質問編集履歴
1
あ
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -27,3 +27,77 @@
|
|
|
27
27
|
これはセキュリティの問題でしょうか？
|
|
28
28
|
|
|
29
29
|
取得することはできないのでしょうか？
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
|
|
33
|
+
```lang-Python
|
|
34
|
+
|
|
35
|
+
from bs4 import BeautifulSoup
|
|
36
|
+
|
|
37
|
+
import urllib
|
|
38
|
+
|
|
39
|
+
from urllib import request
|
|
40
|
+
|
|
41
|
+
from urllib.request import urlopen
|
|
42
|
+
|
|
43
|
+
from urllib.error import URLError, HTTPError
|
|
44
|
+
|
|
45
|
+
import os
|
|
46
|
+
|
|
47
|
+
|
|
48
|
+
|
|
49
|
+
count=0
|
|
50
|
+
|
|
51
|
+
html = urllib.request.urlopen("指定ページ")
|
|
52
|
+
|
|
53
|
+
soup = BeautifulSoup(html)
|
|
54
|
+
|
|
55
|
+
headers={
|
|
56
|
+
|
|
57
|
+
"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:47.0) Gecko/20100101 Firefox/47.0",
|
|
58
|
+
|
|
59
|
+
}
|
|
60
|
+
|
|
61
|
+
clas=soup.find_all(class_="img-responsive img-private")
|
|
62
|
+
|
|
63
|
+
# print(b)
|
|
64
|
+
|
|
65
|
+
# print(b.select())
|
|
66
|
+
|
|
67
|
+
for x in clas:
|
|
68
|
+
|
|
69
|
+
# print(x)
|
|
70
|
+
|
|
71
|
+
try:
|
|
72
|
+
|
|
73
|
+
url=x.get('src')
|
|
74
|
+
|
|
75
|
+
#指定ページの確認
|
|
76
|
+
|
|
77
|
+
print('url='+url)
|
|
78
|
+
|
|
79
|
+
count=count+1
|
|
80
|
+
|
|
81
|
+
print(count)
|
|
82
|
+
|
|
83
|
+
req = request.Request(url=url, headers=headers)
|
|
84
|
+
|
|
85
|
+
img = request.urlopen(req)
|
|
86
|
+
|
|
87
|
+
localfile = open(os.path.basename(url), 'wb')
|
|
88
|
+
|
|
89
|
+
localfile.write(img.read())
|
|
90
|
+
|
|
91
|
+
img.close()
|
|
92
|
+
|
|
93
|
+
localfile.close()
|
|
94
|
+
|
|
95
|
+
except HTTPError as e:
|
|
96
|
+
|
|
97
|
+
print("HTTPError")
|
|
98
|
+
|
|
99
|
+
except URLError as e:
|
|
100
|
+
|
|
101
|
+
print("URLError")
|
|
102
|
+
|
|
103
|
+
```
|