回答編集履歴
2
Update
test
CHANGED
@@ -16,7 +16,9 @@
|
|
16
16
|
|
17
17
|
## 必要な情報を、タグごと取得
|
18
18
|
contents = soup.find('div', class_='main_text')
|
19
|
+
contents = ''.join(
|
19
|
-
|
20
|
+
str(i) if i.name in ('br', 'ruby') else i.text.strip().replace('\r', '')
|
21
|
+
for i in contents)
|
20
22
|
return title, author, contents
|
21
23
|
|
22
24
|
if __name__ == '__main__':
|
1
Update
test
CHANGED
@@ -11,8 +11,8 @@
|
|
11
11
|
soup = BeautifulSoup(html_text.content, 'html.parser')
|
12
12
|
|
13
13
|
# タイトルと著者名を取得する
|
14
|
-
title = soup.find('h1')
|
14
|
+
title = soup.find('h1').text
|
15
|
-
author = soup.find('h2')
|
15
|
+
author = soup.find('h2').text
|
16
16
|
|
17
17
|
## 必要な情報を、タグごと取得
|
18
18
|
contents = soup.find('div', class_='main_text')
|
@@ -21,8 +21,8 @@
|
|
21
21
|
|
22
22
|
if __name__ == '__main__':
|
23
23
|
title, author, contents = get('https://www.aozora.gr.jp/cards/000329/files/18376_12100.html')
|
24
|
+
with open(f'青空文庫_{title}_{author}.txt', 'w') as f:
|
24
|
-
|
25
|
+
f.write(f'{title}\n')
|
25
|
-
|
26
|
+
f.write(f'{author}\n\n')
|
26
|
-
print()
|
27
|
-
|
27
|
+
f.write(contents)
|
28
28
|
```
|