如何使用带有python脚本代码的pyQt 5 can引擎下载文件？

Question

因此，当我得到一些链接时，我想自动下载，假设链接是：http://test.com/somefile.avi

import os
import sys
from PyQt5.QtWidgets import QApplication, QVBoxLayout, QWidget, QWidgetAction
from PyQt5.QtCore import QUrl, QEventLoop
from PyQt5.QtWebEngineWidgets import QWebEngineView, QWebEngineProfile, QWebEngineDownloadItem, QWebEnginePage


class WebPage(QWebEngineView):
    def __init__(self):
        QWebEngineView.__init__(self)
        self.load(QUrl("http://test.com"))
        self.loadFinished.connect(self._on_load_finished)
        self.n = 0

    def _on_load_finished(self):
        print("Finished Loading")
        self.page().toHtml(self.Callable)

    def Callable(self, html_str):
        self.html = html_str
        self.load(QUrl(userInput))

if __name__ == "__main__":
    userInput = input()
    app = QApplication(sys.argv)
    web = WebPage()

除了我只有'test.com‘页面，但我不能得到文件'somefile.avi'，它有可能使它自动下载后，我输入'http://test.com/somefile.avi’在控制台？

谢谢

Answer 1

下面是如何使用requests库执行此操作的代码片段

免责声明

这个例子是以requests__、python第三方库和而不是PyQt作为最初意图的询问者创建的。

import requests
import shutil

def download(url):

    # gets the filename from the url, and
    # creates the download file absolute path
    filename = url.split("/")[-1]
    path = "downloads/" + filename

    # Defines relevant proxies, see `requests` docs
    proxies = {
      'http': 'http://10.10.1.10:3128',
      'https': 'http://10.10.1.10:1080',
    }

    # Add proxies, and leave `stream=True` for file downloads
    r = requests.get(url, stream=True, proxies=proxies)
    if r.status_code == 200:
        with open(path, 'wb') as f:
            r.raw.decode_content = True
            shutil.copyfileobj(r.raw, f)
    else:
        # Manually raise if status code is anything other than 200
        r.raise_for_status()


download('http://test.com/somefile.avi')

编辑：

然而，pac文件不能在任何常见的python请求库中开箱即用，因此user @CarsonLam提供了一个试图解决这个问题的答案这里。

库pypac提供了对此的支持，并且由于它继承自requests对象，因此它可以很好地处理现有代码。一些额外的pac示例可以找到这里。

有了一个pac代理文件，我想这样的事情是可行的；

from pypac import PACSession, get_pac
import shutil

def download(url):

    # gets the filename from the url, and
    # creates the download file absolute path
    filename = url.split("/")[-1]
    path = "downloads/" + filename

    # looks for a pac file at the specified url, and creates a session
    # this session inherits from requests.Session
    pac = get_pac(url='http://foo.corp.local/proxy.pac')
    session = PACSession(pac)

    # Add proxies, and leave `stream=True` for file downloads
    session = requests.get(url, stream=True)
    if r.status_code == 200:
        with open(path, 'wb') as f:
            r.raw.decode_content = True
            shutil.copyfileobj(r.raw, f)
    else:
        # Manually raise if status code is anython other than 200
        r.raise_for_status()