質問編集履歴
1
コードの見辛い部分を修正
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -36,10 +36,6 @@
|
|
|
36
36
|
|
|
37
37
|
|
|
38
38
|
|
|
39
|
-
#coding: UTF-8
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
39
|
import ssl
|
|
44
40
|
|
|
45
41
|
ssl._create_default_https_context = ssl._create_unverified_context
|
|
@@ -56,33 +52,25 @@
|
|
|
56
52
|
|
|
57
53
|
def scraping():
|
|
58
54
|
|
|
59
|
-
|
|
55
|
+
|
|
60
56
|
|
|
61
57
|
url = "https://books.rakuten.co.jp/"
|
|
62
58
|
|
|
63
59
|
|
|
64
60
|
|
|
65
|
-
#get html
|
|
66
|
-
|
|
67
61
|
html = request.urlopen(url)
|
|
68
62
|
|
|
69
63
|
|
|
70
64
|
|
|
71
|
-
#set BueatifulSoup
|
|
72
|
-
|
|
73
65
|
soup = BeautifulSoup(html, "html.parser")
|
|
74
66
|
|
|
75
67
|
|
|
76
|
-
|
|
77
|
-
#get headlines
|
|
78
68
|
|
|
79
69
|
mainNewsIndex = soup.find("div", attrs={"style", "margin: 10px 0;padding: 8px; background: #ff9900;font-size: 15px; font-weight: bold; text-align: center; z-index: 0;color: #330000;" })
|
|
80
70
|
|
|
81
71
|
headlines = mainNewsIndex.find_all("span", attrs={"style", "color: #ffffff;"})
|
|
82
72
|
|
|
83
73
|
|
|
84
|
-
|
|
85
|
-
#print headlines
|
|
86
74
|
|
|
87
75
|
print(headlines)
|
|
88
76
|
|