The ScraperWiki API Ruby Gem

require 'scraperwiki-api'
api = ScraperWiki::API.new

info = api.scraper_getinfo('example-scraper').first

describe 'example-scraper' do
  include ScraperWiki::API::Matchers
  subject {info}

  it {should be_protected}
  it {should be_editable_by('frabcus')}
  it {should run(:daily)}
  it {should_not be_broken}

  # Validate the properties of a SQLite table by chaining on a +on+.
  it {should have_a_row_count_of(42).on('swdata')}

  # Ensure that the scraper sets required fields.
  it {should have_at_least_the_keys(['name', 'email']).on('swdata')}

  # Ensure that the scraper doesn't set too many fields.
  it {should have_at_most_the_keys(['name', 'email', 'tel', 'fax']).on('swdata')}
end

require 'scraperwiki-api'
api = ScraperWiki::API.new

data = api.datastore_sqlite('example-scraper', 'SELECT * from `swdata`')

describe 'example-scraper' do
  include ScraperWiki::API::Matchers
  subject {data}

  # If you need at least one of a set of fields to be set:
  it {should set_any_of(['name', 'first_name', 'last_name'])}

  # Validate the values of individual fields by chaining on an +in+.
  it {should_not have_blank_values.in('name')}
  it {should have_unique_values.in('email')}
  it {should have_values_of(['M', 'F']).in('gender')}
  it {should have_values_matching(/\A[^@\s]+@[^@\s]+\z/).in('email')}
  it {should have_values_starting_with('http://').in('url')}
  it {should have_values_ending_with('Inc.').in('company_name')}
  it {should have_integer_values.in('year')}

  # If you store a hash or an array of hashes in a field as a JSON string,
  # you can validate the values of these subfields by chaining on an +at+.
  it {should have_values_of(['M', 'F']).in('extra').at('gender')}

  # Check for missing keys within subfields.
  it {should have_values_with_at_least_the_keys(['subfield1', 'subfield2']).in('fieldA')}

  # Check for extra keys within subfields.
  it {should have_values_with_at_most_the_keys(['subfield1', 'subfield2', 'subfield3', 'subfield4']).in('fieldA')}
end