在无限循环中使用 QTimer 来运行函数

Question

我是 Python 的新手，仍在努力学习，但我无法解决这个问题。我想在无限循环中运行一些函数（在 class 中）。因为它是一个 QApplication，所以我知道我应该用 QTimer 来完成它。但是，在探索如何做时，我找不到可行的替代方案。一个常见的解决方案是：

timer = QTimer()
timer.timeout.connect(function)
timer.start(60000)

但是当我将它们插入到我的代码中时，没有任何区别。我试过将它插入函数、class 等下，但无法得到结果。我要循环的函数在这里：

__author__ = 'pc'
import requests
from bs4 import BeautifulSoup
from PyQt5 import QtCore, QtWidgets, QtWebEngineWidgets
import sqlite3
import sys, getopt, time
from PyQt5.QtCore import QTimer

records = []
def scrape_page(url, html):
    soup = BeautifulSoup(html, 'html.parser')
    data = soup.find('div', class_='tablo_dual_board')
    try:
        datas = data.text.splitlines()
        datas1 = list(filter(None, datas))
        records.append(datas1)
    except:
        pass

def process_records():
    # add record to database ...
    print('process records:', len(records))

def generate_urls():
    onexurl = "https://1xbahis19.com/en/live/Football/"
    reply = requests.get(onexurl)
    soup = BeautifulSoup(reply.content, "html.parser")
    income = soup.find_all("ul", {"id":"games_content"})
    links = soup.find_all("a", {"class": "c-events__name"})
    urls = []
    for matchlink in links:
        urls.append("https://1xbahis19.com/en/"+(matchlink.get("href")))
    return urls

class WebPage(QtWebEngineWidgets.QWebEnginePage):
    def __init__(self):
        super(WebPage, self).__init__()
        self.loadFinished.connect(self.handleLoadFinished)

    def start(self, urls):
        self._urls = iter(urls)
        self.fetchNext()

    def fetchNext(self):
        try:
            url = next(self._urls)
        except StopIteration:
            return False
        else:
            self.load(QtCore.QUrl(url))
        return True

    def processCurrentPage(self, html):
        scrape_page(self.url().toString(), html)
        if not self.fetchNext():
            process_records()
            print(records)
            QtWidgets.qApp.quit()

    def handleLoadFinished(self):
        self.toHtml(self.processCurrentPage)

app = QtWidgets.QApplication(sys.argv)
webpage = WebPage()
webpage.start(generate_urls())
timer = QTimer()
timer.timeout.connect(WebPage)
timer.start(60000)
app.exec_()

有人可以帮忙吗？

Answer 1

我假设您想要定期运行抓取工具。下面的脚本将每 60 秒抓取一次所有 url。 signal 部分提供了一种终止无限循环的方法 - 只需执行 Ctrl+C（即 KeyboardInterrupt），它将立即停止。

import requests
from bs4 import BeautifulSoup
from PyQt5 import QtCore, QtWidgets, QtWebEngineWidgets
import sqlite3
import sys, getopt, time
from PyQt5.QtCore import QTimer

import signal
# press Ctrl+C to stop the script
signal.signal(signal.SIGINT, signal.SIG_DFL)

records = []
def scrape_page(url, html):
    print('scraping page:', url)
    soup = BeautifulSoup(html, 'html.parser')
    data = soup.find('div', class_='tablo_dual_board')
    try:
        datas = data.text.splitlines()
        datas1 = list(filter(None, datas))
        records.append(datas1)
    except:
        pass

def process_records():
    # add record to database ...
    print('processed records:', len(records))
    # clear the current records
    del records[:]
    # re-run after a timeout
    QTimer.singleShot(60000, run)

def run():
    print('running scraper...')
    webpage.start(generate_urls())

def generate_urls():
    print('generating urls...')
    onexurl = "https://1xbahis19.com/en/live/Football/"
    reply = requests.get(onexurl)
    soup = BeautifulSoup(reply.content, "html.parser")
    income = soup.find_all("ul", {"id":"games_content"})
    links = soup.find_all("a", {"class": "c-events__name"})
    urls = []
    for matchlink in links:
        urls.append("https://1xbahis19.com/en/"+(matchlink.get("href")))
    return urls

class WebPage(QtWebEngineWidgets.QWebEnginePage):
    def __init__(self):
        super(WebPage, self).__init__()
        self.loadFinished.connect(self.handleLoadFinished)

    def start(self, urls):
        self._urls = iter(urls)
        self.fetchNext()

    def fetchNext(self):
        try:
            url = next(self._urls)
        except StopIteration:
            return False
        else:
            self.load(QtCore.QUrl(url))
        return True

    def processCurrentPage(self, html):
        scrape_page(self.url().toString(), html)
        if not self.fetchNext():
            process_records()

    def handleLoadFinished(self):
        self.toHtml(self.processCurrentPage)

app = QtWidgets.QApplication(sys.argv)
webpage = WebPage()
run()
app.exec_()

在无限循环中使用 QTimer 来运行函数

Use QTimer to run functions in an infinte loop

python

loops

qtimer

pyqt5

在无限循环中使用 QTimer 来 运行 函数

Use QTimer to run functions in an infinte loop

python

loops

qtimer

pyqt5

在无限循环中使用 QTimer 来运行函数