novel-downloader 1.2.1__py3-none-any.whl → 1.3.0__py3-none-any.whl

novel_downloader/core/parsers/{qidian_parser → qidian}/browser/main_parser.py

@@ -1,8 +1,7 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
-novel_downloader.core.parsers.qidian_parser.browser.main_parser
----------------------------------------------------------------
+novel_downloader.core.parsers.qidian.browser.main_parser
+--------------------------------------------------------
 
 Main parser class for handling Qidian chapters rendered via a browser environment.
 
@@ -13,10 +12,11 @@ content extracted from dynamically rendered Qidian HTML pages.
 from __future__ import annotations
 
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Dict, Optional
+from typing import TYPE_CHECKING, Any
 
 from novel_downloader.config.models import ParserConfig
-from novel_downloader.core.parsers.base_parser import BaseParser
+from novel_downloader.core.parsers.base import BaseParser
+from novel_downloader.utils.chapter_storage import ChapterDict
 
 from ..shared import (
     is_encrypted,
@@ -47,9 +47,9 @@ class QidianBrowserParser(BaseParser):
 
         self._fixed_font_dir: Path = self._base_cache_dir / "fixed_fonts"
         self._fixed_font_dir.mkdir(parents=True, exist_ok=True)
-        self._font_debug_dir: Optional[Path] = None
+        self._font_debug_dir: Path | None = None
 
-        self._font_ocr: Optional[FontOCR] = None
+        self._font_ocr: FontOCR | None = None
         if self._decode_font:
             from novel_downloader.utils.fontocr import FontOCR
 
@@ -66,19 +66,23 @@ class QidianBrowserParser(BaseParser):
                 vec_weight=config.vec_weight,
                 font_debug=config.save_font_debug,
             )
-            self._font_debug_dir = self._base_cache_dir / "font_debug"
+            self._font_debug_dir = self._base_cache_dir / "qidian" / "font_debug"
             self._font_debug_dir.mkdir(parents=True, exist_ok=True)
 
-    def parse_book_info(self, html: str) -> Dict[str, Any]:
+    def parse_book_info(self, html_str: str) -> dict[str, Any]:
         """
         Parse a book info page and extract metadata and chapter structure.
 
-        :param html: Raw HTML of the book info page.
+        :param html_str: Raw HTML of the book info page.
         :return: Parsed metadata and chapter structure as a dictionary.
         """
-        return parse_book_info(html)
+        return parse_book_info(html_str)
 
-    def parse_chapter(self, html_str: str, chapter_id: str) -> Dict[str, Any]:
+    def parse_chapter(
+        self,
+        html_str: str,
+        chapter_id: str,
+    ) -> ChapterDict | None:
         """
         :param html: Raw HTML of the chapter page.
         :param chapter_id: Identifier of the chapter being parsed.

novel_downloader/core/parsers/{qidian_parser → qidian}/session/__init__.py

@@ -1,8 +1,7 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
-novel_downloader.core.parsers.qidian_parser.session
----------------------------------------------------------------
+novel_downloader.core.parsers.qidian.session
+--------------------------------------------
 
 This package provides parsing components for handling Qidian
 pages that have been rendered by a session.

novel_downloader/core/parsers/{qidian_parser → qidian}/session/chapter_encrypted.py

@@ -1,8 +1,7 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
-novel_downloader.core.parsers.qidian_parser.session.chapter_encrypted
----------------------------------------------------------------------
+novel_downloader.core.parsers.qidian.session.chapter_encrypted
+--------------------------------------------------------------
 
 Support for parsing encrypted chapters from Qidian using font OCR mapping,
 CSS rules, and custom rendering logic.
@@ -19,11 +18,12 @@ from __future__ import annotations
 import json
 import logging
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Any
 
 import tinycss2
 from bs4 import BeautifulSoup, Tag
 
+from novel_downloader.utils.chapter_storage import ChapterDict
 from novel_downloader.utils.network import download_font_file
 from novel_downloader.utils.text_utils import apply_font_mapping
 
@@ -40,7 +40,7 @@ if TYPE_CHECKING:
 
 logger = logging.getLogger(__name__)
 IGNORED_CLASS_LISTS = {"title", "review"}
-_decryptor: Optional[QidianNodeDecryptor] = None
+_decryptor: QidianNodeDecryptor | None = None
 
 
 def _get_decryptor() -> QidianNodeDecryptor:
@@ -58,7 +58,7 @@ def parse_encrypted_chapter(
     soup: BeautifulSoup,
     chapter_id: str,
     fuid: str,
-) -> Dict[str, Any]:
+) -> ChapterDict | None:
     """
     Extract and return the formatted textual content of an encrypted chapter.
 
@@ -75,15 +75,15 @@ def parse_encrypted_chapter(
     """
     try:
         if not (parser._decode_font and parser._font_ocr):
-            return {}
+            return None
         ssr_data = find_ssr_page_context(soup)
         chapter_info = extract_chapter_info(ssr_data)
         if not chapter_info:
             logger.warning(
                 "[Parser] ssr_chapterInfo not found for chapter '%s'", chapter_id
             )
-            return {}
-        debug_base_dir: Optional[Path] = None
+            return None
+        debug_base_dir: Path | None = None
         if parser._font_debug_dir:
             debug_base_dir = parser._font_debug_dir / chapter_id
             debug_base_dir.mkdir(parents=True, exist_ok=True)
@@ -101,15 +101,12 @@ def parse_encrypted_chapter(
         update_timestamp = chapter_info.get("updateTimestamp", 0)
         modify_time = chapter_info.get("modifyTime", 0)
         word_count = chapter_info.get("wordsCount", 0)
-        vip = bool(chapter_info.get("vipStatus", 0))
-        is_buy = bool(chapter_info.get("isBuy", 0))
         seq = chapter_info.get("seq", None)
-        order = chapter_info.get("chapterOrder", None)
         volume = chapter_info.get("extra", {}).get("volumeName", "")
 
         if not raw_html:
             logger.warning("[Parser] raw_html not found for chapter '%s'", chapter_id)
-            return {}
+            return None
 
         # extract + save font
         rf = json.loads(randomFont_str)
@@ -136,7 +133,7 @@ def parse_encrypted_chapter(
                 )
             except Exception as e:
                 logger.error("[Parser] decryption failed for '%s': %s", chapter_id, e)
-                return {}
+                return None
         main_paragraphs = extract_paragraphs_recursively(html_to_soup(raw_html))
         if debug_base_dir:
             main_paragraphs_path = debug_base_dir / "main_paragraphs_debug.json"
@@ -159,7 +156,7 @@ def parse_encrypted_chapter(
             paragraphs_str_path.write_text(paragraphs_str, encoding="utf-8")
 
         # Run OCR + fallback mapping
-        char_set = set(c for c in paragraphs_str if c not in {" ", "\n", "\u3000"})
+        char_set = {c for c in paragraphs_str if c not in {" ", "\n", "\u3000"}}
         refl_set = set(refl_list)
         char_set = char_set - refl_set
         if debug_base_dir:
@@ -190,33 +187,31 @@ def parse_encrypted_chapter(
         final_paragraphs_str = "\n\n".join(
             line.strip() for line in original_text.splitlines() if line.strip()
         )
-        chapter_info = {
+        return {
             "id": str(chapter_id),
-            "title": title,
+            "title": str(title),
             "content": final_paragraphs_str,
-            "author_say": author_say.strip() if author_say else "",
-            "updated_at": update_time,
-            "update_timestamp": update_timestamp,
-            "modify_time": modify_time,
-            "word_count": word_count,
-            "vip": vip,
-            "purchased": is_buy,
-            "order": order,
-            "seq": seq,
-            "volume": volume,
+            "extra": {
+                "author_say": author_say.strip() if author_say else "",
+                "updated_at": update_time,
+                "update_timestamp": update_timestamp,
+                "modify_time": modify_time,
+                "word_count": word_count,
+                "seq": seq,
+                "volume": volume,
+            },
         }
-        return chapter_info
 
     except Exception as e:
         logger.warning(
             "[Parser] parse error for encrypted chapter '%s': %s", chapter_id, e
         )
-    return {}
+    return None
 
 
 def extract_paragraphs_recursively(
     soup: BeautifulSoup, chapter_id: int = -1
-) -> List[Dict[str, Any]]:
+) -> list[dict[str, Any]]:
     """
     Extracts paragraph elements under <main id="c-{chapter_id}"> from HTML
     and converts them to a nested data structure for further processing.
@@ -227,7 +222,7 @@ def extract_paragraphs_recursively(
     :return list: List of parsed <p> paragraph data.
     """
 
-    def parse_element(elem: Any) -> Union[Dict[str, Any], None]:
+    def parse_element(elem: Any) -> dict[str, Any] | None:
         if not isinstance(elem, Tag):
             return None
         result = {"tag": elem.name, "attrs": dict(elem.attrs), "data": []}
@@ -245,7 +240,7 @@ def extract_paragraphs_recursively(
     if chapter_id > 0:
         main_id = f"c-{chapter_id}"
         main_tag = soup.find("main", id=main_id)
-        if not main_tag:
+        if not isinstance(main_tag, Tag):
             return []
     else:
         main_tag = soup
@@ -259,7 +254,7 @@ def extract_paragraphs_recursively(
     return result
 
 
-def parse_rule(css_str: str) -> Dict[str, Any]:
+def parse_rule(css_str: str) -> dict[str, Any]:
     """
     Parse a CSS string and extract style rules for rendering.
 
@@ -274,7 +269,7 @@ def parse_rule(css_str: str) -> Dict[str, Any]:
     :return: Dict with "rules" and "orders" for rendering.
     """
 
-    rules: Dict[str, Any] = {}
+    rules: dict[str, Any] = {}
     orders = []
 
     stylesheet = tinycss2.parse_stylesheet(
@@ -339,8 +334,8 @@ def parse_rule(css_str: str) -> Dict[str, Any]:
 
 
 def render_paragraphs(
-    main_paragraphs: List[Dict[str, Any]], rules: Dict[str, Any]
-) -> Tuple[str, List[str]]:
+    main_paragraphs: list[dict[str, Any]], rules: dict[str, Any]
+) -> tuple[str, list[str]]:
     """
     Applies the parsed CSS rules to the paragraph structure and
     reconstructs the visible text.
@@ -358,11 +353,11 @@ def render_paragraphs(
         - A reconstructed paragraph string with line breaks.
         - A list of mirrored (reflected) characters for later OCR processing.
     """
-    orders: List[Tuple[str, str]] = rules.get("orders", [])
+    orders: list[tuple[str, str]] = rules.get("orders", [])
     rules = rules.get("rules", {})
-    refl_list: List[str] = []
+    refl_list: list[str] = []
 
-    def apply_rule(data: Dict[str, Any], rule: Dict[str, Any]) -> str:
+    def apply_rule(data: dict[str, Any], rule: dict[str, Any]) -> str:
         if rule.get("delete-all", False):
             return ""
 
@@ -373,10 +368,7 @@ def render_paragraphs(
                 curr_str += first_data
 
         if rule.get("delete-first", False):
-            if len(curr_str) <= 1:
-                curr_str = ""
-            else:
-                curr_str = curr_str[1:]
+            curr_str = "" if len(curr_str) <= 1 else curr_str[1:]
 
         curr_str += rule.get("append-end-char", "")
 
@@ -433,7 +425,7 @@ def render_paragraphs(
                     logger.debug(f"[parser] not find p_class_str: {class_list}")
                     continue
                 # 普通标签处理，根据 orders 顺序匹配
-                for ord_selector, ord_id in orders:
+                for ord_selector, _ in orders:
                     tag_name = f"{ord_selector}"
                     if data.get("tag") != tag_name:
                         continue
@@ -442,7 +434,7 @@ def render_paragraphs(
                     ordered_cache[ord_selector] = apply_rule(data, curr_rule)
                     break
         # 最后按 orders 顺序拼接
-        for ord_selector, ord_id in orders:
+        for ord_selector, _ in orders:
             if ord_selector in ordered_cache:
                 paragraphs_str += ordered_cache[ord_selector]
 

novel_downloader/core/parsers/{qidian_parser → qidian}/session/chapter_normal.py

@@ -1,8 +1,7 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
-novel_downloader.core.parsers.qidian_parser.session.chapter_normal
-------------------------------------------------------------------
+novel_downloader.core.parsers.qidian.session.chapter_normal
+-----------------------------------------------------------
 
 Provides `parse_normal_chapter`, which will:
 
@@ -12,10 +11,11 @@ Provides `parse_normal_chapter`, which will:
 """
 
 import logging
-from typing import Any, Dict, Optional
 
 from bs4 import BeautifulSoup
 
+from novel_downloader.utils.chapter_storage import ChapterDict
+
 from ..shared import (
     extract_chapter_info,
     find_ssr_page_context,
@@ -25,7 +25,7 @@ from ..shared import (
 from .node_decryptor import QidianNodeDecryptor
 
 logger = logging.getLogger(__name__)
-_decryptor: Optional[QidianNodeDecryptor] = None
+_decryptor: QidianNodeDecryptor | None = None
 
 
 def _get_decryptor() -> QidianNodeDecryptor:
@@ -42,7 +42,7 @@ def parse_normal_chapter(
     soup: BeautifulSoup,
     chapter_id: str,
     fuid: str,
-) -> Dict[str, Any]:
+) -> ChapterDict | None:
     """
     Extract structured chapter info from a normal Qidian page.
 
@@ -58,7 +58,7 @@ def parse_normal_chapter(
             logger.warning(
                 "[Parser] ssr_chapterInfo not found for chapter '%s'", chapter_id
             )
-            return {}
+            return None
 
         title = chapter_info.get("chapterName", "Untitled")
         raw_html = chapter_info.get("content", "")
@@ -69,15 +69,12 @@ def parse_normal_chapter(
         update_timestamp = chapter_info.get("updateTimestamp", 0)
         modify_time = chapter_info.get("modifyTime", 0)
         word_count = chapter_info.get("wordsCount", 0)
-        vip = bool(chapter_info.get("vipStatus", 0))
-        is_buy = bool(chapter_info.get("isBuy", 0))
         seq = chapter_info.get("seq", None)
-        order = chapter_info.get("chapterOrder", None)
         volume = chapter_info.get("extra", {}).get("volumeName", "")
 
         if not raw_html:
             logger.warning("[Parser] raw_html not found for chapter '%s'", chapter_id)
-            return {}
+            return None
 
         if vip_status(soup):
             try:
@@ -90,7 +87,7 @@ def parse_normal_chapter(
                 )
             except Exception as e:
                 logger.error("[Parser] decryption failed for '%s': %s", chapter_id, e)
-                return {}
+                return None
 
         paras_soup = html_to_soup(raw_html)
         paras = [p.get_text(strip=True) for p in paras_soup.find_all("p")]
@@ -100,20 +97,19 @@ def parse_normal_chapter(
             "id": str(chapter_id),
             "title": title,
             "content": chapter_text,
-            "author_say": author_say.strip() if author_say else "",
-            "updated_at": update_time,
-            "update_timestamp": update_timestamp,
-            "modify_time": modify_time,
-            "word_count": word_count,
-            "vip": vip,
-            "purchased": is_buy,
-            "order": order,
-            "seq": seq,
-            "volume": volume,
+            "extra": {
+                "author_say": author_say.strip() if author_say else "",
+                "updated_at": update_time,
+                "update_timestamp": update_timestamp,
+                "modify_time": modify_time,
+                "word_count": word_count,
+                "seq": seq,
+                "volume": volume,
+            },
         }
 
     except Exception as e:
         logger.warning(
             "[Parser] parse error for normal chapter '%s': %s", chapter_id, e
         )
-        return {}
+    return None

novel_downloader/core/parsers/{qidian_parser → qidian}/session/chapter_router.py

@@ -1,8 +1,7 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
-novel_downloader.core.parsers.qidian_parser.session.chapter_router
-------------------------------------------------------------------
+novel_downloader.core.parsers.qidian.session.chapter_router
+-----------------------------------------------------------
 
 Routing logic for selecting the correct chapter parser for Qidian session pages.
 """
@@ -10,7 +9,9 @@ Routing logic for selecting the correct chapter parser for Qidian session pages.
 from __future__ import annotations
 
 import logging
-from typing import TYPE_CHECKING, Any, Dict
+from typing import TYPE_CHECKING
+
+from novel_downloader.utils.chapter_storage import ChapterDict
 
 from ..shared import (
     can_view_chapter,
@@ -29,7 +30,7 @@ def parse_chapter(
     parser: QidianSessionParser,
     html_str: str,
     chapter_id: str,
-) -> Dict[str, Any]:
+) -> ChapterDict | None:
     """
     Extract and return the formatted textual content of chapter.
 
@@ -45,11 +46,11 @@ def parse_chapter(
             logger.warning(
                 "[Parser] Chapter '%s' is not purchased or inaccessible.", chapter_id
             )
-            return {}
+            return None
 
         if is_encrypted(soup):
             if not parser._decode_font:
-                return {}
+                return None
             try:
                 from .chapter_encrypted import parse_encrypted_chapter
 
@@ -59,9 +60,9 @@ def parse_chapter(
                     "[Parser] Encrypted chapter '%s' requires extra dependencies.",
                     chapter_id,
                 )
-                return {}
+                return None
 
         return parse_normal_chapter(soup, chapter_id, parser._fuid)
     except Exception as e:
         logger.warning("[Parser] parse error for chapter '%s': %s", chapter_id, e)
-        return {}
+    return None

novel_downloader/core/parsers/{qidian_parser → qidian}/session/main_parser.py

@@ -1,8 +1,7 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
-novel_downloader.core.parsers.qidian_parser.session.main_parser
----------------------------------------------------------------
+novel_downloader.core.parsers.qidian.session.main_parser
+--------------------------------------------------------
 
 Main parser class for handling Qidian chapters rendered via a session.
 
@@ -13,10 +12,11 @@ content extracted from dynamically rendered Qidian HTML pages.
 from __future__ import annotations
 
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Dict, Optional
+from typing import TYPE_CHECKING, Any
 
 from novel_downloader.config.models import ParserConfig
-from novel_downloader.core.parsers.base_parser import BaseParser
+from novel_downloader.core.parsers.base import BaseParser
+from novel_downloader.utils.chapter_storage import ChapterDict
 from novel_downloader.utils.state import state_mgr
 
 from ..shared import (
@@ -48,12 +48,12 @@ class QidianSessionParser(BaseParser):
 
         self._fixed_font_dir: Path = self._base_cache_dir / "fixed_fonts"
         self._fixed_font_dir.mkdir(parents=True, exist_ok=True)
-        self._font_debug_dir: Optional[Path] = None
+        self._font_debug_dir: Path | None = None
 
         qd_cookies = state_mgr.get_cookies("qidian")
         self._fuid: str = qd_cookies.get("ywguid", "")
 
-        self._font_ocr: Optional[FontOCR] = None
+        self._font_ocr: FontOCR | None = None
         if self._decode_font:
             from novel_downloader.utils.fontocr import FontOCR
 
@@ -69,19 +69,23 @@ class QidianSessionParser(BaseParser):
                 vec_weight=config.vec_weight,
                 font_debug=config.save_font_debug,
             )
-            self._font_debug_dir = self._base_cache_dir / "font_debug"
+            self._font_debug_dir = self._base_cache_dir / "qidian" / "font_debug"
             self._font_debug_dir.mkdir(parents=True, exist_ok=True)
 
-    def parse_book_info(self, html: str) -> Dict[str, Any]:
+    def parse_book_info(self, html_str: str) -> dict[str, Any]:
         """
         Parse a book info page and extract metadata and chapter structure.
 
-        :param html: Raw HTML of the book info page.
+        :param html_str: Raw HTML of the book info page.
         :return: Parsed metadata and chapter structure as a dictionary.
         """
-        return parse_book_info(html)
+        return parse_book_info(html_str)
 
-    def parse_chapter(self, html_str: str, chapter_id: str) -> Dict[str, Any]:
+    def parse_chapter(
+        self,
+        html_str: str,
+        chapter_id: str,
+    ) -> ChapterDict | None:
         """
         :param html: Raw HTML of the chapter page.
         :param chapter_id: Identifier of the chapter being parsed.

novel_downloader/core/parsers/{qidian_parser → qidian}/session/node_decryptor.py

@@ -1,8 +1,7 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
-novel_downloader.core.parsers.qidian_parser.session.node_decryptor
-------------------------------------------------------------------
+novel_downloader.core.parsers.qidian.session.node_decryptor
+-----------------------------------------------------------
 
 Provides QidianNodeDecryptor, which ensures a Node.js environment,
 downloads or installs the required JS modules (Fock + decrypt script),
@@ -15,7 +14,6 @@ import shutil
 import subprocess
 import uuid
 from pathlib import Path
-from typing import Union
 
 from novel_downloader.utils.constants import (
     JS_SCRIPT_DIR,
@@ -68,7 +66,7 @@ class QidianNodeDecryptor:
         """
         # 1) Check Node.js
         if not shutil.which("node"):
-            raise EnvironmentError("Node.js is not installed or not in PATH.")
+            raise OSError("Node.js is not installed or not in PATH.")
 
         # 2) Copy bundled decrypt script into place if missing
         if not self.QIDIAN_DECRYPT_SCRIPT_PATH.exists():
@@ -102,8 +100,8 @@ class QidianNodeDecryptor:
 
     def decrypt(
         self,
-        ciphertext: Union[str, bytes],
-        chapter_id: Union[str, int],
+        ciphertext: str | bytes,
+        chapter_id: str | int,
         fkp: str,
         fuid: str,
     ) -> str:
@@ -120,7 +118,7 @@ class QidianNodeDecryptor:
         # Normalize inputs
         cipher_str = (
             ciphertext.decode("utf-8")
-            if isinstance(ciphertext, (bytes, bytearray))
+            if isinstance(ciphertext, (bytes | bytearray))
             else str(ciphertext)
         )
         chapter_str = str(chapter_id)
@@ -146,8 +144,7 @@ class QidianNodeDecryptor:
 
             proc = subprocess.run(
                 ["node", self.script_path.name, input_path.name, output_path.name],
-                stdout=subprocess.PIPE,
-                stderr=subprocess.PIPE,
+                capture_output=True,
                 text=True,
                 cwd=str(self.script_dir),
             )

novel_downloader/core/parsers/{qidian_parser → qidian}/shared/__init__.py

@@ -1,8 +1,7 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """
-novel_downloader.core.parsers.qidian_parser.shared
---------------------------------------------------
+novel_downloader.core.parsers.qidian.shared
+-------------------------------------------
 
 Shared parsing utilities for Qidian parser components.