1#!/usr/bin/env python
2"""
3Capture a web page and save its internal frames in different images
4
5  framecapture.py <url> <outputfile>
6
7Notes:
8  'url' is the URL of the web page to be captured
9  'outputfile' is the prefix of the image files to be generated
10
11Example:
12  framecapture qt.nokia.com trolltech.png
13
14Result:
15  trolltech.png (full page)
16  trolltech_frame1.png (...) trolltech_frameN.png ('N' number of internal frames)
17"""
18
19
20#############################################################################
21##
22## Copyright (C) 2013 Riverbank Computing Limited
23## Copyright (C) 2010 Hans-Peter Jansen <hpj@urpla.net>.
24## Copyright (C) 2010 Nokia Corporation and/or its subsidiary(-ies).
25## All rights reserved.
26##
27## This file is part of the examples of PyQt.
28##
29## $QT_BEGIN_LICENSE:BSD$
30## You may use this file under the terms of the BSD license as follows:
31##
32## "Redistribution and use in source and binary forms, with or without
33## modification, are permitted provided that the following conditions are
34## met:
35##   * Redistributions of source code must retain the above copyright
36##     notice, this list of conditions and the following disclaimer.
37##   * Redistributions in binary form must reproduce the above copyright
38##     notice, this list of conditions and the following disclaimer in
39##     the documentation and/or other materials provided with the
40##     distribution.
41##   * Neither the name of Nokia Corporation and its Subsidiary(-ies) nor
42##     the names of its contributors may be used to endorse or promote
43##     products derived from this software without specific prior written
44##     permission.
45##
46## THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
47## "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
48## LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
49## A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
50## OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
51## SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
52## LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
53## DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
54## THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
55## (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
56## OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE."
57## $QT_END_LICENSE$
58##
59###########################################################################
60
61import sys
62
63from PyQt5.QtCore import pyqtSignal, QObject, QSize, Qt, QUrl
64from PyQt5.QtGui import QImage, QPainter
65from PyQt5.QtWidgets import QApplication
66from PyQt5.QtWebKitWidgets import QWebPage
67
68
69def cout(s):
70    sys.stdout.write(s)
71    sys.stdout.flush()
72
73
74def cerr(s):
75    sys.stderr.write(s)
76    sys.stderr.flush()
77
78
79class FrameCapture(QObject):
80
81    finished = pyqtSignal()
82
83    def __init__(self):
84        super(FrameCapture, self).__init__()
85
86        self._percent = 0
87        self._page = QWebPage()
88        self._page.mainFrame().setScrollBarPolicy(Qt.Vertical,
89                Qt.ScrollBarAlwaysOff)
90        self._page.mainFrame().setScrollBarPolicy(Qt.Horizontal,
91                Qt.ScrollBarAlwaysOff)
92        self._page.loadProgress.connect(self.printProgress)
93        self._page.loadFinished.connect(self.saveResult)
94
95    def load(self, url, outputFileName):
96        cout("Loading %s\n" % url.toString())
97        self._percent = 0
98        index = outputFileName.rfind('.')
99        self._fileName = index == -1 and outputFileName + ".png" or outputFileName
100        self._page.mainFrame().load(url)
101        self._page.setViewportSize(QSize(1024, 768))
102
103    def printProgress(self, percent):
104        if self._percent >= percent:
105            return
106        self._percent += 1
107        while self._percent < percent:
108            self._percent += 1
109            cout("#")
110
111    def saveResult(self, ok):
112        cout("\n")
113        # Crude error-checking.
114        if not ok:
115            cerr("Failed loading %s\n" % self._page.mainFrame().url().toString())
116            self.finished.emit()
117            return
118
119        # Save each frame in different image files.
120        self._frameCounter = 0
121        self.saveFrame(self._page.mainFrame())
122        self.finished.emit()
123
124    def saveFrame(self, frame):
125        fileName = self._fileName
126        if self._frameCounter:
127            index = fileName.rfind('.')
128            fileName = "%s_frame%s%s" % (fileName[:index], self._frameCounter, fileName[index:])
129        image = QImage(frame.contentsSize(), QImage.Format_ARGB32_Premultiplied)
130        image.fill(Qt.transparent)
131        painter = QPainter(image)
132        painter.setRenderHint(QPainter.Antialiasing, True)
133        painter.setRenderHint(QPainter.TextAntialiasing, True)
134        painter.setRenderHint(QPainter.SmoothPixmapTransform, True)
135        frame.documentElement().render(painter)
136        painter.end()
137        image.save(fileName)
138        self._frameCounter += 1
139        for childFrame in frame.childFrames():
140            self.saveFrame(childFrame)
141
142
143if __name__ == '__main__':
144    if len(sys.argv) != 3:
145        cerr(__doc__)
146        sys.exit(1)
147
148    url = QUrl.fromUserInput(sys.argv[1])
149    fileName = sys.argv[2]
150
151    app = QApplication(sys.argv)
152
153    capture = FrameCapture()
154    capture.finished.connect(app.quit)
155    capture.load(url, fileName)
156
157    app.exec_()
158