Clear multiple urls using QWebPage

Question

I use Qt QWebPage to render a page using javascript to dynamically refresh its contents, so a library that just loads a static version of the page (e.g. urllib2) will not work.

My problem is that when I make the second page, in about 99% of cases the program will just work. At other times, it will work three times before the failure. I also got some segfaults, but all this is very arbitrary.

I assume that the object I use for rendering is not getting correctly, so trying to reuse it may cause some problems for me. I looked everywhere, and no one seemed to encounter this problem.

Here is the code I'm using. The program downloads web pages from the steam community market, so I can create a database of all the elements. I need to call the function getItemsFromPageseveral times to get all the elements, since they are paginated (showing results 1-10 from the sum of X).

import csv
import re
import sys
from string import replace
from bs4 import BeautifulSoup
from PyQt4.QtGui import *
from PyQt4.QtCore import *
from PyQt4.QtWebKit import *

class Item:
    __slots__ = ("name", "count", "price", "game")

    def __repr__(self):
        return self.name + "(" + str(self.count) + ")"

    def __str__(self):
        return self.name + ", " + str(self.count) + ", $" + str(self.price)

class Render(QWebPage):  
    def __init__(self, url):
        self.app = QApplication(sys.argv)
        QWebPage.__init__(self)
        self.loadFinished.connect(self._loadFinished)
        self.mainFrame().load(QUrl(url))
        self.app.exec_()

    def _loadFinished(self, result):
        self.frame = self.mainFrame()
        self.app.quit()
        self.deleteLater()

def getItemsFromPage(appid, page=1):

    r = Render("http://steamcommunity.com/market/search?q=appid:" + str(appid) + "#p" + str(page))

    soup = BeautifulSoup(str(r.frame.toHtml().toUtf8()))

    itemLst = soup.find_all("div", "market_listing_row market_recent_listing_row")

    items = []

    for k in itemLst:
        i = Item()

        i.name = k.find("span", "market_listing_item_name").string
        i.count = int(replace(k.find("span", "market_listing_num_listings_qty").string, ",", ""))
        i.price = float(re.search(r'\$([0-9]+\.[0-9]+)', str(k)).group(1))
        i.game = appid

        items.append(i)

    return items

if __name__ == "__main__":

    print "Updating market items to dota2.csv ..."

    i = 1

    with open("dota2.csv", "w") as f:
        writer = csv.writer(f)

        r = None

        while True:
            print "Page " + str(i)

            items = getItemsFromPage(570)

            if len(items) == 0:
                print "No items found, stopping..."
                break

            for k in items:
                writer.writerow((k.name, k.count, k.price, k.game))

            i += 1

    print "Done."

A call getItemsFromPageonce works fine. Subsequent calls give me my problem. Program output usually

Updating market items to dota2.csv ...
Page 1
Page 2

and then it will work. It should last more than 700 pages.

Answer 1

The problem with your program is that you are trying to create a new QApplication application with every URL you receive.

QApplication - WebPage. loadFinished URL- loadFinished URL- loadFinished.

( PyQt4 PyQt5) , , . , , :

import sys
from PyQt4 import QtCore, QtGui, QtWebKit

class WebPage(QtWebKit.QWebPage):
    def __init__(self):
        super(WebPage, self).__init__()
        self.mainFrame().loadFinished.connect(self.handleLoadFinished)

    def start(self, urls):
        self._urls = iter(urls)
        self.fetchNext()

    def fetchNext(self):
        try:
            url = next(self._urls)
        except StopIteration:
            return False
        else:
            self.mainFrame().load(QtCore.QUrl(url))
        return True

    def processCurrentPage(self):
        url = self.mainFrame().url().toString()
        html = self.mainFrame().toHtml()
        # do stuff with html...
        print('loaded: [%d bytes] %s' % (self.bytesReceived(), url))

    def handleLoadFinished(self):
        self.processCurrentPage()
        if not self.fetchNext():
            QtGui.qApp.quit()

if __name__ == '__main__':

    # generate some test urls
    urls = []
    url = 'http://pyqt.sourceforge.net/Docs/PyQt4/%s.html'
    for name in dir(QtWebKit):
        if name.startswith('Q'):
            urls.append(url % name.lower())

    app = QtGui.QApplication(sys.argv)
    webpage = WebPage()
    webpage.start(urls)
    sys.exit(app.exec_())

---

PyQt5/QWebEngine :

import sys
from PyQt5 import QtCore, QtWidgets, QtWebEngineWidgets

class WebPage(QtWebEngineWidgets.QWebEnginePage):
    def __init__(self):
        super(WebPage, self).__init__()
        self.loadFinished.connect(self.handleLoadFinished)

    def start(self, urls):
        self._urls = iter(urls)
        self.fetchNext()

    def fetchNext(self):
        try:
            url = next(self._urls)
        except StopIteration:
            return False
        else:
            self.load(QtCore.QUrl(url))
        return True

    def processCurrentPage(self, html):
        url = self.url().toString()
        # do stuff with html...
        print('loaded: [%d chars] %s' % (len(html), url))
        if not self.fetchNext():
            QtWidgets.qApp.quit()

    def handleLoadFinished(self):
        self.toHtml(self.processCurrentPage)

if __name__ == '__main__':

    # generate some test urls
    urls = []
    url = 'http://pyqt.sourceforge.net/Docs/PyQt5/%s.html'
    for name in dir(QtWebEngineWidgets):
        if name.startswith('Q'):
            urls.append(url % name.lower())

    app = QtWidgets.QApplication(sys.argv)
    webpage = WebPage()
    webpage.start(urls)
    sys.exit(app.exec_())