Add author; handle multiple authors

test_xml2bib.py

@@ -24,5 +24,21 @@ def test_basic(self):
         if (self.verbose):
             print('testBasic:', x)
 
+
+class TestXMLReader(unittest.TestCase):
+    def test_one(self):
+        f = 'xmlfiles/_10.14470_6t569239.xml'
+        x = xml2bib.XMLReader(f)
+        d = xml2bib.xml2dict(x)
+
+        c_names = ('Th, H.',
+                   'Ba, N.',
+                   'Ma, V.',
+                   'Ri, J.',
+                   'Ti, F.',)
+        c = ' and '.join(c_names)
+        self.assertEqual(d['author'], c)
+
+
 if __name__ == '__main__':
     unittest.main()

xml2bib.py

@@ -46,7 +46,7 @@ def xml2dict(x):
     r = x.root
     #print('DEBUG', r.attrib)
 
-    xmlfields = ('identifier', 'title', 'publisher',
+    xmlfields = ('creator', 'identifier', 'title', 'publisher',
                  'publicationYear', 'resourceType')
     #nsd = {'dc': 'http://datacite.org/schema/kernel-4'}
     ns = '{http://datacite.org/schema/kernel-4}'
@@ -55,32 +55,29 @@ def xml2dict(x):
     for field in xmlfields:
         #for n in r.findall('dc:' + field, nsd):
         for n in r.iter(ns + field):
+            v = n.text
+            if field == 'creator':
+                v = n.find(ns + 'creatorName').text
+            #print('Found', field, v)
             if n is not None:
-                v = n.text
-                #print('Found', field, v)
-                dc[field] = v
-
-        #for n in r.findall(field):
-        #    print('found', field)
-        #    dc[field] = n.text
+                if dc[field] is None:
+                    dc[field] = v
+                else:
+                    dc[field] = dc[field] + ' and ' + v
 
     #print('DEBUG dc=', dc)
 
     d = dict()
-    d['authors'] = 'Abbott, A and Costello, C'
-    dc_to_bib = {'year': 'publicationYear',
+    dc_to_bib = {'author': 'creator',
+                 'year': 'publicationYear',
                  'DOI': 'identifier',
+                 'howpublished': 'resourceType',
                  'publisher': 'publisher',
                  'title': 'title',
-                 'howpublished': 'resourceType',
                  }
 
     for x in dc_to_bib:
         d[x] = dc[dc_to_bib[x]]
-#    d['year'] = dc['publicationYear']
-#    d['title'] = dc['title']
-#    d['DOI'] = dc['identifier']
-#    d['publisher'] = dc['publisher']
     return d
 
 if __name__ == '__main__':
@@ -91,5 +88,3 @@ def xml2dict(x):
         y = xml2dict(x)
         print(str(BibTeXWriter('ref%i' % (k,), y)))
         print()
-
-

xmlfiles/_10.14470_6t569239.xml

@@ -0,0 +1,53 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4/metadata.xsd">
+  <identifier identifierType="DOI">10.14470/6T569239</identifier>
+  <creators>
+    <creator>
+      <creatorName>Th, H.</creatorName>
+      <givenName>Ha</givenName>
+      <familyName>Th</familyName>
+    </creator>
+    <creator>
+      <creatorName>Ba, N.</creatorName>
+      <givenName>Ni</givenName>
+      <familyName>Ba</familyName>
+    </creator>
+    <creator>
+      <creatorName>Ma, V.</creatorName>
+      <givenName>Va</givenName>
+      <familyName>Ma</familyName>
+    </creator>
+    <creator>
+      <creatorName>Ri, J.</creatorName>
+      <givenName>Jo</givenName>
+      <familyName>Ri</familyName>
+    </creator>
+    <creator>
+      <creatorName>Ti, F.</creatorName>
+      <givenName>Fr</givenName>
+      <familyName>Ti</familyName>
+    </creator>
+  </creators>
+  <titles>
+    <title>ScanArray Core (1G 2012-2017)</title>
+  </titles>
+  <publisher>The ScanArray consortium</publisher>
+  <publicationYear>0</publicationYear>
+  <resourceType resourceTypeGeneral="Other">Seismic Network</resourceType>
+  <subjects>
+    <subject>Broadband seismic waveforms</subject>
+    <subject>Lithosphere</subject>
+    <subject subject_scheme="GEMET - INSPIRE themes, version 1.0" scheme_uri="" text="Monitoring system"/>
+    <subject subject_scheme="Library of Congress Subject Headings" scheme_uri="http://id.loc.gov/authorities/subjects" text="Seismological stations"/>
+  </subjects>
+  <dates>
+    <date dateType="Created">2016-05-23</date>
+    <date dateType="Issued">?</date>
+  </dates>
+  <version/>
+  <descriptions>
+    <description descriptionType="Abstract">The ScanArray experiment is a major collaborative effort of institutions in Scandinavia and Germany to map crustal and mantle structure below Scandinavia using a dense temporary deployment of broadband seismometers.
+[..]
+Waveform data will be fully opened in early 2020.</description>
+  </descriptions>
+</resource>