scrapeemailadressen.rb

# start with empty list
list = []

# split pdf file into many text files (one for each page)
# `docsplit text jaarboek.pdf --no-ocr --pages all`

# define pattern for email address
regex = /[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,4}/i

# loop through all the pages
(1..705).each do |page|
  # open page
  f = File.open("jaarboek_#{page}.txt")

  # read content of page
  content_of_page = f.read

  # find addresses on page
  addresses_found_on_page = content_of_page.scan regex

  # append results to the list
  list += addresses_found_on_page
end

# write list to txt-file
File.open("adressen.txt", 'w') {|f| f.write(list.join(", ")) }

puts "#{list.count} adressen gevonden"