novel-downloader 1.5.0__py3-none-any.whl → 2.0.1__py3-none-any.whl

novel_downloader/core/exporters/linovelib/epub.py

@@ -17,6 +17,7 @@ from novel_downloader.core.exporters.epub_util import (
     finalize_export,
     inline_remote_images,
     prepare_builder,
+    remove_all_images,
 )
 from novel_downloader.utils import (
     download,
@@ -41,7 +42,7 @@ _IMG_HEADERS["Referer"] = "https://www.linovelib.com/"
 def export_whole_book(
     exporter: LinovelibExporter,
     book_id: str,
-) -> None:
+) -> Path | None:
     """
     Export a single novel (identified by `book_id`) to an EPUB file.
 
@@ -73,7 +74,7 @@ def export_whole_book(
     # --- Load book_info.json ---
     book_info = exporter._load_book_info(book_id)
     if not book_info:
-        return
+        return None
 
     book_name = book_info.get("book_name", book_id)
     book_author = book_info.get("author", "")
@@ -99,7 +100,7 @@ def export_whole_book(
         title=book_name,
         author=book_author,
         description=book_info.get("summary", ""),
-        subject=book_info.get("subject", []),
+        subject=book_info.get("tags", []),
         serial_status=book_info.get("serial_status", ""),
         word_count=book_info.get("word_count", ""),
         cover_path=cover_path,
@@ -118,7 +119,7 @@ def export_whole_book(
 
         # Batch-fetch chapters for this volume
         chap_ids = [
-            chap.get("chapterId")
+            chap["chapterId"]
             for chap in vol.get("chapters", [])
             if chap.get("chapterId")
         ]
@@ -152,7 +153,7 @@ def export_whole_book(
                 )
                 continue
 
-            chap_title = cleaner.clean_title(chap_meta.get("title", ""))
+            chap_title = chap_meta.get("title", "")
             data = chap_map.get(chap_id)
             if not data:
                 exporter.logger.info(
@@ -165,11 +166,10 @@ def export_whole_book(
 
             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,
+            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(
@@ -177,7 +177,7 @@ def export_whole_book(
                 paragraphs=content,
                 extras={},
             )
-            curr_vol.add_chapter(
+            curr_vol.chapters.append(
                 Chapter(
                     id=f"c_{chap_id}",
                     filename=f"c{chap_id}.xhtml",
@@ -195,20 +195,19 @@ def export_whole_book(
         author=book_info.get("author"),
         ext="epub",
     )
-    finalize_export(
+    return finalize_export(
         book=book,
         out_dir=out_dir,
         filename=out_name,
         logger=exporter.logger,
         tag=TAG,
     )
-    return
 
 
 def export_by_volume(
     exporter: LinovelibExporter,
     book_id: str,
-) -> None:
+) -> Path | None:
     """
     Export each volume of a novel as a separate EPUB file.
 
@@ -241,7 +240,7 @@ def export_by_volume(
     # --- Load book_info.json ---
     book_info = exporter._load_book_info(book_id)
     if not book_info:
-        return
+        return None
 
     book_name = book_info.get("book_name", book_id)
     book_author = book_info.get("author", "")
@@ -263,7 +262,7 @@ def export_by_volume(
 
         # Batch-fetch chapters for this volume
         chap_ids = [
-            chap.get("chapterId")
+            chap["chapterId"]
             for chap in vol.get("chapters", [])
             if chap.get("chapterId")
         ]
@@ -286,8 +285,8 @@ def export_by_volume(
             title=book_name,
             author=book_author,
             description=vol.get("volume_intro") or book_summary,
-            subject=book_info.get("subject", []),
-            serial_status=vol.get("serial_status", ""),
+            subject=book_info.get("tags", []),
+            serial_status=book_info.get("serial_status", ""),
             word_count=vol.get("word_count", ""),
             cover_path=vol_cover,
         )
@@ -302,7 +301,7 @@ def export_by_volume(
                 )
                 continue
 
-            chap_title = cleaner.clean_title(chap_meta.get("title", ""))
+            chap_title = chap_meta.get("title", "")
             data = chap_map.get(chap_id)
             if not data:
                 exporter.logger.info(
@@ -315,11 +314,10 @@ def export_by_volume(
 
             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,
+            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,
@@ -348,4 +346,4 @@ def export_by_volume(
             logger=exporter.logger,
             tag=TAG,
         )
-    return
+    return None

novel_downloader/core/exporters/linovelib/main_exporter.py

@@ -3,13 +3,19 @@
 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
 
 
@@ -29,7 +35,7 @@ class LinovelibExporter(BaseExporter):
         """
         super().__init__(config, "linovelib")
 
-    def export_as_txt(self, book_id: str) -> None:
+    def export_as_txt(self, book_id: str) -> Path | None:
         """
         Compile and export a novel as a single .txt file.
 
@@ -38,23 +44,13 @@ class LinovelibExporter(BaseExporter):
         self._init_chapter_storages(book_id)
         return linovelib_export_as_txt(self, book_id)
 
-    def export_as_epub(self, book_id: str) -> None:
+    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.
         """
-        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 = {

novel_downloader/core/exporters/linovelib/txt.py

@@ -9,13 +9,14 @@ 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, save_as_txt
+from novel_downloader.utils import get_cleaner, write_file
 
 if TYPE_CHECKING:
     from .main_exporter import LinovelibExporter
@@ -24,17 +25,17 @@ if TYPE_CHECKING:
 def linovelib_export_as_txt(
     exporter: LinovelibExporter,
     book_id: str,
-) -> None:
+) -> 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.
+        * 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`.
 
@@ -53,7 +54,7 @@ def linovelib_export_as_txt(
     # --- Load book_info.json ---
     book_info = exporter._load_book_info(book_id)
     if not book_info:
-        return
+        return None
 
     # --- Compile chapters ---
     parts: list[str] = []
@@ -70,7 +71,7 @@ def linovelib_export_as_txt(
 
         # Batch-fetch chapters for this volume
         chap_ids = [
-            chap.get("chapterId")
+            chap["chapterId"]
             for chap in vol.get("chapters", [])
             if chap.get("chapterId")
         ]
@@ -84,7 +85,7 @@ def linovelib_export_as_txt(
                 )
                 continue
 
-            chap_title = cleaner.clean_title(chap_meta.get("title", ""))
+            chap_title = chap_meta.get("title", "")
             data = chap_map.get(chap_id)
             if not data:
                 exporter.logger.info(
@@ -125,9 +126,14 @@ def linovelib_export_as_txt(
     out_path = out_dir / out_name
 
     # --- Save final text ---
-    result = save_as_txt(content=final_text, filepath=out_path)
-    if result:
+    try:
+        result = write_file(
+            content=final_text,
+            filepath=out_path,
+            on_exist="overwrite",
+        )
         exporter.logger.info("%s Novel saved to: %s", TAG, out_path)
-    else:
-        exporter.logger.error("%s Failed to write novel to %s", TAG, out_path)
-    return
+    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/qidian.py

@@ -3,9 +3,7 @@
 novel_downloader.core.exporters.qidian
 --------------------------------------
 
-This module provides the `QidianExporter` class for handling the saving process
-of novels sourced from Qidian (起点中文网). It implements the platform-specific
-logic required to structure and export novel content into desired formats.
+Exporter implementation for Qidian novels, supporting plain and encrypted sources.
 """
 
 __all__ = ["QidianExporter"]
@@ -31,8 +29,4 @@ class QidianExporter(CommonExporter):
         self,
         config: ExporterConfig,
     ):
-        super().__init__(
-            config,
-            site="qidian",
-            priorities=self.PRIORITIES_MAP,
-        )
+        super().__init__(config, site="qidian")

novel_downloader/core/exporters/registry.py

@@ -3,6 +3,7 @@
 novel_downloader.core.exporters.registry
 ----------------------------------------
 
+Registry and factory helpers for creating site-specific or common exporters.
 """
 
 __all__ = ["register_exporter", "get_exporter"]
@@ -10,6 +11,7 @@ __all__ = ["register_exporter", "get_exporter"]
 from collections.abc import Callable, Sequence
 from typing import TypeVar
 
+from novel_downloader.core.exporters.common import CommonExporter
 from novel_downloader.core.interfaces import ExporterProtocol
 from novel_downloader.models import ExporterConfig
 
@@ -48,6 +50,6 @@ def get_exporter(site: str, config: ExporterConfig) -> ExporterProtocol:
     site_key = site.lower()
     try:
         exporter_cls = _EXPORTER_MAP[site_key]
-    except KeyError as err:
-        raise ValueError(f"Unsupported site: {site}") from err
+    except KeyError:
+        return CommonExporter(config, site_key)
     return exporter_cls(config)

novel_downloader/core/exporters/txt_util.py

@@ -13,7 +13,7 @@ __all__ = [
 
 import re
 
-_IMG_TAG_RE = re.compile(r"<img[^>]*>")
+_IMG_TAG_RE = re.compile(r"<img[^>]*>", re.IGNORECASE)
 
 
 def build_txt_header(fields: list[tuple[str, str]]) -> str:
@@ -37,14 +37,14 @@ def build_txt_chapter(
     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.
+      * 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 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.
+    :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()]
 

novel_downloader/core/fetchers/__init__.py

@@ -3,65 +3,71 @@
 novel_downloader.core.fetchers
 ------------------------------
 
-This package provides fetcher implementations for different novel platforms.
-Each submodule corresponds to a specific site and encapsulates the logic needed
-to perform network interactions, such as logging in, sending requests,
-or interacting with browser/session-based sources.
-
-Subpackages:
-- biquge (笔趣阁)
-- esjzone (ESJ Zone)
-- linovelib (哔哩轻小说)
-- qianbi (铅笔小说)
-- qidian (起点中文网)
-- sfacg (SF轻小说)
-- yamibo (百合会)
+Fetcher implementations for retrieving raw data and HTML from various novel sources
 """
 
 __all__ = [
     "get_fetcher",
-    "BiqugeBrowser",
+    "AaatxtSession",
     "BiqugeSession",
-    "EsjzoneBrowser",
+    "BiquyueduSession",
+    "DxmwxSession",
+    "EightnovelSession",
     "EsjzoneSession",
-    "LinovelibBrowser",
+    "GuidayeSession",
+    "HetushuSession",
+    "I25zwSession",
+    "Ixdzs8Session",
+    "Jpxs123Session",
+    "LewennSession",
     "LinovelibSession",
-    "QianbiBrowser",
+    "PiaotiaSession",
+    "QbtrSession",
     "QianbiSession",
-    "QidianBrowser",
     "QidianSession",
-    "SfacgBrowser",
+    "Quanben5Session",
     "SfacgSession",
-    "YamiboBrowser",
+    "ShencouSession",
+    "ShuhaigeSession",
+    "TongrenquanSession",
+    "TtkanSession",
+    "WanbengoSession",
+    "XiaoshuowuSession",
+    "XiguashuwuSession",
+    "Xs63bSession",
+    "XshbookSession",
     "YamiboSession",
+    "YibigeSession",
 ]
 
-from .biquge import (
-    BiqugeBrowser,
-    BiqugeSession,
-)
-from .esjzone import (
-    EsjzoneBrowser,
-    EsjzoneSession,
-)
-from .linovelib import (
-    LinovelibBrowser,
-    LinovelibSession,
-)
-from .qianbi import (
-    QianbiBrowser,
-    QianbiSession,
-)
-from .qidian import (
-    QidianBrowser,
-    QidianSession,
-)
+from .aaatxt import AaatxtSession
+from .b520 import BiqugeSession
+from .biquyuedu import BiquyueduSession
+from .dxmwx import DxmwxSession
+from .eightnovel import EightnovelSession
+from .esjzone import EsjzoneSession
+from .guidaye import GuidayeSession
+from .hetushu import HetushuSession
+from .i25zw import I25zwSession
+from .ixdzs8 import Ixdzs8Session
+from .jpxs123 import Jpxs123Session
+from .lewenn import LewennSession
+from .linovelib import LinovelibSession
+from .piaotia import PiaotiaSession
+from .qbtr import QbtrSession
+from .qianbi import QianbiSession
+from .qidian import QidianSession
+from .quanben5 import Quanben5Session
 from .registry import get_fetcher
-from .sfacg import (
-    SfacgBrowser,
-    SfacgSession,
-)
-from .yamibo import (
-    YamiboBrowser,
-    YamiboSession,
-)
+from .sfacg import SfacgSession
+from .shencou import ShencouSession
+from .shuhaige import ShuhaigeSession
+from .tongrenquan import TongrenquanSession
+from .ttkan import TtkanSession
+from .wanbengo import WanbengoSession
+from .xiaoshuowu import XiaoshuowuSession
+from .xiguashuwu import XiguashuwuSession
+from .xs63b import Xs63bSession
+from .xshbook import XshbookSession
+from .yamibo import YamiboSession
+from .yibige import YibigeSession

novel_downloader/core/fetchers/aaatxt.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.fetchers.aaatxt
+-------------------------------------
+
+"""
+
+from typing import Any
+
+from novel_downloader.core.fetchers.base import BaseSession
+from novel_downloader.core.fetchers.registry import register_fetcher
+from novel_downloader.models import FetcherConfig
+
+
+@register_fetcher(
+    site_keys=["aaatxt"],
+)
+class AaatxtSession(BaseSession):
+    """
+    A session class for interacting with the 3A电子书 (www.aaatxt.com) novel website.
+    """
+
+    BOOK_INFO_URL = "http://www.aaatxt.com/shu/{book_id}.html"
+    CHAPTER_URL = "http://www.aaatxt.com/yuedu/{chapter_id}.html"
+
+    def __init__(
+        self,
+        config: FetcherConfig,
+        cookies: dict[str, str] | None = None,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__("aaatxt", config, cookies, **kwargs)
+
+    async def get_book_info(
+        self,
+        book_id: str,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Fetch the raw HTML of the book info page asynchronously.
+
+        :param book_id: The book identifier.
+        :return: The page content as string list.
+        """
+        url = self.book_info_url(book_id=book_id)
+        return [await self.fetch(url, **kwargs)]
+
+    async def get_book_chapter(
+        self,
+        book_id: str,
+        chapter_id: str,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Fetch the raw HTML of a single chapter asynchronously.
+
+        :param book_id: The book identifier.
+        :param chapter_id: The chapter identifier.
+        :return: The page content as string list.
+        """
+        url = self.chapter_url(chapter_id=chapter_id)
+        return [await self.fetch(url, encoding="gb2312", **kwargs)]
+
+    @classmethod
+    def book_info_url(cls, book_id: str) -> str:
+        """
+        Construct the URL for fetching a book's info page.
+
+        :param book_id: The identifier of the book.
+        :return: Fully qualified URL for the book info page.
+        """
+        return cls.BOOK_INFO_URL.format(book_id=book_id)
+
+    @classmethod
+    def chapter_url(cls, chapter_id: str) -> str:
+        """
+        Construct the URL for fetching a specific chapter.
+
+        :param book_id: The identifier of the book.
+        :param chapter_id: The identifier of the chapter.
+        :return: Fully qualified chapter URL.
+        """
+        return cls.CHAPTER_URL.format(chapter_id=chapter_id)

novel_downloader/core/fetchers/{biquge/session.py → b520.py}

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 """
-novel_downloader.core.fetchers.biquge.session
----------------------------------------------
+novel_downloader.core.fetchers.b520
+-----------------------------------
 
 """
 
@@ -13,12 +13,11 @@ from novel_downloader.models import FetcherConfig
 
 
 @register_fetcher(
-    site_keys=["biquge", "bqg"],
-    backends=["session"],
+    site_keys=["biquge", "bqg", "b520"],
 )
 class BiqugeSession(BaseSession):
     """
-    A session class for interacting with the Biquge (www.b520.cc) novel website.
+    A session class for interacting with the 笔趣阁 (www.b520.cc) novel website.
     """
 
     BOOK_INFO_URL = "http://www.b520.cc/{book_id}/"
@@ -41,7 +40,7 @@ class BiqugeSession(BaseSession):
         Fetch the raw HTML of the book info page asynchronously.
 
         :param book_id: The book identifier.
-        :return: The page content as a string.
+        :return: The page content as string list.
         """
         url = self.book_info_url(book_id=book_id)
         return [await self.fetch(url, **kwargs)]
@@ -57,7 +56,7 @@ class BiqugeSession(BaseSession):
 
         :param book_id: The book identifier.
         :param chapter_id: The chapter identifier.
-        :return: The chapter content as a string.
+        :return: The page content as string list.
         """
         url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
         return [await self.fetch(url, encoding="gbk", **kwargs)]
@@ -82,7 +81,3 @@ class BiqugeSession(BaseSession):
         :return: Fully qualified chapter URL.
         """
         return cls.CHAPTER_URL.format(book_id=book_id, chapter_id=chapter_id)
-
-    @property
-    def hostname(self) -> str:
-        return "www.b520.cc"