joyceshop 0.0.3 → 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/bin/joyceshop +31 -3
- data/lib/joyceshop/scraper.rb +100 -78
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 05a440353df86f1a449acbe8633aefd1139a0c55
|
4
|
+
data.tar.gz: 9cedcb43aca538bb30e5e1de8bf0a17d472e795e
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: e2a8e4481761300cc527fc1103c377a54a1d547ee5d92a3a5fb14ebd60438e10427d8458625ec8484da37f4cb6a5253b464c124ff6a13c7859e67e8de472abfb
|
7
|
+
data.tar.gz: 986e94aa57f5ebe8c9470491079c0452c0e06aaa2886d3e767c0191ac3e5c51f07d6b19b462c48b7b20c1a8a5717a4f8e87b8a57ae0fe037a345f23bdf0d9ae2
|
data/bin/joyceshop
CHANGED
@@ -2,6 +2,34 @@
|
|
2
2
|
# require 'joyceshop' # for production
|
3
3
|
require_relative '../lib/joyceshop.rb' # for testing
|
4
4
|
|
5
|
-
scraper = JoyceShop::Scraper.new
|
6
|
-
|
7
|
-
|
5
|
+
@scraper = JoyceShop::Scraper.new
|
6
|
+
|
7
|
+
# command type keyword lprice hprice page_limit
|
8
|
+
def parse_args argv
|
9
|
+
input_length = argv.length
|
10
|
+
abort 'invalid usage' unless input_length <= 5
|
11
|
+
|
12
|
+
if input_length == 0 # scrape main category
|
13
|
+
@scraper.scrape('latest')
|
14
|
+
elsif input_length == 1 # scrape main category
|
15
|
+
@scraper.scrape(argv[0])
|
16
|
+
elsif input_length == 2
|
17
|
+
t = argv[1].to_i
|
18
|
+
if t != 0
|
19
|
+
options = { page_limit: argv[1] }
|
20
|
+
else
|
21
|
+
options = { keyword: argv[1] }
|
22
|
+
end
|
23
|
+
@scraper.scrape(argv[0], options)
|
24
|
+
elsif input_length == 3
|
25
|
+
options = { keyword: argv[1], page_limit: argv[2] }
|
26
|
+
@scraper.scrape(argv[0], options)
|
27
|
+
elsif input_length == 5
|
28
|
+
options = { keyword: argv[2], page_limit: argv[5],
|
29
|
+
price_boundary: [argv[3], argv[4]]
|
30
|
+
}
|
31
|
+
@scraper.scrape_filter(argv[0], options)
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
puts parse_args ARGV
|
data/lib/joyceshop/scraper.rb
CHANGED
@@ -5,104 +5,84 @@ require 'open-uri'
|
|
5
5
|
|
6
6
|
# scrape data
|
7
7
|
module JoyceShop
|
8
|
+
# extract_data class uses xpath selectors to get attribs
|
8
9
|
class Scraper
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
#
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
#
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
@@ITEM_INFO_SELECTOR = "div[contains(@class, 'NEW_shop_list_info')]"
|
26
|
-
@@TITLE_SELECTOR = "#{@@ITEM_INFO_SELECTOR}/div[1]"
|
27
|
-
@@PRICE_SELECTOR = "#{@@ITEM_INFO_SELECTOR}/span"
|
10
|
+
BASE_URL = 'https://www.joyce-shop.com'
|
11
|
+
BASE_SCRAPE_URL = "#{BASE_URL}/PDList.asp?"
|
12
|
+
|
13
|
+
LATEST_URI = "#{BASE_SCRAPE_URL}brand=01&item1=&item2=&ya19=&keyword=&recommand=1412170001&ob=F"
|
14
|
+
POPULAR_URI = "#{BASE_SCRAPE_URL}brand=01&item1=&item2=&ya19=&keyword=&recommand=1305080002&ob=F"
|
15
|
+
TOPS_URI = "#{BASE_SCRAPE_URL}brand=01&item1=110&item2=111&ya19=&keyword=&recommand=&ob=F"
|
16
|
+
PANTS_URI = "#{BASE_SCRAPE_URL}brand=01&item1=120&item2=121&ya19=&keyword=&recommand=&ob=F"
|
17
|
+
ACCESSORIES_URI = "#{BASE_SCRAPE_URL}brand=01&item1=140&item2=141&ya19=&keyword=&recommand=&ob=F"
|
18
|
+
|
19
|
+
# xml selectors that will be used to scrape data
|
20
|
+
ITEM_SELECTOR = "//div[contains(@class, 'NEW_shop_list')]/ul/li/div[contains(@class, 'NEW_shop_list_pic')]"
|
21
|
+
ITEM_INFO_SELECTOR = "div[contains(@class, 'NEW_shop_list_info')]"
|
22
|
+
TITLE_SELECTOR = "#{ITEM_INFO_SELECTOR}/div[1]"
|
23
|
+
IMAGE_SELECTOR = "a/img[contains(@class, 'lazyload')]/@src"
|
24
|
+
PRICE_SELECTOR = "#{ITEM_INFO_SELECTOR}/span"
|
25
|
+
LINK_SELECTOR = "a[1]/@href"
|
28
26
|
|
29
27
|
# Regular
|
30
|
-
|
28
|
+
TITLE_REGEX = /([.\p{Han}[a-zA-Z]]+)/
|
31
29
|
|
32
|
-
def latest(page, options={})
|
33
|
-
uri =
|
34
|
-
|
35
|
-
data = parse_html(body)
|
36
|
-
filter(data, options)
|
30
|
+
def latest(page, options = {})
|
31
|
+
uri = uri_with_options(build_uri(LATEST_URI, options), page)
|
32
|
+
process_request(uri, options)
|
37
33
|
end
|
38
34
|
|
39
|
-
def popular(page, options={})
|
40
|
-
uri =
|
41
|
-
|
42
|
-
data = parse_html(body)
|
43
|
-
filter(data, options)
|
35
|
+
def popular(page, options = {})
|
36
|
+
uri = uri_with_options(build_uri(POPULAR_URI, options), page)
|
37
|
+
process_request(uri, options)
|
44
38
|
end
|
45
39
|
|
46
|
-
def tops(page, options={})
|
47
|
-
uri =
|
48
|
-
|
49
|
-
data = parse_html(body)
|
50
|
-
filter(data, options)
|
40
|
+
def tops(page, options = {})
|
41
|
+
uri = uri_with_options(build_uri(TOPS_URI, options), page)
|
42
|
+
process_request(uri, options)
|
51
43
|
end
|
52
44
|
|
53
|
-
def pants(page, options={})
|
54
|
-
uri =
|
55
|
-
|
56
|
-
data = parse_html(body)
|
57
|
-
filter(data, options)
|
45
|
+
def pants(page, options = {})
|
46
|
+
uri = uri_with_options(build_uri(PANTS_URI, options), page)
|
47
|
+
process_request(uri, options)
|
58
48
|
end
|
59
49
|
|
60
|
-
def accessories(page, options={})
|
61
|
-
uri =
|
62
|
-
|
63
|
-
data = parse_html(body)
|
64
|
-
filter(data, options)
|
50
|
+
def accessories(page, options = {})
|
51
|
+
uri = uri_with_options(build_uri(ACCESSORIES_URI, options), page)
|
52
|
+
process_request(uri, options)
|
65
53
|
end
|
66
54
|
|
67
|
-
def search(
|
68
|
-
uri =
|
69
|
-
|
70
|
-
data = parse_html(body)
|
71
|
-
filter(data, options)
|
55
|
+
def search(page, options = {})
|
56
|
+
uri = uri_with_options(build_uri(BASE_SCRAPE_URL, options), page)
|
57
|
+
process_request(uri, options)
|
72
58
|
end
|
73
59
|
|
74
|
-
def scrape(type,
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
|
60
|
+
def scrape(type, options = {})
|
61
|
+
records = []
|
62
|
+
valid_args = [:tops, :popular, :pants, :pants,
|
63
|
+
:accessories, :latest, :search]
|
64
|
+
abort 'invalid parameter - scrape type' unless valid_args.include?(type.to_sym)
|
65
|
+
scrape_what(type, options)
|
79
66
|
end
|
80
67
|
|
81
68
|
private
|
82
|
-
def uri_with_page(uri, page)
|
83
|
-
"#{uri}&pageno=#{page}"
|
84
|
-
end
|
85
|
-
|
86
|
-
def uri_with_search(keyword)
|
87
|
-
"#{@@SEARCH_URI}keyword=#{URI.escape(keyword)}"
|
88
|
-
end
|
89
69
|
|
90
|
-
def
|
91
|
-
|
70
|
+
def process_request(uri, options)
|
71
|
+
body = open_uri(uri)
|
72
|
+
data = extract_data(body)
|
73
|
+
filter(data, options)
|
92
74
|
end
|
93
75
|
|
94
|
-
#
|
95
|
-
# ------------------------------------------------------------
|
76
|
+
# filter by price if the options are not empty
|
96
77
|
def filter(data, options)
|
97
78
|
results = data
|
98
|
-
|
99
79
|
unless options.empty?
|
100
80
|
results = match_price(results, options[:price_boundary]) if options[:price_boundary]
|
101
81
|
end
|
102
|
-
|
103
82
|
results
|
104
83
|
end
|
105
84
|
|
85
|
+
# do the actual extraction of prices from the result set
|
106
86
|
def match_price(data, boundary)
|
107
87
|
lower_bound = boundary.first || 0
|
108
88
|
upper_bound = boundary.last || Float::INFINITY
|
@@ -110,14 +90,39 @@ module JoyceShop
|
|
110
90
|
data.select { |item| lower_bound <= item[:price] && item[:price] <= upper_bound }
|
111
91
|
end
|
112
92
|
|
113
|
-
|
114
|
-
|
115
|
-
|
93
|
+
def build_uri(uri, options = {})
|
94
|
+
opts = { uri: uri }
|
95
|
+
unless options.empty?
|
96
|
+
opts[:keyword] = options[:keyword] if options[:keyword]
|
97
|
+
end
|
98
|
+
opts
|
99
|
+
end
|
100
|
+
|
101
|
+
def uri_with_options(options = {}, page)
|
102
|
+
uri = ''
|
103
|
+
unless options.empty?
|
104
|
+
keyword = options[:keyword] || nil
|
105
|
+
uri << "#{options[:uri]}&pageno=#{page}" if options[:uri]
|
106
|
+
uri << "br=X&keyword=#{URI.escape(keyword)}" if options[:keyword]
|
107
|
+
end
|
108
|
+
uri
|
109
|
+
end
|
110
|
+
|
111
|
+
# try open the URL, fail on error
|
112
|
+
def open_uri(uri)
|
113
|
+
open(uri) {|file| file.read}
|
114
|
+
rescue StandardError
|
115
|
+
'error opening site url'
|
116
|
+
end
|
117
|
+
|
118
|
+
# iterate over every element of item using xpath
|
119
|
+
def extract_data(raw)
|
116
120
|
Oga.parse_html(raw)
|
117
|
-
.xpath(
|
121
|
+
.xpath(ITEM_SELECTOR)
|
118
122
|
.map { |item| parse(item) }
|
119
123
|
end
|
120
124
|
|
125
|
+
# call methods to extract the data using xpath
|
121
126
|
def parse(item)
|
122
127
|
{
|
123
128
|
title: extract_title(item),
|
@@ -127,24 +132,41 @@ module JoyceShop
|
|
127
132
|
}
|
128
133
|
end
|
129
134
|
|
135
|
+
# Iconv is neccessary here otherwise text is unreadable
|
130
136
|
def extract_title(item)
|
131
|
-
item.xpath(
|
132
|
-
.scan(
|
137
|
+
item.xpath(TITLE_SELECTOR).text
|
138
|
+
.scan(TITLE_REGEX)
|
133
139
|
.flatten[0]
|
134
140
|
end
|
135
141
|
|
142
|
+
# get rid of the NT and convert to integer
|
136
143
|
def extract_price(item)
|
137
|
-
item.xpath(
|
144
|
+
item.xpath(PRICE_SELECTOR).text.sub(/NT. /, '').to_i
|
138
145
|
end
|
139
146
|
|
147
|
+
# extract two images and return array or urls
|
140
148
|
def extract_images(item)
|
141
|
-
image = item.xpath(
|
149
|
+
image = item.xpath(IMAGE_SELECTOR).text
|
142
150
|
image_hover = image.sub(/\.jpg/, '-h.jpg')
|
143
|
-
|
151
|
+
image_hover = image.sub(/\.png/, '-h.png') unless image_hover != image
|
152
|
+
["#{BASE_URL}#{image}", "#{BASE_URL}#{image_hover}"]
|
144
153
|
end
|
145
154
|
|
155
|
+
# get the link to the item
|
146
156
|
def extract_link(item)
|
147
|
-
"#{
|
157
|
+
"#{BASE_URL}/#{item.xpath(LINK_SELECTOR).text}"
|
158
|
+
end
|
159
|
+
|
160
|
+
def scrape_what(type, options)
|
161
|
+
records = []
|
162
|
+
pl = options[:page_limit].to_i
|
163
|
+
page_limit = pl != 0 ? pl : 5
|
164
|
+
|
165
|
+
1.upto(page_limit) do |page|
|
166
|
+
method = self.method(type)
|
167
|
+
records.push(method.call(page, options))
|
168
|
+
end
|
169
|
+
records.reject { |c| c.empty? }.flatten(1).uniq
|
148
170
|
end
|
149
171
|
end
|
150
172
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: joyceshop
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.4
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Even Chang
|
@@ -11,7 +11,7 @@ authors:
|
|
11
11
|
autorequire:
|
12
12
|
bindir: bin
|
13
13
|
cert_chain: []
|
14
|
-
date: 2016-01-
|
14
|
+
date: 2016-01-10 00:00:00.000000000 Z
|
15
15
|
dependencies: []
|
16
16
|
description: This is a gem scraping joyceshop's website and returns the popular/latest
|
17
17
|
items
|