daodao 0.1.3 → 0.1.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +3 -3
- data/lib/daodao.rb +20 -9
- data/lib/daodao/hotel.rb +1 -1
- data/lib/daodao/hotel_list.rb +1 -1
- data/lib/daodao/rank.rb +42 -33
- data/lib/daodao/version.rb +1 -1
- data/spec/hotel_spec.rb +3 -3
- data/spec/rank_fast_spec.rb +2 -1
- data/spec/rank_spec.rb +1 -4
- 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: 9b7e9eacbf6cbe5bbfc30e566447703171f97c88
|
4
|
+
data.tar.gz: 6b3d10c511674c81b83d3776fb7d894540a823f2
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 016d318b1aa5093632ed066c32b92c0d1fe85d863daaece9451fe5b136f0f285f94c3dfa1bee99a03f1d7c7ff2d96076c5dc29a313ba0823a56cbd97f1a7db93
|
7
|
+
data.tar.gz: f9d53f41a5ed4f21e4961c0f2537aefd8da3fe169807c3e9ff05bf77ed2c8facb0e6541c424cbfbb74258206a1628a072d3805862b4f15f0b8394454527f622c
|
data/README.md
CHANGED
@@ -28,14 +28,14 @@ Or install it yourself as:
|
|
28
28
|
|
29
29
|
```ruby
|
30
30
|
require 'daodao'
|
31
|
-
|
32
|
-
sample = Daodao::Rank.new(
|
31
|
+
hotel_id = "2682464"
|
32
|
+
sample = Daodao::Rank.new(hotel_id)
|
33
33
|
puts 'The rooms details are as follow :'
|
34
34
|
puts sample.rooms_details
|
35
35
|
```
|
36
36
|
This will crawl the rooms details of the target hotel for you.
|
37
37
|
|
38
|
-
`Note:` You can pass other
|
38
|
+
`Note:` You can pass other hotel_id to `initialize` representing the hotel page.
|
39
39
|
|
40
40
|
#### Get ota's ranking
|
41
41
|
|
data/lib/daodao.rb
CHANGED
@@ -7,17 +7,28 @@ require 'daodao/rank'
|
|
7
7
|
require 'daodao/hotel'
|
8
8
|
require 'daodao/hotel_list'
|
9
9
|
module Daodao
|
10
|
-
def self.rank(
|
11
|
-
|
10
|
+
def self.rank(hotel_id)
|
11
|
+
url = "http://www.daodao.com/Hotel_Review/d#{hotel_id}"
|
12
|
+
@html = Nokogiri::HTML(open(url))
|
12
13
|
row = {}
|
13
|
-
row[:hotel_id] =
|
14
|
-
row[:hotel_name] = page.xpath('//span[@itemprop="name"]').text
|
14
|
+
row[:hotel_id] = hotel_id[/\d+/]
|
15
15
|
rank=1
|
16
|
-
|
17
|
-
|
18
|
-
row[
|
19
|
-
|
20
|
-
|
16
|
+
provider = @html.css("div.no_cpu.offer or span.no_cpu.offer")
|
17
|
+
if provider.empty?
|
18
|
+
row[:hotel_name] = @html.xpath("//span[@itemprop='name']").text
|
19
|
+
@html.css("div.provider_meta_overview").each { |item|
|
20
|
+
key = 'rank'+rank.to_s
|
21
|
+
row[key.to_sym] = item.at("span[@class='providerLogo_96x41']/img")['alt']
|
22
|
+
rank+=1
|
23
|
+
}
|
24
|
+
else
|
25
|
+
row[:hotel_name] = @html.xpath("//h1[@id='HEADING']").text
|
26
|
+
provider.each { |item|
|
27
|
+
key = 'rank'+rank.to_s
|
28
|
+
row[key.to_sym] = item['data-vendorname']
|
29
|
+
rank+=1
|
30
|
+
}
|
31
|
+
end
|
21
32
|
row
|
22
33
|
end
|
23
34
|
end
|
data/lib/daodao/hotel.rb
CHANGED
@@ -6,7 +6,7 @@ module Daodao
|
|
6
6
|
def initialize(hotel_id)
|
7
7
|
raise "The argument of class HotelInfo should be string" if !hotel_id.instance_of?(String)
|
8
8
|
@id = hotel_id
|
9
|
-
@url = URI("http://daodao.com/Hotel_Review
|
9
|
+
@url = URI("http://daodao.com/Hotel_Review-d#{hotel_id}")
|
10
10
|
@pages = Nokogiri::HTML(open(@url))
|
11
11
|
end
|
12
12
|
|
data/lib/daodao/hotel_list.rb
CHANGED
data/lib/daodao/rank.rb
CHANGED
@@ -2,33 +2,59 @@ module Daodao
|
|
2
2
|
class Rank
|
3
3
|
include Capybara::DSL
|
4
4
|
|
5
|
-
def initialize(
|
6
|
-
|
7
|
-
|
5
|
+
def initialize(hotel_id)
|
6
|
+
raise ArgumentError, "initizlize: Argument should be string " if !hotel_id.instance_of?(String)
|
7
|
+
Capybara.current_driver = :webkit
|
8
8
|
Capybara.default_selector = :xpath
|
9
|
-
|
10
9
|
Capybara.app_host ="http://daodao.com"
|
10
|
+
|
11
11
|
page.driver.header "User-Agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_4) AppleWebKit/537.77.4 (KHTML, like Gecko) Version/7.0.5 Safari/537.77.4"
|
12
|
-
|
13
|
-
|
14
|
-
page.visit
|
12
|
+
@id = hotel_id
|
13
|
+
uri = "/Hotel_Review/d#{hotel_id}"
|
14
|
+
page.visit URI(uri)
|
15
15
|
# Click the div to navigate hidden info
|
16
16
|
page.all("//div[@class='tab ']").each do |node|
|
17
17
|
node.trigger('click')
|
18
18
|
end
|
19
19
|
# Expand all divs tagged with '展开报价'
|
20
|
-
page.all("
|
21
|
-
puts '展开报价...'
|
20
|
+
page.all("//span[text()='展开报价']").each do |layout|
|
22
21
|
layout.trigger('click')
|
23
22
|
end
|
24
|
-
@
|
23
|
+
@html = Nokogiri::HTML(page.html)
|
24
|
+
end
|
25
|
+
|
26
|
+
def id
|
27
|
+
@id
|
28
|
+
end
|
29
|
+
|
30
|
+
def rank
|
31
|
+
row = {}
|
32
|
+
row[:hotel_id] = self.id
|
33
|
+
rank=1
|
34
|
+
poi = @html.css("div.no_cpu.offer or span.no_cpu.offer")
|
35
|
+
if poi.empty?
|
36
|
+
row[:hotel_name] = @html.xpath("//span[@itemprop='name']").text
|
37
|
+
@html.css("div.provider_meta_overview").each { |item|
|
38
|
+
key = 'rank'+rank.to_s
|
39
|
+
row[key.to_sym] = item.at("span[@class='providerLogo_96x41']/img")['alt']
|
40
|
+
rank+=1
|
41
|
+
}
|
42
|
+
else
|
43
|
+
row[:hotel_name] = @html.xpath("//h1[@id='HEADING']").text
|
44
|
+
poi.each { |item|
|
45
|
+
key = 'rank'+rank.to_s
|
46
|
+
row[key.to_sym] = item['data-vendorname']
|
47
|
+
rank+=1
|
48
|
+
}
|
49
|
+
end
|
50
|
+
row
|
25
51
|
end
|
26
52
|
|
27
53
|
# Get all the rooms details
|
28
54
|
# @Return: an array, a list of rooms details
|
29
55
|
def rooms_details
|
30
56
|
otas = []
|
31
|
-
@
|
57
|
+
@html.css("div.provider_meta_overview").each { |item|
|
32
58
|
row = {}
|
33
59
|
row[:ota_name] = item.css("span.providerLogo_96x41").xpath('./img/@alt').first.value
|
34
60
|
|
@@ -42,7 +68,7 @@ module Daodao
|
|
42
68
|
end
|
43
69
|
|
44
70
|
rooms = []
|
45
|
-
dropdown_room_list = @
|
71
|
+
dropdown_room_list = @html.css("div.provider_rooms_details")[otas.size]
|
46
72
|
dropdown_room_list.xpath("./a").each do |room_details|
|
47
73
|
room = {}
|
48
74
|
room[:room_type] = room_details.at_css("span.room_type").text
|
@@ -63,30 +89,13 @@ module Daodao
|
|
63
89
|
return otas
|
64
90
|
end
|
65
91
|
|
66
|
-
def name
|
67
|
-
@page.xpath('//span[@itemprop="name"]').text
|
68
|
-
end
|
69
|
-
|
70
|
-
def id
|
71
|
-
@uri.split('-')[2]
|
72
|
-
end
|
73
|
-
|
74
|
-
def rank
|
75
|
-
row = {}
|
76
|
-
row[:hotel_id] = self.id
|
77
|
-
row[:hotel_name] = self.name
|
78
|
-
rank=1
|
79
|
-
@page.css("div.provider_meta_overview").each { |item|
|
80
|
-
key = 'rank'+rank.to_s
|
81
|
-
row[key.to_sym] = item.css("span.providerLogo_96x41").xpath('./img/@alt').first.value
|
82
|
-
rank+=1
|
83
|
-
}
|
84
|
-
return row
|
85
|
-
end
|
86
|
-
|
87
92
|
def screen_shot
|
88
93
|
page.save_screenshot("#{Time.now}.png")
|
89
94
|
end
|
90
95
|
|
96
|
+
def html
|
97
|
+
@html
|
98
|
+
end
|
99
|
+
|
91
100
|
end
|
92
101
|
end
|
data/lib/daodao/version.rb
CHANGED
data/spec/hotel_spec.rb
CHANGED
@@ -2,14 +2,14 @@ require 'spec_helper'
|
|
2
2
|
|
3
3
|
describe Daodao::Hotel do
|
4
4
|
# hotel in guangzhou
|
5
|
-
gz_sample = Daodao::Hotel.new("
|
5
|
+
gz_sample = Daodao::Hotel.new("2682464")
|
6
6
|
|
7
7
|
it "has name '四季酒店'" do
|
8
8
|
expect(gz_sample.name).to eq '四季酒店'
|
9
9
|
end
|
10
10
|
|
11
11
|
it "has id 'd2682464'" do
|
12
|
-
expect(gz_sample.id).to eq '
|
12
|
+
expect(gz_sample.id).to eq '2682464'
|
13
13
|
end
|
14
14
|
|
15
15
|
it "has stars 5.0星级" do
|
@@ -34,7 +34,7 @@ describe Daodao::Hotel do
|
|
34
34
|
|
35
35
|
#=====================================================================================================
|
36
36
|
# hotel in beijing
|
37
|
-
bj_sample = Daodao::Hotel.new("
|
37
|
+
bj_sample = Daodao::Hotel.new("3256870")
|
38
38
|
|
39
39
|
it "has name '北京怡亨酒店'" do
|
40
40
|
expect(bj_sample.name).to eq '北京怡亨酒店'
|
data/spec/rank_fast_spec.rb
CHANGED
@@ -1,6 +1,7 @@
|
|
1
1
|
require 'spec_helper'
|
2
2
|
describe Daodao do
|
3
|
-
ranks = Daodao.rank('
|
3
|
+
ranks = Daodao.rank('2682464')
|
4
|
+
puts ranks
|
4
5
|
it "The first Ota name 'Booking.com' " do
|
5
6
|
expect(ranks[:rank1]).to eq 'Booking.com'
|
6
7
|
end
|
data/spec/rank_spec.rb
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
require 'spec_helper'
|
2
2
|
describe Daodao::Rank do
|
3
|
-
gz_sample = Daodao::Rank.new('
|
3
|
+
gz_sample = Daodao::Rank.new('2682464')
|
4
4
|
details = gz_sample.rooms_details
|
5
5
|
p gz_sample.rank
|
6
6
|
# screen shot
|
@@ -38,8 +38,5 @@ describe Daodao::Rank do
|
|
38
38
|
expect(details[4][:rooms_details][0][:room_price]).to eq 2330
|
39
39
|
end
|
40
40
|
|
41
|
-
it "has The hotel name '四季酒店'"do
|
42
|
-
expect(gz_sample.name).to eq "四季酒店"
|
43
|
-
end
|
44
41
|
|
45
42
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: daodao
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- timlen
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-02-
|
11
|
+
date: 2015-02-06 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|