回答編集履歴
3
追記
test
CHANGED
|
@@ -190,7 +190,11 @@
|
|
|
190
190
|
|
|
191
191
|
別回答も置いておきます。
|
|
192
192
|
|
|
193
|
+
前提条件として liの子要素にi要素が必ず1個だけ存在する。
|
|
194
|
+
|
|
195
|
+
|
|
196
|
+
|
|
193
|
-
|
|
197
|
+
というのを仮定できるならば以下のコードでも取得できます。
|
|
194
198
|
|
|
195
199
|
```Python
|
|
196
200
|
|
2
別回答を追加
test
CHANGED
|
@@ -185,3 +185,17 @@
|
|
|
185
185
|
[Beautiful Soup 4.2.0 Doc. 日本語訳](http://kondou.com/BS4/)
|
|
186
186
|
|
|
187
187
|
[str.strip](https://docs.python.org/3.6/library/stdtypes.html#str.strip)
|
|
188
|
+
|
|
189
|
+
|
|
190
|
+
|
|
191
|
+
別回答も置いておきます。
|
|
192
|
+
|
|
193
|
+
liの子要素にi要素が必ず存在する前提を置けるならば。以下のコードでも取得できます。
|
|
194
|
+
|
|
195
|
+
```Python
|
|
196
|
+
|
|
197
|
+
tag = soup.find("li", class_="text-en text-c")
|
|
198
|
+
|
|
199
|
+
print(tag.i.text.strip())
|
|
200
|
+
|
|
201
|
+
```
|
1
追記
test
CHANGED
|
@@ -3,3 +3,185 @@
|
|
|
3
3
|
|
|
4
4
|
|
|
5
5
|
contentsList[index].text で取得できませんか？
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
|
|
13
|
+
2018/02/28追記
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
|
|
17
|
+
以下のソースコードでどうでしょうか？
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
```Python
|
|
22
|
+
|
|
23
|
+
# -*- coding: utf8 -*-
|
|
24
|
+
|
|
25
|
+
from bs4 import BeautifulSoup, NavigableString
|
|
26
|
+
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
def get_content():
|
|
32
|
+
|
|
33
|
+
body = """
|
|
34
|
+
|
|
35
|
+
<li class="text-en text-c">
|
|
36
|
+
|
|
37
|
+
A
|
|
38
|
+
|
|
39
|
+
<a href="/word/en/change/#ej-14756">
|
|
40
|
+
|
|
41
|
+
<span class="a_line">
|
|
42
|
+
|
|
43
|
+
<span class="a_moji" title="changeの意味">change</span>
|
|
44
|
+
|
|
45
|
+
</span>
|
|
46
|
+
|
|
47
|
+
</a>
|
|
48
|
+
|
|
49
|
+
<a href="/word/en/of/#ej-58587">
|
|
50
|
+
|
|
51
|
+
<span class="a_line">
|
|
52
|
+
|
|
53
|
+
<span class="a_moji" title="ofの意味">
|
|
54
|
+
|
|
55
|
+
of
|
|
56
|
+
|
|
57
|
+
</span>
|
|
58
|
+
|
|
59
|
+
</span>
|
|
60
|
+
|
|
61
|
+
</a>
|
|
62
|
+
|
|
63
|
+
<a href="/word/en/air/#ej-1635">
|
|
64
|
+
|
|
65
|
+
<span class="a_line">
|
|
66
|
+
|
|
67
|
+
<span class="a_moji" title="airの意味">
|
|
68
|
+
|
|
69
|
+
air
|
|
70
|
+
|
|
71
|
+
</span>
|
|
72
|
+
|
|
73
|
+
</span>
|
|
74
|
+
|
|
75
|
+
</a>
|
|
76
|
+
|
|
77
|
+
<a href="/word/en/always/#ej-2421">
|
|
78
|
+
|
|
79
|
+
<span class="a_line">
|
|
80
|
+
|
|
81
|
+
<span class="a_moji" title="alwaysの意味">
|
|
82
|
+
|
|
83
|
+
always
|
|
84
|
+
|
|
85
|
+
</span>
|
|
86
|
+
|
|
87
|
+
</span>
|
|
88
|
+
|
|
89
|
+
</a>
|
|
90
|
+
|
|
91
|
+
<i><i>profit</i>s</i>
|
|
92
|
+
|
|
93
|
+
<a href="/word/en/in/#ej-43166">
|
|
94
|
+
|
|
95
|
+
<span class="a_line">
|
|
96
|
+
|
|
97
|
+
<span class="a_moji" title="inの意味">
|
|
98
|
+
|
|
99
|
+
in
|
|
100
|
+
|
|
101
|
+
</span>
|
|
102
|
+
|
|
103
|
+
</span>
|
|
104
|
+
|
|
105
|
+
</a>
|
|
106
|
+
|
|
107
|
+
<a href="/word/en/your/#ej-96280">
|
|
108
|
+
|
|
109
|
+
<span class="a_line">
|
|
110
|
+
|
|
111
|
+
<span class="a_moji" title="yourの意味">
|
|
112
|
+
|
|
113
|
+
your
|
|
114
|
+
|
|
115
|
+
</span>
|
|
116
|
+
|
|
117
|
+
</span>
|
|
118
|
+
|
|
119
|
+
</a>
|
|
120
|
+
|
|
121
|
+
<a href="/word/en/case/#ej-13775">
|
|
122
|
+
|
|
123
|
+
<span class="a_line">
|
|
124
|
+
|
|
125
|
+
<span class="a_moji" title="caseの意味">
|
|
126
|
+
|
|
127
|
+
case
|
|
128
|
+
|
|
129
|
+
</span>
|
|
130
|
+
|
|
131
|
+
</span>
|
|
132
|
+
|
|
133
|
+
</a>
|
|
134
|
+
|
|
135
|
+
.
|
|
136
|
+
|
|
137
|
+
</li>
|
|
138
|
+
|
|
139
|
+
|
|
140
|
+
|
|
141
|
+
"""
|
|
142
|
+
|
|
143
|
+
return BeautifulSoup(body, "html.parser")
|
|
144
|
+
|
|
145
|
+
|
|
146
|
+
|
|
147
|
+
|
|
148
|
+
|
|
149
|
+
def main() -> None:
|
|
150
|
+
|
|
151
|
+
soup = get_content()
|
|
152
|
+
|
|
153
|
+
contentsList = soup.find("li", class_="text-en text-c").contents
|
|
154
|
+
|
|
155
|
+
for _, data in enumerate(contentsList):
|
|
156
|
+
|
|
157
|
+
if len(data) == 0:
|
|
158
|
+
|
|
159
|
+
continue
|
|
160
|
+
|
|
161
|
+
if isinstance(data, NavigableString):
|
|
162
|
+
|
|
163
|
+
continue
|
|
164
|
+
|
|
165
|
+
print("#" * 40)
|
|
166
|
+
|
|
167
|
+
print(data.text.strip())
|
|
168
|
+
|
|
169
|
+
|
|
170
|
+
|
|
171
|
+
|
|
172
|
+
|
|
173
|
+
if __name__ == '__main__':
|
|
174
|
+
|
|
175
|
+
main()
|
|
176
|
+
|
|
177
|
+
|
|
178
|
+
|
|
179
|
+
```
|
|
180
|
+
|
|
181
|
+
|
|
182
|
+
|
|
183
|
+
■参考情報
|
|
184
|
+
|
|
185
|
+
[Beautiful Soup 4.2.0 Doc. 日本語訳](http://kondou.com/BS4/)
|
|
186
|
+
|
|
187
|
+
[str.strip](https://docs.python.org/3.6/library/stdtypes.html#str.strip)
|