1 <?xml version="1.0" encoding="UTF-8"?>
2 <?xml-stylesheet type="text/xsl" href="xs3p.xsl"?>
3 <xs:schema attributeFormDefault="unqualified" elementFormDefault="qualified"
4 xmlns:xs="http://www.w3.org/2001/XMLSchema">
5 <!--This is the main element, required. It contains crawler and/data entries-->
6 <xs:element name="crawler_output">
10 Crawler entries contain the information of the crawler, there can be multiple
12 <xs:element name="crawler" maxOccurs="unbounded" minOccurs="0">
15 <xs:extension base="xs:string">
16 <xs:attribute type="xs:string" name="name" use="optional"/>
17 <xs:attribute type="xs:string" name="venue" use="optional"/>
18 <xs:attribute type="xs:string" name="freq" use="optional"/>
19 <xs:attribute type="xs:string" name="def_loc" use="optional"/>
20 <xs:attribute type="xs:string" name="adress" use="optional"/>
21 <xs:attribute type="xs:anyURI" name="website" use="optional"/>
22 <xs:attribute type="xs:anyURI" name="url" use="optional"/>
28 Data entries contain the information of a single crawled entry, there can be
31 <xs:element name="data" maxOccurs="unbounded" minOccurs="0">
34 <xs:element name="entry">
37 <!--These four fields contain the user data-->
38 <xs:element type="xs:string" name="where"/>
39 <xs:element type="xs:string" name="what"/>
40 <xs:element type="xs:string" name="date"/>
41 <xs:element type="xs:string" name="time"/>
42 <!--These fields contain the raw original title and summary-->
43 <xs:element type="xs:string" name="full_title"/>
44 <xs:element type="xs:string" name="full_summary"/>
45 <!--These fields contain some other information from the rss-->
46 <xs:element type="xs:anyURI" name="link"
47 maxOccurs="unbounded" minOccurs="0"/>
48 <xs:element type="xs:string" name="pub_date"
49 maxOccurs="unbounded" minOccurs="0"/>
50 <!--Extracted URIs is a list of urls, this can be empty-->