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

novel_downloader/core/exporters/linovelib/epub.py

@@ -1,349 +0,0 @@
-#!/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
-
-from pathlib import Path
-from typing import TYPE_CHECKING
-
-from novel_downloader.core.exporters.epub_util import (
-    build_epub_chapter,
-    download_cover,
-    finalize_export,
-    inline_remote_images,
-    prepare_builder,
-    remove_all_images,
-)
-from novel_downloader.utils import (
-    download,
-    get_cleaner,
-)
-from novel_downloader.utils.constants import (
-    DEFAULT_HEADERS,
-    DEFAULT_IMAGE_SUFFIX,
-)
-from novel_downloader.utils.epub import (
-    Chapter,
-    Volume,
-)
-
-if TYPE_CHECKING:
-    from .main_exporter import LinovelibExporter
-
-_IMG_HEADERS = DEFAULT_HEADERS.copy()
-_IMG_HEADERS["Referer"] = "https://www.linovelib.com/"
-
-
-def export_whole_book(
-    exporter: LinovelibExporter,
-    book_id: str,
-) -> Path | 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 in volume-batches, convert each to XHTML.
-      5. Assemble the spine, TOC, CSS and write out the final `.epub`.
-
-    :param exporter: The exporter instance, carrying config and path info.
-    :param book_id: Identifier of the novel (used as subdirectory name).
-    """
-    TAG = "[exporter]"
-    config = exporter._config
-
-    raw_base = exporter._raw_data_dir / book_id
-    img_dir = raw_base / "images"
-    out_dir = exporter.output_dir
-
-    img_dir.mkdir(parents=True, exist_ok=True)
-    out_dir.mkdir(parents=True, exist_ok=True)
-
-    cleaner = get_cleaner(
-        enabled=config.clean_text,
-        config=config.cleaner_cfg,
-    )
-
-    # --- Load book_info.json ---
-    book_info = exporter._load_book_info(book_id)
-    if not book_info:
-        return None
-
-    book_name = book_info.get("book_name", book_id)
-    book_author = book_info.get("author", "")
-
-    exporter.logger.info(
-        "%s Starting EPUB generation: %s (ID: %s)", TAG, book_name, book_id
-    )
-
-    # --- Generate intro + cover ---
-    cover_path = download_cover(
-        book_info.get("cover_url", ""),
-        raw_base,
-        config.include_cover,
-        exporter.logger,
-        TAG,
-        headers=_IMG_HEADERS,
-    )
-
-    # --- Initialize EPUB ---
-    book, main_css = prepare_builder(
-        site_name=exporter.site,
-        book_id=book_id,
-        title=book_name,
-        author=book_author,
-        description=book_info.get("summary", ""),
-        subject=book_info.get("tags", []),
-        serial_status=book_info.get("serial_status", ""),
-        word_count=book_info.get("word_count", ""),
-        cover_path=cover_path,
-    )
-
-    # --- Compile chapters ---
-    volumes = book_info.get("volumes", [])
-    if not volumes:
-        exporter.logger.warning("%s No volumes found in metadata.", TAG)
-
-    for vol_index, vol in enumerate(volumes, start=1):
-        raw_name = vol.get("volume_name", "")
-        raw_name = raw_name.replace(book_name, "").strip()
-        vol_name = raw_name or f"Volume {vol_index}"
-        exporter.logger.info("Processing volume %d: %s", vol_index, 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)
-
-        vol_cover: Path | None = None
-        vol_cover_url = vol.get("volume_cover", "")
-        if vol_cover_url:
-            vol_cover = download(
-                vol_cover_url,
-                img_dir,
-                on_exist="skip",
-                default_suffix=DEFAULT_IMAGE_SUFFIX,
-                headers=_IMG_HEADERS,
-            )
-
-        curr_vol = Volume(
-            id=f"vol_{vol_index}",
-            title=vol_name,
-            intro=cleaner.clean_content(vol.get("volume_intro", "")),
-            cover=vol_cover,
-        )
-
-        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
-
-            title = cleaner.clean_title(data.get("title", chap_title)) or chap_id
-            content = cleaner.clean_content(data.get("content", ""))
-            content = (
-                inline_remote_images(book, content, img_dir, headers=_IMG_HEADERS)
-                if config.include_picture
-                else remove_all_images(content)
-            )
-
-            chap_html = build_epub_chapter(
-                title=title,
-                paragraphs=content,
-                extras={},
-            )
-            curr_vol.chapters.append(
-                Chapter(
-                    id=f"c_{chap_id}",
-                    filename=f"c{chap_id}.xhtml",
-                    title=title,
-                    content=chap_html,
-                    css=[main_css],
-                )
-            )
-
-        book.add_volume(curr_vol)
-
-    # --- 5. Finalize EPUB ---
-    out_name = exporter.get_filename(
-        title=book_name,
-        author=book_info.get("author"),
-        ext="epub",
-    )
-    return finalize_export(
-        book=book,
-        out_dir=out_dir,
-        filename=out_name,
-        logger=exporter.logger,
-        tag=TAG,
-    )
-
-
-def export_by_volume(
-    exporter: LinovelibExporter,
-    book_id: str,
-) -> Path | None:
-    """
-    Export each volume of a novel as a separate EPUB file.
-
-    Steps:
-      1. Load metadata from `book_info.json`.
-      2. For each volume:
-         a. Clean the volume title and determine output filename.
-         b. Batch-fetch all chapters in this volume to minimize SQLite overhead.
-         c. Initialize an EPUB builder for the volume, including cover and intro.
-         d. For each chapter: clean title & content, inline remote images.
-         e. Finalize and write the volume EPUB.
-
-    :param book_id: Identifier of the novel (used as subdirectory name).
-    """
-    TAG = "[exporter]"
-    config = exporter._config
-
-    raw_base = exporter._raw_data_dir / book_id
-    img_dir = raw_base / "images"
-    out_dir = exporter.output_dir
-
-    img_dir.mkdir(parents=True, exist_ok=True)
-    out_dir.mkdir(parents=True, exist_ok=True)
-
-    cleaner = get_cleaner(
-        enabled=config.clean_text,
-        config=config.cleaner_cfg,
-    )
-
-    # --- Load book_info.json ---
-    book_info = exporter._load_book_info(book_id)
-    if not book_info:
-        return None
-
-    book_name = book_info.get("book_name", book_id)
-    book_author = book_info.get("author", "")
-    book_summary = book_info.get("summary", "")
-
-    exporter.logger.info(
-        "%s Starting EPUB generation: %s (ID: %s)", TAG, book_name, book_id
-    )
-
-    # --- Compile columes ---
-    volumes = book_info.get("volumes", [])
-    if not volumes:
-        exporter.logger.warning("%s No volumes found in metadata.", TAG)
-
-    for vol_index, vol in enumerate(volumes, start=1):
-        raw_name = vol.get("volume_name", "")
-        raw_name = cleaner.clean_title(raw_name.replace(book_name, ""))
-        vol_name = raw_name or f"Volume {vol_index}"
-
-        # 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)
-
-        vol_cover: Path | None = None
-        vol_cover_url = vol.get("volume_cover", "")
-        if config.include_cover and vol_cover_url:
-            vol_cover = download(
-                vol_cover_url,
-                img_dir,
-                headers=_IMG_HEADERS,
-                on_exist="skip",
-                default_suffix=DEFAULT_IMAGE_SUFFIX,
-            )
-
-        book, main_css = prepare_builder(
-            site_name=exporter.site,
-            book_id=book_id,
-            title=book_name,
-            author=book_author,
-            description=vol.get("volume_intro") or book_summary,
-            subject=book_info.get("tags", []),
-            serial_status=book_info.get("serial_status", ""),
-            word_count=vol.get("word_count", ""),
-            cover_path=vol_cover,
-        )
-
-        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
-
-            title = cleaner.clean_title(data.get("title", chap_title)) or chap_id
-            content = cleaner.clean_content(data.get("content", ""))
-            content = (
-                inline_remote_images(book, content, img_dir, headers=_IMG_HEADERS)
-                if config.include_picture
-                else remove_all_images(content)
-            )
-            chap_html = build_epub_chapter(
-                title=title,
-                paragraphs=content,
-                extras={},
-            )
-            book.add_chapter(
-                Chapter(
-                    id=f"c_{chap_id}",
-                    filename=f"c{chap_id}.xhtml",
-                    title=title,
-                    content=chap_html,
-                    css=[main_css],
-                )
-            )
-
-        out_name = exporter.get_filename(
-            title=vol_name,
-            author=book_info.get("author"),
-            ext="epub",
-        )
-        finalize_export(
-            book=book,
-            out_dir=out_dir,
-            filename=out_name,
-            logger=exporter.logger,
-            tag=TAG,
-        )
-    return None

novel_downloader/core/exporters/linovelib/main_exporter.py

@@ -1,66 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.exporters.linovelib.main_exporter
--------------------------------------------------------
-
-Exporter implementation for Linovelib novels, supporting TXT and EPUB outputs.
-"""
-
-from pathlib import Path
-
-from novel_downloader.core.exporters.base import BaseExporter
-from novel_downloader.core.exporters.registry import register_exporter
-from novel_downloader.models import ExporterConfig
-
-from .epub import (
-    export_by_volume,
-    export_whole_book,
-)
-from .txt import linovelib_export_as_txt
-
-
-@register_exporter(site_keys=["linovelib"])
-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")
-
-    def export_as_txt(self, book_id: str) -> Path | 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) -> Path | None:
-        """
-        Persist the assembled book as a EPUB (.epub) file.
-
-        :param book_id: The book identifier.
-        :raises NotImplementedError: If the method is not overridden.
-        """
-        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)

novel_downloader/core/exporters/linovelib/txt.py

@@ -1,139 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.exporters.linovelib.txt
----------------------------------------------
-
-Defines `linovelib_export_as_txt` to assemble and export a Linovelib novel
-into a single `.txt` file. Intended for use by `LinovelibExporter`.
-"""
-
-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 LinovelibExporter
-
-
-def linovelib_export_as_txt(
-    exporter: LinovelibExporter,
-    book_id: str,
-) -> Path | None:
-    """
-    Export a novel as a single text file by merging all chapter data.
-
-    Steps:
-      1. Read metadata from `book_info.json`.
-      2. For each volume:
-        * Clean & append the volume title.
-        * Clean & append optional volume intro.
-        * Batch-fetch all chapters in this volume to minimize SQLite overhead.
-        * For each chapter: clean title & content, then append.
-      3. Build a header block with metadata.
-      4. Concatenate header + all chapter blocks, then save as `{book_name}.txt`.
-
-    :param exporter: The LinovelibExporter instance.
-    :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] = []
-
-    for vol in book_info.get("volumes", []):
-        vol_title = cleaner.clean_title(vol.get("volume_name", ""))
-        if vol_title:
-            parts.append(f"\n\n{'=' * 6} {vol_title} {'=' * 6}\n\n")
-            exporter.logger.info("%s Processing volume: %s", TAG, vol_title)
-
-        vol_intro = cleaner.clean_content(vol.get("volume_intro", ""))
-        if vol_intro:
-            parts.append(f"{vol_intro}\n\n")
-
-        # 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 structured fields
-            title = cleaner.clean_title(data.get("title", chap_title))
-            content = cleaner.clean_content(data.get("content", ""))
-
-            parts.append(build_txt_chapter(title=title, paragraphs=content, extras={}))
-
-    # --- 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),
-        ("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/txt_util.py

@@ -1,67 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.exporters.txt_util
-----------------------------------------
-
-Utilities for generating plain-text exports of novel content.
-"""
-
-__all__ = [
-    "build_txt_header",
-    "build_txt_chapter",
-]
-
-import re
-
-_IMG_TAG_RE = re.compile(r"<img[^>]*>", re.IGNORECASE)
-
-
-def build_txt_header(fields: list[tuple[str, str]]) -> str:
-    """
-    Build a simple text header from label-value pairs, followed by a dashed separator.
-
-    :param fields: List of (label, value) pairs.
-    :return: A single string containing the formatted header.
-    """
-    header_lines = [f"{label}: {value}" for label, value in fields if value]
-    header_lines += ["", "-" * 10, ""]
-    return "\n".join(header_lines)
-
-
-def build_txt_chapter(
-    title: str,
-    paragraphs: str,
-    extras: dict[str, str] | None = None,
-) -> str:
-    """
-    Build a formatted chapter text block including title, body paragraphs,
-    and optional extra sections.
-
-      * Strips any `<img...>` tags from paragraphs.
-      * Title appears first (stripped of surrounding whitespace).
-      * Each non-blank line in `paragraphs` becomes its own paragraph.
-
-    :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 string where title, paragraphs, and extras are joined by lines.
-    """
-    parts: list[str] = [title.strip()]
-
-    # add each nonempty paragraph line
-    paragraphs = _IMG_TAG_RE.sub("", paragraphs)
-    for ln in paragraphs.splitlines():
-        line = ln.strip()
-        if line:
-            parts.append(line)
-
-    if extras:
-        for title, text in extras.items():
-            lines = [ln.strip() for ln in text.splitlines() if ln.strip()]
-            if not lines:
-                continue
-            parts.append("---")
-            parts.append(title.strip())
-            parts.extend(lines)
-
-    return "\n\n".join(parts)

novel_downloader/core/parsers/qidian/__init__.py

@@ -1,10 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.parsers.qidian
-------------------------------------
-
-"""
-
-__all__ = ["QidianParser"]
-
-from .main_parser import QidianParser

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

@@ -1,11 +0,0 @@
-#!/usr/bin/env python3
-"""
-novel_downloader.core.parsers.qidian.utils
-------------------------------------------
-
-Utility functions and helpers for parsing and decrypting Qidian novel pages
-"""
-
-__all__ = ["get_decryptor"]
-
-from .node_decryptor import get_decryptor