Retrieving Dynamic Webpage Content PyQt5

Question

After being able to login into a protected website, I'd like the scrape some of the content of thesame webpage that is being loading dynamically. This code block handles the authentication properly but if I try to access a pre tag element with class name lang-py I get None return to me as the output.

import sys

from PyQt5.QtCore import QByteArray, QUrl
from PyQt5.QtWidgets import QApplication
from PyQt5.QtWebEngineCore import QWebEngineHttpRequest
from PyQt5.QtWebEngineWidgets import QWebEnginePage


class Render(QWebEnginePage):
    def __init__(self, url):
        app = QApplication(sys.argv)
        QWebEnginePage.__init__(self)
        self.loadFinished.connect(self._loadFinished)

        self._html = ""

        username = "username"
        password = "password"
        base64string = QByteArray(("%s:%s" % (username, password)).encode()).toBase64()
        request = QWebEngineHttpRequest(QUrl.fromUserInput(url))
        equest.setHeader(b"Authorization", b"Basic: %s" % (base64string,))

        self.load(request)

        app.exec_()

    @property
    def html(self):
        return self._html

    def _loadFinished(self):
        self.toHtml(self.handle_to_html)

    def handle_to_html(self, html):
        self._html = html
        QApplication.quit()


def main():
    url = "https://stackoverflow.com/questions/64055445/scraping-websites-with-protected-content-using-pyqt5/64055601?noredirect=1#comment113272437_64055601"
    r = Render(url)
    print(r.html)


if __name__ == "__main__":
    main()

How can I load the content in <pre> ?

score 1 · Accepted Answer · answered Sep 25 '20 at 01:14

The element with tag "pre" and class "lang-py" is present in the html so you can use BeautifulSoup to get the data:

# ...
from bs4 import BeautifulSoup

# ...

def main():
    url = "https://stackoverflow.com/questions/64055445/scraping-websites-with-protected-content-using-pyqt5/64055601?noredirect=1#comment113272437_64055601"
    r = Render(url)
    soup = BeautifulSoup(r.html, "html.parser")
    for tag in soup.find_all("pre", {"class": "lang-py"}):
        print("=" * 50)
        print(tag.text)

Retrieving Dynamic Webpage Content PyQt5

1 Answers1