回答編集履歴
1
実行結果を付与
test
CHANGED
@@ -1,31 +1,93 @@
|
|
1
|
-
next がclass="b"の間はclass="a"にappend
|
2
1
|
|
3
|
-
> for e in doc.findall('.//div[@class="a"]'):
|
4
2
|
|
5
|
-
|
3
|
+
```shell
|
6
4
|
|
7
|
-
|
5
|
+
dockerdev@py3:~$ cat a
|
8
6
|
|
9
|
-
|
7
|
+
#!/usr/bin/env python3
|
10
8
|
|
11
|
-
|
9
|
+
# -*- coding: utf-8 -*-
|
12
10
|
|
13
|
-
> if img.tag == 'img':
|
14
|
-
|
15
|
-
> e.append(img)
|
16
|
-
|
17
|
-
|
11
|
+
import lxml.html
|
18
|
-
|
19
|
-
> break
|
20
|
-
|
21
|
-
> n = n.getnext()
|
22
12
|
|
23
13
|
|
24
14
|
|
25
|
-
|
15
|
+
html = """
|
26
16
|
|
27
|
-
>
|
17
|
+
<div class='a'><img src='aa.jpg'></div>
|
28
18
|
|
29
|
-
>
|
19
|
+
<div class='b'><img src='ab.jpg'></div>
|
30
20
|
|
21
|
+
<div class='b'><img src='ac.jpg'></div>
|
22
|
+
|
23
|
+
<div class='b'><img src='ad.jpg'></div>
|
24
|
+
|
25
|
+
<div class='a'><img src='ba.jpg'></div>
|
26
|
+
|
27
|
+
<div class='b'><img src='bb.jpg'></div>
|
28
|
+
|
29
|
+
<div class='b'><img src='bc.jpg'></div>
|
30
|
+
|
31
|
+
<div class='a'><img src='ca.jpg'></div>
|
32
|
+
|
33
|
+
<div class='b'><img src='cb.jpg'></div>
|
34
|
+
|
35
|
+
"""
|
36
|
+
|
37
|
+
doc = lxml.html.fromstring(html)
|
38
|
+
|
39
|
+
# next がclass="b"の間はclass="a"にappend
|
40
|
+
|
41
|
+
for e in doc.findall('.//div[@class="a"]'):
|
42
|
+
|
43
|
+
n = e.getnext()
|
44
|
+
|
45
|
+
while True:
|
46
|
+
|
47
|
+
if n != None and n.get('class') == 'b':
|
48
|
+
|
49
|
+
for img in n:
|
50
|
+
|
51
|
+
if img.tag == 'img':
|
52
|
+
|
53
|
+
e.append(img)
|
54
|
+
|
55
|
+
else:
|
56
|
+
|
57
|
+
break
|
58
|
+
|
59
|
+
n = n.getnext()
|
60
|
+
|
61
|
+
# 不要なdivを一気に消す
|
62
|
+
|
63
|
+
for e in doc.findall('.//div[@class="b"]'):
|
64
|
+
|
65
|
+
parent = e.getparent()
|
66
|
+
|
31
|
-
|
67
|
+
parent.remove(e)
|
68
|
+
|
69
|
+
|
70
|
+
|
71
|
+
print(lxml.etree.tostring(doc, pretty_print=True).decode('utf8'))
|
72
|
+
|
73
|
+
dockerdev@py3:~$ python3 a
|
74
|
+
|
75
|
+
python3 a
|
76
|
+
|
77
|
+
<div><div class="a"><img src="aa.jpg"/><img src="ab.jpg"/><img src="ac.jpg"/><img src="ad.jpg"/></div>
|
78
|
+
|
79
|
+
<div class="a"><img src="ba.jpg"/><img src="bb.jpg"/><img src="bc.jpg"/></div>
|
80
|
+
|
81
|
+
<div class="a"><img src="ca.jpg"/><img src="cb.jpg"/></div>
|
82
|
+
|
83
|
+
</div>
|
84
|
+
|
85
|
+
|
86
|
+
|
87
|
+
dockerdev@py3:~$
|
88
|
+
|
89
|
+
```
|
90
|
+
|
91
|
+
|
92
|
+
|
93
|
+
|