2
我现在正在尝试编写一些代码来从某些Java呈现的页面中抓取网页内容。我通过使用PyQt5从网上找到了一些例子。但是,当我用PyQt5.5.7安装我的Python 3.5但未能导入其模块(ImportError:无法导入名称'QWebPage')时。我附上以下代码以供参考。非常感谢,如果任何人都可以建议该怎么做来解决这个问题,或者任何其他方式来取消Java渲染的网页内容。无法从Python 3.5中的PyQt5导入QWebPage
# standard imports
import sys
# third-party imports
import requests
from bs4 import BeautifulSoup
from pyvirtualdisplay import Display
from PyQt5.QtWebEngineWidgets import QWebPage
from PyQt5.QtWidgets import QApplication
class Render(QWebPage):
"""Render HTML with PyQt5 WebKit."""
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()
url = 'https://impythonist.wordpress.com/2015/01/06/ultimate-guide-for-scraping-javascript-rendered-web-pages/'
# get the raw HTML
source_html = requests.get(url).text
# return the JavaScript rendered HTML
with Display(visible=0, size=(800, 600)):
rendered_html = Render(source_html).html
# get the BeautifulSoup
soup = BeautifulSoup(rendered_html, 'html.parser')
print('title is %r' % soup.select_one('title').text)