[已解决]求助。。。。

XD--Wrf

def prtpos(key_dict):
    keys = key_dict.keys()
    keys = sorted(keys)
    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 find_line(line, key):
    pos = []
    begin = line.find(key)
    while begin != -1:
        pos.append(begin +1)
        begin = line.find(key, begin+1)

    return pos


def search_file(file_name, key):
    f = open(file_name, encoding='utf-8')
    count = 0
    key_dict = dict()

    for each_line in f:
        count += 1
        if key in each_line:
            pos = find_line(each_line, key)
            key_dict[count] = pos

    f.close()


def search_files(key, file_addr):

    all_files = os.walk(file_addr)
    txt_file = []

    for i in all_files:
        for each_file in i[2]:
            if os.path.splitext(each_file)[1] == '.txt':
                each_file = os.path.join(i[0], each_file)
                txt_file.append(each_file)

    for each in txt_file:
        key_dict =   search_file(each, key)
        if key_dict:
            print('在文件【%s】中找到关键字【%s】'%(each, key))
            prtpos(key_dict)

key = input('请输入关键字：')
file_addr = input('请输入地址：')
search_files(key, file_addr)






错误显示：
D:\py----practice\venv\Scripts\python.exe D:/py----practice/11.py
请输入关键字：希望
请输入地址：D://
Traceback (most recent call last):
  File "D:/py----practice/11.py", line 86, in <module>
    search_files(key, file_addr)
  File "D:/py----practice/11.py", line 79, in search_files
    key_dict =   search_file(each, key)
  File "D:/py----practice/11.py", line 58, in search_file
    for each_line in f:
  File "D:\Python\lib\codecs.py", line 322, in decode
    (result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xb4 in position 0: invalid start byte

进程已结束，退出代码 1

最佳答案

月排行榜 / 总排行榜

qiuyouzhi

2020-5-21 17:18:21

XD--Wrf 发表于 2020-5-21 17:16
去掉是类似gbk编码的错误

那你就用记事本改下编码试试
具体百度

跳转到最佳答案楼层

Twilight6

去掉 encoding = 'utf-8'

Twilight6

def prtpos(key_dict):
    keys = key_dict.keys()
    keys = sorted(keys)
    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 find_line(line, key):
    pos = []
    begin = line.find(key)
    while begin != -1:
        pos.append(begin +1)
        begin = line.find(key, begin+1)

    return pos


def search_file(file_name, key):
    f = open(file_name)
    count = 0
    key_dict = dict()

    for each_line in f:
        count += 1
        if key in each_line:
            pos = find_line(each_line, key)
            key_dict[count] = pos

    f.close()


def search_files(key, file_addr):

    all_files = os.walk(file_addr)
    txt_file = []

    for i in all_files:
        for each_file in i[2]:
            if os.path.splitext(each_file)[1] == '.txt':
                each_file = os.path.join(i[0], each_file)
                txt_file.append(each_file)

    for each in txt_file:
        key_dict =   search_file(each, key)
        if key_dict:
            print('在文件【%s】中找到关键字【%s】'%(each, key))
            prtpos(key_dict)

key = input('请输入关键字：')
file_addr = input('请输入地址：')
search_files(key, file_addr)

qiuyouzhi

把encoding = "utf-8"去掉

XD--Wrf

Twilight6 发表于 2020-5-21 16:18
去掉 encoding = 'utf-8'

D:\py----practice\venv\Scripts\python.exe D:/py----practice/11.py
请输入关键字：希望
请输入地址：D://
Traceback (most recent call last):
  File "D:/py----practice/11.py", line 86, in <module>
    search_files(key, file_addr)
  File "D:/py----practice/11.py", line 79, in search_files
    key_dict =   search_file(each, key)
  File "D:/py----practice/11.py", line 58, in search_file
    for each_line in f:
UnicodeDecodeError: 'gbk' codec can't decode byte 0xd2 in position 19: illegal multibyte sequence



删掉之后的结果是这样的。。想请问一下为什么

Twilight6

XD--Wrf 发表于 2020-5-21 16:47
D:\py----practice\venv\Scripts\python.exe D:/py----practice/11.py
请输入关键字：希望
请输入地址 ...

不要去掉试试，新建个干净点的文件夹，把那个txt文本放文件夹里面，如何地址填这个文件夹的路径试试

XD--Wrf

Twilight6 发表于 2020-5-21 16:57
不要去掉试试，新建个干净点的文件夹，把那个txt文本放文件夹里面，如何地址填这个文件夹的路径试试

加上之后，放到新文件夹中报出的还是最开始那个错误。。。

XD--Wrf

qiuyouzhi 发表于 2020-5-21 16:19
把encoding = "utf-8"去掉

去掉是类似gbk编码的错误

qiuyouzhi

XD--Wrf 发表于 2020-5-21 17:16
去掉是类似gbk编码的错误

那你就用记事本改下编码试试
具体百度

XD--Wrf

qiuyouzhi 发表于 2020-5-21 17:18
那你就用记事本改下编码试试
具体百度

另存为改成utf之后，还是会报出第一个的那种错误