Get a screenshot of a webpage with python

screener.py

#to install PyQt4 on mac brew install cartr/qt4/pyqt
#to remove javascripts tag from html https://stackoverflow.com/questions/8554035/remove-all-javascript-tags-and-style-tags-from-html-with-python-and-the-lxml-mod

import sys
import time
from PyQt4.QtCore import *
from PyQt4.QtGui import *
from PyQt4.QtWebKit import *
import lxml
from lxml.html.clean import Cleaner

def clean_js_and_css(url):
    cleaner = Cleaner()
    cleaner.javascript = True # This is True because we want to activate the javascript filter
    return lxml.html.tostring(cleaner.clean_html(lxml.html.parse(url)))

def download_screenshot_and_html(url, name):
    html = clean_js_and_css(url)
    Screenshot().capture(url,name+".png")
    with open(name+".html", 'w') as text:
        text.write(html)

class Screenshot(QWebView):
    def __init__(self):
        self.app = QApplication(sys.argv)
        QWebView.__init__(self)
        self._loaded = False
        self.loadFinished.connect(self._loadFinished)

    def capture(self, url, output_file):
        self.load(QUrl(url))
        self.wait_load()
        # set to webpage size
        frame = self.page().mainFrame()
        self.page().setViewportSize(frame.contentsSize())
        # render image
        image = QImage(self.page().viewportSize(), QImage.Format_ARGB32)
        painter = QPainter(image)
        frame.render(painter)
        painter.end()
        print 'saving', output_file
        image.save(output_file)

    def wait_load(self, delay=0):
        # process app events until page loaded
        while not self._loaded:
            self.app.processEvents()
            time.sleep(delay)
        self._loaded = False

    def _loadFinished(self, result):
        self._loaded = True


download_screenshot_and_html('http://gazzetta.it', 'gazzetta')