質問編集履歴
1
文法の修正
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -2,140 +2,8 @@
|
|
|
2
2
|
|
|
3
3
|
現在、クローラを用いてヤフーファイナンスから全銘柄の基本情報(株価、PER,PBRなど)を取得しようと考えています。
|
|
4
4
|
|
|
5
|
-
|
|
5
|
+
どう展開していけばよいでしょうか??
|
|
6
6
|
|
|
7
7
|
|
|
8
8
|
|
|
9
9
|
ご教授のほど、よろしくお願いしますm(_ _)m
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
# -*- coding: utf-8 -*-
|
|
14
|
-
|
|
15
|
-
require 'nokogiri'
|
|
16
|
-
|
|
17
|
-
require 'open-uri'
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
|
|
21
|
-
class CompanyInfo
|
|
22
|
-
|
|
23
|
-
def initialize(ticker_code)
|
|
24
|
-
|
|
25
|
-
@baseUrl = "http://stocks.finance.yahoo.co.jp/stocks"
|
|
26
|
-
|
|
27
|
-
@tickerCode = ticker_code
|
|
28
|
-
|
|
29
|
-
scrape
|
|
30
|
-
|
|
31
|
-
end
|
|
32
|
-
|
|
33
|
-
attr_reader :name, :tickerCode, :category,
|
|
34
|
-
|
|
35
|
-
:unit, :recentHighPrice, :recentLowPrice,
|
|
36
|
-
|
|
37
|
-
:highPrice, :lowPrice, :price, :PER, :PBR
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
private
|
|
42
|
-
|
|
43
|
-
def scrape_stock_info(html, index)
|
|
44
|
-
|
|
45
|
-
get_content(html, "dd", "ymuiEditLink mar0", index, "/strong").delete(",")
|
|
46
|
-
|
|
47
|
-
end
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
def get_company_info()
|
|
52
|
-
|
|
53
|
-
url = "#{@baseUrl}/profile/?code=#{@tickerCode}"
|
|
54
|
-
|
|
55
|
-
doc = get_nokogiri_doc(url)
|
|
56
|
-
|
|
57
|
-
@name = doc.xpath("//th[@class='symbol']/h1").text
|
|
58
|
-
|
|
59
|
-
@category = doc.xpath("//table[@class='boardFinCom marB6']/tr[6]/td").text
|
|
60
|
-
|
|
61
|
-
@unit = doc.xpath("//table[@class='boardFinCom marB6']/tr[13]/td").text
|
|
62
|
-
|
|
63
|
-
end
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
def get_stock_info()
|
|
68
|
-
|
|
69
|
-
url = "#{@baseUrl}/detail/?code=#{@tickerCode}"
|
|
70
|
-
|
|
71
|
-
doc = get_nokogiri_doc(url)
|
|
72
|
-
|
|
73
|
-
@PER = doc.xpath("//div[@class='chartFinance']/div[5]/dl/dd[@class='ymuiEditLink mar0']/strong").text
|
|
74
|
-
|
|
75
|
-
@PBR = doc.xpath("//div[@class='chartFinance']/div[6]/dl/dd[@class='ymuiEditLink mar0']/strong").text
|
|
76
|
-
|
|
77
|
-
@recentHighPrice = doc.xpath("//div[11]/dl/dd[@class='ymuiEditLink mar0']/strong").text
|
|
78
|
-
|
|
79
|
-
@recentLowPrice = doc.xpath("//div[12]/dl/dd[@class='ymuiEditLink mar0']/strong").text
|
|
80
|
-
|
|
81
|
-
@highPrice = doc.xpath("//div[@class='innerDate']/div[3]/dl/dd[@class='ymuiEditLink mar0']/strong").text
|
|
82
|
-
|
|
83
|
-
@lowPrice = doc.xpath("//div[@class='innerDate']/div[4]/dl/dd[@class='ymuiEditLink mar0']/strong").text
|
|
84
|
-
|
|
85
|
-
@price = doc.xpath("//td[@class='stoksPrice']").text
|
|
86
|
-
|
|
87
|
-
end
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
def get_nokogiri_doc(url)
|
|
92
|
-
|
|
93
|
-
begin
|
|
94
|
-
|
|
95
|
-
html = open(url)
|
|
96
|
-
|
|
97
|
-
rescue OpenURI::HTTPError
|
|
98
|
-
|
|
99
|
-
return
|
|
100
|
-
|
|
101
|
-
end
|
|
102
|
-
|
|
103
|
-
Nokogiri::HTML(html.read, nil, 'utf-8')
|
|
104
|
-
|
|
105
|
-
end
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
|
|
109
|
-
def scrape
|
|
110
|
-
|
|
111
|
-
get_company_info
|
|
112
|
-
|
|
113
|
-
get_stock_info
|
|
114
|
-
|
|
115
|
-
end
|
|
116
|
-
|
|
117
|
-
end
|
|
118
|
-
|
|
119
|
-
|
|
120
|
-
|
|
121
|
-
company = CompanyInfo.new("4689")
|
|
122
|
-
|
|
123
|
-
puts company.name
|
|
124
|
-
|
|
125
|
-
puts company.category
|
|
126
|
-
|
|
127
|
-
puts company.unit
|
|
128
|
-
|
|
129
|
-
puts "PER："+company.PER
|
|
130
|
-
|
|
131
|
-
puts "PBR："+company.PBR
|
|
132
|
-
|
|
133
|
-
puts "年初来高値："+company.recentHighPrice
|
|
134
|
-
|
|
135
|
-
puts "年初来安値："+company.recentLowPrice
|
|
136
|
-
|
|
137
|
-
puts "高値："+company.highPrice
|
|
138
|
-
|
|
139
|
-
puts "安値："+company.lowPrice
|
|
140
|
-
|
|
141
|
-
puts "株価："+company.price
|