crown 0.0.6 → 0.0.7
Sign up to get free protection for your applications and to get access to all the features.
- data/ChangeLog +5 -1
- data/VERSION +1 -1
- data/crown.gemspec +2 -1
- data/lib/crown/amazon.rb +138 -0
- metadata +4 -3
data/ChangeLog
CHANGED
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.0.
|
1
|
+
0.0.7
|
data/crown.gemspec
CHANGED
@@ -5,7 +5,7 @@
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |s|
|
7
7
|
s.name = %q{crown}
|
8
|
-
s.version = "0.0.
|
8
|
+
s.version = "0.0.7"
|
9
9
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
11
|
s.authors = ["clown"]
|
@@ -34,6 +34,7 @@ Gem::Specification.new do |s|
|
|
34
34
|
"example/sbmcount.rb",
|
35
35
|
"example/twcount.rb",
|
36
36
|
"lib/crown.rb",
|
37
|
+
"lib/crown/amazon.rb",
|
37
38
|
"lib/crown/backtype.rb",
|
38
39
|
"lib/crown/buzzurl.rb",
|
39
40
|
"lib/crown/delicious.rb",
|
data/lib/crown/amazon.rb
ADDED
@@ -0,0 +1,138 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
# --------------------------------------------------------------------------- #
|
3
|
+
#
|
4
|
+
# twitter.rb
|
5
|
+
#
|
6
|
+
# Copyright (c) 2008 - 2011, clown.
|
7
|
+
#
|
8
|
+
# Redistribution and use in source and binary forms, with or without
|
9
|
+
# modification, are permitted provided that the following conditions
|
10
|
+
# are met:
|
11
|
+
#
|
12
|
+
# - Redistributions of source code must retain the above copyright
|
13
|
+
# notice, this list of conditions and the following disclaimer.
|
14
|
+
# - Redistributions in binary form must reproduce the above copyright
|
15
|
+
# notice, this list of conditions and the following disclaimer in the
|
16
|
+
# documentation and/or other materials provided with the distribution.
|
17
|
+
# - No names of its contributors may be used to endorse or promote
|
18
|
+
# products derived from this software without specific prior written
|
19
|
+
# permission.
|
20
|
+
#
|
21
|
+
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
22
|
+
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
23
|
+
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
24
|
+
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
25
|
+
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
26
|
+
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
|
27
|
+
# TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
28
|
+
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
29
|
+
# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
30
|
+
# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
31
|
+
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
32
|
+
#
|
33
|
+
# --------------------------------------------------------------------------- #
|
34
|
+
module Crown
|
35
|
+
module Amazon
|
36
|
+
require 'uri'
|
37
|
+
require 'net/http'
|
38
|
+
require 'crown/http'
|
39
|
+
require 'rubygems'
|
40
|
+
require 'amazon/ecs'
|
41
|
+
require 'nokogiri'
|
42
|
+
Net::HTTP.version_1_2
|
43
|
+
|
44
|
+
# ------------------------------------------------------------------- #
|
45
|
+
#
|
46
|
+
# AsinExtractor
|
47
|
+
#
|
48
|
+
# 指定した URI の a タグ href 属性から Amazon の ASIN と思われる
|
49
|
+
# 情報を抽出するクラス.
|
50
|
+
#
|
51
|
+
# ------------------------------------------------------------------- #
|
52
|
+
class AsinExtractor
|
53
|
+
def initialize(proxy_host = nil, proxy_port = nil)
|
54
|
+
@proxy_host = proxy_host
|
55
|
+
@proxy_port = proxy_port
|
56
|
+
end
|
57
|
+
|
58
|
+
# --------------------------------------------------------------- #
|
59
|
+
# get
|
60
|
+
# --------------------------------------------------------------- #
|
61
|
+
def get(uri)
|
62
|
+
result = Array.new
|
63
|
+
|
64
|
+
parser = URI.parse(uri.strip)
|
65
|
+
path = parser.path
|
66
|
+
path += parser.query if (parser.query != nil)
|
67
|
+
|
68
|
+
session = Net::HTTP.new(parser.host, parser.port, @proxy_host, @proxy_port)
|
69
|
+
response = Crown::HTTP.get(session, path)
|
70
|
+
return result if (response == nil || response.code.to_i != 200)
|
71
|
+
|
72
|
+
html = Nokogiri::HTML.parse(response.body)
|
73
|
+
html.search("a").each { |node|
|
74
|
+
next if (node['href'] == nil)
|
75
|
+
|
76
|
+
begin
|
77
|
+
parser = URI.parse(node['href'].strip)
|
78
|
+
rescue URI::InvalidURIError
|
79
|
+
parser = URI.parse(URI.encode(node['href'].strip))
|
80
|
+
end
|
81
|
+
next if (parser == nil || parser.host == nil || parser.path == nil)
|
82
|
+
|
83
|
+
if (parser.host.match(/^(?:www\.)?amazon\.(?:com|ca|co\.uk|de|co\.jp|jp|fr|cn)$/) != nil)
|
84
|
+
asin = get_asin(parser.path, parser.query)
|
85
|
+
result.push(asin) if (asin != nil)
|
86
|
+
end
|
87
|
+
}
|
88
|
+
|
89
|
+
return result
|
90
|
+
end
|
91
|
+
|
92
|
+
private
|
93
|
+
# --------------------------------------------------------------- #
|
94
|
+
#
|
95
|
+
# get_asin
|
96
|
+
#
|
97
|
+
# パスおよびクエリーから ASIN を抽出する.推測方法は,
|
98
|
+
# /[B0123489][A-Z0-9]{9}/ にマッチする文字列を探すと言う方法を
|
99
|
+
# 採用している.
|
100
|
+
#
|
101
|
+
# --------------------------------------------------------------- #
|
102
|
+
def get_asin(path, query)
|
103
|
+
path.split('/').each { |item|
|
104
|
+
asin = item.match(/[B0123489][A-Z0-9]{9}/)
|
105
|
+
return asin[0] if (asin != nil)
|
106
|
+
}
|
107
|
+
|
108
|
+
if (query != nil)
|
109
|
+
asin = query.match(/[B0123489][A-Z0-9]{9}/)
|
110
|
+
return asin[0] if (asin != nil)
|
111
|
+
end
|
112
|
+
|
113
|
+
return nil
|
114
|
+
end
|
115
|
+
end
|
116
|
+
|
117
|
+
# ------------------------------------------------------------------- #
|
118
|
+
#
|
119
|
+
# each
|
120
|
+
#
|
121
|
+
# AsinExtractor クラスを使用して指定された URL に存在する
|
122
|
+
# ASIN コードを抽出し,Amazon::Ecs を用いてそれらの情報を
|
123
|
+
# 取得する
|
124
|
+
#
|
125
|
+
# ------------------------------------------------------------------- #
|
126
|
+
def each(uri, options = {})
|
127
|
+
AsinExtractor.new.get(uri).each { |asin|
|
128
|
+
result = ::Amazon::Ecs.item_lookup(asin, options)
|
129
|
+
yield(result.first_item) if (result != nil && result.items.length > 0)
|
130
|
+
}
|
131
|
+
end
|
132
|
+
|
133
|
+
# ------------------------------------------------------------------- #
|
134
|
+
# module functions
|
135
|
+
# ------------------------------------------------------------------- #
|
136
|
+
module_function :each
|
137
|
+
end # Amazon
|
138
|
+
end # Crown
|
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: crown
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash:
|
4
|
+
hash: 17
|
5
5
|
prerelease:
|
6
6
|
segments:
|
7
7
|
- 0
|
8
8
|
- 0
|
9
|
-
-
|
10
|
-
version: 0.0.
|
9
|
+
- 7
|
10
|
+
version: 0.0.7
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- clown
|
@@ -100,6 +100,7 @@ files:
|
|
100
100
|
- example/sbmcount.rb
|
101
101
|
- example/twcount.rb
|
102
102
|
- lib/crown.rb
|
103
|
+
- lib/crown/amazon.rb
|
103
104
|
- lib/crown/backtype.rb
|
104
105
|
- lib/crown/buzzurl.rb
|
105
106
|
- lib/crown/delicious.rb
|