零基础入门python第30讲课后第4题出现错误，请问怎么解决

fengyunkuang

30讲4题遇到错误，代码打了一遍不对，直接拷贝的小甲鱼的答案，还是这个错误，请问怎么处理：

请将该脚本放于待查找的文件夹内，请输入关键字：小甲鱼
请问是否需要打印关键字【小甲鱼】在文件中的具体位置（YES/NO）：yes
Traceback (most recent call last):
  File "D:\homework5.py", line 56, in <module>
    search_files(key, detail)
  File "D:\homework5.py", line 46, in search_files
    key_dict = search_in_file(each_txt_file, key)
  File "D:\homework5.py", line 25, in search_in_file
    for each_line in f:
  File "D:\Python36\lib\codecs.py", line 321, in decode
    (result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xa0 in position 16: invalid start byte

zltzlt

把小甲鱼的代码发上来

fengyunkuang

zltzlt 发表于 2020-3-3 11:25
把小甲鱼的代码发上来

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
   
    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[count] = 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[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)

zltzlt

这样试试：

1. import os
   
2. 
   
3. def print_pos(key_dict):
   
4.     keys = key_dict.keys()
   
5.     keys = sorted(keys) # 由于字典是无序的，我们这里对行数进行排序
   
6.     for each_key in keys:
   
7.         print('关键字出现在第 %s 行，第 %s 个位置。' % (each_key, str(key_dict[each_key])))
   
8. 
   
9. 
   
10. def pos_in_line(line, key):
    
11.     pos = []
    
12.     begin = line.find(key)
    
13.     while begin != -1:
    
14.         pos.append(begin + 1) # 用户的角度是从1开始数
    
15.         begin = line.find(key, begin+1) # 从下一个位置继续查找
    
16. 
    
17.     return pos
    
18. 
    
19. 
    
20. def search_in_file(file_name, key):
    
21.     f = open(file_name, encoding="utf-8")
    
22.     count = 0 # 记录行数
    
23.     key_dict = dict() # 字典，用户存放key所在具体行数对应具体位置
    
24.    
    
25.     for each_line in f:
    
26.         count += 1
    
27.         if key in each_line:
    
28.             pos = pos_in_line(each_line, key) # key在每行对应的位置
    
29.             key_dict[count] = pos
    
30.    
    
31.     f.close()
    
32.     return key_dict
    
33. 
    
34. 
    
35. def search_files(key, detail):   
    
36.     all_files = os.walk(os.getcwd())
    
37.     txt_files = []
    
38. 
    
39.     for i in all_files:
    
40.         for each_file in i[2]:
    
41.             if os.path.splitext(each_file)[1] == '.txt': # 根据后缀判断是否文本文件
    
42.                 each_file = os.path.join(i[0], each_file)
    
43.                 txt_files.append(each_file)
    
44. 
    
45.     for each_txt_file in txt_files:
    
46.         key_dict = search_in_file(each_txt_file, key)
    
47.         if key_dict:
    
48.             print('================================================================')
    
49.             print('在文件【%s】中找到关键字【%s】' % (each_txt_file, key))
    
50.             if detail in ['YES', 'Yes', 'yes']:
    
51.                 print_pos(key_dict)
    
52. 
    
53. 
    
54. key = input('请将该脚本放于待查找的文件夹内，请输入关键字：')
    
55. 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)
    
56. search_files(key, detail)

复制代码

fengyunkuang

zltzlt 发表于 2020-3-3 11:28
这样试试：

还是报错

Traceback (most recent call last):
  File "D:\homework5.py", line 56, in <module>
    search_files(key, detail)
  File "D:\homework5.py", line 46, in search_files
    key_dict = search_in_file(each_txt_file, key)
  File "D:\homework5.py", line 25, in search_in_file
    for each_line in f:
  File "D:\Python36\lib\codecs.py", line 321, in decode
    (result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xa0 in position 16: invalid start byte

zltzlt

fengyunkuang 发表于 2020-3-3 11:30
还是报错

Traceback (most recent call last):

这样呢：

1. import os
   
2. 
   
3. def print_pos(key_dict):
   
4.     keys = key_dict.keys()
   
5.     keys = sorted(keys) # 由于字典是无序的，我们这里对行数进行排序
   
6.     for each_key in keys:
   
7.         print('关键字出现在第 %s 行，第 %s 个位置。' % (each_key, str(key_dict[each_key])))
   
8. 
   
9. 
   
10. def pos_in_line(line, key):
    
11.     pos = []
    
12.     begin = line.find(key)
    
13.     while begin != -1:
    
14.         pos.append(begin + 1) # 用户的角度是从1开始数
    
15.         begin = line.find(key, begin+1) # 从下一个位置继续查找
    
16. 
    
17.     return pos
    
18. 
    
19. 
    
20. def search_in_file(file_name, key):
    
21.     f = open(file_name, encoding="gbk")
    
22.     count = 0 # 记录行数
    
23.     key_dict = dict() # 字典，用户存放key所在具体行数对应具体位置
    
24.    
    
25.     for each_line in f:
    
26.         count += 1
    
27.         if key in each_line:
    
28.             pos = pos_in_line(each_line, key) # key在每行对应的位置
    
29.             key_dict[count] = pos
    
30.    
    
31.     f.close()
    
32.     return key_dict
    
33. 
    
34. 
    
35. def search_files(key, detail):   
    
36.     all_files = os.walk(os.getcwd())
    
37.     txt_files = []
    
38. 
    
39.     for i in all_files:
    
40.         for each_file in i[2]:
    
41.             if os.path.splitext(each_file)[1] == '.txt': # 根据后缀判断是否文本文件
    
42.                 each_file = os.path.join(i[0], each_file)
    
43.                 txt_files.append(each_file)
    
44. 
    
45.     for each_txt_file in txt_files:
    
46.         key_dict = search_in_file(each_txt_file, key)
    
47.         if key_dict:
    
48.             print('================================================================')
    
49.             print('在文件【%s】中找到关键字【%s】' % (each_txt_file, key))
    
50.             if detail in ['YES', 'Yes', 'yes']:
    
51.                 print_pos(key_dict)
    
52. 
    
53. 
    
54. key = input('请将该脚本放于待查找的文件夹内，请输入关键字：')
    
55. 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)
    
56. search_files(key, detail)

复制代码

fengyunkuang

zltzlt 发表于 2020-3-3 11:31
这样呢：

还是有错
Traceback (most recent call last):
  File "D:\homework5.py", line 56, in <module>
    search_files(key, detail)
  File "D:\homework5.py", line 46, in search_files
    key_dict = search_in_file(each_txt_file, key)
  File "D:\homework5.py", line 25, in search_in_file
    for each_line in f:
UnicodeDecodeError: 'gbk' codec can't decode byte 0xb4 in position 17: illegal multibyte sequence

zltzlt

用记事本打开你的文件，选择另存为，将右下角的编码改为 UTF-8 再保存。

然后用这段代码试试：

1. import os
   
2. 
   
3. def print_pos(key_dict):
   
4.     keys = key_dict.keys()
   
5.     keys = sorted(keys) # 由于字典是无序的，我们这里对行数进行排序
   
6.     for each_key in keys:
   
7.         print('关键字出现在第 %s 行，第 %s 个位置。' % (each_key, str(key_dict[each_key])))
   
8. 
   
9. 
   
10. def pos_in_line(line, key):
    
11.     pos = []
    
12.     begin = line.find(key)
    
13.     while begin != -1:
    
14.         pos.append(begin + 1) # 用户的角度是从1开始数
    
15.         begin = line.find(key, begin+1) # 从下一个位置继续查找
    
16. 
    
17.     return pos
    
18. 
    
19. 
    
20. def search_in_file(file_name, key):
    
21.     f = open(file_name, encoding="utf-8")
    
22.     count = 0 # 记录行数
    
23.     key_dict = dict() # 字典，用户存放key所在具体行数对应具体位置
    
24.    
    
25.     for each_line in f:
    
26.         count += 1
    
27.         if key in each_line:
    
28.             pos = pos_in_line(each_line, key) # key在每行对应的位置
    
29.             key_dict[count] = pos
    
30.    
    
31.     f.close()
    
32.     return key_dict
    
33. 
    
34. 
    
35. def search_files(key, detail):   
    
36.     all_files = os.walk(os.getcwd())
    
37.     txt_files = []
    
38. 
    
39.     for i in all_files:
    
40.         for each_file in i[2]:
    
41.             if os.path.splitext(each_file)[1] == '.txt': # 根据后缀判断是否文本文件
    
42.                 each_file = os.path.join(i[0], each_file)
    
43.                 txt_files.append(each_file)
    
44. 
    
45.     for each_txt_file in txt_files:
    
46.         key_dict = search_in_file(each_txt_file, key)
    
47.         if key_dict:
    
48.             print('================================================================')
    
49.             print('在文件【%s】中找到关键字【%s】' % (each_txt_file, key))
    
50.             if detail in ['YES', 'Yes', 'yes']:
    
51.                 print_pos(key_dict)
    
52. 
    
53. 
    
54. key = input('请将该脚本放于待查找的文件夹内，请输入关键字：')
    
55. 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)
    
56. search_files(key, detail)

复制代码

fengyunkuang

zltzlt 发表于 2020-3-3 11:38
用记事本打开你的文件，选择另存为，将右下角的编码改为 UTF-8 再保存。

然后用这段代码试试：

可以查到了，不过是这样提示的：

在文件【D:\看一看.txt】中找到关键字【小甲鱼】
关键字出现在第 1 行，第 [2] 个位置。
Traceback (most recent call last):
  File "D:\homework5.py", line 56, in <module>
    search_files(key, detail)
  File "D:\homework5.py", line 46, in search_files
    key_dict = search_in_file(each_txt_file, key)
  File "D:\homework5.py", line 25, in search_in_file
    for each_line in f:
  File "D:\Python36\lib\codecs.py", line 321, in decode
    (result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xa0 in position 16: invalid start byte

zltzlt

fengyunkuang 发表于 2020-3-3 11:45
可以查到了，不过是这样提示的：

在文件【D:\看一看.txt】中找到关键字【小甲鱼】

另存为时编码改为 UTF-8 了吗 ？

fengyunkuang

zltzlt 发表于 2020-3-3 11:46
另存为时编码改为 UTF-8 了吗 ？

改了，否则是查不到的，我看默认是ansi模式存的

fengyunkuang

有没有大佬能解答下，如果大家的都好用，是我的什么设置不对吗？

File "D:\Python36\lib\codecs.py", line 321, in decode
    (result, consumed) = self._buffer_decode(data, self.errors, final)
这个什么意思？

在文件【D:\看一看.txt】中找到关键字【小甲鱼】
关键字出现在第 1 行，第 [2] 个位置。
Traceback (most recent call last):
  File "D:\homework5.py", line 56, in <module>
    search_files(key, detail)
  File "D:\homework5.py", line 46, in search_files
    key_dict = search_in_file(each_txt_file, key)
  File "D:\homework5.py", line 25, in search_in_file
    for each_line in f:
  File "D:\Python36\lib\codecs.py", line 321, in decode
    (result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xa0 in position 16: invalid start byte