【发布时间】:2020-09-24 22:51:37
【问题描述】:
我正在尝试从需要登录的动态网站上抓取内容。我发现这段代码适用于 PyQt4 Scraping Javascript driven web pages with PyQt4 - how to access pages that need authentication?
#!/usr/bin/python
# -*- coding: latin-1 -*-
import sys
import base64
from PyQt4.QtGui import *
from PyQt4.QtCore import *
from PyQt4.QtWebKit import *
from PyQt4 import QtNetwork
class Render(QWebPage):
def __init__(self, url):
self.app = QApplication(sys.argv)
username = 'username'
password = 'password'
base64string = base64.encodestring('%s:%s' % (username, password))[:-1]
authheader = "Basic %s" % base64string
headerKey = QByteArray("Authorization")
headerValue = QByteArray(authheader)
url = QUrl(url)
req = QtNetwork.QNetworkRequest()
req.setRawHeader(headerKey, headerValue)
req.setUrl(url)
QWebPage.__init__(self)
self.loadFinished.connect(self._loadFinished)
self.mainFrame().load(req)
self.app.exec_()
def _loadFinished(self, result):
self.frame = self.mainFrame()
self.app.quit()
def main():
url = 'http://www.google.com'
r = Render(url)
html = r.frame.toHtml()
我怎样才能将它们翻译成适用于 PyQt5 ?
【问题讨论】:
标签: python python-3.x pyqt5