241106

hwpx/test05.py

@@ -38,14 +38,9 @@ class print_xml :
             data_file = open(xml_file_path,'r',encoding='utf-8')
             soup = BeautifulSoup(data_file,"xml")
             self.parsing(soup,extract_path)
-        
-        #soup_xml = soup.prettify()
-
-        #with open(xml_file_path,'rb') as f:
-        #   xml_content = f.read()
-        
-        #root = etree.XML(xml_content)
-        #pretty_xml_string = etree.tostring(root,pretty_print=True).decode('utf-8')
+        '''
+        xml 원본 파일 text 로 확인하기
+        '''
         '''
             with open(f"fine{i}.txt", "w",encoding='utf-8') as file:
                 file.write(soup.prettify())
@@ -53,20 +48,6 @@ class print_xml :
         '''
         return True
                
-        
-        '''
-        xml_dict = xmltodict.parse(xml_content)
-        json_data = json.dumps(xml_dict, indent=4)
-        # JSON 데이터를 파일로 저장
-        with open('output.json', 'w') as json_file:
-            json.dump(xml_dict, json_file, indent=4)
-
-        print("JSON 파일로 저장 완료: output.json")
-        '''
-        #print(pretty_xml_string)
-        #exit()
-        #return self.parsing(soup,extract_path) 
-               
     def table(self,tbl,zip_file_path) :
         
         max = 0
@@ -110,57 +91,32 @@ class print_xml :
                                 continue
                         elif t.text is None:
                             continue 
-                        #text += t.text 
         
                         if run.find("hp:tbl") :
                             data = self.table(run,zip_file_path)   
                             make_table[int(row)][int(col)].append(data)
      
-                       
-                        #print(text)
                         span = tc.find('hp:cellSpan')
                         colSpan = span.get('colSpan')
                         rowSpan = span.get('rowSpan')
-                            #make_table = make_table.tolist()
+                     
                         if rowSpan != "1" :
                             for i in range(0,int(rowSpan)):
                                 make_table[int(row)+i][int(col)].append(t.text)
-                        
                         else :
                             make_table[int(row)][int(col)].append(t.text) 
         
-                            ''' cellSpan을 구해서 같은 머라해야하노.. 세부분야?로 나눠져 있는 것을 넣어준다'''
-                        
-                            '''if colSpan != "1":
-                            for i in range(0,int(colSpan)):
-                                make_table[int(row)][int(col)+i] = text 
+                            ''' 
+                            cellSpan을 구해서 셀 병합 처리
                             '''
   
-        #make_table = make_table.tolist()
         data = {
             "type": "table",
             "content": make_table,
         }
         tbl.decompose() 
-        #self.obj_list.append(data)
         return data
     
-        '''
-        for i in make_table[0]:
-            if i is None :
-                print(i)
-        '''
-        '''
-        data = {
-            "type": "table",
-            "content": make_table,
-        }
-        '''
-        '''
-        self.obj_list.append(data)
-         
-        return make_table 
-        '''
 
     def text(self,p) :
         text_list = []
@@ -176,24 +132,15 @@ class print_xml :
             else:
                 continue
             text += ''.join(t.stripped_strings)
+            
         if text.strip() :
             text_list.append(text)
             
-        #print(text)
-        #text_list.append(text)
-     
-            
-        
-        #for i in p.find_all("hp:t"):
-       
-          
-        #text_array = np.array(text)
-        #text_array = text_array.tolist()
         data = {
             "type": "text",
             "content": text_list
         } 
-        #print(data)
+
         self.obj_list.append(data)
 
 
@@ -222,22 +169,12 @@ class print_xml :
                 data = self.image(tag_p,zip_file_path)
                 self.obj_list.append(data) 
                 
-            
             #elif tag_p.find_all('hp:drawText'):
             #    self.drawText(tag_p)
             
             elif tag_p.find_all('hp:t'):
                 if not tag_p.find_parent('hp:tbl'):
                     self.text(tag_p)    
-        #exit()
-            # for run in tag_p.findall('./hp:run',self.np):
-            #     for tag in run : 
-            #         if tag.tag == f'{{{self.np["hp"]}}}t':
-            #             self.text(tag)
-            #         elif tag.tag == f'{{{self.np["hp"]}}}tbl':
-            #             self.table(tag) 
-            #         elif tag.tag == f'{{{self.np["hp"]}}}pic': 
-            #             self.image(tag,zip_file_path)
                     
     def add(self,list):
         result = []
@@ -247,12 +184,6 @@ class print_xml :
                 if not item["content"] or item["content"] == [[]]:
                     continue  # 빈 content일 경우 추가하지 않고 건너뜀
                 current_text.append(item["content"])
-            #elif item["type"] == "table":
-            #    for i in item["content"]:
-            #        print(i)
-                    #for j in range(len(i)):
-                    #    if i[j]
-                #exit()    
             elif item["type"] != "text":
                 if current_text:
                     result.append({"type": "text", "content": current_text})