scripts to harvest a collection out of Merritt

extract_links.xsl

<xsl:stylesheet 
  version="1.0" 
  xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xmlns:atom="http://www.w3.org/2005/Atom"
  xmlns:dct="http://purl.org/dc/terms/"
  xmlns:str="http://exslt.org/strings"
  xmlns:xlink="http://www.w3.org/1999/xlink">
 
  <!-- xslt for 

 one-off

  -->

  <xsl:output method="text"/>

  <xsl:param name="base"/>
 
  <xsl:template match="atom:feed">
    <xsl:apply-templates select="atom:entry"/>
  </xsl:template>

  <xsl:template match="atom:entry">
    <xsl:variable name="lid" select="str:replace(atom:id,'http://n2t.net/ark:/28722/','')"/>

    <xsl:text>curl -u $MERRITT https://merritt.cdlib.org</xsl:text>
    <xsl:value-of select="atom:link[@title='producer/mets.txt']/@href"/>
    <xsl:text> &gt; </xsl:text>
    <xsl:value-of select="$lid"/><xsl:text>.mets.xml
</xsl:text>
    <xsl:text>curl -u $MERRITT https://merritt.cdlib.org</xsl:text>
    <xsl:value-of select="atom:link[@title='producer/FID1.tiff']/@href"/>
    <xsl:text> &gt; </xsl:text>
    <xsl:value-of select="$lid"/><xsl:text>.tiff
</xsl:text>
  </xsl:template>
 
</xsl:stylesheet>

grab_atom.bash

#!/bin/env bash
set -eu
for i in $(seq 1 40)
  do 
    curl -u $MERRITT "https://merritt.cdlib.org/object/recent.atom?collection=ark:/13030/m5xk8jh0&page=$i" > atom$i.xml
done