回答編集履歴
1
edit
test
CHANGED
|
@@ -21,3 +21,277 @@
|
|
|
21
21
|
https://qiita.com/ryu19maki/items/e5a3b470795de883a09a
|
|
22
22
|
|
|
23
23
|
https://pythondatascience.plavox.info/pandas/データフレームを出力する
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
|
|
27
|
+
---
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
手元では特に問題なくCSVファイルにできます。
|
|
32
|
+
|
|
33
|
+
|
|
34
|
+
|
|
35
|
+
```python
|
|
36
|
+
|
|
37
|
+
import pandas as pd
|
|
38
|
+
|
|
39
|
+
from bs4 import BeautifulSoup
|
|
40
|
+
|
|
41
|
+
|
|
42
|
+
|
|
43
|
+
a = '''
|
|
44
|
+
|
|
45
|
+
<table class="pro-table pro-table02 mb5 tableCross_1">
|
|
46
|
+
|
|
47
|
+
<thead>
|
|
48
|
+
|
|
49
|
+
<tr>
|
|
50
|
+
|
|
51
|
+
<th class="w7p" rowspan="2"> </th>
|
|
52
|
+
|
|
53
|
+
<th class="w5p" rowspan="2">合計</th>
|
|
54
|
+
|
|
55
|
+
<th colspan="9">内訳</th>
|
|
56
|
+
|
|
57
|
+
<th class="w5p area-disabled" rowspan="2"><a class="gonFloat8 cboxElement" href="#print">地図・クーポン印刷</a></th>
|
|
58
|
+
|
|
59
|
+
<th class="w5p area-disabled" rowspan="2">チョットぐに追加</th>
|
|
60
|
+
|
|
61
|
+
<th class="w5p area-disabled" rowspan="2">口コミ</th>
|
|
62
|
+
|
|
63
|
+
<th class="w5p area-disabled" rowspan="2">お店のブログ</th>
|
|
64
|
+
|
|
65
|
+
</tr>
|
|
66
|
+
|
|
67
|
+
<tr>
|
|
68
|
+
|
|
69
|
+
<th class="w5p">店舗トップ</th>
|
|
70
|
+
|
|
71
|
+
<th class="w5p"><a class="gonFloat cboxElement" href="#menu">メニュー</a></th>
|
|
72
|
+
|
|
73
|
+
<th class="w5p"><a class="gonFloat5 cboxElement" href="#seat">席・個室・貸切</a></th>
|
|
74
|
+
|
|
75
|
+
<th class="w5p"><a class="gonFloat2 cboxElement" href="#photo">写真</a></th>
|
|
76
|
+
|
|
77
|
+
<th class="w5p">こだわり</th>
|
|
78
|
+
|
|
79
|
+
<th class="w5p"><a class="gonFloat7 cboxElement" href="#map">地図</a></th>
|
|
80
|
+
|
|
81
|
+
<th class="w5p">クーポン</th>
|
|
82
|
+
|
|
83
|
+
<th class="w5p"><a class="gonFloat3 cboxElement" href="#yoyaku">予約</a></th>
|
|
84
|
+
|
|
85
|
+
<th class="w5p"><a class="gonFloat6 cboxElement" href="#other">その他</a></th>
|
|
86
|
+
|
|
87
|
+
</tr>
|
|
88
|
+
|
|
89
|
+
</thead>
|
|
90
|
+
|
|
91
|
+
<tbody>
|
|
92
|
+
|
|
93
|
+
<tr>
|
|
94
|
+
|
|
95
|
+
<th class="txtLeft">2016/11</th>
|
|
96
|
+
|
|
97
|
+
<td class="txtRight table1item1">8158</td>
|
|
98
|
+
|
|
99
|
+
<td class="txtRight table1item2">2740</td>
|
|
100
|
+
|
|
101
|
+
<td class="txtRight table1item3">2199</td>
|
|
102
|
+
|
|
103
|
+
<td class="txtRight table1item4">998</td>
|
|
104
|
+
|
|
105
|
+
<td class="txtRight table1item5">420</td>
|
|
106
|
+
|
|
107
|
+
<td class="txtRight table1item6">214</td>
|
|
108
|
+
|
|
109
|
+
<td class="txtRight table1item7">542</td>
|
|
110
|
+
|
|
111
|
+
<td class="txtRight table1item8">242</td>
|
|
112
|
+
|
|
113
|
+
<td class="txtRight table1item9">790</td>
|
|
114
|
+
|
|
115
|
+
<td class="txtRight table1item10">13</td>
|
|
116
|
+
|
|
117
|
+
<td class="txtRight table1item11">49</td>
|
|
118
|
+
|
|
119
|
+
<td class="txtRight table1item12">0</td>
|
|
120
|
+
|
|
121
|
+
<td class="txtRight table1item13">111</td>
|
|
122
|
+
|
|
123
|
+
<td class="txtRight table1item14">0</td>
|
|
124
|
+
|
|
125
|
+
</tr>
|
|
126
|
+
|
|
127
|
+
<tr>
|
|
128
|
+
|
|
129
|
+
<th class="txtLeft">2016/12</th>
|
|
130
|
+
|
|
131
|
+
<td class="txtRight table1item1">5401</td>
|
|
132
|
+
|
|
133
|
+
<td class="txtRight table1item2">1909</td>
|
|
134
|
+
|
|
135
|
+
<td class="txtRight table1item3">1255</td>
|
|
136
|
+
|
|
137
|
+
<td class="txtRight table1item4">510</td>
|
|
138
|
+
|
|
139
|
+
<td class="txtRight table1item5">360</td>
|
|
140
|
+
|
|
141
|
+
<td class="txtRight table1item6">140</td>
|
|
142
|
+
|
|
143
|
+
<td class="txtRight table1item7">562</td>
|
|
144
|
+
|
|
145
|
+
<td class="txtRight table1item8">139</td>
|
|
146
|
+
|
|
147
|
+
<td class="txtRight table1item9">515</td>
|
|
148
|
+
|
|
149
|
+
<td class="txtRight table1item10">11</td>
|
|
150
|
+
|
|
151
|
+
<td class="txtRight table1item11">75</td>
|
|
152
|
+
|
|
153
|
+
<td class="txtRight table1item12">0</td>
|
|
154
|
+
|
|
155
|
+
<td class="txtRight table1item13">67</td>
|
|
156
|
+
|
|
157
|
+
<td class="txtRight table1item14">0</td>
|
|
158
|
+
|
|
159
|
+
</tr>
|
|
160
|
+
|
|
161
|
+
<tr>
|
|
162
|
+
|
|
163
|
+
<th class="txtLeft">2017/01</th>
|
|
164
|
+
|
|
165
|
+
<td class="txtRight table1item1">4584</td>
|
|
166
|
+
|
|
167
|
+
<td class="txtRight table1item2">1534</td>
|
|
168
|
+
|
|
169
|
+
<td class="txtRight table1item3">1219</td>
|
|
170
|
+
|
|
171
|
+
<td class="txtRight table1item4">413</td>
|
|
172
|
+
|
|
173
|
+
<td class="txtRight table1item5">341</td>
|
|
174
|
+
|
|
175
|
+
<td class="txtRight table1item6">137</td>
|
|
176
|
+
|
|
177
|
+
<td class="txtRight table1item7">333</td>
|
|
178
|
+
|
|
179
|
+
<td class="txtRight table1item8">135</td>
|
|
180
|
+
|
|
181
|
+
<td class="txtRight table1item9">460</td>
|
|
182
|
+
|
|
183
|
+
<td class="txtRight table1item10">12</td>
|
|
184
|
+
|
|
185
|
+
<td class="txtRight table1item11">18</td>
|
|
186
|
+
|
|
187
|
+
<td class="txtRight table1item12">0</td>
|
|
188
|
+
|
|
189
|
+
<td class="txtRight table1item13">49</td>
|
|
190
|
+
|
|
191
|
+
<td class="txtRight table1item14">0</td>
|
|
192
|
+
|
|
193
|
+
</tr>
|
|
194
|
+
|
|
195
|
+
<tr>
|
|
196
|
+
|
|
197
|
+
<th class="txtLeft">2017/02</th>
|
|
198
|
+
|
|
199
|
+
<td class="txtRight table1item1">4821</td>
|
|
200
|
+
|
|
201
|
+
<td class="txtRight table1item2">1711</td>
|
|
202
|
+
|
|
203
|
+
<td class="txtRight table1item3">1243</td>
|
|
204
|
+
|
|
205
|
+
<td class="txtRight table1item4">407</td>
|
|
206
|
+
|
|
207
|
+
<td class="txtRight table1item5">335</td>
|
|
208
|
+
|
|
209
|
+
<td class="txtRight table1item6">134</td>
|
|
210
|
+
|
|
211
|
+
<td class="txtRight table1item7">299</td>
|
|
212
|
+
|
|
213
|
+
<td class="txtRight table1item8">169</td>
|
|
214
|
+
|
|
215
|
+
<td class="txtRight table1item9">513</td>
|
|
216
|
+
|
|
217
|
+
<td class="txtRight table1item10">10</td>
|
|
218
|
+
|
|
219
|
+
<td class="txtRight table1item11">22</td>
|
|
220
|
+
|
|
221
|
+
<td class="txtRight table1item12">0</td>
|
|
222
|
+
|
|
223
|
+
<td class="txtRight table1item13">60</td>
|
|
224
|
+
|
|
225
|
+
<td class="txtRight table1item14">0</td>
|
|
226
|
+
|
|
227
|
+
</tr>
|
|
228
|
+
|
|
229
|
+
<tr>
|
|
230
|
+
|
|
231
|
+
<tr class="total">
|
|
232
|
+
|
|
233
|
+
<th class="txtLeft">合計</th>
|
|
234
|
+
|
|
235
|
+
<td class="txtRight w100 table1item1">59010</td>
|
|
236
|
+
|
|
237
|
+
<td class="txtRight w100 table1item2">19188</td>
|
|
238
|
+
|
|
239
|
+
<td class="txtRight w100 table1item3">14620</td>
|
|
240
|
+
|
|
241
|
+
<td class="txtRight w100 table1item4">5547</td>
|
|
242
|
+
|
|
243
|
+
<td class="txtRight w100 table1item5">3837</td>
|
|
244
|
+
|
|
245
|
+
<td class="txtRight w100 table1item6">1584</td>
|
|
246
|
+
|
|
247
|
+
<td class="txtRight w100 table1item7">3993</td>
|
|
248
|
+
|
|
249
|
+
<td class="txtRight w100 table1item8">1521</td>
|
|
250
|
+
|
|
251
|
+
<td class="txtRight w100 table1item9">8615</td>
|
|
252
|
+
|
|
253
|
+
<td class="txtRight w100 table1item10">105</td>
|
|
254
|
+
|
|
255
|
+
<td class="txtRight w100 table1item11">347</td>
|
|
256
|
+
|
|
257
|
+
<td class="txtRight w100 table1item12">0</td>
|
|
258
|
+
|
|
259
|
+
<td class="txtRight w100 table1item13">664</td>
|
|
260
|
+
|
|
261
|
+
<td class="txtRight w100 table1item14">0</td>
|
|
262
|
+
|
|
263
|
+
</tr>
|
|
264
|
+
|
|
265
|
+
</tbody>
|
|
266
|
+
|
|
267
|
+
</table>
|
|
268
|
+
|
|
269
|
+
'''
|
|
270
|
+
|
|
271
|
+
|
|
272
|
+
|
|
273
|
+
dfs = pd.io.html.read_html(a)
|
|
274
|
+
|
|
275
|
+
df = dfs[0]
|
|
276
|
+
|
|
277
|
+
|
|
278
|
+
|
|
279
|
+
df.columns = ['date', '合計', '店舗トップ', 'メニュー',
|
|
280
|
+
|
|
281
|
+
'席・個室・貸切', '写真', 'こだわり', '地図',
|
|
282
|
+
|
|
283
|
+
'クーポン', '予約', 'その他', '地図・クーポン印刷',
|
|
284
|
+
|
|
285
|
+
'チョットぐに追加', '口コミ', 'お店のブログ']
|
|
286
|
+
|
|
287
|
+
|
|
288
|
+
|
|
289
|
+
df = df.set_index('date')
|
|
290
|
+
|
|
291
|
+
del df.index.name
|
|
292
|
+
|
|
293
|
+
|
|
294
|
+
|
|
295
|
+
df.to_csv('mydata.csv')
|
|
296
|
+
|
|
297
|
+
```
|