質問編集履歴
1
コードの追加
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -5,3 +5,101 @@
|
|
|
5
5
|
何か良い方法はありますか？？
|
|
6
6
|
|
|
7
7
|
zipファイルを回収できたらなお良いです。
|
|
8
|
+
|
|
9
|
+
動きませんが現在のところこんな感じです。
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
|
|
13
|
+
```
|
|
14
|
+
|
|
15
|
+
# -*- coding: utf-8 -*-
|
|
16
|
+
|
|
17
|
+
|
|
18
|
+
|
|
19
|
+
from bs4 import BeautifulSoup
|
|
20
|
+
|
|
21
|
+
from urllib import request
|
|
22
|
+
|
|
23
|
+
from urllib.error import URLError, HTTPError
|
|
24
|
+
|
|
25
|
+
import os.path
|
|
26
|
+
|
|
27
|
+
import os
|
|
28
|
+
|
|
29
|
+
import time
|
|
30
|
+
|
|
31
|
+
#https://www.flickr.com/photos/ncsm-sky/sets/72157681801352463
|
|
32
|
+
|
|
33
|
+
def download(url):
|
|
34
|
+
|
|
35
|
+
url = url
|
|
36
|
+
|
|
37
|
+
headers = {
|
|
38
|
+
|
|
39
|
+
"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:47.0) Gecko/20100101 Firefox/47.0",
|
|
40
|
+
|
|
41
|
+
}
|
|
42
|
+
|
|
43
|
+
print(url)
|
|
44
|
+
|
|
45
|
+
req = request.Request(url, None, headers)
|
|
46
|
+
|
|
47
|
+
img = request.urlopen(req)
|
|
48
|
+
|
|
49
|
+
localfile = open(os.path.basename(url), 'wb')
|
|
50
|
+
|
|
51
|
+
localfile.write(img.read())
|
|
52
|
+
|
|
53
|
+
img.close()
|
|
54
|
+
|
|
55
|
+
localfile.close()
|
|
56
|
+
|
|
57
|
+
|
|
58
|
+
|
|
59
|
+
def main():
|
|
60
|
+
|
|
61
|
+
try:
|
|
62
|
+
|
|
63
|
+
url="https://www.flickr.com/photos/ncsm-sky/albums/page1"
|
|
64
|
+
|
|
65
|
+
urlb="https://www.flickr.com"
|
|
66
|
+
|
|
67
|
+
# urlアクセス
|
|
68
|
+
|
|
69
|
+
res = request.urlopen(url)
|
|
70
|
+
|
|
71
|
+
# beautifulsoupでパース
|
|
72
|
+
|
|
73
|
+
soup = BeautifulSoup(res.read(),"html.parser")
|
|
74
|
+
|
|
75
|
+
for link in soup.find_all('a', class_='interaction-view avatar photo-list-album album ginormous'):
|
|
76
|
+
|
|
77
|
+
linka=link.get("href")
|
|
78
|
+
|
|
79
|
+
urlc=urlb+linka
|
|
80
|
+
|
|
81
|
+
res1= request.urlopen(urlc)
|
|
82
|
+
|
|
83
|
+
soup = BeautifulSoup(res1.read(),"html.parser")
|
|
84
|
+
|
|
85
|
+
for src in soup.find_all('img.src'):
|
|
86
|
+
|
|
87
|
+
print(src)
|
|
88
|
+
|
|
89
|
+
# print(urlc)=それぞれのページ
|
|
90
|
+
|
|
91
|
+
# download(urlc)
|
|
92
|
+
|
|
93
|
+
except HTTPError as e:
|
|
94
|
+
|
|
95
|
+
print('Error code: ', e.code)
|
|
96
|
+
|
|
97
|
+
except URLError as e:
|
|
98
|
+
|
|
99
|
+
print('Error code: ', e.code)
|
|
100
|
+
|
|
101
|
+
if __name__ == '__main__':
|
|
102
|
+
|
|
103
|
+
main()
|
|
104
|
+
|
|
105
|
+
```
|