transportscrapper 1.0.4 → 1.0.9
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/{TransportScrapper.rb → transportscrapper.rb} +18 -10
- metadata +6 -6
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: df6bbac266216716968ad977ec95eebf7750cae15806d570b5acb06496bc1bb1
|
4
|
+
data.tar.gz: 2951e30ea786b975a3c5c9b1bbc5fa1493c5407429bb566df5f8068028e4e45d
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: d9480280713ff05968a9f742f5d74943d4b97d700c10f1396bc30e75cec75da627e9c96fa5ffe723b3a9888c65ff3b2394064e0bd024b15731646d3fea876fad
|
7
|
+
data.tar.gz: aa66c4b9895bdf695426d7595342255cd6ffd2cc2cf3659ffce08ca22d92122ac8bc1df84cf752b7ef67b957a1a4f0f85aec224e9f47292ae519b9fd889e6442
|
@@ -1,19 +1,22 @@
|
|
1
1
|
require 'nokogiri'
|
2
2
|
require 'watir'
|
3
|
+
require 'open-uri'
|
3
4
|
|
4
5
|
class TransportScrapper
|
5
6
|
|
6
|
-
@outwardArr = []
|
7
|
-
@returnArr = []
|
8
|
-
|
9
7
|
def self.scrapewithtime(value, time)
|
10
8
|
@browser.goto value
|
9
|
+
puts value
|
10
|
+
#doc = Nokogiri::HTML.parse(open(value))
|
11
11
|
doc = Nokogiri::HTML.parse(@browser.html)
|
12
12
|
#taking all the hotels list in HTML
|
13
|
+
puts "---------------doc-----------"
|
14
|
+
puts doc
|
13
15
|
onwardtransport_snip = doc.search('div#JourneyRowsOut')
|
14
16
|
onwardtransport_snip_Full= onwardtransport_snip.css('div.fullTable')
|
15
17
|
onwardtransport_snip_array = onwardtransport_snip_Full.css('div.tableDataRow.Divtrue')
|
16
18
|
|
19
|
+
puts onwardtransport_snip_array
|
17
20
|
|
18
21
|
#iterating over each hotel
|
19
22
|
onwardtransport_snip_array.each do |transport_elemets|
|
@@ -48,12 +51,12 @@ onwardtransport_snip_array.each do |transport_elemets|
|
|
48
51
|
output.store("arrival", arrival)
|
49
52
|
output.store("price", price)
|
50
53
|
output.store("route",route)
|
51
|
-
output.store("time",time)
|
52
54
|
output.store("id", "#{depart}_#{arrival}_#{route}")
|
53
55
|
|
54
56
|
|
55
57
|
#pushing to array
|
56
|
-
|
58
|
+
|
59
|
+
if(!@outwardArr.include?(output))
|
57
60
|
@outwardArr.push(output)
|
58
61
|
end
|
59
62
|
end
|
@@ -98,16 +101,15 @@ returntransport_snip_array.each do |transport_elemets|
|
|
98
101
|
output.store("arrival", arrival)
|
99
102
|
output.store("price", price)
|
100
103
|
output.store("route",route)
|
101
|
-
output.store("time",time)
|
102
104
|
output.store("id", "#{depart}_#{arrival}_#{route}")
|
103
105
|
|
104
106
|
#pushing to array
|
105
107
|
|
106
|
-
if(!@returnArr.
|
108
|
+
if(!@returnArr.include?(output))
|
107
109
|
@returnArr.push(output)
|
108
110
|
end
|
109
111
|
end
|
110
|
-
|
112
|
+
doc=nil
|
111
113
|
puts '----------------------------------------------------------------------------'
|
112
114
|
puts @outwardArr
|
113
115
|
puts @returnArr
|
@@ -117,6 +119,9 @@ end
|
|
117
119
|
|
118
120
|
def self.scrape(value)
|
119
121
|
|
122
|
+
@outwardArr = []
|
123
|
+
@returnArr = []
|
124
|
+
|
120
125
|
args = %w[--disable-infobars --headless window-size=1600,1200 --no-sandbox --disable-gpu --disable-dev-shm-usage]
|
121
126
|
options = {
|
122
127
|
binary: ENV['GOOGLE_CHROME_BIN'],
|
@@ -140,10 +145,13 @@ end
|
|
140
145
|
result = Hash.new
|
141
146
|
result.store("outward" ,@outwardArr)
|
142
147
|
result.store("return" ,@returnArr)
|
143
|
-
|
148
|
+
@browser.quit()
|
149
|
+
@browser= nil
|
150
|
+
|
144
151
|
return result
|
145
152
|
|
146
|
-
end
|
153
|
+
end
|
154
|
+
|
147
155
|
|
148
156
|
end
|
149
157
|
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: transportscrapper
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.9
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Niranjan Karunanithi
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2019-
|
11
|
+
date: 2019-12-05 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|
@@ -17,7 +17,7 @@ dependencies:
|
|
17
17
|
- - ">="
|
18
18
|
- !ruby/object:Gem::Version
|
19
19
|
version: '0'
|
20
|
-
type: :
|
20
|
+
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
@@ -31,20 +31,20 @@ dependencies:
|
|
31
31
|
- - ">="
|
32
32
|
- !ruby/object:Gem::Version
|
33
33
|
version: '0'
|
34
|
-
type: :
|
34
|
+
type: :runtime
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
38
|
- - ">="
|
39
39
|
- !ruby/object:Gem::Version
|
40
40
|
version: '0'
|
41
|
-
description: Scraps the transport data
|
41
|
+
description: Scraps the transport data from nationalbuseireann
|
42
42
|
email: niranjankarunanidhi@gmail.com
|
43
43
|
executables: []
|
44
44
|
extensions: []
|
45
45
|
extra_rdoc_files: []
|
46
46
|
files:
|
47
|
-
- lib/
|
47
|
+
- lib/transportscrapper.rb
|
48
48
|
homepage: http://rubygems.org/gems/transportscrapper
|
49
49
|
licenses: []
|
50
50
|
metadata: {}
|