回答編集履歴
2
エラー内容追加
test
CHANGED
|
@@ -1,3 +1,15 @@
|
|
|
1
|
+
# エラー内容
|
|
2
|
+
|
|
3
|
+
http://blog.pyq.jp/entry/Python_kaiketsu_180516
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
インデントがそろってないようなので確認してください。
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
|
|
1
13
|
pandasでスクレイピングするほうが簡単ですよ。
|
|
2
14
|
|
|
3
15
|
|
1
追記
test
CHANGED
|
@@ -23,3 +23,73 @@
|
|
|
23
23
|
dfs[7]
|
|
24
24
|
|
|
25
25
|
```
|
|
26
|
+
|
|
27
|
+
# 追記
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
Colaboratoryでスクレイピング
|
|
32
|
+
|
|
33
|
+
https://imabari.hateblo.jp/entry/2018/04/16/172117
|
|
34
|
+
|
|
35
|
+
|
|
36
|
+
|
|
37
|
+
こちらからURLを変えるだけで動きましたよ
|
|
38
|
+
|
|
39
|
+
|
|
40
|
+
|
|
41
|
+
```python
|
|
42
|
+
|
|
43
|
+
import pandas as pd
|
|
44
|
+
|
|
45
|
+
import requests
|
|
46
|
+
|
|
47
|
+
from bs4 import BeautifulSoup
|
|
48
|
+
|
|
49
|
+
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
|
|
53
|
+
url = 'https://www.river.go.jp/kawabou/ipDamGaikyo.do?init=init&areaCd=89&prefCd=4001&townCd=&gamenId=01-0903&fldCtlParty=no'
|
|
54
|
+
|
|
55
|
+
|
|
56
|
+
|
|
57
|
+
headers = {
|
|
58
|
+
|
|
59
|
+
'User-Agent':
|
|
60
|
+
|
|
61
|
+
'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko'
|
|
62
|
+
|
|
63
|
+
}
|
|
64
|
+
|
|
65
|
+
|
|
66
|
+
|
|
67
|
+
r = requests.get(url, headers=headers)
|
|
68
|
+
|
|
69
|
+
|
|
70
|
+
|
|
71
|
+
if r.status_code == requests.codes.ok:
|
|
72
|
+
|
|
73
|
+
|
|
74
|
+
|
|
75
|
+
soup = BeautifulSoup(r.content, 'html5lib')
|
|
76
|
+
|
|
77
|
+
|
|
78
|
+
|
|
79
|
+
result = [[
|
|
80
|
+
|
|
81
|
+
x.get_text(strip=True) for x in y.find_all(['th', 'td'])
|
|
82
|
+
|
|
83
|
+
] for y in soup.select('body > div.gaikyoCntt > table > tbody > tr ')]
|
|
84
|
+
|
|
85
|
+
|
|
86
|
+
|
|
87
|
+
df = pd.DataFrame(data=result[1:], columns=result[0])
|
|
88
|
+
|
|
89
|
+
df.set_index('ダム名', inplace=True)
|
|
90
|
+
|
|
91
|
+
|
|
92
|
+
|
|
93
|
+
df
|
|
94
|
+
|
|
95
|
+
```
|