/
ExtractorBase.java
110 lines (101 loc) · 3.57 KB
/
ExtractorBase.java
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
/**
* boilerpipe
*
* Copyright (c) 2009, 2014 Christian Kohlschütter
*
* The author licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package com.kohlschutter.boilerpipe.extractors;
import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
import java.net.URL;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import com.kohlschutter.boilerpipe.BoilerpipeExtractor;
import com.kohlschutter.boilerpipe.BoilerpipeProcessingException;
import com.kohlschutter.boilerpipe.document.TextDocument;
import com.kohlschutter.boilerpipe.sax.BoilerpipeSAXInput;
import com.kohlschutter.boilerpipe.sax.HTMLFetcher;
/**
* The base class of Extractors. Also provides some helper methods to quickly retrieve the text that
* remained after processing.
*/
public abstract class ExtractorBase implements BoilerpipeExtractor {
/**
* Extracts text from the HTML code given as a String.
*
* @param html The HTML code as a String.
* @return The extracted text.
* @throws BoilerpipeProcessingException
*/
public String getText(final String html) throws BoilerpipeProcessingException {
try {
return getText(new BoilerpipeSAXInput(new InputSource(new StringReader(html)))
.getTextDocument());
} catch (SAXException e) {
throw new BoilerpipeProcessingException(e);
}
}
/**
* Extracts text from the HTML code available from the given {@link InputSource}.
*
* @param is The InputSource containing the HTML
* @return The extracted text.
* @throws BoilerpipeProcessingException
*/
public String getText(final InputSource is) throws BoilerpipeProcessingException {
try {
return getText(new BoilerpipeSAXInput(is).getTextDocument());
} catch (SAXException e) {
throw new BoilerpipeProcessingException(e);
}
}
/**
* Extracts text from the HTML code available from the given {@link URL}. NOTE: This method is
* mainly to be used for show case purposes. If you are going to crawl the Web, consider using
* {@link #getText(InputSource)} instead.
*
* @param url The URL pointing to the HTML code.
* @return The extracted text.
* @throws BoilerpipeProcessingException
*/
public String getText(final URL url) throws BoilerpipeProcessingException {
try {
return getText(HTMLFetcher.fetch(url).toInputSource());
} catch (IOException e) {
throw new BoilerpipeProcessingException(e);
}
}
/**
* Extracts text from the HTML code available from the given {@link Reader}.
*
* @param r The Reader containing the HTML
* @return The extracted text.
* @throws BoilerpipeProcessingException
*/
public String getText(final Reader r) throws BoilerpipeProcessingException {
return getText(new InputSource(r));
}
/**
* Extracts text from the given {@link TextDocument} object.
*
* @param doc The {@link TextDocument}.
* @return The extracted text.
* @throws BoilerpipeProcessingException
*/
public String getText(TextDocument doc) throws BoilerpipeProcessingException {
process(doc);
return doc.getContent();
}
}