new json

temp.py

@@ -0,0 +1,87 @@
+import json
+
+with open('./data/final_wisdom.json', 'r' , encoding='utf-8') as f:
+    records = json.load(f)
+
+# new2records = {}
+# for item in records:
+#     key = records[item]['hekmat_number']
+#     new2records[key] = records[item]
+    
+# dictio = dict(sorted(new2records.items()))
+# final_data = json.dumps(dictio, ensure_ascii=False, indent=4)       
+# with open('./data/final_wisdom2.json', 'w', encoding='utf-8') as out:
+#     out.write(final_data)
+    
+before_hekmat_number = 0
+new_records = {}
+multi = [
+    'http://nahj.makarem.ir/wisdom/988',
+    "http://nahj.makarem.ir/wisdom/1089",
+    "http://nahj.makarem.ir/wisdom/1107",# 3 part
+    "http://nahj.makarem.ir/wisdom/1113",
+    "http://nahj.makarem.ir/wisdom/1314",
+    "http://nahj.makarem.ir/wisdom/1334"
+    ]
+
+titles = [row['title'] for row in records]
+for i, item in enumerate(records): 
+    url = item['url']
+    is_subpart = item['is-subpart']
+    title = item['title']
+    
+    if url == 'http://nahj.makarem.ir/wisdom/1070':
+        continue
+    if url in multi:
+        if url == "http://nahj.makarem.ir/wisdom/1107":
+            record_part_1 = records[i+1]
+            record_part_2 = records[i+2]
+            record_part_3 = records[i+3]
+            
+            is_subpart = False
+            arabic_text = f'{item['arabic_text']}\n{record_part_1['arabic_text']}\n{record_part_2['arabic_text']}\n{record_part_3['arabic_text']}'
+            persian_translate = f'{item['persian_translate']}\n{record_part_1['persian_translate']}\n{record_part_2['persian_translate']}\n{record_part_3['persian_translate']}'
+            Interpretation = f'{item['Interpretation']}\n{record_part_1['Interpretation']}\n{record_part_2['Interpretation']}\n{record_part_3['Interpretation']}'
+            
+            print(f'url merged =>> {record_part_1['url']} into {item['url']}')
+            print(f'url merged =>> {record_part_2['url']} into {item['url']}')
+            print(f'url merged =>> {record_part_3['url']} into {item['url']}')
+        else:
+            record_part_1 = records[i+1]
+            record_part_2 = records[i+2]
+            
+            is_subpart = False
+            arabic_text = f'{item['arabic_text']}\n{record_part_1['arabic_text']}\n{record_part_2['arabic_text']}'
+            persian_translate = f'{item['persian_translate']}\n{record_part_1['persian_translate']}\n{record_part_2['persian_translate']}'
+            Interpretation = f'{item['Interpretation']}\n{record_part_1['Interpretation']}\n{record_part_2['Interpretation']}'
+            
+            print(f'url merged =>> {record_part_1['url']} into {item['url']}')
+            print(f'url merged =>> {record_part_2['url']} into {item['url']}')
+    else:
+        arabic_text = item['arabic_text']
+        persian_translate = item['persian_translate']
+        Interpretation = item['Interpretation']
+    
+    if is_subpart:
+        print(f'jump for title: {title}')
+        continue
+    else:
+        hekmat_number = int(title.lstrip('حکمت').strip())
+        new_hekmat = {
+            "hekmat_number": hekmat_number,
+            "title": title,
+            "is-subpart": is_subpart,
+            "url": url,
+            "arabic_text": arabic_text,
+            "persian_translate": persian_translate,
+            "Interpretation": Interpretation
+        }
+        new_records[f'hekmat-{int(hekmat_number)}'] = new_hekmat
+        before_hekmat_number = hekmat_number
+        # print(f'hekmat {before_hekmat_number} inserted')
+ 
+final_data = json.dumps(new_records, ensure_ascii=False, indent=4)       
+with open('./data/final_wisdom.json', 'w', encoding='utf-8') as out:
+    out.write(final_data)
+
+print('finished')