|
10鱼币
错误原因:
for each_line in f:
UnicodeDecodeError: 'gbk' codec can't decode byte 0xbf in position 2: illegal multibyte sequence
“gbk”编解码器无法在位置4中解码字节0x80:非法多字节序列
错误位置:
第三个def函数【def search_in_file(file_name,key)】第6行
下面是第30讲第4题答案:
- import os
- def print_pos(key_dict):
- keys = key_dict.keys()
- keys = sorted(keys) # 由于字典是无序的,我们这里对行数进行排序
- for each_key in keys:
- print('关键字出现在第 %s 行,第 %s 个位置。' % (each_key, str(key_dict[each_key])))
- def pos_in_line(line, key):
- pos = []
- begin = line.find(key)
- while begin != -1:
- pos.append(begin + 1) # 用户的角度是从1开始数
- begin = line.find(key, begin+1) # 从下一个位置继续查找
- return pos
- def search_in_file(file_name, key):
- f = open(file_name)
- count = 0 # 记录行数
- key_dict = dict() # 字典,用户存放key所在具体行数对应具体位置
- print('测试一')
- [color=Red] for each_line in f:[/color]
- count += 1
- print('测试三')
- if key in each_line:
- pos = pos_in_line(each_line, key) # key在每行对应的位置
- key_dict[count] = pos
- print('测试二')
- f.close()
- return key_dict
- def search_files(key, detail):
- all_files = os.walk(os.getcwd())
- txt_files = []
- for i in all_files:
- for each_file in i[2]:
- if os.path.splitext(each_file)[1] == '.txt': # 根据后缀判断是否文本文件
- each_file = os.path.join(i[0], each_file)
- txt_files.append(each_file)
-
- for each_txt_file in txt_files:
- key_dict = search_in_file(each_txt_file, key)
- if key_dict:
- print('================================================================')
- print('在文件【%s】中找到关键字【%s】' % (each_txt_file, key))
- if detail in ['YES', 'Yes', 'yes']:
- print_pos(key_dict)
- key = input('请将该脚本放于待查找的文件夹内,请输入关键字:')
- detail = input('请问是否需要打印关键字【%s】在文件中的具体位置(YES/NO):' % key)
- search_files(key, detail)
复制代码
|
-
最佳答案
查看完整内容
编码问题
open的时候要正确指定编码
参考我这个回答
http://bbs.fishc.com/forum.php?mod=viewthread&tid=89913&page=1#pid2934373
|