Last active
October 17, 2015 03:05
-
-
Save bshyong/1ede22f25efea044c766 to your computer and use it in GitHub Desktop.
Quick scraper to fetch first paragraph of Wikipedia for a list of topics
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
require 'open-uri' | |
require 'nokogiri' | |
require 'csv' | |
require 'cgi' | |
# BASE_URL = 'http://en.wikipedia.org/w/api.php?format=json&action=query&prop=revisions&rvprop=content&titles=' | |
BASE_URL = 'http://en.wikipedia.org/wiki/' | |
while($input_filename.nil?) | |
puts "Enter input filename (should be a CSV)" | |
$input_filename = gets.chomp! | |
end | |
while($filename.nil?) | |
puts "Enter a filename (output will be stored as a CSV)" | |
$filename = gets.chomp! | |
end | |
output = File.new("#{$filename}.csv", "a+") | |
CSV.foreach($input_filename) do |row| | |
puts "processing #{row[0]}" | |
puts url = BASE_URL + row[0].gsub(' ', '_') | |
begin | |
doc = Nokogiri::HTML(open(url)) | |
description = doc.css('#mw-content-text').css('p')[0].content.split('.')[0,2].join('. ') | |
output.puts(CSV.generate_line([row[0], description])) | |
rescue | |
puts "something went wrong! skipping" | |
puts $!.message | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment