怎样用PyQt5.6 爬取网页

PyQt 5.6 以后选用chromium 是新一代QT用的浏览器引擎。。。与之前的Webkit有很大的区别。经过长时间的测试，终于可以用了!

# -*- coding: utf-8 -*-

import sys

from PyQt5.QtCore import QUrl

from PyQt5.QtWidgets import QApplication

from PyQt5.QtWebEngineWidgets import QWebEnginePage, QWebEngineView

class Render(QWebEngineView):

def __init__(self, url):

self.app = QApplication(sys.argv)

QWebEngineView.__init__(self)

self.loadFinished.connect(self._loadFinished)

self.load(QUrl(url))

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()

import lxml.html

#定义一个网页地址

url = 'https://xxxxxxxxxxxx'

r = Render(url)

result = r.html

tree = lxml.html.fromstring(result)

参考下面的文章：

https://stackoverflow.com/questions/37754138/how-to-render-html-with-pyqt5s-qwebengineview