1
|
package eu.dnetlib.msro.workflows.nodes.download;
|
2
|
|
3
|
import java.io.ByteArrayInputStream;
|
4
|
import java.util.ArrayList;
|
5
|
import java.util.List;
|
6
|
|
7
|
import javax.xml.parsers.DocumentBuilder;
|
8
|
import javax.xml.parsers.DocumentBuilderFactory;
|
9
|
import javax.xml.xpath.XPath;
|
10
|
import javax.xml.xpath.XPathConstants;
|
11
|
import javax.xml.xpath.XPathExpression;
|
12
|
import javax.xml.xpath.XPathFactory;
|
13
|
|
14
|
import org.apache.commons.logging.Log;
|
15
|
import org.apache.commons.logging.LogFactory;
|
16
|
import org.w3c.dom.Document;
|
17
|
import org.w3c.dom.NodeList;
|
18
|
|
19
|
import com.google.common.base.Function;
|
20
|
import com.google.gson.Gson;
|
21
|
|
22
|
import eu.dnetlib.data.download.rmi.DownloadItem;
|
23
|
|
24
|
/**
|
25
|
* The Class UrlExtractor.
|
26
|
*/
|
27
|
public class UrlExtractor implements Function<String, String> {
|
28
|
|
29
|
private static final Log log = LogFactory.getLog(UrlExtractor.class);
|
30
|
|
31
|
/** The xpath. */
|
32
|
private String xpath;
|
33
|
|
34
|
/** The xpath. */
|
35
|
private String xpathMetadataID;
|
36
|
|
37
|
public UrlExtractor(final String xpath, final String xpathMetadataID) {
|
38
|
this.xpath = xpath;
|
39
|
this.xpathMetadataID = xpathMetadataID;
|
40
|
}
|
41
|
|
42
|
/*
|
43
|
* (non-Javadoc)
|
44
|
*
|
45
|
* @see com.google.common.base.Function#apply(java.lang.Object)
|
46
|
*/
|
47
|
@Override
|
48
|
public String apply(final String input) {
|
49
|
try {
|
50
|
|
51
|
DownloadItem di = new DownloadItem();
|
52
|
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
|
53
|
DocumentBuilder builder;
|
54
|
builder = factory.newDocumentBuilder();
|
55
|
Document doc = builder.parse(new ByteArrayInputStream(input.getBytes()));
|
56
|
XPathFactory xPathFactory = XPathFactory.newInstance();
|
57
|
XPath myXpath = xPathFactory.newXPath();
|
58
|
XPathExpression expression = myXpath.compile(xpath);
|
59
|
Object values = expression.evaluate(doc, XPathConstants.NODESET);
|
60
|
di.setUrl(getNodes((NodeList) values));
|
61
|
di.setOriginalUrl(getNodes((NodeList) values));
|
62
|
expression = myXpath.compile(xpathMetadataID);
|
63
|
String extracted_metadataId = expression.evaluate(doc);
|
64
|
di.setIdItemMetadata(extracted_metadataId);
|
65
|
// di.setFileName(extracted_metadataId);
|
66
|
return di.toJSON();
|
67
|
} catch (Exception e) {
|
68
|
log.error("OPSSS... Something bad happen on evaluating ", e);
|
69
|
return null;
|
70
|
}
|
71
|
|
72
|
}
|
73
|
|
74
|
private String getNodes(final NodeList nodes) {
|
75
|
List<String> extracted_Url = new ArrayList<String>();
|
76
|
if (nodes != null) {
|
77
|
for (int i = 0; i < nodes.getLength(); i++) {
|
78
|
extracted_Url.add(nodes.item(i).getNodeValue());
|
79
|
}
|
80
|
}
|
81
|
return new Gson().toJson(extracted_Url);
|
82
|
}
|
83
|
|
84
|
/**
|
85
|
* Gets the xpath.
|
86
|
*
|
87
|
* @return the xpath
|
88
|
*/
|
89
|
public String getXpath() {
|
90
|
return xpath;
|
91
|
}
|
92
|
|
93
|
/**
|
94
|
* Sets the xpath.
|
95
|
*
|
96
|
* @param xpath
|
97
|
* the xpath to set
|
98
|
*/
|
99
|
public void setXpath(final String xpath) {
|
100
|
this.xpath = xpath;
|
101
|
}
|
102
|
|
103
|
/**
|
104
|
* @return the xpathMetadataID
|
105
|
*/
|
106
|
public String getXpathMetadataID() {
|
107
|
return xpathMetadataID;
|
108
|
}
|
109
|
|
110
|
/**
|
111
|
* @param xpathMetadataID
|
112
|
* the xpathMetadataID to set
|
113
|
*/
|
114
|
public void setXpathMetadataID(final String xpathMetadataID) {
|
115
|
this.xpathMetadataID = xpathMetadataID;
|
116
|
}
|
117
|
|
118
|
}
|