Created
March 4, 2019 13:21
-
-
Save masao/0afab4595482aa3a8de6eae73f357d7a to your computer and use it in GitHub Desktop.
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
#!/usr/bin/env ruby | |
require "nokogiri" | |
NAMESPACES = { | |
"education" => "http://www.orcid.org/ns/education", | |
"employment" => "http://www.orcid.org/ns/employment", | |
"common" => "http://www.orcid.org/ns/common", | |
"person" => "http://www.orcid.org/ns/person", | |
"personal-details" => "http://www.orcid.org/ns/personal-details", | |
} | |
def extract_orgname_start_end(doc, namespace) | |
doc.xpath("//#{namespace}:#{namespace}-summary", NAMESPACES).each do |education| | |
name = education.xpath("./#{namespace}:organization/common:name", NAMESPACES).first.content | |
if name =~ /University of Tsukuba/i | |
#puts education | |
start_date = education.xpath("./common:start-date", NAMESPACES).first | |
start_date = start_date.xpath("./*").map{|e| e.content }.join("-") if start_date | |
end_date = education.xpath("./common:end-date", NAMESPACES).first | |
end_date = end_date.xpath("./*").map{|e| e.content }.join("-") if end_date | |
return "#{start_date}-#{end_date}" | |
end | |
end | |
nil | |
end | |
ARGV.each do |f| | |
doc = Nokogiri::XML(open(f)) | |
data = {} | |
data[:education] = extract_orgname_start_end(doc, "education") | |
data[:employment] = extract_orgname_start_end(doc, "employment") | |
doc.xpath("//email:email").each do |email| | |
email = email.content | |
if email =~ /\.tsukuba.ac.jp/ | |
data[:email] = email | |
end | |
end | |
if data[:education] or data[:employment] or data[:email] | |
name = doc.at("//person:name") | |
#puts name | |
given = name.at("./personal-details:given-names").content | |
family = name.at("./personal-details:family-name") | |
family = family.content if family | |
data[:name] = "#{given} #{family}".strip | |
data[:id] = doc.at("//common:orcid-identifier/common:path", NAMESPACES).content | |
puts [ data[:id], data[:name], data[:email], | |
data[:education], data[:employment] ].join("\t") | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment