opening_Files-checkpoint.ipynb
7.17 KB
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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#-*- coding: utf-8 -*-\n",
"\n",
"import os\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"def print_files_in_dir(root_dir, prefix):\n",
" files = os.listdir(root_dir)\n",
" fileList= []\n",
" for file in files:\n",
" if file == \".DS_Store\":\n",
" continue\n",
" path = os.path.join(root_dir, file)\n",
" fileList.append(prefix + path)\n",
" return fileList\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"C://Users//김서영//Desktop//temp//data//romance\\그리스.txt\n",
"C://Users//김서영//Desktop//temp//data//romance\\리틀잭.txt\n",
"C://Users//김서영//Desktop//temp//data//romance\\사랑은비를타고.txt\n",
"C://Users//김서영//Desktop//temp//data//romance\\시라노넘버.txt\n",
"C://Users//김서영//Desktop//temp//data//fantasy\\jesus_christ_superstar.txt\n",
"C://Users//김서영//Desktop//temp//data//fantasy\\더데빌.txt\n",
"C://Users//김서영//Desktop//temp//data//fantasy\\위키드.txt\n",
"C://Users//김서영//Desktop//temp//data//fantasy\\지저스크라이스트수퍼스타.txt\n",
"C://Users//김서영//Desktop//temp//data//fantasy\\지킬앤하이드.txt\n",
"C://Users//김서영//Desktop//temp//data//fantasy\\프랑켄슈타인.txt\n",
"C://Users//김서영//Desktop//temp//data//etc\\레미제라블.txt\n",
"C://Users//김서영//Desktop//temp//data//etc\\사운드오브뮤직.txt\n",
"C://Users//김서영//Desktop//temp//data//etc\\스웨그에이지 외쳐 조선.txt\n"
]
},
{
"ename": "UnicodeDecodeError",
"evalue": "'utf-8' codec can't decode byte 0xbd in position 4: invalid start byte",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mUnicodeDecodeError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-12-2a98c34edc2f>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 14\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 15\u001b[0m \u001b[0mfile\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mopen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;34m'r'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mencoding\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'UTF-8'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 16\u001b[1;33m \u001b[0mAll\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mfile\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 17\u001b[0m \u001b[0mlines\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mAll\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'\\n'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 18\u001b[0m \u001b[0mtotWords\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0midx\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlines\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\codecs.py\u001b[0m in \u001b[0;36mdecode\u001b[1;34m(self, input, final)\u001b[0m\n\u001b[0;32m 320\u001b[0m \u001b[1;31m# decode input (taking the buffer into account)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 321\u001b[0m \u001b[0mdata\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbuffer\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 322\u001b[1;33m \u001b[1;33m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mconsumed\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_buffer_decode\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0merrors\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfinal\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 323\u001b[0m \u001b[1;31m# keep undecoded input until the next call\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 324\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbuffer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mconsumed\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mUnicodeDecodeError\u001b[0m: 'utf-8' codec can't decode byte 0xbd in position 4: invalid start byte"
]
}
],
"source": [
"\n",
"\n",
"romanceWords = [] #모든 로맨스파일 단어 모음\n",
"etcWords = [] #모든 기타파일 단어 모음\n",
"fantasyWords = [] #모든 판타지파일 단어 모음\n",
"\n",
"totWords = [[],[],[]] #로맨스 - 판타지 - 기타\n",
"\n",
"folderDir = [\"C://Users//김서영//Desktop//temp//data//romance\",\"C://Users//김서영//Desktop//temp//data//fantasy\",\n",
" \"C://Users//김서영//Desktop//temp//data//etc\"]\n",
"\n",
"\n",
"for idx, folder in enumerate(folderDir):\n",
" subPaths = print_files_in_dir(folder,\"\") #각 폴더 하위 파일 경로\n",
" for path in subPaths:\n",
" print(path)\n",
" file = open(path,'r',encoding='UTF-8')\n",
" All = file.read()\n",
" lines = All.split('\\n')\n",
" totWords[idx].extend(lines)\n",
"print(totWords)\n",
" \n",
"\n",
" \n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[1, 2, 3, [5]]\n"
]
}
],
"source": [
"a = [1,2,3]\n",
"a.append([5])\n",
"print(a)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}