scraping memo

Gemfile

source 'https://rubygems.org'

gem 'mechanize'
gem 'csv'

scraper.rb

require 'nokogiri'
require 'open-uri'
require 'csv'

## twitter
#url = 'https://twitter.com/fujiwara_coltd'
#url = 'https://twitter.com/ryuji_fujimura'
#charset = nil
#
#html = open(url) do |f|
#    charset = f.charset
#    f.read
#end
#
#doc = Nokogiri::HTML.parse(html, nil, charset)
#doc.xpath('//div[@class="ProfileHeaderCard"]').each do |node|                                     
#    p node.xpath('h1[@class="ProfileHeaderCard-name"]/a').text                                    
#    p node.xpath('h2[@class="ProfileHeaderCard-screenname u-inlineBlock u-dir"]/a/span/b').text   
#    p node.xpath('div[@class="ProfileHeaderCard-location"]/a/span/b').text                        
#    #p node.css('a').inner_text
#end

## tabelog
#url = 'https://tabelog.com/tokyo/A1307/A130701/13005298/' # GONPACHI                              
url = 'https://tabelog.com/tokyo/A1310/A131002/13004170' # CARP                                    
charset = nil

html = open(url) do |f|
    charset = f.charset
    f.read
end

doc = Nokogiri::HTML.parse(html, nil, charset)
table = doc.xpath('//div[@class="rstinfo-table"]/table')                                           

shop_name_node =  table.xpath('.//tbody/tr').first
#p shop_name_node
shop_name = shop_name_node.xpath('td').text
#p shop_name.gsub(/\n|  /,'')
p shop_name.gsub(/  |\n/,'')
shop_address_node =  table.xpath('.//tbody/tr/td/p[@class="rstinfo-table__address"]')              
#p shop_address_node
shop_address =  shop_address_node.xpath('span').text                                               
p shop_address