restaurantscrapper 0.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/lib/RestaurantScrapper.rb +73 -0
- metadata +70 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA256:
|
|
3
|
+
metadata.gz: af06c7167792f8902d3ef17e77e588d92f83be34c79e7a486dde04d8fb1c9df6
|
|
4
|
+
data.tar.gz: ae2283bd7264015d965dba9c535e8fff5e53c509258c942c513207657306ac22
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: 643fe459e3b403c3b757c0591db9b999e483b65fa533978f2d12cdd6d98bde1673cf159e4a56d4e63bdb545ef132dfce910ed9db1627ff513bead7688e6e5b34
|
|
7
|
+
data.tar.gz: 1a368e6b15b072f4dfda9e2c1481394cb2549c24e014cd77077840a66e484d570707bd251e1e14231351036dd8c8096440c3038abbc96bf402898e4c2dfda3e8
|
|
@@ -0,0 +1,73 @@
|
|
|
1
|
+
require 'nokogiri'
|
|
2
|
+
require 'watir'
|
|
3
|
+
|
|
4
|
+
class RestaurantScrapper
|
|
5
|
+
|
|
6
|
+
def self.scrape(value)
|
|
7
|
+
|
|
8
|
+
outputArray = []
|
|
9
|
+
|
|
10
|
+
args = %w[--disable-infobars --headless window-size=1600,1200 --no-sandbox --disable-gpu --disable-dev-shm-usage]
|
|
11
|
+
options = {
|
|
12
|
+
binary: ENV['GOOGLE_CHROME_BIN'],
|
|
13
|
+
prefs: { password_manager_enable: false, credentials_enable_service: false },
|
|
14
|
+
args: args
|
|
15
|
+
}
|
|
16
|
+
|
|
17
|
+
browser = Watir::Browser.new(:chrome, options: options)
|
|
18
|
+
browser.goto value
|
|
19
|
+
doc = Nokogiri::HTML.parse(browser.html)
|
|
20
|
+
|
|
21
|
+
#taking all the hotels list in HTML
|
|
22
|
+
restaurant_list_snippets = doc.css('div.restaurants-list-ListCell__cellContainer--2mpJS')
|
|
23
|
+
|
|
24
|
+
#iterating over each hotel
|
|
25
|
+
restaurant_list_snippets.each do |restaurant_elements|
|
|
26
|
+
|
|
27
|
+
restaurantname_element = restaurant_elements.search('div.restaurants-list-ListCell__nameBlock--1hL7F')
|
|
28
|
+
restaurant_name = restaurantname_element.search('a.restaurants-list-ListCell__restaurantName--2aSdo').text
|
|
29
|
+
|
|
30
|
+
type_element1 = restaurant_elements.search('div.restaurants-list-ListCell__infoRow--31xBt.restaurants-list-ListCell__hideLeftDivider--3vXbe.restaurants-list-ListCell__cuisinePriceMenu--r4-Re')
|
|
31
|
+
type_element2 = type_element1.search('span.restaurants-list-ListCell__infoCell--1Fz8a')
|
|
32
|
+
|
|
33
|
+
restaurant_type = type_element2.search('span.restaurants-list-ListCell__infoRowElement--2E6E3').text
|
|
34
|
+
|
|
35
|
+
if restaurant_name
|
|
36
|
+
|
|
37
|
+
restaurant_name=restaurant_name.split(". ", 2)
|
|
38
|
+
name = restaurant_name[1]
|
|
39
|
+
|
|
40
|
+
end
|
|
41
|
+
|
|
42
|
+
if restaurant_type
|
|
43
|
+
restaurant_type=restaurant_type.gsub("\u20AC","money")
|
|
44
|
+
restaurant_type=restaurant_type.split("money", 2)
|
|
45
|
+
restaurant_type[1]= "money#{restaurant_type[1]}"
|
|
46
|
+
restaurant_range=restaurant_type[1].split("-")
|
|
47
|
+
if(restaurant_range.size>1)
|
|
48
|
+
fromrange=restaurant_range[0].scan(/(?=money)/).count
|
|
49
|
+
torange= restaurant_range[1].scan(/(?=money)/).count
|
|
50
|
+
range="#{fromrange}-#{torange}"
|
|
51
|
+
else
|
|
52
|
+
range =restaurant_range[0].scan(/(?=money)/).count
|
|
53
|
+
range="#{range}"
|
|
54
|
+
end
|
|
55
|
+
end
|
|
56
|
+
|
|
57
|
+
#new Hash is created and all the values are pushed into the hash map
|
|
58
|
+
output = Hash.new
|
|
59
|
+
output.store("name", name)
|
|
60
|
+
output.store("type", restaurant_type[0])
|
|
61
|
+
output.store("range", range)
|
|
62
|
+
|
|
63
|
+
|
|
64
|
+
#pushing to array
|
|
65
|
+
outputArray.push(output)
|
|
66
|
+
|
|
67
|
+
end
|
|
68
|
+
#returning array
|
|
69
|
+
return outputArray
|
|
70
|
+
|
|
71
|
+
end
|
|
72
|
+
|
|
73
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: restaurantscrapper
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.0.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Niranjan Karunanithi
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2019-11-28 00:00:00.000000000 Z
|
|
12
|
+
dependencies:
|
|
13
|
+
- !ruby/object:Gem::Dependency
|
|
14
|
+
name: nokogiri
|
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
|
16
|
+
requirements:
|
|
17
|
+
- - ">="
|
|
18
|
+
- !ruby/object:Gem::Version
|
|
19
|
+
version: '0'
|
|
20
|
+
type: :development
|
|
21
|
+
prerelease: false
|
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
23
|
+
requirements:
|
|
24
|
+
- - ">="
|
|
25
|
+
- !ruby/object:Gem::Version
|
|
26
|
+
version: '0'
|
|
27
|
+
- !ruby/object:Gem::Dependency
|
|
28
|
+
name: watir
|
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
|
30
|
+
requirements:
|
|
31
|
+
- - ">="
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: '0'
|
|
34
|
+
type: :development
|
|
35
|
+
prerelease: false
|
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
37
|
+
requirements:
|
|
38
|
+
- - ">="
|
|
39
|
+
- !ruby/object:Gem::Version
|
|
40
|
+
version: '0'
|
|
41
|
+
description: Scraps the restaurant data
|
|
42
|
+
email: niranjankarunanidhi@gmail.com
|
|
43
|
+
executables: []
|
|
44
|
+
extensions: []
|
|
45
|
+
extra_rdoc_files: []
|
|
46
|
+
files:
|
|
47
|
+
- lib/RestaurantScrapper.rb
|
|
48
|
+
homepage: http://rubygems.org/gems/restaurantscrapper
|
|
49
|
+
licenses: []
|
|
50
|
+
metadata: {}
|
|
51
|
+
post_install_message:
|
|
52
|
+
rdoc_options: []
|
|
53
|
+
require_paths:
|
|
54
|
+
- lib
|
|
55
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
56
|
+
requirements:
|
|
57
|
+
- - ">="
|
|
58
|
+
- !ruby/object:Gem::Version
|
|
59
|
+
version: '0'
|
|
60
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
61
|
+
requirements:
|
|
62
|
+
- - ">="
|
|
63
|
+
- !ruby/object:Gem::Version
|
|
64
|
+
version: '0'
|
|
65
|
+
requirements: []
|
|
66
|
+
rubygems_version: 3.0.3
|
|
67
|
+
signing_key:
|
|
68
|
+
specification_version: 4
|
|
69
|
+
summary: Scraps the restaurant data
|
|
70
|
+
test_files: []
|