG_RE.sub("", content)
-
-
-def build_epub_chapter(
-    title: str,
-    paragraphs: str,
-    extras: dict[str, str] | None = None,
-) -> str:
-    """
-    Build a formatted chapter epub HTML including title, body paragraphs,
-    and optional extra sections.
-
-    :param title: Chapter title.
-    :param paragraphs: Raw multi-line string. Blank lines are ignored.
-    :param extras: Optional dict mapping section titles to multi-line strings.
-    :return: A HTML include title, paragraphs, and extras.
-    """
-
-    def _render_block(text: str) -> str:
-        out: list[str] = []
-        for raw in text.splitlines():
-            line = raw.strip()
-            if not line:
-                continue
-
-            # case 1: already wrapped in a <div>...</div>
-            if line.startswith("<div") and line.endswith("</div>"):
-                out.append(line)
-                continue
-
-            # case 2: single <img> line
-            if _IMG_TAG_RE.fullmatch(line):
-                out.append(_IMAGE_WRAPPER.format(img=line))
-                continue
-
-            # case 3: inline <img> in text -> escape other text, preserve <img>
-            if "<img " in line:
-                pieces = []
-                last = 0
-                for m in _IMG_TAG_RE.finditer(line):
-                    pieces.append(escape(line[last : m.start()]))
-                    pieces.append(m.group(0))
-                    last = m.end()
-                pieces.append(escape(line[last:]))
-                out.append("<p>" + "".join(pieces) + "</p>")
-            else:
-                # plain text line
-                out.append(f"<p>{escape(line)}</p>")
-
-        return "\n".join(out)
-
-    parts = []
-    parts.append(f"<h2>{escape(title)}</h2>")
-    parts.append(_render_block(paragraphs))
-
-    if extras:
-        for title, note in extras.items():
-            note = note.strip()
-            if not note:
-                continue
-            parts.extend(
-                [
-                    "<hr />",
-                    f"<h3>{escape(title)}</h3>",
-                    _render_block(note),
-                ]
-            )
-
-    return "\n".join(parts)

novel_downloader/core/exporters/linovelib/__init__.py

@@ -1,11 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.exporters.linovelib
------------------------------------------
-
-Exporter implementation for handling Linovelib novels.
-"""
-
-__all__ = ["LinovelibExporter"]
-
-from .main_exporter import LinovelibExporter