updated code to avoid translating already translated content
This commit is contained in:
+4
-4
@@ -14,7 +14,7 @@ import pandas as pd
|
||||
|
||||
from database import get_all
|
||||
from clean_data import clean_content_df
|
||||
from translate import translate
|
||||
from translate import translate, get_untranslated
|
||||
from database import Data_table
|
||||
|
||||
# def update():
|
||||
@@ -74,6 +74,8 @@ def translate_content():
|
||||
# load all content from database
|
||||
print('loading data from database...')
|
||||
df = get_all()
|
||||
# remove already translated content
|
||||
df = df[df['content_en'].isna()]
|
||||
# clean content
|
||||
print('cleaning content...')
|
||||
content_clean_list, id_list = clean_content_df(df)
|
||||
@@ -101,9 +103,7 @@ def translate_content():
|
||||
dt.execute(query, val_dict)
|
||||
except Exception as e:
|
||||
print(f'error when sending translated content to database: id={id}')
|
||||
|
||||
|
||||
|
||||
time.sleep(2)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
Reference in New Issue
Block a user