刮使用QWebPage多个网址刮使用QWebPage多个网址(Scrape multiple url

我使用Qt的QWebPage来呈现使用JavaScript来动态地更新其内容的页面 - 使刚刚下载页面的静态版本（如urllib2的）库将无法正常工作。

我的问题是，当我渲染第二页，方案只是崩溃的时间约99％。在其他时候，它会崩溃工作之前的三倍。我也得到了一些内存设计缺陷，但它是所有非常随机的。

我的猜测是我使用的渲染中，无法正常删除，所以想重新使用它可能会造成一些问题，为自己的对象。我看了遍，没有人真的好像遇到了同样的问题。

下面是我使用的代码。从蒸汽的社区市场的应用程序下载的网页这样我就可以创建所有项目的数据库。我需要调用getItemsFromPage多次函数来获取所有的项目，因为它们被分解成页（显示结果1-10出来的X量）。

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."

调用getItemsFromPage一次正常工作。后续调用给我的问题。该程序的输出是通常

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

然后崩溃。它应该对超过700页。

与你的程序的问题是，你正试图创建每次提取网址新的QApplication。

相反，你应该创建一个QApplication的，而内处理所有的加载和网页的处理WebPage类本身。关键概念是使用loadFinished信号由目前的一个已经被加载和处理后获取一个新的URL创建一个循环。

下面的两个演示脚本（PyQt4的和PyQt5）是显示如何构建该程序简化的例子。我们希望，它应该是相当明显，如何适应他们自己使用：

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_())

这里是上面的脚本的PyQt5 / QWebEngine版本：

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_())