Python：'gbk' codec can't decode byte 0x80 in position 20: illegal multibyte seq
自己写程序时，使用with open（） 打开文件时，出现这个错误，复制小甲鱼的示例代码运行还是出现这个问题。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)))
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
for each_line in f:
count += 1
if key in each_line:
pos = pos_in_line(each_line, key)# key在每行对应的位置
key_dict = pos
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:
if os.path.splitext(each_file) == '.txt':# 根据后缀判断是否文本文件
each_file = os.path.join(i, 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)
============================================================
Traceback (most recent call last):
File "F:/python/pythonProject/find_key.py", line 57, in <module>
search_files(key, detail)
File "F:/python/pythonProject/find_key.py", line 47, in search_files
key_dict = search_in_file(each_txt_file, key)
File "F:/python/pythonProject/find_key.py", line 26, in search_in_file
for each_line in f:
UnicodeDecodeError: 'gbk' codec can't decode byte 0x80 in position 20: illegal multibyte sequence
open里加个参数:encoding='utf-8' hrp 发表于 2020-11-17 20:19
open里加个参数:encoding='utf-8'
大佬，修改之后运行就出现了这样的错误
Traceback (most recent call last):
File "F:/python/pythonProject/find_key.py", line 57, in <module>
search_files(key, detail)
File "F:/python/pythonProject/find_key.py", line 47, in search_files
key_dict = search_in_file(each_txt_file, key)
File "F:/python/pythonProject/find_key.py", line 26, in search_in_file
for each_line in f:
File "C:\Python38\lib\codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xb3 in position 0: invalid start byte 这句
def search_in_file(file_name, key):
f = open(file_name)# 改这句
改为
def search_in_file(file_name, key):
f = open(file_name , encoding = 'UTF-8')# 改这句 jackz007 发表于 2020-11-17 20:33
这句
改为
大佬，我修改之后运行出现了另外的错误
def search_in_file(file_name, key):
f = open(file_name, encoding="UTF-8")
=====================================
Traceback (most recent call last):
File "F:/python/pythonProject/find_key.py", line 57, in <module>
search_files(key, detail)
File "F:/python/pythonProject/find_key.py", line 47, in search_files
key_dict = search_in_file(each_txt_file, key)
File "F:/python/pythonProject/find_key.py", line 26, in search_in_file
for each_line in f:
File "C:\Python38\lib\codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xb3 in position 0: invalid start byte 本帖最后由 hrp 于 2020-11-17 21:21 编辑
mcy2223535173 发表于 2020-11-17 20:31
大佬，修改之后运行就出现了这样的错误
Traceback (most recent call last):
那就是你的文件都不是以这两种编码保存的了，用chardet模块来猜测文件编码再打开吧，要不就用记事本打开那个报错的文件，重新以utf-8编码保存。
hrp 发表于 2020-11-17 21:03
那就是你的文件都不是以这两种编码保存的了，用chardet模块来猜测文件编码再打开吧，要不就用记事本打 ...
谢谢大佬，有文件无法用这两种编码打开，我使用其他的文件就可以打开了。
页:
[1]