如何使用 PyQt5 v5.6 QWebEngineView“渲染”HTML？

我之前用PyQt5 v5.4.1 QWebPage执行过任务，但是是suggested 尝试更新的 QWebEngineView。

这是该实现(它通常按预期工作，但在某些站点和情况下有无限期挂起的趋势):

def render(source_html):
    """Fully render HTML, JavaScript and all."""

    import sys
    from PyQt5.QtWidgets import QApplication
    from PyQt5.QtWebKitWidgets import QWebPage

    class Render(QWebPage):
        def __init__(self, html):
            self.html = None
            self.app = QApplication(sys.argv)
            QWebPage.__init__(self)
            self.loadFinished.connect(self._loadFinished)
            self.mainFrame().setHtml(html)
            self.app.exec_()

        def _loadFinished(self, result):
            self.html = self.mainFrame().toHtml()
            self.app.quit()

    return Render(source_html).html

import requests
sample_html = requests.get(dummy_url).text
print(render(sample_html))

接下来是我尝试使用QWebEngineView。一、PyQt5 v5.6的安装与设置在 Ubuntu 上:

# install PyQt5 v5.6 wheel from PyPI
pip3 install --user pyqt5

# link missing resources
ln -s ../resources/icudtl.dat ../resources/qtwebengine_resources.pak ../resources/qtwebengine_resources_100p.pak ../resources/qtwebengine_resources_200p.pak ../translations/qtwebengine_locales ~/.local/lib/python3.5/site-packages/PyQt5/Qt/libexec/

现在对于 Python...以下导致段错误:

def render(source_html):
    """Fully render HTML, JavaScript and all."""

    import sys
    from PyQt5.QtWidgets import QApplication
    from PyQt5.QtWebEngineWidgets import QWebEngineView

    class Render(QWebEngineView):
        def __init__(self, html):
            self.html = None
            self.app = QApplication(sys.argv)
            QWebEngineView.__init__(self)
            self.loadFinished.connect(self._loadFinished)
            self.setHtml(html)
            self.app.exec_()

        def _loadFinished(self, result):
            # what's going on here? how can I get the HTML from toHtml?
            self.page().toHtml(self.callable)
            self.app.quit()

        def callable(self, data):
            self.html = data

    return Render(source_html).html

import requests
sample_html = requests.get(dummy_url).text
print(render(sample_html))

问题似乎在于对异步 toHtml() 的调用。看起来它应该相当简单，但我不知道如何处理它。我看到它是discussed在 C++ 的上下文中，但我不确定如何将其转换为 Python。我怎样才能得到 HTML？

最佳答案

在以下线程中对该主题进行了相当多的讨论:https://riverbankcomputing.com/pipermail/pyqt/2015-January/035324.html

新的 QWebEngine 接口(interface)考虑了以下事实: 底层 Chromium 引擎是异步的。因此，我们必须将异步 API 转变为同步 API。

这是它的样子:

def render(source_html):
    """Fully render HTML, JavaScript and all."""

    import sys
    from PyQt5.QtCore import QEventLoop
    from PyQt5.QtWidgets import QApplication
    from PyQt5.QtWebEngineWidgets import QWebEngineView

    class Render(QWebEngineView):
        def __init__(self, html):
            self.html = None
            self.app = QApplication(sys.argv)
            QWebEngineView.__init__(self)
            self.loadFinished.connect(self._loadFinished)
            self.setHtml(html)
            while self.html is None:
                self.app.processEvents(QEventLoop.ExcludeUserInputEvents | QEventLoop.ExcludeSocketNotifiers | QEventLoop.WaitForMoreEvents)
            self.app.quit()

        def _callable(self, data):
            self.html = data

        def _loadFinished(self, result):
            self.page().toHtml(self._callable)

    return Render(source_html).html

import requests
sample_html = requests.get(dummy_url).text
print(render(sample_html))

关于python - 如何使用 PyQt5 的 QWebEngineView 处理 "render"HTML，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/37754138/