回答編集履歴
2
d
answer
CHANGED
|
@@ -42,4 +42,31 @@
|
|
|
42
42
|
soup = BeautifulSoup(html)
|
|
43
43
|
vals = [t.text for t in soup.find_all('p')]
|
|
44
44
|
print(vals) # ['ZZZ', 'AAA', 'BBB', 'CCC', 'YYY', '', 'TTTSSS', 'RRR', '4', 'XXX']
|
|
45
|
+
```
|
|
46
|
+
|
|
47
|
+
## 追記
|
|
48
|
+
|
|
49
|
+
```python
|
|
50
|
+
html = '''<p><span>ZZZ</span></p>,
|
|
51
|
+
<p>AAA</p>,
|
|
52
|
+
<p>BBB</p>,
|
|
53
|
+
<p>CCC</p>,
|
|
54
|
+
<p class="tags">YYY</p>,
|
|
55
|
+
<p class="list"><a href="/WWW/"><img alt="VVV" src="/UUU"/></a></p>,
|
|
56
|
+
<p class="tags">TTT<br class="sp"/>SSS</p>,
|
|
57
|
+
<p class="hoge"><a class="tagb" href="/socialmedia/">RRR</a></p>,
|
|
58
|
+
<p class="fuga"><a class="typesquare_tags" href="/chronicle/04/">4</a></p>,
|
|
59
|
+
<p class="capion typesquare_tags">XXX</p>'''
|
|
60
|
+
|
|
61
|
+
from bs4 import BeautifulSoup
|
|
62
|
+
|
|
63
|
+
soup = BeautifulSoup(html)
|
|
64
|
+
|
|
65
|
+
vals = []
|
|
66
|
+
for t in soup.find_all('p'):
|
|
67
|
+
# p タグの子でテキストがある要素のみ検索
|
|
68
|
+
p_text = t.find(text=True, recursive=False)
|
|
69
|
+
if p_text:
|
|
70
|
+
vals.append(p_text)
|
|
71
|
+
print(vals) # ['AAA', 'BBB', 'CCC', 'YYY', 'TTT', 'XXX']
|
|
45
72
|
```
|
1
d
answer
CHANGED
|
@@ -19,4 +19,27 @@
|
|
|
19
19
|
soup = BeautifulSoup(html)
|
|
20
20
|
vals = [t.text for t in soup.find_all('p', attrs=lambda attrs: not attrs)]
|
|
21
21
|
print(vals) # ['ZZZ', 'AAA', 'BBB', 'CCC']
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
## 追記
|
|
25
|
+
|
|
26
|
+
単純に p タグの値だけ取り出すという意味でしたら、以下です。
|
|
27
|
+
|
|
28
|
+
```python
|
|
29
|
+
html = '''<p><span>ZZZ</span></p>,
|
|
30
|
+
<p>AAA</p>,
|
|
31
|
+
<p>BBB</p>,
|
|
32
|
+
<p>CCC</p>,
|
|
33
|
+
<p class="tags">YYY</p>,
|
|
34
|
+
<p class="list"><a href="/WWW/"><img alt="VVV" src="/UUU"/></a></p>,
|
|
35
|
+
<p class="tags">TTT<br class="sp"/>SSS</p>,
|
|
36
|
+
<p class="hoge"><a class="tagb" href="/socialmedia/">RRR</a></p>,
|
|
37
|
+
<p class="fuga"><a class="typesquare_tags" href="/chronicle/04/">4</a></p>,
|
|
38
|
+
<p class="capion typesquare_tags">XXX</p>'''
|
|
39
|
+
|
|
40
|
+
from bs4 import BeautifulSoup
|
|
41
|
+
|
|
42
|
+
soup = BeautifulSoup(html)
|
|
43
|
+
vals = [t.text for t in soup.find_all('p')]
|
|
44
|
+
print(vals) # ['ZZZ', 'AAA', 'BBB', 'CCC', 'YYY', '', 'TTTSSS', 'RRR', '4', 'XXX']
|
|
22
45
|
```
|