Shared collection conversion v1

parse.py

import xml.etree.ElementTree as ET
from xml.dom.minidom import parseString

pretty_print = lambda data: '\n'.join([line for line in parseString(data).toprettyxml(indent=' '*2).split('\n') if line.strip()])

def remove_namespace(doc, namespace):
  """Remove namespace in the passed document in place."""
  ns = u'{%s}' % namespace
  nsl = len(ns)
  for elem in doc.getiterator():
    if elem.tag.startswith(ns):
      elem.tag = elem.tag[nsl:]


metadata = 'RecapSharedCirc2a.xml'
tree = ET.parse(metadata)
root = tree.getroot()

# remove the namespace prefix on all the elements
remove_namespace(root, 'http://www.loc.gov/MARC21/slim')


bibRecords = ET.Element("bibRecords")


# loop through each marc:record
for record in root:

  # this will be the new record/holding/items components
  newBibRecord = ET.Element('record')
  newHolding = ET.Element('record')
  # the new items could be repeatable (?) so make the collection here and add them all in at the end of the elements
  newItems = ET.Element('collection')
  newItems.set('xmlns', 'http://www.loc.gov/MARC21/slim')
  newItemsList = []

  # update date
  updateDate = "12-09-2014 12:00"

  # gather the data we need
  for aTag in record:
    # the 'holdings'
    if ('tag' in aTag.attrib and aTag.attrib['tag'] == '852'):
      newHolding.append(aTag)
    # the items collection
    elif ('tag' in aTag.attrib and (aTag.attrib['tag'] == '876' or aTag.attrib['tag'] == '900')):
      newItemsList.append(aTag)
    # all the rest of the bib fields
    else:
      newBibRecord.append(aTag)
      # grab the date if we can to add it in the update date (?)
      if ('tag' in aTag.attrib and aTag.attrib['tag'] == '945'):
        for aSubfield in aTag:
          if ('code' in aSubfield.attrib and aSubfield.attrib['code'] == 'k'):
           updateDate = aSubfield.text

  # add in all the items we gathered
  newitem = ET.Element('record')

  for aItem in newItemsList:
    newitem.append(aItem)

  newItems.append(newitem)


  # now we have all the components for each bibRecord, make that.
  # make a new bib
  bibRecord = ET.SubElement(bibRecords, 'bibRecord')
  bib = ET.SubElement(bibRecord, "bib")
  # add in the owningInstitutionId and lastUpdatedDate
  owningInstitutionId = ET.Element('owningInstitutionId')
  owningInstitutionId.text = 'NY'
  bib.append(owningInstitutionId)
  lastUpdatedDate = ET.Element('lastUpdatedDate')
  lastUpdatedDate.text = updateDate
  bib.append(lastUpdatedDate)

  bibContent = ET.SubElement(bib, 'content')
  bibCollection = ET.SubElement(bibContent, 'collection')
  bibCollection.set('xmlns', 'http://www.loc.gov/MARC21/slim')
  bibCollection.append(newBibRecord)

  holdings = ET.SubElement(bibRecord, "holdings")

  holding = ET.SubElement(holdings, "holding")

  holdingLastUpdatedDate = ET.SubElement(holding, "lastUpdatedDate")
  holdingLastUpdatedDate.text = updateDate
  holdingOwningInstitutionHoldingsId = ET.SubElement(holding, "owningInstitutionHoldingsId")

  holdingOwningInstitutionHoldingsId.text = "?"

  holdingContent = ET.SubElement(holding, "content")

  holdingCollection = ET.SubElement(holdingContent, "collection")
  holdingCollection.set('xmlns', 'http://www.loc.gov/MARC21/slim')
  holdingCollection.append(newHolding)

  items = ET.SubElement(holding, "items")
  itemContent = ET.SubElement(items, "content")

  itemContent.append(newItems)

with open('output.xml', 'w') as f:
    f.write(pretty_print(ET.tostring(bibRecords, 'utf-8')))