回答編集履歴
1
a
test
CHANGED
|
@@ -38,43 +38,53 @@
|
|
|
38
38
|
|
|
39
39
|
soup = BeautifulSoup(req.read(), 'html.parser')
|
|
40
40
|
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
poem_elem = soup.select('td[height=40] b')
|
|
44
|
-
|
|
45
|
-
if not poem_elem:
|
|
46
|
-
|
|
47
|
-
return False # 存在しないID
|
|
48
|
-
|
|
49
41
|
|
|
50
42
|
|
|
51
43
|
# 俳句
|
|
52
44
|
|
|
53
|
-
poem_elem = p
|
|
45
|
+
poem_elem = soup.select('td[height=40] b')[0]
|
|
54
46
|
|
|
55
47
|
poem = poem_elem.text.replace('*', '').strip() # サニタイズ
|
|
56
48
|
|
|
49
|
+
if not poem:
|
|
50
|
+
|
|
51
|
+
return False # 存在しないID
|
|
52
|
+
|
|
57
53
|
# 作者
|
|
58
54
|
|
|
59
|
-
author_elem = soup.select('table[
|
|
55
|
+
author_elem = soup.select('table[cellspacing="1"] tr:nth-of-type(1) td:nth-of-type(2)')[0]
|
|
60
56
|
|
|
61
57
|
author = author_elem.text.strip() # サニタイズ
|
|
62
58
|
|
|
63
59
|
# 季語
|
|
64
60
|
|
|
65
|
-
season_word_elem = soup.select('table[
|
|
61
|
+
season_word_elem = soup.select('table[cellspacing="1"] tr:nth-of-type(2) td:nth-of-type(2)')[0]
|
|
66
62
|
|
|
67
63
|
season_word = season_word_elem.text.strip() # サニタイズ
|
|
68
64
|
|
|
69
65
|
# 季節
|
|
70
66
|
|
|
71
|
-
season_elem = soup.select('table[
|
|
67
|
+
season_elem = soup.select('table[cellspacing="1"] tr:nth-of-type(3) td:nth-of-type(2)')[0]
|
|
72
68
|
|
|
73
69
|
season = season_elem.text.strip() # サニタイズ
|
|
74
70
|
|
|
75
|
-
|
|
71
|
+
# 出典
|
|
76
72
|
|
|
73
|
+
source_elem = soup.select('table[cellspacing="1"] tr:nth-of-type(4) td:nth-of-type(2)')[0]
|
|
74
|
+
|
|
75
|
+
source = source_elem.text.strip() # サニタイズ
|
|
76
|
+
|
|
77
|
+
# 前書
|
|
78
|
+
|
|
79
|
+
foreword_elem = soup.select('table[cellspacing="1"] tr:nth-of-type(5) td:nth-of-type(2)')[0]
|
|
80
|
+
|
|
81
|
+
foreword = foreword_elem.text.strip() # サニタイズ
|
|
82
|
+
|
|
83
|
+
|
|
84
|
+
|
|
77
|
-
return {'poem': poem, 'author': author, 'season_word': season_word,
|
|
85
|
+
return {'poem': poem, 'author': author, 'season_word': season_word,
|
|
86
|
+
|
|
87
|
+
'season': season, 'source': source, 'foreword': foreword}
|
|
78
88
|
|
|
79
89
|
```
|
|
80
90
|
|
|
@@ -124,9 +134,7 @@
|
|
|
124
134
|
|
|
125
135
|
with open('output.csv', 'w', newline='', encoding='utf-8') as f:
|
|
126
136
|
|
|
127
|
-
fieldnames = ['first_name', 'last_name']
|
|
128
|
-
|
|
129
|
-
writer = csv.DictWriter(f, fieldnames=['poem', 'author', 'season_word', 'season'])
|
|
137
|
+
writer = csv.DictWriter(f, fieldnames=['poem', 'author', 'season_word', 'season', 'source', 'foreword'])
|
|
130
138
|
|
|
131
139
|
writer.writeheader()
|
|
132
140
|
|