rubinsztajn

<!-- RDFa snippet example for SNAC -->
<div xmlns:owl="http://www.w3.org/2002/07/owl#">
   <div about="http://socialarchive.iath.virginia.edu/xtf/view?docId=Eisenhower+Dwight+D+Dwight+David+1890-1969-cr.xml#entity">
       <div>sameAs</div>
       <a rel="owl:sameAs" href="http://viaf.org/viaf/100176316">http://viaf.org/viaf/100176316</a>
   </div>
</div>

rubinsztajn

import csv
import rdflib
from rdflib.graph import Graph
from rdflib import plugin

out = csv.writer(open('databib.csv', 'w'))
out.writerow(['Name','Page','License','Deposit'])

plugin.register(
    'sparql', rdflib.query.Processor,

rubinsztajn

<?xml version="1.0" encoding="utf-8"?>
<?xml-stylesheet href="marmota.xsl" type="text/xsl"?>
<!DOCTYPE ead PUBLIC "+//ISBN 1-931666-00-8//DTD ead.dtd (Encoded Archival Description (EAD) Version 2002)//EN" "ead.dtd">
<ead>
<eadheader langencoding="iso639-2b" countryencoding="iso3166-1" dateencoding="iso8601" repositoryencoding="iso15511" scriptencoding="iso15924" audience="internal" id="head" relatedencoding="MARC21">

<eadid publicid="-//us::mu//TEXT us::mu::mums129.xml//EN" countrycode="us" mainagencycode="mu">mums129</eadid>

<filedesc>
<titlestmt>

rubinsztajn

if binders:
   Burn 'em...

test:
   if binders.ash?:
      log = "Thank fucking god"   

rubinsztajn

Some quick and dirty RDF serializer benchmarks

1MB file of RDF/XML from SNAC-VIAF data, https://gist.github.com/tingletech/1593245#file-snac-viaf-rdf

rapper

http://librdf.org/raptor/rapper.html

Command: rapper -i rdfxml -o ntriples snac-viaf.rdf

rubinsztajn

#!/usr/bin/env python
import os, sys

ids = open(sys.argv[1])

for id in ids:
    id = id.strip()
    pdf_cmd = "wget http://archive.org/download/%s/%s.pdf" % (id, id)
    marc_cmd = "wget http://archive.org/download/%s/%s_archive_marc.xml" % (id, id)