Question

我开始使用PyQt5进行动态javascript抓取并且已经遇到了麻烦。当我有多个urls要刮，python在第一个或第二个url后崩溃，无论域名是什么。我可以从第一页获取数据，但不能从第二页获取数据。来自Windows的错误日志显示Qt5WebEngineCore.dll是错误的原因，但我不知道该怎么做。我真的没有从网上的其他地方找到任何有用的东西。这是代码：

import sys
import requests
from PyQt5.QtWidgets import QApplication
from PyQt5.QtCore import QUrl
from PyQt5.QtWebEngineWidgets import QWebEnginePage
from bs4 import BeautifulSoup
import re


class Client(QWebEnginePage):

    def __init__(self, url):
        self.app = QApplication(sys.argv)
        QWebEnginePage.__init__(self)
        self.html = ''
        self.loadFinished.connect(self._on_load_finished)
        self.load(QUrl(url))    #Ignote mainFrame from PyQt4
        self.app.exec_()

    def _on_load_finished(self):
        self.html = self.toHtml(self.Callable)
        print('Load finished')

    def Callable(self, html_str):
        self.html = html_str
        self.app.quit()


def scrape_pyqt5():
    lists = ['example1.com/a', 'example1.com/b', 'example1.com/c']
    for url in lists:
        r = Client(url)
        bs = BeautifulSoup(r.html, 'html.parser')
        for link in bs.find_all('div', {'id': 'media-player'}):
            for directlink in link.find_all('iframe'):
                print(directlink)

Python.exe崩溃与PyQt5

0 个答案: