在遇到各种比较大的问题时候,行数过多导致打开处理会出问题,则需要切割,则可以用按行数切割的方法来处理。
代码如下:
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59
|
import os class SplitFiles(): """按行分割文件""" def __init__(self, file_name, line_count=200): """初始化要分割的源文件名和分割后的文件行数""" self.file_name = file_name self.line_count = line_count def split_file(self): if self.file_name and os.path.exists(self.file_name): try: with open(self.file_name) as f : temp_count = 0 temp_content = [] part_num = 1 for line in f: if temp_count < self.line_count: temp_count += 1 else : self.write_file(part_num, temp_content) part_num += 1 temp_count = 1 temp_content = [] temp_content.append(line) else : self.write_file(part_num, temp_content) except IOError as err: print(err) else: print("%s is not a validate file" % self.file_name) def get_part_file_name(self, part_num): """"获取分割后的文件名称:在源文件相同目录下建立临时文件夹temp_part_file,然后将分割后的文件放到该路径下""" temp_path = os.path.dirname(self.file_name) part_file_name = temp_path + "temp_part_file" if not os.path.exists(temp_path) : os.makedirs(temp_path) part_file_name += os.sep + "temp_file_" + str(part_num) + ".part" return part_file_name def write_file(self, part_num, *line_content): """将按行分割后的内容写入相应的分割文件中""" part_file_name = self.get_part_file_name(part_num) print(line_content) try : with open(part_file_name, "w") as part_file: part_file.writelines(line_content[0]) except IOError as err: print(err) if __name__ == "__main__": sf = SplitFiles(r"F:\multiple_thread_read_file.txt") sf.split_file()
|