Optimized the functions.

split_document.py

@@ -13,51 +13,42 @@ def file_open():
     __processor(file)
 
 
-def __writer(doc_id, title, content, url):
+def __writer(doc_id, title, content, url, tags, date, category):
     file = open(f"docs/{doc_id}.json", "w")
     dictionary = {
         "doc_id": doc_id,
         "title": title,
         "content": content,
-        "url": url
+        "tags": tags,
+        "date": date,
+        "url": url,
+        "category": category
     }
 
     json.dump(dictionary, file)
 
 
-def __object_clear(lst):
-    lst.clear()
-
-
-def __processor(file):
-    data = json.load(file)
-
-    for i in tqdm(range(14000), desc="Splatted: "):
+def __retrieval(data, i, tag):
+    try:
         obj_cnt = ''
         lst = list()
-
-        try:
-            for characters in data[f"{i}"]["title"]:
+        for characters in data[f"{i}"][tag]:
             lst.append(characters)
             obj_cnt = ''.join(lst)
+        return obj_cnt
+    except Exception as ignore:
+        print(f"We have a Exception!! {ignore.with_traceback}")
 
-            title = obj_cnt
-            __object_clear(lst)
-
-            for characters in data[f"{i}"]["content"]:
-                lst.append(characters)
-                obj_cnt = ''.join(lst)
-
-            content = obj_cnt
-            __object_clear(lst)
-
-            for characters in data[f"{i}"]["url"]:
-                lst.append(characters)
-                obj_cnt = ''.join(lst)
 
-            url = obj_cnt
-            __object_clear(lst)
+def __processor(file):
+    data = json.load(file)
 
-            __writer(i, title, content, url)
-        except Exception as ignore:
-            pass
+    for i in tqdm(range(14000), desc="Splatted: "):
+        title = __retrieval(data, i, "title")
+        content = __retrieval(data, i, "content")
+        url = __retrieval(data, i, "url")
+        tags = __retrieval(data, i, "tags")
+        date = __retrieval(data, i, "date")
+        category = __retrieval(data, i, "category")
+
+        __writer(i, title, content, url, tags, date, category)