We are currently working on a Python script to collect technical metadata of our crawl configs (workflows), crawls and WACZ files via the Browsertrix API and transform that into PREMIS 3 XML (shortened example below).
Unfortunately, we’re pretty new to PREMIS…
As you can see, we’re currently using our own improvised namespace for Browsertrix. Of course, we’re not keen on maintaining such a schema and adapting it to future API updates.
Is there already an official Browsertrix XML schema somewhere that we can use instead?
Once the project is a little more mature, we’ll also share the code online and would then ask the PREMIS experts to take another critical look at our mapping.
Regards,
Heinz
<?xml version="1.0" encoding="UTF-8"?>
<premis:premis xmlns:btrix="https://dla-marbach.de/ns/browsertrix/v1" xmlns:premis="http://www.loc.gov/premis/v3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" version="3.0" xsi:schemaLocation="http://www.loc.gov/premis/v3 http://www.loc.gov/standards/premis/premis.xsd">
<premis:object xsi:type="premis:intellectualEntity">
<premis:objectIdentifier>
<premis:objectIdentifierType>UUID</premis:objectIdentifierType>
<premis:objectIdentifierValue>_0c09619a-dc71-4490-962f-df5be4df9ef5</premis:objectIdentifierValue>
</premis:objectIdentifier>
<premis:significantProperties>
<premis:significantPropertiesType>crawl workflow configuration</premis:significantPropertiesType>
<premis:significantPropertiesExtension>
<btrix:crawlWorkflow workflowId="0c09619a-dc71-4490-962f-df5be4df9ef5">
<btrix:scope>
<btrix:scopeType>page</btrix:scopeType>
<btrix:startUrl>https://archiv.metatrons.net/nanoboter/index.html</btrix:startUrl>
<btrix:maxDepth>-1</btrix:maxDepth>
<btrix:extraHops>1</btrix:extraHops>
<btrix:includeLinkedPages>true</btrix:includeLinkedPages>
<btrix:useRobots>false</btrix:useRobots>
<btrix:useSitemap>false</btrix:useSitemap>
<btrix:selectLinks>a[href]->href</btrix:selectLinks>
<btrix:alwaysAddBehaviorLinks>false</btrix:alwaysAddBehaviorLinks>
<btrix:failOnFailedSeed>false</btrix:failOnFailedSeed>
<btrix:failOnContentCheck>false</btrix:failOnContentCheck>
</btrix:scope>
[...]
<btrix:metadata>
<btrix:name>Kyon: Die geheimen Bücher</btrix:name>
<btrix:description>Kyons Skizzenbücher (Digitalisate, PDF)</btrix:description>
<btrix:jobType>url-list</btrix:jobType>
<btrix:created>2024-08-20T14:12:20Z</btrix:created>
<btrix:createdBy>Heinz Werner Kramski</btrix:createdBy>
<btrix:modified>2024-08-20T14:12:20Z</btrix:modified>
<btrix:modifiedBy>Heinz Werner Kramski</btrix:modifiedBy>
<btrix:revision>0</btrix:revision>
</btrix:metadata>
</btrix:crawlWorkflow>
[...]
<premis:object xsi:type="premis:representation">
<premis:objectIdentifier>
<premis:objectIdentifierType>UUID</premis:objectIdentifierType>
<premis:objectIdentifierValue>_manual-20240820141220-0c09619a-dc7</premis:objectIdentifierValue>
</premis:objectIdentifier>
<premis:originalName>Kyon: Die geheimen Bücher (manual-20240820141220-0c09619a-dc7)</premis:originalName>
[...]
<premis:object xsi:type="premis:file">
<premis:objectIdentifier>
<premis:objectIdentifierType>UUID</premis:objectIdentifierType>
<premis:objectIdentifierValue>_4027db14-13a7-5941-9cd9-38f34f6c5ba8</premis:objectIdentifierValue>
</premis:objectIdentifier>
<premis:objectCharacteristics>
<premis:compositionLevel>0</premis:compositionLevel>
<premis:fixity>
<premis:messageDigestAlgorithm>SHA-256</premis:messageDigestAlgorithm>
<premis:messageDigest>05122452e53bfa183b48a2756ad752cc40efb94cbdd5c711b1dda1426d778e16</premis:messageDigest>
</premis:fixity>
<premis:size>695304758</premis:size>
<premis:format>
<premis:formatDesignation>
<premis:formatName>WACZ</premis:formatName>
</premis:formatDesignation>
</premis:format>
[...]