Question

我正在尝试在PyQt5上学习动态Web抓取。我正在查找PyQt4的教程，所以在Qt5中有一些不同的库。

import sys
from PyQt5.QtWidgets import QApplication
from PyQt5.QtCore import QUrl
from PyQt5.QtWebEngineWidgets import QWebEnginePage
import bs4 as bs
import urllib.request

class Client(QWebEnginePage):
    def _init_(self, url):
        self.app=QApplication(sys.argv)
        QWebPage._init_(self)
        self.loadFinished.connect(self.on_page_load)
        self.mainFrame().load(QUrl(url))
        self.app.exec_()
    def on_page_load(self):
        self.app.quit()

url='https://pythonprogramming.net/parsememcparseface/'
client_response=Client(url)
source=client_response.mainFrame().toHtml()

#sauce=urllib.request.urlopen('https://pythonprogramming.net/sitemap.xml').read()
soup=bs.BeautifulSoup(sauce,'xml')
js_test=soup.find('p',class_='jstest')
print(js_test.text)

正在显示以下错误：

Traceback (most recent call last):
  File "jsp.py", line 19, in <module>
    client_response=Client(url)
TypeError: arguments did not match any overloaded call:
  QWebEnginePage(parent: QObject = None): argument 1 has unexpected type 'str'
  QWebEnginePage(QWebEngineProfile, parent: QObject = None): argument 1 has unexpected

有人帮助我！

Answer 1

您的代码有几个错误：

init之前和之后必须有2个下划线。
QWebEnginePage没有mainFrame()作为方法，现在您必须直接加载
出现的另一个变化是toHtml()函数不再同步，所以它会要求你回调来获取html，但是我的修改后再次同步。

<强>代码：

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

class Client(QWebEnginePage):
    toHtmlFinished = pyqtSignal()

    def __init__(self, url):
        self.app=QApplication(sys.argv)
        QWebEnginePage.__init__(self)
        self.loadFinished.connect(self.on_page_load)
        self.load(QUrl(url))
        self.app.exec_()

    def on_page_load(self):
        self.app.quit()

    def store_html(self, html):
        self.html = html
        self.toHtmlFinished.emit()

    def get_html(self):
        self.toHtml(self.store_html)
        loop = QEventLoop()
        self.toHtmlFinished.connect(loop.quit)
        loop.exec_()
        return self.html

url='https://pythonprogramming.net/parsememcparseface/'
client_response=Client(url)
source=client_response.get_html()

print(source)

参考文献：

不能使用QUrl

1 个答案: