#!/bin/sh ########################################################## # Version ST.36 XML Formatted Patent Data Converter # Converts selected XML data to tab-separated values # July 31, 2008 by Guy Hagen, Innovation Insight # http://innovationinsight.com/ ########################################################## # usage - ls | sh patentconvert ########################################################## COUNTER=0 echo 'PatNum IssueDate MainClass FurtherClass intlClas Title inventor_firstname inventor_lastname InventorCity InventorState InventorCountry assignee AssigneeCity AssigneeState AssigneeCountry'> patentextract.txt while read THISFILE do COUNTER=$(expr $COUNTER + 1) echo ''>/tmp/patentconversion.xml cat $THISFILE | grep -v '> /tmp/patentconversion.xml echo '' >> /tmp/patentconversion.xml /sw/bin/xml sel -t -m //us-patent-grant/us-bibliographic-data-grant/ -v publication-reference/document-id/doc-number -o "#" -v publication-reference/document-id/date -o "#" -v classification-national/main-classification -o "#" -v classification-national/further-classification -o "#" -v classification-locarno/main-classification -o "#" -v invention-title -o "#" -v parties/applicants/applicant/addressbook/first-name -o "#" -v parties/applicants/applicant/addressbook/last-name -o "#" -v parties/applicants/applicant/addressbook/address/city -o "#" -v parties/applicants/applicant/addressbook/address/state -o "#" -v parties/applicants/applicant/addressbook/address/country -o "#" -v assignees/assignee/addressbook/orgname -o "#" -v assignees/assignee/addressbook/address/city -o "#" -v assignees/assignee/addressbook/address/state -o "#" -v assignees/assignee/addressbook/address/country -n /tmp/patentconversion.xml > /tmp/patentconversion.txt cat /tmp/patentconversion.txt | tr '#' '\t' >> patentextract.txt echo "Converted file $COUNTER = $THISFILE" done echo "All files completed processing!"