代码:
# 定义一个函数来处理文件 def process_file(src_filename, unique_filename): seen = set() duplicates = set() with open(src_filename, 'r', encoding='utf-8') as file: for line in file: # 将读取的行转换为小写,以避免大小写差异导致的重复 normalized_line = line.strip().lower() if normalized_line in seen: duplicates.add(normalized_line) else: seen.add(normalized_line) # 打印重复的行 for dup in duplicates: print(f"Duplicate: {dup}") # 将不重复的行写入新文件 with open(unique_filename, 'w', encoding='utf-8') as file: for line in seen: file.write(line + '\n') # 调用函数,指定源文件和新文件的名称 process_file('zhong.srt', 'unique.srt')
标签:并打印,重复,filename,内容,normalized,file,seen,line From: https://www.cnblogs.com/jingzaixin/p/18292713