🐛✨ 修复下载问题以及其他小功能

1. 修复了下载问题，现在可以正常下载了 2. 递归读取子文件夹内的漫画，感谢@spr-equinox 3. 新增下载画质和大小选项(未时装) 4. 新增命名样式选项(未时装) 5. 新增哈希值校验选项(未时装) 6. 更新了user-agent
Zeal-L · Nov 14, 2024 · 5dce5af · 5dce5af
1 parent bae7f5f
commit 5dce5af
Show file tree

Hide file tree

Showing 16 changed files with 1,427 additions and 878 deletions.
diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -19,6 +19,7 @@ qrcode = "^7.4.2"
 qt-material = "^2.14"
 requests = "^2.31.0"
 retrying = "^1.3.4"
+pycryptodome = "^3.21.0"
 
 [tool.poetry.group.dev.dependencies]
 auto-py-to-exe = "^2.42.0"

diff --git a/src/BiliQrCode.py b/src/BiliQrCode.py
@@ -31,7 +31,7 @@ def __init__(self, mainGUI: MainGUI) -> None:
         self.qrcode_key = None
         self.close_flag = False
         self.headers = {
-            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
+            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36",
             "origin": "https://manga.bilibili.com",
         }
 

diff --git a/src/Comic.py b/src/Comic.py
@@ -26,10 +26,13 @@
 class Comic:
     """单本漫画 综合信息类"""
 
-    def __init__(self, comic_id: int, mainGUI: MainGUI) -> None:
+    def __init__(self, comic_id: int, mainGUI: MainGUI, save_path: str = "") -> None:
         self.mainGUI = mainGUI
         self.comic_id = comic_id
-        self.save_path = mainGUI.getConfig("save_path")
+        if save_path == "":
+            self.save_path = mainGUI.getConfig("save_path")
+        else:
+            self.save_path = save_path
         self.num_thread = mainGUI.getConfig("num_thread")
         self.num_downloaded = 0
         self.episodes = []
@@ -38,7 +41,7 @@ def __init__(self, comic_id: int, mainGUI: MainGUI) -> None:
             "https://manga.bilibili.com/twirp/comic.v1.Comic/ComicDetail?device=pc&platform=web"
         )
         self.headers = {
-            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
+            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36",
             "origin": "https://manga.bilibili.com",
             "referer": f"https://manga.bilibili.com/detail/mc{comic_id}?from=manga_homepage",
             "cookie": f"SESSDATA={mainGUI.getConfig('cookie')}",

diff --git a/src/DownloadManager.py b/src/DownloadManager.py
@@ -2,6 +2,7 @@
 该模块包含了一个下载管理器类，用于管理漫画下载任务的创建、更新和删除等操作
 """
 
+import re
 import time
 from concurrent.futures import ThreadPoolExecutor
 
@@ -151,11 +152,16 @@ def __thread__EpisodeTask(self, curr_id: int, epi: Episode) -> None:
             if self.terminated:
                 epi.clear(imgs_path)
                 return
-            if img.get("token") is not None:
+            if img.get("token"):
                 img_url = f"{img['url']}?token={img['token']}"
+            elif img.get("complete_url"):
+                img_url = img["complete_url"]
             else:
                 img_url = img["url"]
-            img_path = epi.downloadImg(index, img_url)
+            img_url = re.sub(r"@[^?]*\?", "", img_url)
+            match_cpx = re.search(r"[?&]cpx=([^&]*)", img_url)
+            cpx = match_cpx.group(1) if match_cpx else ""
+            img_path = epi.downloadImg(index, img_url, cpx)
             if img_path is None:
                 self.reportError(curr_id)
                 epi.clearAfterSave(imgs_path)

diff --git a/src/Episode.py b/src/Episode.py
@@ -4,12 +4,14 @@
 
 from __future__ import annotations
 
+import base64
 import glob
 import json
 import os
 import re
 import shutil
 from typing import TYPE_CHECKING
+from urllib.parse import unquote
 from zipfile import ZipFile, ZIP_DEFLATED
 
 import piexif
@@ -30,6 +32,7 @@
     __copyright__,
     __version__,
     isCheckSumValid,
+    AES_CBCDecrypt,
     logger,
     myStrFilter,
 )
@@ -94,7 +97,7 @@ def __init__(
             self.title = re.sub(r"^([0-9\-\.]+)$", r"第\1话", self.title)
 
         self.headers = {
-            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
+            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36",
             "origin": "https://manga.bilibili.com",
             "referer": f"https://manga.bilibili.com/detail/mc{comic_id}/{self.id}?from=manga_homepage",
             "cookie": f"SESSDATA={mainGUI.getConfig('cookie')}",
@@ -511,12 +514,13 @@ def _() -> None:
 
     ############################################################
 
-    def downloadImg(self, index: int, img_url: str) -> str:
-        """根据 url 和 token 下载图片
+    def downloadImg(self, index: int, img_url: str, cpx: str) -> str:
+        """根据 url 和 cpx 下载图片
 
         Args:
             index (int): 章节中图片的序号
             img_url (str): 图片的合法 url
+            cpx (str): 图片的加密密钥
 
         Returns:
             str: 图片的保存路径
@@ -525,12 +529,14 @@ def downloadImg(self, index: int, img_url: str) -> str:
         # ?###########################################################
         # ? 下载图片
         @retry(stop_max_delay=MAX_RETRY_LARGE, wait_exponential_multiplier=RETRY_WAIT_EX)
-        def _() -> bytes:
+        def _() -> list[bytes, str, bool]:
             try:
                 if img_url.find("token") != -1:
                     res = requests.get(img_url, timeout=TIMEOUT_LARGE)
-                else:
+                elif img_url:
                     res = requests.get(img_url, headers=self.headers, timeout=TIMEOUT_LARGE)
+                else:
+                    raise requests.RequestException
 
             except requests.RequestException as e:
                 logger.warning(
@@ -543,17 +549,12 @@ def _() -> bytes:
                     f"状态码：{res.status_code}, 理由: {res.reason} 重试中..."
                 )
                 raise requests.HTTPError()
-            isValid, md5 = isCheckSumValid(res.headers["Etag"], res.content)
-            if not isValid:
-                logger.warning(
-                    f"《{self.comic_name}》章节：{self.title} - {index} - {img_url} - 下载内容Checksum不正确! 重试中...\n"
-                    f"\t{res.headers['Etag']} ≠ {md5}"
-                )
-                raise requests.HTTPError()
-            return res.content
+            md5 = res.headers["Etag"]
+            hit_encrypt = not res.headers.get("content-type").startswith("image/")
+            return res.content, md5, hit_encrypt
 
         try:
-            img = _()
+            img, md5, hit_encrypt = _()
         except requests.RequestException as e:
             logger.error(
                 f"《{self.comic_name}》章节：{self.title} - {index} - {img_url} 重复下载图片多次后失败!\n{e}"
@@ -564,6 +565,47 @@ def _() -> bytes:
             )
             return None
 
+        # ?###########################################################
+        # ? 解密图片
+        @retry(stop_max_attempt_number=1)
+        def _() -> None:
+            nonlocal img
+            if not cpx or not hit_encrypt or not img:
+                return
+            cpx_text = unquote(cpx)
+            cpx_char = base64.b64decode(cpx_text)
+            iv = cpx_char[60:76]
+            img_flag = img[0]
+            if img_flag == 0:
+                raise ValueError("图片文件读取异常!")
+            data_length = int.from_bytes(img[1: 5])
+            key = img[data_length + 5:]
+            content = img[5:data_length + 5]
+            head = AES_CBCDecrypt(content[0:20496], key, iv)
+            img = head + content[20496:]
+
+        try:
+            _()
+            isValid, img_md5 = isCheckSumValid(md5, img)
+            if not isValid:
+                logger.warning(
+                    f"《{self.comic_name}》章节：{self.title} - {index} - {img_url} - 下载内容Checksum不正确! 重试中...\n"
+                    f"\t{md5} ≠ {img_md5}"
+                )
+                raise requests.HTTPError()
+        except OSError as e:
+            logger.error(
+                f"《{self.comic_name}》章节：{self.title} - {index} - {img_url} - {path_to_save} - 处理图片失败!\n{e}"
+            )
+            logger.exception(e)
+            self.mainGUI.signal_message_box.emit(
+                f"《{self.comic_name}》章节：{self.title} - {index} - 处理图片失败!\n"
+                f"已暂时跳过此章节, 并删除所有缓存文件！\n"
+                f"请重新尝试或者重启软件!\n\n"
+                f"更多详细信息请查看日志文件, 或联系开发者！"
+            )
+            raise e
+
         # ?###########################################################
         # ? 保存图片
         img_format = img_url.split(".")[-1].split("?")[0].lower().replace("&append=", "")

diff --git a/src/SearchComic.py b/src/SearchComic.py
@@ -26,7 +26,7 @@ def __init__(self, comic_name: str, sessdata: str) -> None:
             "https://manga.bilibili.com/twirp/comic.v1.Comic/Search?device=pc&platform=web"
         )
         self.headers = {
-            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
+            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36",
             "origin": "https://manga.bilibili.com",
             "referer": "https://manga.bilibili.com/search?from=manga_homepage",
             "cookie": f"SESSDATA={sessdata}",

diff --git a/src/Utils.py b/src/Utils.py
@@ -4,6 +4,7 @@
 
 from __future__ import annotations
 
+import base64
 import ctypes
 import hashlib
 import logging
@@ -13,6 +14,8 @@
 from logging.handlers import TimedRotatingFileHandler
 from sys import platform
 from typing import TYPE_CHECKING
+from Crypto.Util.Padding import unpad
+from Crypto.Cipher import AES
 
 import requests
 from PySide6.QtCore import Qt, QUrl
@@ -145,14 +148,36 @@ def sizeToBytes(size_str: str) -> int:
 ############################################################
 
 
-def isCheckSumValid(etag, content) -> tuple[bool, str]:
+def isCheckSumValid(etag: str, content) -> tuple[bool, str]:
     """判断MD5是否有效
 
     Returns:
         tuple[bool, str]: (是否有效, MD5)
     """
-    md5 = hashlib.md5(content).hexdigest()
-    return etag == md5, md5
+    md5 = base64.b64encode(hashlib.md5(content).digest()).decode()
+    if md5 == etag:
+        return md5 == etag, etag
+    else:
+        md5 = hashlib.md5(content).hexdigest()
+    return md5 == etag, etag
+
+############################################################
+
+
+def AES_CBCDecrypt(cipher_data: bytes, key: bytes, iv: bytes) -> bytes:
+    """使用AES-CBC进行解密
+
+    Args:
+        cipher_data (str): 加密数据
+        key (str): 密钥
+        iv (str): 初始化向量
+
+    Returns:
+        bytes: 解密数据
+    """
+    cipher = AES.new(key, AES.MODE_CBC, iv)
+    decrypted_data = unpad(cipher.decrypt(cipher_data), AES.block_size)
+    return decrypted_data
 
 
 ############################################################

diff --git a/src/ui/MangaUI.py b/src/ui/MangaUI.py
@@ -241,6 +241,7 @@ def updateMyLibrary(self, notice: bool = False) -> bool:
                 self.updateMyLibrarySingle,
                 comic_id,
                 comic_info["comic_path"],
+                comic_info["root_path"],
             )
             for comic_id, comic_info in self.mainGUI.my_library.items()
         )
@@ -274,15 +275,16 @@ def updateMyLibraryWatcher(self, futures: list, notice: bool) -> None:
         self.mainGUI.label_myLibrary_tip.setText("(右键打开文件夹)")
 
     ############################################################
-    def updateMyLibrarySingle(self, comic_id: int, comic_path: str) -> int | None:
+    def updateMyLibrarySingle(self, comic_id: int, comic_path: str, root_path: str) -> int | None:
         """添加单个漫画到我的库存
 
         Args:
             comic_id (int): 漫画ID
             comic_path (str): 漫画保存路径
+            root_path (str): 漫画保存路径上级
         """
 
-        comic = Comic(comic_id, self.mainGUI)
+        comic = Comic(comic_id, self.mainGUI, root_path)
         data = comic.getComicInfo()
         # ? 获取漫画信息失败直接跳过
         if not data:
@@ -547,6 +549,7 @@ def getEpisodeList(self, comic: Comic) -> None:
                 background = QColor(0, 255, 0, 50)
             if not epi.isAvailable():
                 flags = Qt.ItemFlag.NoItemFlags
+                background = QColor(0, 0, 0, 40)
             else:
                 num_unlocked += 1
 
@@ -922,15 +925,17 @@ def get_meta_dict(self, path: str) -> dict:
 
         meta_dict = {}
         try:
-            for item in os.listdir(path):
-                if os.path.exists(os.path.join(path, item, "元数据.json")):
-                    with open(os.path.join(path, item, "元数据.json"), "r", encoding="utf-8") as f:
-                        comic_path = os.path.join(path, item)
-                        data = json.load(f)
-                        meta_dict[data["id"]] = {
-                            "comic_name": data["title"],
-                            "comic_path": comic_path,
-                        }
+            for dirpath, dirs, files in os.walk(path):
+                for item in dirs:
+                    if os.path.exists(os.path.join(dirpath, item, "元数据.json")):
+                        with open(os.path.join(dirpath, item, "元数据.json"), "r", encoding="utf-8") as f:
+                            comic_path = os.path.join(dirpath, item)
+                            data = json.load(f)
+                            meta_dict[data["id"]] = {
+                                "comic_name": data["title"],
+                                "comic_path": comic_path,
+                                "root_path": path,
+                            }
         except (OSError, ValueError) as e:
             logger.error(f"读取元数据时发生错误\n {e}")
         return meta_dict