novel-downloader 1.4.2__tar.gz → 1.4.4__tar.gz

{novel_downloader-1.4.2 → novel_downloader-1.4.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: novel-downloader
-Version: 1.4.2
+Version: 1.4.4
 Summary: A command-line tool for downloading Chinese web novels from Qidian and similar platforms.
 Author-email: Saudade Z <saudadez217@gmail.com>
 License: MIT License
@@ -182,6 +182,7 @@ pip install .
 - [CLI 使用示例](https://github.com/BowenZ217/novel-downloader/blob/main/docs/6-cli-usage-examples.md)
 - [复制 Cookies](https://github.com/BowenZ217/novel-downloader/blob/main/docs/copy-cookies.md)
 - [文件保存](https://github.com/BowenZ217/novel-downloader/blob/main/docs/file-saving.md)
+- [模块与接口文档](https://github.com/BowenZ217/novel-downloader/blob/main/docs/api/README.md)
 - [TODO](https://github.com/BowenZ217/novel-downloader/blob/main/docs/todo.md)
 - [开发](https://github.com/BowenZ217/novel-downloader/blob/main/docs/develop.md)
 - [项目说明](#项目说明)

{novel_downloader-1.4.2 → novel_downloader-1.4.4}/README.md

@@ -111,6 +111,7 @@ pip install .
 - [CLI 使用示例](https://github.com/BowenZ217/novel-downloader/blob/main/docs/6-cli-usage-examples.md)
 - [复制 Cookies](https://github.com/BowenZ217/novel-downloader/blob/main/docs/copy-cookies.md)
 - [文件保存](https://github.com/BowenZ217/novel-downloader/blob/main/docs/file-saving.md)
+- [模块与接口文档](https://github.com/BowenZ217/novel-downloader/blob/main/docs/api/README.md)
 - [TODO](https://github.com/BowenZ217/novel-downloader/blob/main/docs/todo.md)
 - [开发](https://github.com/BowenZ217/novel-downloader/blob/main/docs/develop.md)
 - [项目说明](#项目说明)

{novel_downloader-1.4.2 → novel_downloader-1.4.4}/pyproject.toml

@@ -68,6 +68,7 @@ requires = ["setuptools>=61.0", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [tool.setuptools.packages.find]
+where = ["src"]
 include = ["novel_downloader", "novel_downloader.*"]
 
 [tool.setuptools.package-data]
@@ -110,13 +111,14 @@ strict = true
 [tool.pytest.ini_options]
 minversion = "7.1"
 addopts = "--strict-markers"
+pythonpath = ["src"]
 testpaths = ["tests"]
 
 [tool.commitizen]
 name = "cz_conventional_commits"
-version = "1.4.2"
+version = "1.4.4"
 version_files = [
-    "novel_downloader/__init__.py"
+    "src/novel_downloader/__init__.py"
 ]
 update_changelog_on_bump = true
 changelog_file = "CHANGELOG.md"

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/__init__.py

@@ -6,7 +6,7 @@ novel_downloader
 Core package for the Novel Downloader project.
 """
 
-__version__ = "1.4.2"
+__version__ = "1.4.4"
 
 __author__ = "Saudade Z"
 __email__ = "saudadez217@gmail.com"

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/cli/download.py

@@ -161,7 +161,6 @@ async def _download(
         downloader = get_downloader(
             fetcher=fetcher,
             parser=parser,
-            exporter=exporter,
             site=site,
             config=downloader_cfg,
         )
@@ -172,6 +171,7 @@ async def _download(
                 book,
                 progress_hook=_print_progress,
             )
+            await asyncio.to_thread(exporter.export, book["book_id"])
 
         if downloader_cfg.login_required and fetcher.is_logged_in:
             await fetcher.save_state()

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/config/adapter.py

@@ -127,6 +127,7 @@ class ConfigAdapter:
         site_cfg = self._get_site_cfg()
         return ParserConfig(
             cache_dir=gen.get("cache_dir", "./novel_cache"),
+            use_truncation=site_cfg.get("use_truncation", True),
             decode_font=font_ocr.get("decode_font", False),
             use_freq=font_ocr.get("use_freq", False),
             use_ocr=font_ocr.get("use_ocr", True),

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/__init__.py

@@ -14,8 +14,26 @@ downloading and processing online novel content, including:
 - Exporter: Responsible for exporting downloaded data into various output formats.
 """
 
-from .factory import get_parser
+from .factory import (
+    get_downloader,
+    get_exporter,
+    get_fetcher,
+    get_parser,
+)
+from .interfaces import (
+    DownloaderProtocol,
+    ExporterProtocol,
+    FetcherProtocol,
+    ParserProtocol,
+)
 
 __all__ = [
+    "get_downloader",
+    "get_exporter",
+    "get_fetcher",
     "get_parser",
+    "DownloaderProtocol",
+    "ExporterProtocol",
+    "FetcherProtocol",
+    "ParserProtocol",
 ]

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/downloaders/base.py

@@ -15,7 +15,6 @@ from typing import Any
 
 from novel_downloader.core.interfaces import (
     DownloaderProtocol,
-    ExporterProtocol,
     FetcherProtocol,
     ParserProtocol,
 )
@@ -34,13 +33,11 @@ class BaseDownloader(DownloaderProtocol, abc.ABC):
         self,
         fetcher: FetcherProtocol,
         parser: ParserProtocol,
-        exporter: ExporterProtocol,
         config: DownloaderConfig,
         site: str,
     ):
         self._fetcher = fetcher
         self._parser = parser
-        self._exporter = exporter
         self._config = config
         self._site = site
 
@@ -158,10 +155,6 @@ class BaseDownloader(DownloaderProtocol, abc.ABC):
     def parser(self) -> ParserProtocol:
         return self._parser
 
-    @property
-    def exporter(self) -> ExporterProtocol:
-        return self._exporter
-
     @property
     def config(self) -> DownloaderConfig:
         return self._config

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/downloaders/biquge.py

@@ -7,7 +7,6 @@ novel_downloader.core.downloaders.biquge
 
 from novel_downloader.core.downloaders.common import CommonDownloader
 from novel_downloader.core.interfaces import (
-    ExporterProtocol,
     FetcherProtocol,
     ParserProtocol,
 )
@@ -21,7 +20,6 @@ class BiqugeDownloader(CommonDownloader):
         self,
         fetcher: FetcherProtocol,
         parser: ParserProtocol,
-        exporter: ExporterProtocol,
         config: DownloaderConfig,
     ):
-        super().__init__(fetcher, parser, exporter, config, "biquge")
+        super().__init__(fetcher, parser, config, "biquge")

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/downloaders/common.py

@@ -440,8 +440,6 @@ class CommonDownloader(BaseDownloader):
         normal_cs.close()
         save_as_json(book_info, info_path)
 
-        await asyncio.to_thread(self.exporter.export, book_id)
-
         self.logger.info(
             "%s Novel '%s' download completed.",
             TAG,

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/downloaders/esjzone.py

@@ -7,7 +7,6 @@ novel_downloader.core.downloaders.esjzone
 
 from novel_downloader.core.downloaders.common import CommonDownloader
 from novel_downloader.core.interfaces import (
-    ExporterProtocol,
     FetcherProtocol,
     ParserProtocol,
 )
@@ -21,7 +20,6 @@ class EsjzoneDownloader(CommonDownloader):
         self,
         fetcher: FetcherProtocol,
         parser: ParserProtocol,
-        exporter: ExporterProtocol,
         config: DownloaderConfig,
     ):
-        super().__init__(fetcher, parser, exporter, config, "esjzone")
+        super().__init__(fetcher, parser, config, "esjzone")

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/downloaders/linovelib.py

@@ -7,7 +7,6 @@ novel_downloader.core.downloaders.linovelib
 
 from novel_downloader.core.downloaders.common import CommonDownloader
 from novel_downloader.core.interfaces import (
-    ExporterProtocol,
     FetcherProtocol,
     ParserProtocol,
 )
@@ -21,7 +20,6 @@ class LinovelibDownloader(CommonDownloader):
         self,
         fetcher: FetcherProtocol,
         parser: ParserProtocol,
-        exporter: ExporterProtocol,
         config: DownloaderConfig,
     ):
-        super().__init__(fetcher, parser, exporter, config, "linovelib")
+        super().__init__(fetcher, parser, config, "linovelib")

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/downloaders/qianbi.py

@@ -7,7 +7,6 @@ novel_downloader.core.downloaders.qianbi
 
 from novel_downloader.core.downloaders.common import CommonDownloader
 from novel_downloader.core.interfaces import (
-    ExporterProtocol,
     FetcherProtocol,
     ParserProtocol,
 )
@@ -21,7 +20,6 @@ class QianbiDownloader(CommonDownloader):
         self,
         fetcher: FetcherProtocol,
         parser: ParserProtocol,
-        exporter: ExporterProtocol,
         config: DownloaderConfig,
     ):
-        super().__init__(fetcher, parser, exporter, config, "qianbi")
+        super().__init__(fetcher, parser, config, "qianbi")

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/downloaders/qidian.py

@@ -13,7 +13,6 @@ from typing import Any, cast
 
 from novel_downloader.core.downloaders.base import BaseDownloader
 from novel_downloader.core.interfaces import (
-    ExporterProtocol,
     FetcherProtocol,
     ParserProtocol,
 )
@@ -41,11 +40,10 @@ class QidianDownloader(BaseDownloader):
         self,
         fetcher: FetcherProtocol,
         parser: ParserProtocol,
-        exporter: ExporterProtocol,
         config: DownloaderConfig,
     ):
         config.request_interval = max(1.0, config.request_interval)
-        super().__init__(fetcher, parser, exporter, config, "qidian")
+        super().__init__(fetcher, parser, config, "qidian")
 
     async def _download_one(
         self,
@@ -351,8 +349,6 @@ class QidianDownloader(BaseDownloader):
         normal_cs.close()
         encrypted_cs.close()
 
-        await asyncio.to_thread(self.exporter.export, book_id)
-
         self.logger.info(
             "%s Novel '%s' download completed.",
             TAG,

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/downloaders/sfacg.py

@@ -7,7 +7,6 @@ novel_downloader.core.downloaders.sfacg
 
 from novel_downloader.core.downloaders.common import CommonDownloader
 from novel_downloader.core.interfaces import (
-    ExporterProtocol,
     FetcherProtocol,
     ParserProtocol,
 )
@@ -21,7 +20,6 @@ class SfacgDownloader(CommonDownloader):
         self,
         fetcher: FetcherProtocol,
         parser: ParserProtocol,
-        exporter: ExporterProtocol,
         config: DownloaderConfig,
     ):
-        super().__init__(fetcher, parser, exporter, config, "sfacg")
+        super().__init__(fetcher, parser, config, "sfacg")

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/downloaders/yamibo.py

@@ -7,7 +7,6 @@ novel_downloader.core.downloaders.yamibo
 
 from novel_downloader.core.downloaders.common import CommonDownloader
 from novel_downloader.core.interfaces import (
-    ExporterProtocol,
     FetcherProtocol,
     ParserProtocol,
 )
@@ -21,7 +20,6 @@ class YamiboDownloader(CommonDownloader):
         self,
         fetcher: FetcherProtocol,
         parser: ParserProtocol,
-        exporter: ExporterProtocol,
         config: DownloaderConfig,
     ):
-        super().__init__(fetcher, parser, exporter, config, "yamibo")
+        super().__init__(fetcher, parser, config, "yamibo")

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/factory/downloader.py

@@ -22,14 +22,13 @@ from novel_downloader.core.downloaders import (
 )
 from novel_downloader.core.interfaces import (
     DownloaderProtocol,
-    ExporterProtocol,
     FetcherProtocol,
     ParserProtocol,
 )
 from novel_downloader.models import DownloaderConfig
 
 DownloaderBuilder = Callable[
-    [FetcherProtocol, ParserProtocol, ExporterProtocol, DownloaderConfig],
+    [FetcherProtocol, ParserProtocol, DownloaderConfig],
     DownloaderProtocol,
 ]
 
@@ -47,7 +46,6 @@ _site_map: dict[str, DownloaderBuilder] = {
 def get_downloader(
     fetcher: FetcherProtocol,
     parser: ParserProtocol,
-    exporter: ExporterProtocol,
     site: str,
     config: DownloaderConfig,
 ) -> DownloaderProtocol:
@@ -56,7 +54,6 @@ def get_downloader(
 
     :param fetcher: Fetcher implementation
     :param parser: Parser implementation
-    :param exporter: Exporter implementation
     :param site: Site name (e.g., 'qidian')
     :param config: Downloader configuration
 
@@ -66,11 +63,11 @@ def get_downloader(
 
     # site-specific
     if site_key in _site_map:
-        return _site_map[site_key](fetcher, parser, exporter, config)
+        return _site_map[site_key](fetcher, parser, config)
 
     # fallback
     site_rules = load_site_rules()
     if site_key not in site_rules:
         raise ValueError(f"Unsupported site: {site}")
 
-    return CommonDownloader(fetcher, parser, exporter, config, site_key)
+    return CommonDownloader(fetcher, parser, config, site_key)

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/fetchers/base/browser.py

@@ -201,19 +201,9 @@ class BaseBrowser(FetcherProtocol, abc.ABC):
         **kwargs: Any,
     ) -> str:
         if self._reuse_page:
-            if not self._page:
-                self._page = await self.context.new_page()
-            page = self._page
+            return await self._fetch_with_reuse(url, wait_until, referer, **kwargs)
         else:
-            page = await self.context.new_page()
-
-        await page.goto(url, wait_until=wait_until, referer=referer)
-        content = await page.content()
-
-        if not self._reuse_page:
-            await page.close()
-
-        return str(content)
+            return await self._fetch_with_new(url, wait_until, referer, **kwargs)
 
     async def load_state(self) -> bool:
         """ """
@@ -286,6 +276,36 @@ class BaseBrowser(FetcherProtocol, abc.ABC):
         await self.init(headless=headless)
         self.logger.debug("[browser] Browser restarted (headless=%s).", headless)
 
+    async def _fetch_with_new(
+        self,
+        url: str,
+        wait_until: Literal["commit", "domcontentloaded", "load", "networkidle"]
+        | None = "load",
+        referer: str | None = None,
+        **kwargs: Any,
+    ) -> str:
+        page = await self.context.new_page()
+        try:
+            await page.goto(url, wait_until=wait_until, referer=referer, **kwargs)
+            html: str = await page.content()
+            return html
+        finally:
+            await page.close()
+
+    async def _fetch_with_reuse(
+        self,
+        url: str,
+        wait_until: Literal["commit", "domcontentloaded", "load", "networkidle"]
+        | None = "load",
+        referer: str | None = None,
+        **kwargs: Any,
+    ) -> str:
+        if not self._page:
+            self._page = await self.context.new_page()
+        await self._page.goto(url, wait_until=wait_until, referer=referer, **kwargs)
+        html: str = await self._page.content()
+        return html
+
     @property
     def hostname(self) -> str:
         return ""

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/fetchers/esjzone/browser.py

@@ -49,15 +49,17 @@ class EsjzoneBrowser(BaseBrowser):
 
         login_page = await self.context.new_page()
 
-        await login_page.goto(self.API_LOGIN_URL_1, wait_until="networkidle")
+        try:
+            await login_page.goto(self.API_LOGIN_URL_1, wait_until="networkidle")
 
-        await login_page.fill('input[name="email"]', username)
-        await login_page.fill('input[name="pwd"]', password)
+            await login_page.fill('input[name="email"]', username)
+            await login_page.fill('input[name="pwd"]', password)
 
-        await login_page.click('a.btn-send[data-send="mem_login"]')
+            await login_page.click('a.btn-send[data-send="mem_login"]')
 
-        await login_page.wait_for_load_state("networkidle")
-        await login_page.close()
+            await login_page.wait_for_load_state("networkidle")
+        finally:
+            await login_page.close()
 
         self._is_logged_in = await self._check_login_status()
 

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/fetchers/qidian/browser.py

@@ -22,8 +22,8 @@ class QidianBrowser(BaseBrowser):
 
     HOMEPAGE_URL = "https://www.qidian.com/"
     BOOKCASE_URL = "https://my.qidian.com/bookcase/"
-    BOOK_INFO_URL = "https://book.qidian.com/info/{book_id}/"
-    # BOOK_INFO_URL = "https://www.qidian.com/book/{book_id}/"
+    # BOOK_INFO_URL = "https://book.qidian.com/info/{book_id}/"
+    BOOK_INFO_URL = "https://www.qidian.com/book/{book_id}/"
     CHAPTER_URL = "https://www.qidian.com/chapter/{book_id}/{chapter_id}/"
 
     LOGIN_URL = "https://passport.qidian.com/"

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/fetchers/qidian/session.py

@@ -27,7 +27,8 @@ class QidianSession(BaseSession):
 
     HOMEPAGE_URL = "https://www.qidian.com/"
     BOOKCASE_URL = "https://my.qidian.com/bookcase/"
-    BOOK_INFO_URL = "https://book.qidian.com/info/{book_id}/"
+    # BOOK_INFO_URL = "https://book.qidian.com/info/{book_id}/"
+    BOOK_INFO_URL = "https://www.qidian.com/book/{book_id}/"
     CHAPTER_URL = "https://www.qidian.com/chapter/{book_id}/{chapter_id}/"
 
     LOGIN_URL = "https://passport.qidian.com/"

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/fetchers/yamibo/browser.py

@@ -48,8 +48,8 @@ class YamiboBrowser(BaseBrowser):
             return False
 
         for i in range(1, attempt + 1):
+            login_page = await self.context.new_page()
             try:
-                login_page = await self.context.new_page()
                 await login_page.goto(self.LOGIN_URL, wait_until="networkidle")
 
                 await login_page.fill("#loginform-username", username)
@@ -68,8 +68,6 @@ class YamiboBrowser(BaseBrowser):
                         f"[auth] No URL change after login attempt {i}: {e}"
                     )
 
-                await login_page.close()
-
                 self._is_logged_in = await self._check_login_status()
                 if self._is_logged_in:
                     self.logger.info(f"[auth] Login successful on attempt {i}.")
@@ -83,6 +81,8 @@ class YamiboBrowser(BaseBrowser):
                 self.logger.error(
                     f"[auth] Unexpected error during login attempt {i}: {e}"
                 )
+            finally:
+                await login_page.close()
 
         self.logger.error(f"[auth] Login failed after {attempt} attempt(s).")
         return False

novel_downloader-1.4.4/src/novel_downloader/core/parsers/qidian/book_info_parser.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.parsers.qidian.book_info_parser
+-----------------------------------------------------
+
+This module provides parsing of Qidian book info pages.
+
+It extracts metadata such as title, author, cover URL, update
+time, status, word count, summary, and volume-chapter structure.
+"""
+
+import logging
+import re
+from datetime import datetime
+from typing import Any
+
+from lxml import html
+
+logger = logging.getLogger(__name__)
+
+
+def _chapter_url_to_id(url: str) -> str:
+    return url.rstrip("/").split("/")[-1]
+
+
+def parse_book_info(html_str: str) -> dict[str, Any]:
+    """
+    Extract metadata: title, author, cover_url, update_time, status,
+    word_count, summary, and volumes with chapters.
+
+    :param html_str: Raw HTML of the book info page.
+    :return: A dict containing book metadata.
+    """
+    info: dict[str, Any] = {}
+    try:
+        doc = html.fromstring(html_str)
+
+        info["book_name"] = doc.xpath('string(//h1[@id="bookName"])').strip()
+
+        info["author"] = doc.xpath('string(//a[@class="writer-name"])').strip()
+
+        book_id = doc.xpath('//a[@id="bookImg"]/@data-bid')[0]
+        info[
+            "cover_url"
+        ] = f"https://bookcover.yuewen.com/qdbimg/349573/{book_id}/600.webp"
+
+        ut = (
+            doc.xpath('string(//span[@class="update-time"])')
+            .replace("更新时间:", "")
+            .strip()
+        )
+        if re.match(r"^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}$", ut):
+            info["update_time"] = ut
+        else:
+            info["update_time"] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+
+        info["serial_status"] = doc.xpath(
+            'string(//p[@class="book-attribute"]/span[1])'
+        ).strip()
+
+        tags = doc.xpath('//p[contains(@class,"all-label")]//a/text()')
+        info["tags"] = [t.strip() for t in tags if t.strip()]
+
+        info["word_count"] = doc.xpath('string(//p[@class="count"]/em[1])').strip()
+
+        summary = doc.xpath('string(//p[@class="intro"])').strip()
+        info["summary_brief"] = summary
+
+        raw = doc.xpath('//p[@id="book-intro-detail"]//text()')
+        info["summary"] = "\n".join(line.strip() for line in raw if line.strip())
+
+        volumes = []
+        for vol in doc.xpath('//div[@id="allCatalog"]//div[@class="catalog-volume"]'):
+            vol_name = vol.xpath('string(.//h3[@class="volume-name"])').strip()
+            vol_name = vol_name.split(chr(183))[0].strip()
+            chapters = []
+            for li in vol.xpath('.//ul[contains(@class,"volume-chapters")]/li'):
+                a = li.xpath('.//a[@class="chapter-name"]')[0]
+                title = a.text.strip()
+                url = a.get("href")
+                chapters.append(
+                    {"title": title, "url": url, "chapterId": _chapter_url_to_id(url)}
+                )
+            volumes.append({"volume_name": vol_name, "chapters": chapters})
+        info["volumes"] = volumes
+
+    except Exception as e:
+        logger.warning("[Parser] Error parsing book info: %s", e)
+
+    return info

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/parsers/qidian/chapter_encrypted.py

@@ -19,12 +19,16 @@ from lxml import html
 
 from novel_downloader.models import ChapterDict
 from novel_downloader.utils.network import download_font_file
-from novel_downloader.utils.text_utils import apply_font_mapping
+from novel_downloader.utils.text_utils import (
+    apply_font_mapping,
+    truncate_half_lines,
+)
 
 from .utils import (
     extract_chapter_info,
     find_ssr_page_context,
     get_decryptor,
+    is_duplicated,
     vip_status,
 )
 
@@ -76,6 +80,7 @@ def parse_encrypted_chapter(
         fixedFontWoff2_url = chapter_info["fixedFontWoff2"]
 
         title = chapter_info.get("chapterName", "Untitled")
+        duplicated = is_duplicated(ssr_data)
         raw_html = chapter_info.get("content", "")
         chapter_id = chapter_info.get("chapterId", chapter_id)
         fkp = chapter_info.get("fkp", "")
@@ -83,7 +88,7 @@ def parse_encrypted_chapter(
         update_time = chapter_info.get("updateTime", "")
         update_timestamp = chapter_info.get("updateTimestamp", 0)
         modify_time = chapter_info.get("modifyTime", 0)
-        word_count = chapter_info.get("wordsCount", 0)
+        word_count = chapter_info.get("actualWords", 0)
         seq = chapter_info.get("seq", None)
         volume = chapter_info.get("extra", {}).get("volumeName", "")
 
@@ -177,6 +182,9 @@ def parse_encrypted_chapter(
         final_paragraphs_str = "\n\n".join(
             line.strip() for line in original_text.splitlines() if line.strip()
         )
+        if parser._use_truncation and duplicated:
+            final_paragraphs_str = truncate_half_lines(final_paragraphs_str)
+
         return {
             "id": str(chapter_id),
             "title": str(title),
@@ -187,6 +195,7 @@ def parse_encrypted_chapter(
                 "update_timestamp": update_timestamp,
                 "modify_time": modify_time,
                 "word_count": word_count,
+                "duplicated": duplicated,
                 "seq": seq,
                 "volume": volume,
                 "encrypted": True,

{novel_downloader-1.4.2 → novel_downloader-1.4.4/src}/novel_downloader/core/parsers/qidian/chapter_normal.py

@@ -15,11 +15,13 @@ from typing import TYPE_CHECKING
 from lxml import html
 
 from novel_downloader.models import ChapterDict
+from novel_downloader.utils.text_utils import truncate_half_lines
 
 from .utils import (
     extract_chapter_info,
     find_ssr_page_context,
     get_decryptor,
+    is_duplicated,
     vip_status,
 )
 
@@ -51,6 +53,7 @@ def parse_normal_chapter(
             return None
 
         title = chapter_info.get("chapterName", "Untitled")
+        duplicated = is_duplicated(ssr_data)
         raw_html = chapter_info.get("content", "")
         chapter_id = chapter_info.get("chapterId", chapter_id)
         fkp = chapter_info.get("fkp", "")
@@ -58,7 +61,7 @@ def parse_normal_chapter(
         update_time = chapter_info.get("updateTime", "")
         update_timestamp = chapter_info.get("updateTimestamp", 0)
         modify_time = chapter_info.get("modifyTime", 0)
-        word_count = chapter_info.get("wordsCount", 0)
+        word_count = chapter_info.get("actualWords", 0)
         seq = chapter_info.get("seq", None)
         volume = chapter_info.get("extra", {}).get("volumeName", "")
 
@@ -74,6 +77,9 @@ def parse_normal_chapter(
             if not chapter_text:
                 return None
 
+        if parser._use_truncation and duplicated:
+            chapter_text = truncate_half_lines(chapter_text)
+
         return {
             "id": str(chapter_id),
             "title": title,
@@ -84,6 +90,7 @@ def parse_normal_chapter(
                 "update_timestamp": update_timestamp,
                 "modify_time": modify_time,
                 "word_count": word_count,
+                "duplicated": duplicated,
                 "seq": seq,
                 "volume": volume,
                 "encrypted": False,