arc.xsd

这是个爬虫和lucece相结合最好了

<?xml version="1.0" encoding="UTF-8"?>
<xs:schema xmlns="http://archive.org/arc/1.0/"
    targetNamespace="http://archive.org/arc/1.0/"
    xmlns:arc="http://archive.org/arc/1.0/"
    xmlns:xs="http://www.w3.org/2001/XMLSchema"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:dcterms="http://purl.org/dc/terms/" elementFormDefault="qualified" attributeFormDefault="unqualified">
    <xs:annotation>
        <xs:documentation xml:lang="en">
            Internet Archive ARC file Dublin Core element refinements. 
            
            XML Schema for http://archive.org/arc/1.0/ namespace.
            
            This schema adds Dublin Core element refinements for Internet
            Achive ARC file metadata. It also adds new elements
            that subclass the 'dc:any' type and the 'dc:metadata'
            element container. 
            
            $Id: arc.xsd 2094 2004-05-21 02:08:50Z stack-sf $
        
        </xs:documentation>
    </xs:annotation>
    <xs:import namespace="http://www.w3.org/XML/1998/namespace"
        schemaLocation="http://www.w3.org/2001/03/xml.xsd"/>
    <xs:import namespace="http://purl.org/dc/elements/1.1/"
        schemaLocation="http://dublincore.org/schemas/xmls/qdc/2003/04/02/dc.xsd"/>
    <xs:import namespace="http://purl.org/dc/terms/"
        schemaLocation="http://dublincore.org/schemas/xmls/qdc/2003/04/02/dcterms.xsd"/>
    <xs:element name="robots" substitutionGroup="dc:coverage">
        <xs:annotation>
            <xs:documentation xml:lang="en">
                Element-refinement for 'dc:coverage'.
                The robots policy followed by the
                crawler harvesting this resource.  Example: 'classic'.
            </xs:documentation>
        </xs:annotation>
    </xs:element>
    <xs:element name="http-header-from" substitutionGroup="dc:any">
        <xs:annotation>
            <xs:documentation xml:lang="en">The HTTP 'From' header sent by the
                crawler along with each request. Example:
                '[e-mail]'. Note that this value will be
                removed from metadata when ARC files record the request sent
                (Currently the response only is recorded in ARCs). </xs:documentation>
        </xs:annotation>
    </xs:element>
    <xs:element name="http-header-user-agent" substitutionGroup="dc:any">
        <xs:annotation>
            <xs:documentation xml:lang="en"> The HTTP 'user-agent' header sent
                by the crawler along with each request. Example:
                'os-heritrix/0.7.0 (+http://crawler.archive.org)'. Note that
                this value will be removed from metadata when ARC files record
                the request sent (Currently the response only is recorded in
                ARCs). </xs:documentation>
        </xs:annotation>
    </xs:element>
    <xs:element name="software" substitutionGroup="dc:creator">
        <xs:annotation>
            <xs:documentation xml:lang="en"> Element-refinement for 'dc:creator'.
                The software and software version used creating this resource.
                Example: 'heritrix 0.7.1 http://crawler.archive.org'. </xs:documentation>
        </xs:annotation>
    </xs:element>
    <xs:element name="hostname" substitutionGroup="dc:creator">
        <xs:annotation>
            <xs:documentation xml:lang="en"> Element-refinement for 'dc:creator'.
                The hostname of the machine that created this resource. Example
                'debord.archive.org'. </xs:documentation>
        </xs:annotation>
    </xs:element>
    <xs:element name="ip" substitutionGroup="dc:creator">
        <xs:annotation>
            <xs:documentation xml:lang="en"> Element-refinement for 'dc:creator'.
                The IP address of the machine that created this resource.
                Example '123.1.2.3'. </xs:documentation>
        </xs:annotation>
    </xs:element>
    <xs:element name="operator" substitutionGroup="dc:creator">
        <xs:annotation>
            <xs:documentation xml:lang="en"> Element-refinement for 'dc:creator'.
                Contact name and information for the operator who created this resource.
                Example: 'stack at archive dot org'. </xs:documentation>
        </xs:annotation>
    </xs:element>
    <xs:element name="arcmetadata" type="dcterms:elementOrRefinementContainer">
        <xs:annotation>
            <xs:documentation xml:lang="en"> Root container for ARC metadata.
                Can hold any 'dc:any' element. (All ARC elements are subclasses of
                the 'dc:any' type). </xs:documentation>
        </xs:annotation>
    </xs:element>
</xs:schema>