In Rails 4:
require 'httmultiparty'
class PageTextReceiver
include HTTMultiParty
base_uri 'http://localhost:3000'
def run
response = PageTextReceiver.post('https://pdftables.com/api?key=myapikey', :query => { f: File.new("/path/to/pdf/uploaded_pdf.pdf", "r") })
File.open('/path/to/save/as/html/response.html', 'w') do |f|
f.puts response
end
end
def convert
f = File.open("/path/to/saved/html/response.html")
doc = Nokogiri::HTML(f)
csv = CSV.open("path/to/csv/t.csv", 'w',{:col_sep => ",", :quote_char => '\'', :force_quotes => true})
doc.xpath('//table/tr').each do |row|
tarray = []
row.xpath('td').each do |cell|
tarray << cell.text
end
csv << tarray
end
csv.close
end
end
http://stackoverflow.com/questions/30183738/how-to-convert-pdf-to-excel-or-csv-in-rails-4