feat: 新增pdf 删除

server/apps/information/serializers.py

@@ -67,7 +67,7 @@ class AuditLogSerializer(serializers.ModelSerializer):
         fields = '__all__'
 
 class ParsepdfSerializer(serializers.ModelSerializer):
-
+    dep = serializers.CharField(source='belong_dept.name', read_only=True)
     class Meta(BaseMeta):
         model = Parsepdf
         fields = '__all__'

server/apps/information/views.py

@@ -367,6 +367,21 @@ class ParsePdfViewSet(RbacFilterSet, CreateUpdateCustomMixin, ModelViewSet):
     filterset_fields = ['belong_dept', 'annual']
     perms_map = {'get': '*', 'post': 'pdf_create'}
     
+    def destroy(self, request, *args, **kwargs):
+        # 判断执行状态，如果是“执行中”，则不允许删除
+        if self.get_object().status == "执行中":
+            return Response({'message': '执行中的数据不能删除'}, status=status.HTTP_400_BAD_REQUEST)
+        # 删除文件
+        file_path = os.path.join(settings.BASE_DIR, self.get_object().parse_excel)
+        if os.path.exists(file_path):
+            os.remove(file_path)
+        pdf_path = os.path.join(settings.BASE_DIR, self.get_object().pdf_path)
+        if os.path.exists(pdf_path):
+            os.remove(pdf_path)
+            
+        # 删除数据库记录
+        return super().destroy(request, *args, **kwargs)
+    
     #解析pdf到excel
     @action(detail=False, methods=['post'], perms_map={'post':'pdf_create'})
     @transaction.atomic

server/utils/pdf2txt.py

@@ -345,7 +345,6 @@ def get_index(text, pattern, span):
         return remain_text
 
 def run(pdf_path, excel_path, id):
-    print("-----------ids", id)
     # 提取PDF文本  
     text = extract_text_from_pdf(pdf_path) 
     with open("pdf2txt.txt", "w", encoding="utf-8") as f:
@@ -353,7 +352,6 @@ def run(pdf_path, excel_path, id):
     for pattern, local in RE_LIST:
     # 使用正则表达式匹配文本  
         matches = match_text_with_regex(text, pattern, 1)
-        print(matches,"------")
         fill_excel(matches, excel_path, local)
     # 特殊处理的
     for p, l, s in SPECIALLIST: