Simple script to scrape Worm web serial chapters into aggregate HTML

worm-scraper.rb

#!/usr/bin/ruby

# Scrapes crude HTML representation of Worm (Parahumans) web serial chapters

require 'rubygems'
require 'nokogiri'
require 'open-uri'

# URL of first chapter
nextChapterUri = URI::encode("http://parahumans.wordpress.com/category/stories-arcs-1-10/arc-1-gestation/1-01/")

while true do
  $stderr.puts "Opening #{nextChapterUri}"
  currentPage = Nokogiri::HTML(open(nextChapterUri))
  content = currentPage.css('div.entry-content')
  isEnd = true
  
  #Search for sequence link
  content.css('a').each{ |n|
    if(n.text=='Next Chapter') then
      isEnd = false
      nextChapterUri = URI::encode(n.attr('href'))
    end
  }

  chapterText = content.css('p').to_s
  puts chapterText

  if(isEnd) then
    $stderr.puts "No further chapters find, exiting..."
    exit(0)
  end
end