ruby scraper.rb > polls.json
Created
September 7, 2014 21:36
-
-
Save campreb/25a58a6d60fbbf14c376 to your computer and use it in GitHub Desktop.
NZ Opinion Poll Scraper
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 'nokogiri' | |
| require 'open-uri' | |
| require 'json' | |
| doc = Nokogiri::HTML(open('http://en.wikipedia.org/wiki/Opinion_polling_for_the_next_New_Zealand_general_election')) | |
| rows = doc.css('table:first tr') | |
| headers = rows[0].css('th') | |
| parties = {} | |
| headers[2..headers.length].each_with_index do |cell, i| | |
| parties[i+2] = cell.text | |
| end | |
| results = [] | |
| rows.each do |row| | |
| cells = row.css('td') | |
| next unless cells.length > 1 | |
| poll = cells[0].text.gsub(/\[.*\]/, '') | |
| date = cells[1].text.gsub(/\[.*\]/, '') | |
| parties.each do |key, party| | |
| value = cells[key].text | |
| next if value == '' | |
| results.push({ | |
| poll: poll, | |
| date: date, | |
| party: party, | |
| value: value.to_f | |
| }) | |
| end | |
| end | |
| puts results.to_json |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment