1 | /****************************************************************************
|
---|
2 | **
|
---|
3 | ** Copyright (C) 2011 Nokia Corporation and/or its subsidiary(-ies).
|
---|
4 | ** All rights reserved.
|
---|
5 | ** Contact: Nokia Corporation (qt-info@nokia.com)
|
---|
6 | **
|
---|
7 | ** This file is part of the examples of the Qt Toolkit.
|
---|
8 | **
|
---|
9 | ** $QT_BEGIN_LICENSE:BSD$
|
---|
10 | ** You may use this file under the terms of the BSD license as follows:
|
---|
11 | **
|
---|
12 | ** "Redistribution and use in source and binary forms, with or without
|
---|
13 | ** modification, are permitted provided that the following conditions are
|
---|
14 | ** met:
|
---|
15 | ** * Redistributions of source code must retain the above copyright
|
---|
16 | ** notice, this list of conditions and the following disclaimer.
|
---|
17 | ** * Redistributions in binary form must reproduce the above copyright
|
---|
18 | ** notice, this list of conditions and the following disclaimer in
|
---|
19 | ** the documentation and/or other materials provided with the
|
---|
20 | ** distribution.
|
---|
21 | ** * Neither the name of Nokia Corporation and its Subsidiary(-ies) nor
|
---|
22 | ** the names of its contributors may be used to endorse or promote
|
---|
23 | ** products derived from this software without specific prior written
|
---|
24 | ** permission.
|
---|
25 | **
|
---|
26 | ** THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
---|
27 | ** "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
---|
28 | ** LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
---|
29 | ** A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
---|
30 | ** OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
---|
31 | ** SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
---|
32 | ** LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
---|
33 | ** DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
---|
34 | ** THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
---|
35 | ** (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
---|
36 | ** OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE."
|
---|
37 | ** $QT_END_LICENSE$
|
---|
38 | **
|
---|
39 | ****************************************************************************/
|
---|
40 |
|
---|
41 | #include <QtCore>
|
---|
42 |
|
---|
43 | void parseHtmlFile(QTextStream &out, const QString &fileName) {
|
---|
44 | QFile file(fileName);
|
---|
45 |
|
---|
46 | out << "Analysis of HTML file: " << fileName << endl;
|
---|
47 |
|
---|
48 | if (!file.open(QIODevice::ReadOnly)) {
|
---|
49 | out << " Couldn't open the file." << endl << endl << endl;
|
---|
50 | return;
|
---|
51 | }
|
---|
52 |
|
---|
53 | //! [0]
|
---|
54 | QXmlStreamReader reader(&file);
|
---|
55 | //! [0]
|
---|
56 |
|
---|
57 | //! [1]
|
---|
58 | int paragraphCount = 0;
|
---|
59 | QStringList links;
|
---|
60 | QString title;
|
---|
61 | while (!reader.atEnd()) {
|
---|
62 | reader.readNext();
|
---|
63 | if (reader.isStartElement()) {
|
---|
64 | if (reader.name() == "title")
|
---|
65 | title = reader.readElementText();
|
---|
66 | else if(reader.name() == "a")
|
---|
67 | links.append(reader.attributes().value("href").toString());
|
---|
68 | else if(reader.name() == "p")
|
---|
69 | ++paragraphCount;
|
---|
70 | }
|
---|
71 | }
|
---|
72 | //! [1]
|
---|
73 |
|
---|
74 | //! [2]
|
---|
75 | if (reader.hasError()) {
|
---|
76 | out << " The HTML file isn't well-formed: " << reader.errorString()
|
---|
77 | << endl << endl << endl;
|
---|
78 | return;
|
---|
79 | }
|
---|
80 | //! [2]
|
---|
81 |
|
---|
82 | out << " Title: \"" << title << "\"" << endl
|
---|
83 | << " Number of paragraphs: " << paragraphCount << endl
|
---|
84 | << " Number of links: " << links.size() << endl
|
---|
85 | << " Showing first few links:" << endl;
|
---|
86 |
|
---|
87 | while(links.size() > 5)
|
---|
88 | links.removeLast();
|
---|
89 |
|
---|
90 | foreach(QString link, links)
|
---|
91 | out << " " << link << endl;
|
---|
92 | out << endl << endl;
|
---|
93 | }
|
---|
94 |
|
---|
95 | int main(int argc, char **argv)
|
---|
96 | {
|
---|
97 | // initialize QtCore application
|
---|
98 | QCoreApplication app(argc, argv);
|
---|
99 |
|
---|
100 | // get a list of all html files in the current directory
|
---|
101 | QStringList filter;
|
---|
102 | filter << "*.htm";
|
---|
103 | filter << "*.html";
|
---|
104 | QStringList htmlFiles = QDir::current().entryList(filter, QDir::Files);
|
---|
105 |
|
---|
106 | QTextStream out(stdout);
|
---|
107 |
|
---|
108 | if (htmlFiles.isEmpty()) {
|
---|
109 | out << "No html files available.";
|
---|
110 | return 1;
|
---|
111 | }
|
---|
112 |
|
---|
113 | // parse each html file and write the result to file/stream
|
---|
114 | foreach(QString file, htmlFiles)
|
---|
115 | parseHtmlFile(out, file);
|
---|
116 |
|
---|
117 | return 0;
|
---|
118 | }
|
---|