Created
March 23, 2013 11:13
-
-
Save ttscoff/5227337 to your computer and use it in GitHub Desktop.
Rakefile task for querying Zemanta for keywords
This file contains hidden or 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 'yaml' | |
require 'rubygems' | |
require 'zemanta' # gem install zemanta | |
def get_zemanta_terms(content) | |
$stderr.puts "Querying Zemanta..." | |
zemanta = Zemanta.new "xxxxxxxxxxxxxxxxxxxxxxxx" | |
suggests = zemanta.suggest(content) | |
res = [] | |
suggests['keywords'].each {|k| | |
res << k['name'].downcase.gsub(/\s*\(.*?\)/,'').strip if k['confidence'] > 0.02 | |
} | |
res | |
end | |
desc "Add Zemanta keywords to post YAML" | |
task :add_keywords, :post do |t, args| | |
file = args.post | |
if File.exists?(file) | |
# Split the post by --- to extract YAML headers | |
contents = IO.read(file).split(/^---\s*$/) | |
headers = YAML::load("---\n"+contents[1]) | |
content = contents[2].strip | |
# skip adding keywords if it's already been done | |
unless headers['keywords'] && headers['keywords'] != [] | |
begin | |
$stderr.puts "getting terms for #{file}" | |
# retrieve the suggested keywords | |
keywords = get_zemanta_terms(content) | |
# insert them in the YAML array | |
headers['keywords'] = keywords | |
# Dump the headers and contents back to the post | |
File.open(file,'w+') {|file| file.puts YAML::dump(headers) + "---\n" + content + "\n"} | |
rescue | |
$stderr.puts "ERROR: #{file}" | |
end | |
else | |
puts "Skipped: post already has keywords header" | |
end | |
else | |
puts "No such file." | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment