Created
April 10, 2014 19:34
-
-
Save sheepeeh/10415207 to your computer and use it in GitHub Desktop.
For a given search URL, retrieve the Omeka item IDs for all results.
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 'mechanize' | |
require 'open-uri' | |
def get_ids(fname) | |
# Create Mechanize agent | |
a = Mechanize.new { |agent| | |
agent.follow_meta_refresh = true | |
} | |
# GET Search page | |
puts "Getting search page.." | |
# Replace SEARCH URL with the appropriate Omeka search URL | |
a.get('SEARCH URL') do |page| | |
# Open Output File | |
f = File.open(fname, "a") | |
puts "Getting links." | |
# Set up array | |
items = [] | |
loop do | |
# Find desired links | |
page.links.each do |item| | |
hrf = item.attributes['href'] | |
items << hrf if hrf.match("/items/show/") unless hrf.nil? | |
puts "Evaluating #{hrf}..." | |
end | |
# Get the next page and find desired links | |
next_page = page.link_with(:text => ">") | |
break unless next_page | |
puts "Getting next page.." | |
next_page = next_page.click | |
page = next_page | |
end | |
# Remove empty items and duplicate items, print values to file | |
puts "---------\nWriting to file.." | |
items = items.compact | |
items = items.uniq | |
items = items.join("\n") | |
items = items.gsub("/items/show/", "") | |
f.puts items | |
f.close | |
puts "---------\nDone." | |
end | |
end | |
# Change the text in quotes for a differently named file | |
get_ids("omeka_ids.txt") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment