Created
April 25, 2018 21:13
-
-
Save kirushik/11025fc8c9e8b43a5c54af1dd34885b0 to your computer and use it in GitHub Desktop.
Fetches all ST:TNG episode summaries from Wikipedia
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env ruby | |
| require 'rubygems' | |
| require 'mechanize' | |
| require 'uri' | |
| a = Mechanize.new | |
| root = URI.parse('https://en.wikipedia.org/wiki/List_of_Star_Trek:_The_Next_Generation_episodes') | |
| urls = [] | |
| a.get(root) do |page| | |
| page.search('.wikiepisodetable').each do |table| | |
| table.search('.summary a').each do |cell| | |
| urls << root.merge(cell['href']) | |
| end | |
| end | |
| end | |
| File.open('episodes.txt', 'w') do |file| | |
| urls.lazy.map{|url| a.get(url)}.each do |page| | |
| page.search('.mw-parser-output').first | |
| .search("//span[@id='Plot']/parent::h2/following-sibling::*") | |
| .take_while{|n| n.name=='p'}.each do |par| | |
| file.puts par.text | |
| end | |
| end.to_a | |
| end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment