Created
September 13, 2009 11:39
-
-
Save gregelin/186162 to your computer and use it in GitHub Desktop.
Ruby parse csv file
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
# Command line parse csv file | |
require 'CSV' | |
gf = "ucp_top_500_pages.txt" | |
af = "ucp_top_500_091209_categorized.txt" | |
src = File.open(gf,"r").read | |
views = {} | |
views = build_views(src) | |
src2 = File.open(af,"r").read | |
views2 = {} | |
views2 = build_views(src2) | |
views3 = {} | |
views.keys.each { |k| | |
puts k | |
next if k.nil? or views[k].nil? or views2[k].nil? | |
url = views[k] + views2[k] | |
views3[k] = url | |
} | |
# "/ucp_channeldoc.cfm/1/15/11383/11383-11383/2848"=>["/ucp_channeldoc.cfm/1/15/11383/11383-11383/2848", "20", "17", "156.25", "0.875", "0.8", "0", "/ucp_channeldoc.cfm/1/15/11383/11383-11383/2848", "Sports / Leisure", "UCP: Sports / Leisure"], | |
# >> views3["/ucp_generaldoc.cfm/1/3/6633/6633-6633/6256"][8] | |
# => "About Organization" | |
def build_views(src) | |
idx = 0 | |
fs = "\t" | |
views = {} | |
begin | |
parsed = [] | |
parsed_cells, idx = CSV.parse_row(src, idx, parsed, fs) | |
puts "Parsed #{ parsed_cells } cells." | |
puts parsed[0] | |
p parsed | |
views[parsed[0]] = parsed | |
end while parsed_cells > 0 | |
return views | |
end | |
# Other parts of code | |
views4 = {} | |
views.keys.each { |k| | |
next if views3[k].nil? | |
category = views3[k][8] | |
pv = views3[k][1] | |
puts "#{pv} #{category}" | |
if views4.has_key?(category) then | |
views4[category] = views4[category].to_i + views3[k][1].to_i | |
else | |
views4[category] = views3[k][1].to_i | |
end | |
} | |
views4.keys.each {|k| | |
puts "#{views4[k]}, #{k}" | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment