org.archive.modules.writer.arc_metadata_template.xml Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of heritrix-modules Show documentation

This project contains some of the configurable modules used within the Heritrix application to crawl the web. The modules in this project can be used in applications other than Heritrix, however.

There is a newer version: 3.6.0

Show newest version

<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<arcmetadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:arc="http://archive.org/arc/1.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://archive.org/arc/1.0/" xsi:schemaLocation="http://archive.org/arc/1.0/ http://www.archive.org/arc/1.0/arc.xsd">
<arc:software>Heritrix ${VERSION} http://crawler.archive.org</arc:software>
<arc:hostname>${HOST}</arc:hostname>
<arc:ip>${IP}</arc:ip>
<dcterms:isPartOf>${JOB_NAME}</dcterms:isPartOf>
<dc:description>${DESCRIPTION}</dc:description>
<arc:operator>${OPERATOR}</arc:operator>
<arc:http-header-user-agent>${USER_AGENT}</arc:http-header-user-agent>
<arc:http-header-from>${FROM}</arc:http-header-from>
<arc:robots>${ROBOTS}</arc:robots>
<dc:format>ARC file version 1.1</dc:format>
<dcterms:conformsTo xsi:type="dcterms:URI">http://www.archive.org/web/researcher/ArcFileFormat.php</dcterms:conformsTo>
</arcmetadata>