bookingscrapper 0.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: b9c1a5aa34c2d3ecfb0942c8356456adccf685b0eb17c2895ba86a9dd76da5f3
+  data.tar.gz: 5b2f486b122bf40a7698ef18ec6230cf698e9fa52e9b185cec59c501742b6c90
+SHA512:
+  metadata.gz: 597ec10415d0ce3e1c4e72f0ed3e564e1d066d992b6c037429b50722f2da77cd2adf2d2aa286a76dc1c807b427c42bc82d13fe87b2ee7f1a1c8ada60e0d2adfc
+  data.tar.gz: 0bda92aa445c505b5f77bdf13203e826c2fb5dbe67ea49df954a546eca5c5c9ae8d5485b88322f7e8761ba3b3b80eafcf83f5fcd923cb1bcc9e8c40e23e1ca43

data/lib/bookingscrapper.rb

@@ -0,0 +1,89 @@
+require 'nokogiri'
+require 'open-uri'
+require 'pry'
+require 'watir'
+
+
+def scrape(value)
+  
+outputArray = []
+browser = Watir::Browser.new
+browser.goto value
+doc = Nokogiri::HTML.parse(browser.html)
+
+url =browser.url
+#taking all the hotels list in HTML
+hotel_list_snippets = doc.css('div.sr_item.sr_item_new.sr_item_default.sr_property_block')
+
+#iterating over each hotel
+hotel_list_snippets.each do |hotel_elements|
+
+	hotel_name=	hotel_elements.search('span.sr-hotel__name').text.strip!
+	hotel_rank= hotel_elements.search('div.bui-review-score__badge').text.strip!
+	
+	location_doc = hotel_elements.css('div.sr_card_address_line')
+	hotel_location = location_doc.search('a.bui-link').attribute('data-coords').value
+	hotel_address = location_doc.search('a').text.strip!
+	
+	roomtype_doc =hotel_elements.css('a.room_link')
+	hotel_roomtype=	roomtype_doc.at('strong')
+	
+	#some hotel does not have this tag, and result will be Nil, so here its checking for Nil
+	if hotel_roomtype
+	hotel_roomtype=	roomtype_doc.at('strong').text
+	
+	end
+	
+	bedtype_doc =hotel_elements.css('span.room_info')
+	hotel_bedtype=	bedtype_doc.search('span.sr_gr_bed_type').text.strip!
+	
+	hotel_price= hotel_elements.search('div.bui-price-display__value.prco-inline-block-maker-helper').text.strip!
+
+	
+	hotel_name = hotel_name
+	hotel_rank = hotel_rank
+	hotel_location = hotel_location
+	
+	#removing Show on map string before that its checking for Nil value
+	if hotel_address
+	hotel_address.slice! "Show on map"
+	hotel_address= hotel_address.strip!
+	end
+	
+	#checking for Nil value
+	if hotel_roomtype
+	hotel_roomtype.gsub("\n","")
+	end
+	
+	#checking for Nil Value
+	if hotel_bedtype
+	hotel_bedtype.gsub("\n","")
+	end
+	
+	#checking for Nil Value
+	if hotel_price
+	hotel_price.slice! "\u20AC\u00A0"
+	end
+	
+	#new Hash is created and all the values are pushed into the hash map
+	output = Hash.new
+	output.store("name", hotel_name)
+	output.store("rank", hotel_rank)
+	output.store("location", hotel_location)
+	output.store("address", hotel_address)
+	output.store("roomtype", hotel_roomtype)
+	output.store("bedtype", hotel_bedtype)
+	output.store("price", hotel_price)
+
+#prints the hash map
+	outputArray.push(output)
+	
+   end
+   
+return outputArray
+
+end
+
+res=scrape('https://www.booking.com/searchresults.en-gb.html?label=gen173nr-1DCAEoggI46AdIM1gEaGmIAQGYAQm4ARfIAQzYAQPoAQGIAgGoAgO4Aqju0O0FwAIB&lang=en-gb&sid=cedaa5898969a74044a5c76485351761&sb=1&src=index&src_elem=sb&error_url=https%3A%2F%2Fwww.booking.com%2Findex.en-gb.html%3Flabel%3Dgen173nr-1DCAEoggI46AdIM1gEaGmIAQGYAQm4ARfIAQzYAQPoAQGIAgGoAgO4Aqju0O0FwAIB%3Bsid%3Dcedaa5898969a74044a5c76485351761%3Bsb_price_type%3Dtotal%26%3B&ss=Dublin&is_ski_area=0&ssne=Dublin&ssne_untouched=Dublin&dest_id=-1502554&dest_type=city&checkin_monthday=1&checkin_month=11&checkin_year=2019&checkout_monthday=6&checkout_month=11&checkout_year=2019&group_adults=1&group_children=0&no_rooms=1&b_h4u_keep_filters=&from_sf=1')
+
+puts res

metadata

@@ -0,0 +1,42 @@
+--- !ruby/object:Gem::Specification
+name: bookingscrapper
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+platform: ruby
+authors:
+- Niranjan Karunanithi
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2019-10-28 00:00:00.000000000 Z
+dependencies: []
+description: Retrives hotel data
+email: niranjankarunanidhi@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/bookingscrapper.rb
+homepage: http://rubygems.org/gems/bookingscrapper
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: Hotel data
+test_files: []