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
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
|
import json
import re
from lxml import etree
def write(path, data):
with open(path, 'w', encoding='utf-8') as f:
_data = json.dumps(data, ensure_ascii=False)
f.write(_data)
return True
list_end = []
for i in range(1, 48):
path = 'data/%s.html' % i
f = open(path, 'r', encoding='utf-8')
st = f.read()
html = etree.HTML(st)
all_list = []
_id = html.xpath('/html/body/div[2]/div[2]/div/table/tbody/tr')
title = html.xpath('//*//font')
a = 0
c = '、'
for index in range(len(_id)):
new_title = title[a]
if '、' in new_title.text and bool(re.search(r'\d', new_title.text)):
c = c.split(sep='、', maxsplit=-1)
if c[0].isdigit():
c.remove(c[0])
c = '、'.join(c)
all_list.append(c)
c = new_title.text
else:
if bool(re.search(r'\d', new_title.text)) or '、' in new_title.text:
print('请确认这不是标题 || ', new_title.text)
c += '|' + new_title.text
c = c.replace('\n', '').replace('\r', '').replace('\t', '')
a += 1
all_list.remove(all_list[0])
all_list.append('##$%#%$#%$#$@$$%^#%$@#%$!#^$%$#^%')
a = 0
list_temp = []
for index in range(len(_id)):
id_num = dict(_id[a].attrib)
list_temp.append(id_num)
a += 1
list_emd = []
for x in list_temp:
if bool(x):
list_emd.append(x)
for index in range(len(list_emd)):
list_emd[index]['question_txt'] = all_list[index]
list_emd[index]['answer'] = '正确答案填在此'
list_emd[index]['answer_check_1'] = '检验成员1的答案'
list_emd[index]['answer_check_2'] = '检验成员2的答案'
list_emd[index]['answer_check_3'] = '检验成员3的答案'
list_emd[index]['answer_check_4'] = '检验成员4的答案'
list_emd[index]['answer_check_5'] = '检验成员5的答案'
list_emd[index]['answer_txt'] = '使用说明：将正确答案填入answer的引号中就可，多选不用间隔，示例 *A* *ABCD*'
list_emd[index]['id'] = '3'
del list_emd[index]['id']
list_end.append(list_emd)
list_end = sum(list_end, [])
def deletedup(li):
seen = set()
new_list_2 = []
print(li)
for d in li:
d2 = d['question_txt']
str1 = d['question_txt']
if str1 == '##$%#%$#%$#$@$$%^#%$@#%$!#^$%$#^%':
continue
if d2 not in seen:
new_list_2.append(d)
seen.add(d2)
return new_list_2
if __name__ == '__main__':
list_tools = deletedup(list_end)
print(list_tools)
print('总计:', len(list_tools), '条数据', '\n注意:请划到顶部确认那些东西是不是标题!!!!')
out_result = write('result.json', list_tools)
print('是否成功写入result.json文件:', out_result)
|
