如何使用 PyQt5 的 QWebEngineView “渲染” HTML

Question

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

我之前使用 PyQt5 v5.4.1 QWebPage 執行過任務，但建議嘗試較新的 QWebEngineView。

這是該實現（它通常按預期工作，但在某些站點和情況下有無限期掛起的趨勢）：

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))

下面是我使用 QWebEngineView 的嘗試。 一、 PyQt5 v5.6在Ubuntu上的安裝設置：

# 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/

現在對於 Python... 以下導致分段錯誤：

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))

問題似乎在於對異步toHtml()的調用。 看起來它應該相當簡單，但我不知道該怎么做。 我看到它已經在 C++ 的上下文中進行了討論，但我不確定如何將其轉換為 Python。 我怎樣才能得到 HTML？

Answer 1

在以下線程中對該主題進行了相當多的討論： https : //riverbankcomputing.com/pipermail/pyqt/20​​15-January/035324.html

新的 QWebEngine 接口考慮了底層 Chromium 引擎是異步的這一事實。 因此，我們必須將異步 API 轉換為同步 API。

這是它的外觀：

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))

Answer 2

Six & Veehmot 的回答很好，但我發現這對我來說是不夠的，因為它沒有擴展我想要抓取的頁面的下拉元素。 一個輕微的修改修復了這個：

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

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

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


print(render(dummy_url))

Answer 3

正如您所指出的，Qt5.4 依賴於異步調用。 沒有必要使用循環（如您的答案所示），因為您唯一的錯誤是在toHtml調用完成之前調用quit 。

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):
            # This is an async call, you need to wait for this
            # to be called before closing the app
            self.page().toHtml(self.callable)

        def callable(self, data):
            self.html = data
            # Data has been stored, it's safe to quit the app
            self.app.quit()

    return Render(source_html).html

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

Answer 4

當再次運行render（）時，以上代碼會導致“分段錯誤（核心轉儲）”錯誤。 稍作修改即可解決此問題：

import sys

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


def render(source_html):
    app = QApplication(sys.argv)

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

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

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

    return Render(source_html).html

Answer 5

我並不完全清楚你所說的“渲染”是什么意思。 我理解它的意思是“在屏幕上相應地顯示 HTML”。 下面就是這樣做的。

# main.py
import sys
import os
from PyQt5 import QtCore, QtWidgets, QtWebEngineWidgets


class Browser(QtWebEngineWidgets.QWebEngineView):

    def __init__(self):
        super().__init__()

        html = """
        <!DOCTYPE html>
        <html>
            <head>
                <title>Example</title>
                <meta charset="utf-8" />
            </head>
            <body>
                <script>alert('Running some Javascript');</script>
                <h1>Hello world!</h1>
                <p>Goodbye, cruel world...</p>
            </body>
        </html>

        """

        # With QWebEnginePage.setHtml, the html is loaded immediately.
        # baseUrl is used to resolve relative URLs in the document.
        # For whatever reason, it seems like the baseUrl resolves to
        # the parent of the path, not the baseUrl itself.  As a
        # workaround, either append a dummy directory to the base url
        # or start all relative paths in the html with the current
        # directory.
        # https://doc-snapshots.qt.io/qtforpython-5.15/PySide2/QtWebEngineWidgets/QWebEnginePage.html#PySide2.QtWebEngineWidgets.PySide2.QtWebEngineWidgets.QWebEnginePage.setHtml
        here = os.path.dirname(os.path.abspath(__file__)).replace('\\', '/')
        base_path = os.path.join(os.path.dirname(here), 'dummy').replace('\\', '/')
        self.url = QtCore.QUrl('file:///' + base_path)
        self.page().setHtml(html, baseUrl=self.url)


class MainWindow(QtWidgets.QMainWindow):

    def __init__(self):
        super().__init__()

        self.init_widgets()
        self.init_layout()

    def init_widgets(self):
        self.browser = Browser()
        self.browser.loadFinished.connect(self.load_finished)

    def init_layout(self):
        layout = QtWidgets.QVBoxLayout()
        layout.addWidget(self.browser)

        centralWidget = QtWidgets.QWidget()
        centralWidget.setLayout(layout)
        self.setCentralWidget(centralWidget)

    def load_finished(self, status):
        self.msg = QtWidgets.QMessageBox()
        self.msg.setIcon(QtWidgets.QMessageBox.Information)
        self.msg.setWindowTitle('Load Status')
        self.msg.setText(f"It is {str(status)} that the page loaded.")
        self.msg.show()


if __name__ == '__main__':
    app = QtWidgets.QApplication(sys.argv)
    main_window = MainWindow()
    main_window.show()
    sys.exit(app.exec_())

setHtml方法接受一個字符串，因此在使用 HTML 文件時必須首先讀取它。