使用 QWebPage 抓取多个 URL

问题描述：

我正在使用 Qt 的 QWebPage 来呈现一个使用 javascript 动态更新其内容的页面 - 因此仅下载页面静态版本的库（例如 urllib2）将无法工作。

我的问题是，当我渲染第二个页面时，大约 99% 的时间程序都会崩溃。在其他时候，它会运行三次才会崩溃。我也遇到了一些段错误，但都是非常随机的。

我猜是因为我用来渲染的对象没有被正确删除，所以尝试重新使用它可能会给我自己带来一些问题。我到处找了找，似乎没有人遇到同样的问题。

这是我使用的代码。该程序从 steam 的社区市场下载网页，这样我就可以创建所有项目的数据库。我需要getItemsFromPage多次调用该函数来获取所有项目，因为它们被分成几页（显示 X 个结果中的 1-10 个）。

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一次没问题。后续调用会出现问题。程序的输出通常是

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

然后就崩溃了。它应该能运行超过 700 页。

解决方案 1：

您的程序的问题在于您试图使用获取的每个 URL 创建一个新的 QApplication。

相反，只应创建一个 QApplication 和一个 WebPage。WebPage 可以使用其loadFinished信号来创建内部循环，方法是在处理完每个 URL 后获取新的 URL。可以通过将用户定义的插槽连接到信号来添加自定义 html 处理，该信号在 html 文本和 URL 可用时发出它们。下面的脚本（适用于 PyQt5 和 PyQt4）显示了如何实现这一点。

以下一些示例展示了如何使用 WebPage 类：

用法：

def my_html_processor(html, url):
    print('loaded: [%d chars] %s' % (len(html), url))

import sys
app = QApplication(sys.argv)
webpage = WebPage(verbose=False)
webpage.htmlReady.connect(my_html_processor)

# example 1: process list of urls

urls = ['https://en.wikipedia.org/wiki/Special:Random'] * 3
print('Processing list of urls...')
webpage.process(urls)

# example 2: process one url continuously
#
# import signal, itertools
# signal.signal(signal.SIGINT, signal.SIG_DFL)
#
# print('Processing url continuously...')
# print('Press Ctrl+C to quit')
#
# url = 'https://en.wikipedia.org/wiki/Special:Random'
# webpage.process(itertools.repeat(url))

sys.exit(app.exec_())

PyQt5网页：

from PyQt5.QtCore import pyqtSignal, QUrl
from PyQt5.QtWidgets import QApplication
from PyQt5.QtWebEngineWidgets import QWebEnginePage

class WebPage(QWebEnginePage):
    htmlReady = pyqtSignal(str, str)

    def __init__(self, verbose=False):
        super().__init__()
        self._verbose = verbose
        self.loadFinished.connect(self.handleLoadFinished)

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

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

    def processCurrentPage(self, html):
        self.htmlReady.emit(html, self.url().toString())
        if not self.fetchNext():
            QApplication.instance().quit()

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

    def javaScriptConsoleMessage(self, *args, **kwargs):
        if self._verbose:
            super().javaScriptConsoleMessage(*args, **kwargs)

PyQt4网页：

from PyQt4.QtCore import pyqtSignal, QUrl
from PyQt4.QtGui import QApplication
from PyQt4.QtWebKit import QWebPage

class WebPage(QWebPage):
    htmlReady = pyqtSignal(str, str)

    def __init__(self, verbose=False):
        super(WebPage, self).__init__()
        self._verbose = verbose
        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(QUrl(url))
        return True

    def processCurrentPage(self):
        self.htmlReady.emit(
            self.mainFrame().toHtml(), self.mainFrame().url().toString())
        print('loaded: [%d bytes] %s' % (self.bytesReceived(), url))

    def handleLoadFinished(self):
        self.processCurrentPage()
        if not self.fetchNext():
            QApplication.instance().quit()

    def javaScriptConsoleMessage(self, *args, **kwargs):
        if self._verbose:
            super(WebPage, self).javaScriptConsoleMessage(*args, **kwargs)