fix: 修复非法文件名称报错的问题

1. 替换文件名称包含的非法字符
2. 替换文件名称包含的 Emoji 表情

README.md

@@ -426,3 +426,4 @@ async def example():
 * https://aiosqlite.omnilib.dev/en/stable/
 * https://click.palletsprojects.com/en/8.1.x/
 * https://github.com/thewh1teagle/rookie
+* https://github.com/carpedm20/emoji/

README_EN.md

@@ -427,3 +427,4 @@ async def example():
 * https://aiosqlite.omnilib.dev/en/stable/
 * https://click.palletsprojects.com/en/8.1.x/
 * https://github.com/thewh1teagle/rookie
+* https://github.com/carpedm20/emoji/

requirements.txt

@@ -9,3 +9,4 @@ httpx>=0.27.0
 fastapi>=0.111.0
 uvicorn>=0.30.1
 aiofiles>=24.1.0
+emoji>=2.12.1

source/application/app.py

@@ -17,8 +17,10 @@ from uvicorn import Config
 from uvicorn import Server
 
 from source.expansion import BrowserCookie
+from source.expansion import Cleaner
 from source.expansion import Converter
 from source.expansion import Namespace
+from source.expansion import beautify_string
 from source.module import DataRecorder
 from source.module import ExtractData
 from source.module import ExtractParams
@@ -65,6 +67,7 @@ class XHS:
     SHARE = compile(r"https?://www\.xiaohongshu\.com/discovery/item/\S+")
     SHORT = compile(r"https?://xhslink\.com/\S+")
     __INSTANCE = None
+    CLEANER = Cleaner()
 
     def __new__(cls, *args, **kwargs):
         if not cls.__INSTANCE:
@@ -270,7 +273,13 @@ class XHS:
                     values.append(self.__get_name_title(data))
                 case _:
                     values.append(data[key])
-        return self.manager.SEPARATE.join(values)
+        return self.CLEANER.filter_name(
+            self.manager.SEPARATE.join(values),
+            default=self.manager.SEPARATE.join((
+                data["作者ID"],
+                data["作品ID"],
+            )),
+        )
 
     @staticmethod
     def __get_name_time(data: dict) -> str:
@@ -280,7 +289,10 @@ class XHS:
         return self.manager.filter_name(data["作者昵称"]) or data["作者ID"]
 
     def __get_name_title(self, data: dict) -> str:
-        return self.manager.filter_name(data["作品标题"])[:64] or data["作品ID"]
+        return beautify_string(
+            self.manager.filter_name(data["作品标题"]),
+            64,
+        ) or data["作品ID"]
 
     async def monitor(self, delay=1, download=False, log=None, bar=None, data=True, ) -> None:
         logging(

source/expansion/__init__.py

@@ -6,3 +6,4 @@ from .truncate import trim_string
 from .truncate import truncate_string
 from .file_folder import file_switch
 from .file_folder import remove_empty_directories
+from .cleaner import Cleaner

source/expansion/cleaner.py

@@ -0,0 +1,89 @@
+from platform import system
+from string import whitespace
+from emoji import replace_emoji
+from warnings import warn
+
+
+class Cleaner:
+    def __init__(self):
+        """
+        替换字符串中包含的非法字符，默认根据系统类型生成对应的非法字符字典，也可以自行设置非法字符字典
+        """
+        self.rule = self.default_rule()  # 默认非法字符字典
+
+    @staticmethod
+    def default_rule():
+        """根据系统类型生成默认非法字符字典"""
+        if (s := system()) in ("Windows", "Darwin"):
+            rule = {
+                "/": "",
+                "\\": "",
+                "|": "",
+                "<": "",
+                ">": "",
+                "\"": "",
+                "?": "",
+                ":": "",
+                "*": "",
+                "\x00": "",
+            }  # Windows 系统和 Mac 系统
+        elif s == "Linux":
+            rule = {
+                "/": "",
+                "\x00": "",
+            }  # Linux 系统
+        else:
+            warn("不受支持的操作系统类型，可能无法正常去除非法字符！")
+            rule = {}
+        cache = {i: "" for i in whitespace[1:]}  # 补充换行符等非法字符
+        return rule | cache
+
+    def set_rule(self, rule: dict[str, str], update=True):
+        """
+        设置非法字符字典
+
+        :param rule: 替换规则，字典格式，键为非法字符，值为替换后的内容
+        :param update: 如果是 True，则与原有规则字典合并，否则替换原有规则字典
+        """
+        self.rule = {**self.rule, **rule} if update else rule
+
+    def filter(self, text: str) -> str:
+        """
+        去除非法字符
+
+        :param text: 待处理的字符串
+        :return: 替换后的字符串，如果替换后字符串为空，则返回 None
+        """
+        for i in self.rule:
+            text = text.replace(i, self.rule[i])
+        return text
+
+    def filter_name(
+            self,
+            text: str,
+            replace: str = "",
+            default: str = "",
+    ) -> str:
+        """过滤文件夹名称中的非法字符"""
+        text = text.replace(":", ".")
+
+        text = self.filter(text)
+
+        text = replace_emoji(text, replace, )
+
+        text = self.clear_spaces(text)
+
+        text = text.strip().strip(".").strip("_")
+
+        return text or default
+
+    @staticmethod
+    def clear_spaces(string: str):
+        """将连续的空格转换为单个空格"""
+        return " ".join(string.split())
+
+
+if __name__ == "__main__":
+    demo = Cleaner()
+    print(demo.rule)
+    print(demo.filter_name(""))