回答編集履歴
2
改行忘れてた
test
CHANGED
|
@@ -44,6 +44,6 @@
|
|
|
44
44
|
|
|
45
45
|
h4 = exa.find(re.compile("h[1-6]"), text=re.compile("経済関係$"))
|
|
46
46
|
|
|
47
|
-
honbun1.append(''.join([m.string.strip() for m in elements_to_next_header(h4)]))
|
|
47
|
+
honbun1.append('\n'.join([m.string.strip() for m in elements_to_next_header(h4)]))
|
|
48
48
|
|
|
49
49
|
```
|
1
「次のヘッダまでの要素」というヘルパ関数を導入
test
CHANGED
|
@@ -10,16 +10,40 @@
|
|
|
10
10
|
|
|
11
11
|
```python
|
|
12
12
|
|
|
13
|
+
h4 = exa.find("h4", text=re.compile("経済関係"))
|
|
14
|
+
|
|
13
15
|
for m in h4.find_next_siblings("p", limit = 3):
|
|
14
16
|
|
|
15
17
|
honbun1.append(m.string)
|
|
16
18
|
|
|
17
19
|
```
|
|
18
20
|
|
|
19
|
-
↓
|
|
21
|
+
↓ 日付単位で1回だけappendするように修正
|
|
20
22
|
|
|
21
23
|
```python
|
|
24
|
+
|
|
25
|
+
h4 = exa.find("h4", text=re.compile("経済関係"))
|
|
22
26
|
|
|
23
27
|
honbun1.append(''.join([m.string for m in h4.find_next_siblings("p", limit = 3)]))
|
|
24
28
|
|
|
25
29
|
```
|
|
30
|
+
|
|
31
|
+
↓ pかどうか曖昧だし3個かどうかも曖昧なので「次のヘッダまでの要素」というヘルパ関数を導入
|
|
32
|
+
|
|
33
|
+
```python
|
|
34
|
+
|
|
35
|
+
def elements_to_next_header(start):
|
|
36
|
+
|
|
37
|
+
next = start.find_next_sibling()
|
|
38
|
+
|
|
39
|
+
while next and not re.match('h[1-6]', next.name):
|
|
40
|
+
|
|
41
|
+
yield next
|
|
42
|
+
|
|
43
|
+
next = next.find_next_sibling()
|
|
44
|
+
|
|
45
|
+
h4 = exa.find(re.compile("h[1-6]"), text=re.compile("経済関係$"))
|
|
46
|
+
|
|
47
|
+
honbun1.append(''.join([m.string.strip() for m in elements_to_next_header(h4)]))
|
|
48
|
+
|
|
49
|
+
```
|