Created
April 7, 2012 13:08
-
-
Save shuma/2328752 to your computer and use it in GitHub Desktop.
Ruby crawler, csv
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 'ap' | |
require 'csv' | |
class MyDocument < Nokogiri::XML::SAX::Document | |
def initialize | |
@infodata = {} | |
@infodata[:titles] = Array.new([]) | |
end | |
def start_element(name, attrs) | |
@attrs = attrs | |
@content = '' | |
end | |
def end_element(name) | |
if name == 'title' | |
Hash[@attrs]['xml:lang'] | |
@infodata[:titles] << @content.inspect | |
@content = nil | |
end | |
if name == 'identifier' | |
@infodata[:identifier] = @content.inspect | |
@content = nil | |
end | |
if name == 'typeOfLevel' | |
@infodata[:typeOfLevel] = @content.inspect | |
@content = nil | |
end | |
if name == 'typeOfResponsibleBody' | |
@infodata[:typeOfResponsibleBody] = @content.inspect | |
@content = nil | |
end | |
if name == 'type' | |
@infodata[:type] = @content.inspect | |
@content = nil | |
end | |
if name == 'exact' | |
@infodata[:exact] = @content.inspect | |
@content = nil | |
end | |
if name == 'degree' | |
@infodata[:degree] = @content.inspect | |
@content = nil | |
end | |
if name == 'academic' | |
@infodata[:academic] = @content.inspect | |
@content = nil | |
end | |
if name == 'code' | |
Hash[@attrs]['source="vhs"'] | |
@infodata[:code] = @content.inspect | |
@content = nil | |
end | |
if name == 'ct:text' | |
@infodata[:beskrivning] = @content.inspect | |
@content = nil | |
end | |
end | |
def characters(string) | |
@content << string if @content | |
end | |
def cdata_block(string) | |
characters(string) | |
end | |
def end_document | |
CSV.open("info.csv", "wb") do |row| | |
row << @infodata.values | |
end | |
puts "Finished..." | |
end | |
end | |
parser = Nokogiri::XML::SAX::Parser.new(MyDocument.new) | |
parser.parse(File.open("arkivvetenskap.xml", 'rb')) |
You can make your code cleaner like this:
case name
when 'title'
Hash[@attrs]['xml:lang']
@infodata[:titles] << @content.inspect
@content = nil
when 'identifier', 'typeOfLevel', 'typeOfResponsibleBody', 'type', 'exact', 'degree', 'academic'
@infodata[name.to_sym] = @content.inspect
@content = nil
when 'code'
Hash[@attrs]['source="vhs"']
@infodata[:code] = @content.inspect
@content = nil
when 'ct:text'
@infodata[:beskrivning] = @content.inspect
@content = nil
end
Thanks SixArm! that is awesome.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Ruby has a fast way to write comparisons like this: