移除字幕檔中的英文句子，保留中文的句子

如果一個字幕檔，包含類似這樣的內容:

00:00:12:05 --> 00:00:12:20
Welcome.
歡迎大家。

要把這樣的檔案中英文句子的部分移除，可以用下列的 python 程式碼來處理。


    

      

        

  

    
    


        


  


  

        

          

          
def is_chinese(string):
        
        

          

          
    for ch in string:
        
        

          

          
        if u'\u4e00' <= ch <= u'\u9ffff':
        
        

          

          
            return True
        
        

          

          
    return False
        
        

          

          


        
        

          

          


        
        

          

          
with open('MindfulnessofBreathing3.txt', mode='r') as in_file, \
        
        

          

          
     open('MindfulnessofBreathing3zh.txt', mode='w') as out_file:
        
        

          

          


        
        

          

          
    for line in in_file:
        
        

          

          
        if (line[0].isnumeric()):
        
        

          

          
            # print(line)
        
        

          

          
            out_file.write(line)
        
        

          

          
        elif (is_chinese(line)):
        
        

          

          
            # print(line)
        
        

          

          
            out_file.write(line)
        
        

          

          
            out_file.write("\n")
        
  



    

  


      
      

        view raw
        
          subtitle.remove.english.py
        
        hosted with ❤ by GitHub