iss-identifyer.rb

iss-identifyer.rb

#!/usr/bin/env ruby

require "uri"
require "open-uri"
require "nokogiri"

NS = {
  dcndl: "http://ndl.go.jp/dcndl/terms/",
  dcterms: "http://purl.org/dc/terms/",
  foaf: "http://xmlns.com/foaf/0.1/",
}

ARGV.each do |file|
  File.open(file) do |io|
    doc = Nokogiri::XML(io)
    title = doc.xpath("//dcndl:BibResource/dcterms:title", NS).first&.content
    publisher = doc.xpath("//dcndl:BibResource/dcterms:publisher/foaf:Agent/foaf:name", NS).first&.content
    year = doc.xpath("//dcndl:BibResource/dcterms:issued", NS).first&.content&.to_i
    if year.nil?
      year = doc.xpath("//dcndl:BibResource/dcterms:date", NS).first&.content&.to_i
      year = nil if year == 0
    end
    p [ File.basename(file), title, publisher, year ]
    #p file if publisher.nil?
    #p file if year.nil?
    query = {
      dpid: "iss-ndl-opac",
      title: title.gsub(/:/, " ").gsub(/\s+/, " ").strip,
    }
    query[:publisher] = publisher if publisher
    if year
      query[:from] = year
      query[:until] = year
    end
    query_string = {
      operation: "searchRetrieve",
      maximumRecords: 10,
      recordSchema: "dcndl",
      recordPacking: "xml",
      query: query.map{|k,v| "#{k}=\"#{v}\""}.join(" AND "),
    }
    url = "https://iss.ndl.go.jp/api/sru?#{URI.encode_www_form query_string}"
    puts url
    basename = File.basename(file)
    next if File.exist? basename
    open(basename, "w") do |io|
      io.print URI.parse(url).open.read
    end
    sleep 1
  end
end

iss-summary.rb

#!/usr/bin/env ruby

require "uri"
require "open-uri"
require "nokogiri"

NS = {
  dcndl: "http://ndl.go.jp/dcndl/terms/",
  dcterms: "http://purl.org/dc/terms/",
  foaf: "http://xmlns.com/foaf/0.1/",
  sru: "http://www.loc.gov/zing/srw/",
  rdf: "http://www.w3.org/1999/02/22-rdf-syntax-ns#",
}

ARGV.each do |file|
  File.open(file) do |io|
    doc = Nokogiri::XML(io)
    hits = doc.xpath("//sru:numberOfRecords", NS)&.first&.content&.to_i
    next if hits.nil? or hits == 0
    next if hits > 10
    bibids = doc.xpath('//dcterms:identifier[@rdf:datatype="http://ndl.go.jp/dcndl/terms/NDLBibID"]', NS).to_a
    puts [ File.basename(file), hits, bibids.join("\t")].join("\t")
  end
end