Merge pull request #1059 from TachibanaKimika/master

添加自定义正则 & 番号大写转换配置

config.ini

@@ -53,6 +53,11 @@ naming_rule = number+'-'+title
 max_title_len = 50
 ; 刮削后图片是否命名为番号
 image_naming_with_number = 0
+; 番号大写 1 | 0, 仅在写入数据时会进行大写转换, 搜索刮削流程则不影响
+number_uppercase = 0
+; 自定义正则表达式, 多个正则使用空格隔开, 第一个分组为提取的番号, 若自定义正则未能匹配到番号则使用默认规则
+; example: ([A-Za-z]{2,4}\-\d{3}) ([A-Za-z]{2,4}00\d{3})
+number_regexs = 
 
 [update]
 update_check = 1

config.py

@@ -343,6 +343,18 @@ def image_naming_with_number(self) -> bool:
         except:
             return False
 
+    def number_uppercase(self) -> bool:
+        try:
+            return self.conf.getboolean("Name_Rule", "number_uppercase")
+        except:
+            return False
+
+    def number_regexs(self) -> str:
+        try:
+            return self.conf.get("Name_Rule", "number_regexs")
+        except:
+            return ""
+
     def update_check(self) -> bool:
         try:
             return self.conf.getboolean("update", "update_check")
@@ -473,6 +485,8 @@ def _default_config() -> configparser.ConfigParser:
         conf.set(sec4, "naming_rule", "number + '-' + title")
         conf.set(sec4, "max_title_len", "50")
         conf.set(sec4, "image_naming_with_number", "0")
+        conf.set(sec4, "number_uppercase", "0")
+        conf.set(sec4, "number_regexs", "")
 
         sec5 = "update"
         conf.add_section(sec5)

number_parser.py

@@ -40,6 +40,15 @@ def get_number(debug: bool, file_path: str) -> str:
     filepath = os.path.basename(file_path)
     # debug True 和 False 两块代码块合并，原因是此模块及函数只涉及字符串计算，没有IO操作，debug on时输出导致异常信息即可
     try:
+        # 先对自定义正则进行匹配
+        if config.getInstance().number_regexs().split().__len__() > 0:
+            for regex in config.getInstance().number_regexs().split():
+                try:
+                    if re.search(regex, filepath):
+                        return re.search(regex, filepath).group()
+                except Exception as e:
+                    print(f'[-]custom regex exception: {e} [{regex}]')
+
         file_number = get_number_by_dict(filepath)
         if file_number:
             return file_number

scraper.py

@@ -165,6 +165,10 @@ def get_data_from_json(
         cover_small = tmpArr[0].strip('\"').strip('\'')
     # ====================处理异常字符 END================== #\/:*?"<>|
 
+    # 处理大写
+    if conf.number_uppercase():
+        json_data['number'] = number.upper()
+
     # 返回处理后的json_data
     json_data['title'] = title
     json_data['original_title'] = title