v2.5.10: 修正zip插件在压缩本子时未正确判断章节路径的问题，优化插件配置的文档 (hect0x7#225)

Author: hect0x7

assets/docs/sources/option_file_syntax.md

@@ -166,10 +166,10 @@ plugins:
     - plugin: subscribe_album_update # 自动订阅本子并下载、发送邮件通知的插件
       kwargs:
         download_if_has_update: true
-        email_notify: # 见下【发送qq邮件插件】
-          msg_from: x
-          msg_to: x
-          password: x
+        email_notify: # 参数说明见下【发送qq邮件插件】
+          msg_from: aaa@qq.com
+          msg_to: aaa@qq.com
+          password: dkjlakdjlkas
           title: album update !!!
           content: album update !!!
         album_photo_dict:
@@ -179,7 +179,14 @@ plugins:
     - plugin: zip # 压缩文件插件
       kwargs:
         level: photo # 按照章节，一个章节一个压缩文件
+        # level 也可以配成 album，表示一个本子对应一个压缩文件，该压缩文件会包含这个本子的所有章节
+
         filename_rule: Ptitle # 压缩文件的命名规则
+        # 请注意⚠ [https://github.com/hect0x7/JMComic-Crawler-Python/issues/223#issuecomment-2045227527]
+        # filename_rule和level有对应关系
+        # 如果level=[photo], filename_rule只能写Pxxx
+        # 如果level=[album], filename_rule只能写Axxx
+
         zip_dir: D:/jmcomic/zip/ # 压缩文件存放的文件夹
         delete_original_file: true # 压缩成功后，删除所有原文件和文件夹
 
@@ -195,17 +202,22 @@ plugins:
     - plugin: favorite_folder_export # 导出收藏夹插件
       log: false
       kwargs:
-        zip_enable: true # 对收藏夹进行压缩
+        zip_enable: true # 对导出文件进行压缩
         zip_filepath: ${JM_DOWNLOAD_DIR}/export.zip # 压缩文件路径
         zip_password: ${ZIP_PASSWORD} # 压缩密码
 
   before_photo:
     - plugin: skip_photo_with_few_images # 跳过下载章节图片数量过少的章节。一些韩漫的章节是公告，没有实际内容，就可以用该插件来跳过下载这些章节。
       kwargs:
-        at_least_image_count: 3
+        at_least_image_count: 3 # 至少要有多少张图，才下载此章节
 
   after_photo:
-    - plugin: j2p # jpg图片合成为一个pdf插件
+    - plugin: j2p # 图片合并插件，可以将下载下来的jpg图片合成为一个pdf插件
+      # 请注意⚠ 该插件的使用前提是，下载下来的图片是jpg图片
+      # 因此，使用该插件前，需要有如下配置:（下载图片格式转为jpg，上文有解释过此配置）
+      # download:
+      #   image:
+      #     suffix: .jpg
       kwargs:
         pdf_dir: D:/pdf # pdf存放文件夹
         filename_rule: Pid # pdf命名规则

src/jmcomic/__init__.py

@@ -2,7 +2,7 @@
 # 被依赖方 <--- 使用方
 # config <--- entity <--- toolkit <--- client <--- option <--- downloader
 
-__version__ = '2.5.9'
+__version__ = '2.5.10'
 
 from .api import *
 from .jm_plugin import *

src/jmcomic/jm_config.py

@@ -368,7 +368,7 @@ def new_postman(cls, session=False, **kwargs):
             'postman': {
                 'type': 'cffi',
                 'meta_data': {
-                    'impersonate': 'chrome',
+                    'impersonate': 'chrome110',
                     'headers': None,
                     'proxies': None,
                 }

src/jmcomic/jm_option.py

@@ -236,28 +236,6 @@ def decide_image_batch_count(self, photo: JmPhotoDetail):
     def decide_photo_batch_count(self, album: JmAlbumDetail):
         return self.download.threading.photo
 
-    def decide_album_dir(self, album: JmAlbumDetail) -> str:
-        """
-        该方法目前仅在 plugin-zip 中使用，不建议外部调用
-        """
-        dir_layer = []
-        dir_rule = self.dir_rule
-        for rule in dir_rule.rule_dsl.split('_'):
-            if rule == 'Bd':
-                dir_layer.append(dir_rule.base_dir)
-                continue
-
-            if rule[0] == 'A':
-                name = dir_rule.apply_rule_directly(album, None, rule)
-                dir_layer.append(name)
-
-            if rule[0] == 'P':
-                break
-
-        from os.path import join
-        # noinspection PyTypeChecker
-        return join(*dir_layer)
-
     # noinspection PyMethodMayBeStatic
     def decide_image_filename(self, image: JmImageDetail) -> str:
         """

src/jmcomic/jm_plugin.py

@@ -302,27 +302,19 @@ def invoke(self,
 
         if level == 'album':
             zip_path = self.get_zip_path(album, None, filename_rule, suffix, zip_dir)
-            dir_path = self.zip_album(album, photo_dict, zip_path)
-            if dir_path is not None:
-                # 要删除这个album文件夹
-                dir_zip_dict[dir_path] = zip_path
-                # 也要删除album下的photo文件夹
-                for d in files_of_dir(dir_path):
-                    dir_zip_dict[d] = None
+            self.zip_album(album, photo_dict, zip_path, dir_zip_dict)
 
         elif level == 'photo':
             for photo, image_list in photo_dict.items():
                 zip_path = self.get_zip_path(None, photo, filename_rule, suffix, zip_dir)
-                dir_path = self.zip_photo(photo, image_list, zip_path)
-                if dir_path is not None:
-                    dir_zip_dict[dir_path] = zip_path
+                self.zip_photo(photo, image_list, zip_path, dir_zip_dict)
 
         else:
             ExceptionTool.raises(f'Not Implemented Zip Level: {level}')
 
         self.after_zip(dir_zip_dict)
 
-    def zip_photo(self, photo, image_list: list, zip_path: str) -> Optional[str]:
+    def zip_photo(self, photo, image_list: list, zip_path: str, dir_zip_dict) -> Optional[str]:
         """
         压缩photo文件夹
         :returns: photo文件夹路径
@@ -333,50 +325,58 @@ def zip_photo(self, photo, image_list: list, zip_path: str) -> Optional[str]:
 
         all_filepath = set(map(lambda t: self.unified_path(t[0]), image_list))
 
-        return self.do_zip(photo_dir,
-                           zip_path,
-                           all_filepath,
-                           f'压缩章节[{photo.photo_id}]成功 → {zip_path}',
-                           )
+        if len(all_filepath) == 0:
+            self.log('无下载文件，无需压缩', 'skip')
+            return None
+
+        from common import backup_dir_to_zip
+        backup_dir_to_zip(
+            photo_dir,
+            zip_path,
+            acceptor=lambda f: os.path.isdir(f) or self.unified_path(f) in all_filepath
+        ).close()
+
+        self.log(f'压缩章节[{photo.photo_id}]成功 → {zip_path}', 'finish')
+        dir_zip_dict[self.unified_path(photo_dir)] = zip_path
 
     @staticmethod
     def unified_path(f):
         return fix_filepath(f, os.path.isdir(f))
 
-    def zip_album(self, album, photo_dict: dict, zip_path) -> Optional[str]:
+    def zip_album(self, album, photo_dict: dict, zip_path, dir_zip_dict) -> Optional[str]:
         """
         压缩album文件夹
         :returns: album文件夹路径
         """
-        all_filepath: Set[str] = set()
-
-        def addpath(f):
-            all_filepath.update(set(f))
 
-        album_dir = self.option.decide_album_dir(album)
-        # addpath(self.option.decide_image_save_dir(photo) for photo in photo_dict.keys())
-        addpath(path for ls in photo_dict.values() for path, _ in ls)
+        # 所有下载了的图片文件的路径
+        all_filepath: Set[str] = set(path for ls in photo_dict.values() for path, _ in ls)
 
-        return self.do_zip(album_dir,
-                           zip_path,
-                           all_filepath,
-                           msg=f'压缩本子[{album.album_id}]成功 → {zip_path}',
-                           )
-
-    def do_zip(self, source_dir, zip_path, all_filepath, msg):
         if len(all_filepath) == 0:
             self.log('无下载文件，无需压缩', 'skip')
-            return None
+            return
 
+        # 该本子的所有章节的图片所在文件夹
+        photo_dir_list = [self.option.decide_image_save_dir(photo) for photo in photo_dict.keys()]
+
+        # 压缩文件对象
         from common import backup_dir_to_zip
-        backup_dir_to_zip(
-            source_dir,
-            zip_path,
-            acceptor=lambda f: os.path.isdir(f) or self.unified_path(f) in all_filepath
-        ).close()
+        import zipfile
+        zfile = zipfile.ZipFile(zip_path, 'w')
+
+        for photo_dir in photo_dir_list:
+            photo_dir = self.unified_path(photo_dir)
+            backup_dir_to_zip(
+                photo_dir,
+                zip_path,
+                zfile=zfile,
+                prefix=os.path.basename(photo_dir.rstrip('/')),
+                acceptor=lambda f: os.path.isdir(f) or self.unified_path(f) in all_filepath
+            )
+            dir_zip_dict[photo_dir] = zip_path
 
-        self.log(msg, 'finish')
-        return self.unified_path(source_dir)
+        zfile.close()
+        self.log(f'压缩本子[{album.album_id}]成功 → {zip_path}', 'finish')
 
     def after_zip(self, dir_zip_dict: Dict[str, Optional[str]]):
         # 删除所有原文件