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

novel_downloader/core/parsers/xiguashuwu.py

@@ -284,8 +284,7 @@ class XiguashuwuParser(BaseParser):
                 return char
         return f'<img src="{url}" />'
 
-    @classmethod
-    def _recognize_glyph_from_url(cls, url: str) -> str | None:
+    def _recognize_glyph_from_url(self, url: str) -> str | None:
         """
         Download the glyph image at `url` and run the font OCR on it.
 
@@ -293,7 +292,7 @@ class XiguashuwuParser(BaseParser):
         :return: The recognized character (top-1) if OCR succeeds, otherwise None.
         """
         try:
-            ocr = get_font_ocr()
+            ocr = get_font_ocr(self._fontocr_cfg)
             if not ocr:
                 return None
 
@@ -304,7 +303,7 @@ class XiguashuwuParser(BaseParser):
 
             char, score = ocr.predict([img_np])[0]
 
-            return char if score >= cls._CONF_THRESHOLD else None
+            return char if score >= self._CONF_THRESHOLD else None
 
         except Exception as e:
             logger.warning("[Parser] Failed to ocr glyph image %s: %s", url, e)

novel_downloader/core/searchers/__init__.py

@@ -11,12 +11,12 @@ __all__ = [
     "AaatxtSearcher",
     "BiqugeSearcher",
     "DxmwxSearcher",
-    "EightnovelSearcher",
     "EsjzoneSearcher",
     "HetushuSearcher",
     "I25zwSearcher",
     "Ixdzs8Searcher",
     "Jpxs123Searcher",
+    "N8novelSearcher",
     "PiaotiaSearcher",
     "QbtrSearcher",
     "QianbiSearcher",
@@ -32,12 +32,12 @@ __all__ = [
 from .aaatxt import AaatxtSearcher
 from .b520 import BiqugeSearcher
 from .dxmwx import DxmwxSearcher
-from .eightnovel import EightnovelSearcher
 from .esjzone import EsjzoneSearcher
 from .hetushu import HetushuSearcher
 from .i25zw import I25zwSearcher
 from .ixdzs8 import Ixdzs8Searcher
 from .jpxs123 import Jpxs123Searcher
+from .n8novel import N8novelSearcher
 from .piaotia import PiaotiaSearcher
 from .qbtr import QbtrSearcher
 from .qianbi import QianbiSearcher

novel_downloader/core/searchers/b520.py

@@ -17,7 +17,7 @@ logger = logging.getLogger(__name__)
 
 
 @register_searcher(
-    site_keys=["biquge", "bqg", "b520"],
+    site_keys=["biquge", "b520"],
 )
 class BiqugeSearcher(BaseSearcher):
     site_name = "biquge"

novel_downloader/core/searchers/base.py

@@ -12,13 +12,13 @@ from urllib.parse import quote_plus, urljoin
 
 import aiohttp
 
-from novel_downloader.core.interfaces import SearcherProtocol
 from novel_downloader.models import SearchResult
 from novel_downloader.utils.constants import DEFAULT_USER_HEADERS
 
 
-class BaseSearcher(abc.ABC, SearcherProtocol):
+class BaseSearcher(abc.ABC):
     site_name: str
+    priority: int = 1000
     BASE_URL: str = ""
     _session: ClassVar[aiohttp.ClientSession | None] = None
 

novel_downloader/core/searchers/{eightnovel.py → n8novel.py}

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 """
-novel_downloader.core.searchers.eightnovel
-------------------------------------------
+novel_downloader.core.searchers.n8novel
+---------------------------------------
 
 """
 
@@ -17,10 +17,10 @@ logger = logging.getLogger(__name__)
 
 
 @register_searcher(
-    site_keys=["eightnovel", "8novel"],
+    site_keys=["n8novel", "8novel"],
 )
-class EightnovelSearcher(BaseSearcher):
-    site_name = "8novel"
+class N8novelSearcher(BaseSearcher):
+    site_name = "n8novel"
     priority = 20
     BASE_URL = "https://www.8novel.com"
     SEARCH_URL = "https://www.8novel.com/search/"

novel_downloader/models/__init__.py

@@ -11,6 +11,7 @@ __all__ = [
     "DownloaderConfig",
     "ParserConfig",
     "FetcherConfig",
+    "FontOCRConfig",
     "ExporterConfig",
     "TextCleanerConfig",
     "BookInfoDict",
@@ -32,6 +33,7 @@ from .config import (
     DownloaderConfig,
     ExporterConfig,
     FetcherConfig,
+    FontOCRConfig,
     ParserConfig,
     TextCleanerConfig,
 )

novel_downloader/models/book.py

@@ -19,6 +19,7 @@ class ChapterInfoDict(TypedDict):
     title: str
     url: str
     chapterId: str
+    accessible: NotRequired[bool]
 
 
 class VolumeInfoDict(TypedDict):

novel_downloader/models/config.py

@@ -39,6 +39,17 @@ class DownloaderConfig:
     storage_batch_size: int = 1
 
 
+@dataclass
+class FontOCRConfig:
+    model_name: str | None = None
+    model_dir: str | None = None
+    input_shape: tuple[int, int, int] | None = None
+    device: str | None = None
+    precision: str = "fp32"
+    cpu_threads: int = 10
+    enable_hpi: bool = False
+
+
 @dataclass
 class ParserConfig:
     cache_dir: str = "./novel_cache"
@@ -46,6 +57,7 @@ class ParserConfig:
     decode_font: bool = False
     batch_size: int = 32
     save_font_debug: bool = False
+    fontocr_cfg: FontOCRConfig = field(default_factory=FontOCRConfig)
 
 
 @dataclass

novel_downloader/resources/config/settings.toml

@@ -2,13 +2,13 @@
 [general]
 retry_times = 3                    # 请求失败重试次数
 backoff_factor = 2.0
-timeout = 30.0                     # 页面加载超时时间 (秒)
+timeout = 30.0                     # 请求加载超时时间 (秒)
 max_connections = 10               # 并发连接的最大数
-max_rps = 1.0                      # 最大请求速率 (requests per second), 如不设置则请设置一个较大的数或负数
-request_interval = 2.0             # 同一本书各章节请求间隔 (秒)
-raw_data_dir = "./raw_data"        # 原始章节 JSON/DB 存放目录
+max_rps = 1000.0                   # 最大请求速率 (requests per second), 如不设置则请设置一个较大的数或负数
+request_interval = 1.0             # 同一本书各章节请求间隔 (秒)
+raw_data_dir = "./raw_data"        # 书籍原始 JSON/DB/图片 数据存放目录
 output_dir = "./downloads"         # 最终输出文件存放目录
-cache_dir = "./novel_cache"        # 本地缓存目录 (字体 / 图片等)
+cache_dir = "./novel_cache"        # 本地缓存目录
 workers = 2                        # 工作协程数
 skip_existing = true               # 是否跳过已存在章节
 storage_batch_size = 1             # SQLite 批量提交的章节数量
@@ -23,6 +23,17 @@ decode_font = false                # 是否尝试本地解码混淆字体
 batch_size = 32
 save_font_debug = false            # 是否保存字体解码调试数据
 
+# 以下为 PaddleOCR 文本识别的可选参数
+# 默认情况下, 请保持注释, 程序会使用 PaddleOCR 内置的默认值
+# 如果需要修改配置, 请取消注释并填写参数值 (参考官网文档)
+# https://www.paddleocr.ai/main/version3.x/module_usage/text_recognition.html
+
+model_name = "PP-OCRv5_mobile_rec"
+# model_dir = "/path/to/inference"
+# input_shape = [3, 48, 320]        # [C, H, W], 按所选模型文档填写, 不确定请注释
+# device = "gpu"                    # "cpu" / "gpu"
+# cpu_threads = 10
+
 # 各站点的特定配置
 [sites.qidian]  # 起点中文网
 book_ids = [
@@ -32,6 +43,13 @@ book_ids = [
 login_required = true              # 是否需要登录才能访问
 use_truncation = true              # 是否基于章节长度截断以避免重复内容
 
+[sites.qqbook]  # QQ 阅读
+book_ids = [
+  "0000000000",
+  "0000000000"
+]
+login_required = true
+
 [sites.esjzone]  # ESJ Zone
 book_ids = [
   "0000000000",

novel_downloader/resources/js_scripts/expr_to_json.js

@@ -0,0 +1,14 @@
+#!/usr/bin/env node
+
+let code = "";
+process.stdin.on("data", chunk => code += chunk);
+process.stdin.on("end", () => {
+  try {
+    // Make sure object literals parse correctly
+    const result = eval("(" + code + ")");
+    console.log(JSON.stringify(result));
+  } catch (err) {
+    console.error("Error:", err);
+    process.exit(1);
+  }
+});

novel_downloader/resources/js_scripts/qidian_decrypt_node.js

@@ -1,18 +1,22 @@
-window = global;
-null_fun = function(){console.log(arguments);}
-window.outerHeight = 1000
-window.innerHeight = 100
-globalThis = window
-self = window
-window.location = {}
-location.protocol = "https:"
-location.hostname = "vipreader.qidian.com"
-setTimeout = null_fun
-setInterval = null_fun
-document = {createElement: null_fun, documentElement: {}, createEvent: null_fun, currentScript: {src: "https://qdfepccdn.qidian.com/www.qidian.com/fock/116594983210.js"}, domain: 'qidian.com'}
-navigator = {userAgent: 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36'}
-performance = {}
-performance.navigation = {type: 1}
+#!/usr/bin/env node
+
+// ---- GLOBAL ENVIRONMENT SHIMS ----
+const shimEnv = {
+  outerHeight: 1000,
+  innerHeight: 100,
+  location: {
+    protocol: "https:",
+    hostname: "vipreader.qidian.com",
+  },
+};
+
+global.window = global;
+globalThis.window = global;
+globalThis.self = global;
+
+for (const [key, value] of Object.entries(shimEnv)) {
+  globalThis[key] = value;
+}
 
 // ---- DECRYPT FUNCTION ----
 const Fock = require('./4819793b.qeooxh.js');
@@ -41,7 +45,7 @@ const fs = require('fs');
   const [inputPath, outputPath] = process.argv.slice(2);
   if (!inputPath || !outputPath) {
     console.error(
-      "Usage: node script.js <input.json> <output.txt>"
+      "Usage: node decrypt_qd.js <input.json> <output.txt>"
     );
     process.exit(1);
   }
@@ -75,6 +79,7 @@ const fs = require('fs');
     ]);
 
     fs.writeFileSync(outputPath, result, "utf-8");
+    process.exit(0);
   } catch (err) {
     console.error("Failed to decrypt:", err);
     process.exit(1);

novel_downloader/resources/js_scripts/qq_decrypt_node.js

@@ -0,0 +1,92 @@
+#!/usr/bin/env node
+
+// ---- GLOBAL ENVIRONMENT SHIMS ----
+const _setInterval = global.setInterval;
+
+const shimEnv = {
+  location: {
+    protocol: "https:",
+    hostname: "book.qq.com",
+  },
+  setInterval: (fn, t) => typeof fn === "function" ? _setInterval(fn, t) : undefined,
+  document: {
+    createElement: (tag) => {
+      if (tag === "iframe") {
+        const win = {};
+        win.window = win;
+        win.eval = (code) => eval(code);
+        return {
+          style: {},
+          contentWindow: win,
+        };
+      }
+      return { style: {}, appendChild: () => {} };
+    },
+    body: { appendChild: () => {} },
+  },
+};
+
+global.window = global;
+globalThis.window = global;
+globalThis.self = global;
+
+for (const [key, value] of Object.entries(shimEnv)) {
+  globalThis[key] = value;
+}
+
+// ---- DECRYPT FUNCTION ----
+const Fock = require('./cefc2a5d.pz1phw.js');
+
+async function decrypt(enContent, cuChapterId, fkp, fuid) {
+  Fock.setupUserKey(fuid);
+  eval(atob(fkp));
+  isFockInit = true;
+
+  return new Promise((resolve, reject) => {
+    Fock.unlock(enContent, cuChapterId, (code, decrypted) => {
+      if (code === 0) {
+        resolve(decrypted);
+      } else {
+        reject(new Error(`Fock.unlock failed, code=${code}`));
+      }
+    });
+  });
+}
+
+// ---- MAIN ----
+const fs = require('fs');
+
+(async () => {
+  const [inputPath, outputPath] = process.argv.slice(2);
+
+  if (!inputPath || !outputPath) {
+    console.error("Usage: node decrypt_qq.js <input.json> <output.txt>");
+    process.exit(1);
+  }
+
+  try {
+    const inputData = fs.readFileSync(inputPath, "utf-8");
+    const [raw_enContent, raw_cuChapterId, raw_fkp, raw_fuid] = JSON.parse(inputData);
+
+    const decryptPromise = decrypt(
+      String(raw_enContent),
+      String(raw_cuChapterId),
+      String(raw_fkp),
+      String(raw_fuid)
+    );
+
+    const timeoutMs = 5000;
+    const timerPromise = new Promise((_, reject) => {
+      setTimeout(() => reject(new Error(`decrypt timeout after ${timeoutMs}ms`)), timeoutMs);
+    });
+
+    const result = await Promise.race([decryptPromise, timerPromise]);
+    console.log("result", result);
+
+    fs.writeFileSync(outputPath, result, "utf-8");
+    process.exit(0);
+  } catch (err) {
+    console.error("Failed to decrypt:", err);
+    process.exit(1);
+  }
+})();

novel_downloader/utils/constants.py

@@ -90,6 +90,12 @@ XIGUASHUWU_FONT_MAP_PATH = files("novel_downloader.resources.json").joinpath(
 )
 
 # JavaScript
+EXPR_TO_JSON_SCRIPT_PATH = files("novel_downloader.resources.js_scripts").joinpath(
+    "expr_to_json.js"
+)
 QD_DECRYPT_SCRIPT_PATH = files("novel_downloader.resources.js_scripts").joinpath(
     "qidian_decrypt_node.js"
 )
+QQ_DECRYPT_SCRIPT_PATH = files("novel_downloader.resources.js_scripts").joinpath(
+    "qq_decrypt_node.js"
+)

novel_downloader/utils/crypto_utils/aes_util.py

@@ -65,7 +65,7 @@ try:
 except ImportError:
     print(
         "[crypto_utils] Falling back to pure-Python AES_CBC.\n"
-        "Tip: pip install pycryptodome for ~800x faster speed."
+        "Tip: `pip install pycryptodome` for ~800x faster speed."
     )
     from novel_downloader.utils.crypto_utils.aes_v2 import AES_CBC
 

novel_downloader/utils/epub/constants.py

@@ -3,12 +3,7 @@
 novel_downloader.utils.epub.constants
 -------------------------------------
 
-EPUB-specific constants used by the builder, including:
-  * Directory names for OEBPS structure
-  * XML namespace URIs
-  * Package attributes and document-type declarations
-  * Media type mappings for images
-  * Template strings for container.xml and cover image HTML
+EPUB-specific constants used by the builder.
 """
 
 ROOT_PATH = "OEBPS"

novel_downloader/utils/fontocr/core.py

@@ -34,6 +34,7 @@ class FontOCR:
         device: str | None = None,
         precision: str = "fp32",
         cpu_threads: int = 10,
+        enable_hpi: bool = False,
         **kwargs: Any,
     ) -> None:
         """
@@ -54,6 +55,7 @@ class FontOCR:
             device=device,
             precision=precision,
             cpu_threads=cpu_threads,
+            enable_hpi=enable_hpi,
         )
 
     def predict(

novel_downloader/utils/fontocr/loader.py

@@ -9,6 +9,8 @@ Lazily load the FontOCR class.
 import logging
 from typing import TYPE_CHECKING
 
+from novel_downloader.models import FontOCRConfig
+
 if TYPE_CHECKING:
     from .core import FontOCR
 
@@ -17,11 +19,7 @@ logger = logging.getLogger(__name__)
 _FONT_OCR: "FontOCR | None" = None
 
 
-def get_font_ocr(
-    model_name: str | None = None,
-    model_dir: str | None = None,
-    input_shape: tuple[int, int, int] | None = None,
-) -> "FontOCR | None":
+def get_font_ocr(cfg: FontOCRConfig) -> "FontOCR | None":
     """
     Try to initialize and return a singleton FontOCR instance.
     Returns None if FontOCR or its dependencies are not available.
@@ -32,9 +30,13 @@ def get_font_ocr(
             from .core import FontOCR
 
             _FONT_OCR = FontOCR(
-                model_name=model_name,
-                model_dir=model_dir,
-                input_shape=input_shape,
+                model_name=cfg.model_name,
+                model_dir=cfg.model_dir,
+                input_shape=cfg.input_shape,
+                device=cfg.device,
+                precision=cfg.precision,
+                cpu_threads=cfg.cpu_threads,
+                enable_hpi=cfg.enable_hpi,
             )
         except ImportError:
             logger.warning(

novel_downloader/utils/node_decryptor/__init__.py

@@ -0,0 +1,13 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.utils.node_decryptor
+-------------------------------------
+
+Provides NodeDecryptor, which ensures a Node.js environment,
+downloads or installs the required JS modules (Fock + decrypt script),
+and invokes a Node.js subprocess to decrypt chapter content.
+"""
+
+__all__ = ["get_decryptor"]
+
+from .decryptor import get_decryptor