Created
January 31, 2015 23:43
-
-
Save rbpd5015/af981a15080e837c55f3 to your computer and use it in GitHub Desktop.
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 'rubygems' | |
require 'nokogiri' | |
require 'open-uri' | |
f = File.open("NBAtest.html") | |
doc = Nokogiri::HTML(f, nil, "UTF-8") | |
doc.gsub("½", ".5") | |
gameid = doc.xpath('.//*[@itemtype="http://schema.org/SportsEvent"]/@id').collect {|node| node.text.strip} | |
startdate = doc.xpath('.//*[@itemprop="startdate"]/@content').collect {|node| node.text.strip} | |
name = doc.xpath('.//*[@itemprop="name"]/@content').collect {|node| node.text.strip} | |
url = doc.xpath('.//*[@itemprop="url"]/@content').collect {|node| node.text.strip} | |
address = doc.xpath('.//*[@itemprop="address"]/@content').collect {|node| node.text.strip} | |
rotation = doc.xpath('.//*[@class="el-div eventLine-rotation"]/*[@class="eventLine-book-value"]').collect {|node| node.text.strip} | |
time = doc.xpath('.//*[@class="el-div eventLine-time"]').collect {|node| node.text.strip} | |
teams = doc.xpath('.//*[@class="el-div eventLine-team"]/*[@class="eventLine-value"]').collect {|node| node.text.strip} | |
tv = doc.xpath('.//*[@class="el-div eventLine-tvStation"]/*[@class="eventLine-book-value"]').collect {|node| node.text.strip} | |
opener = doc.xpath('.//*[@class="el-div eventLine-opener"]/*[@class="eventLine-book-value"]').collect {|node| node.text.strip} | |
# puts gameid | |
# puts startdate | |
# puts name | |
# puts url | |
# puts address | |
# puts rotation | |
# puts time | |
# puts teams | |
# puts tv | |
# puts opener | |
puts doc | |
#puts doc | |
f.close | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment