requests实现系统模拟登录_request模块模拟登陆获取网页-CSDN博客

本文链接：https://blog.csdn.net/weixin_45228198/article/details/130331755

本文介绍了如何使用Python的requests库进行模拟登录，通过获取和设置Cookie来实现登录状态的保持。接着展示了在PySide2的QWebEngineView中设置Cookie以实现QWebEngine的模拟登录。此外，还讨论了存储爬虫请求API获取的数据集到数据库的操作流程。

摘要由CSDN通过智能技术生成

文章目录

requests模拟登录
QWebEngine登录
存储数据
PySide2使用QWebEngineView报错extension_system_qt.cpp(122) failed to parse extension manifest

requests模拟登录

使用requests发送post请求；
获取响应头中的Set-Cookie的值；
将该Cookie值存入浏览器对应的域名，测试是否可用。
可以使用

import requests


url = "http://localhost:5050/login/"


def login(url, headers, data):
    res = requests.post(url, headers=headers, data=data)
    print("response code:", res.status_code)
    print("content:", res.headers)


if __name__ == "__main__":

    """
    Host: localhost:5050

    User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36

    Accept-Encoding: gzip, deflate, br

    Accept: */*

    Connection: keep-alive

    Cookie: session=.eJwlzjESAjEIAMC_UFsAISTcZ25CCKPtnVc5_l0d6232BXse67zD9jyudYP9EbCBG3qMoDGVSZYP0mjGJZ0Kkk0tTYh6IrNzuqvFIEK1ZKKhOdVqGV1EqIi1iVHcrGFG7yqNf0S8ljSUrDpYxdKnYmKN7gbfyHWu478heH8Ad3suDA.ZEU0hw.5N9yfwPep8tDGT-Y9wxfLXR3Ohw
    
    """
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36",

    }
    data = {
        "username": "admin",
        "password": "admin"
    }

    login(url, headers, data=data)

QWebEngine登录

将以上获取的Cookie信息，设置QWebEngine的cookie，实现模拟登录。

# __author__ = "laufing"
# class_based_qt
# laufing_qt
import sys
import time

import sys
from urllib.parse import urlparse
from PySide2.QtWidgets import *
from PySide2.QtCore import *   # QByteArray
from PySide2.QtGui import *
from PySide2.QtWebEngineWidgets import QWebEngineView, QWebEngineProfile
from PySide2.QtWebEngineCore import QWebEngineHttpRequest, QWebEngineCookieStore
from PySide2.QtNetwork import QNetworkCookie


class Window(QWidget):
    def __init__(self):
        super(Window, self).__init__()
        # 窗口标题
        self.setWindowTitle("laufing[*]")
        # 窗口图标
        pixmap = QPixmap("./imgs/dog.jpg").scaled(50, 50)
        icon = QIcon(pixmap)
        # icon.addPixmap(pixmap, QIcon.Normal, QIcon.Off)
        self.setWindowIcon(icon)

        # 设置宽高
        self.resize(900, 800)

        # 窗口居中
        desktop_geo = QDesktopWidget().geometry()
        width, height = desktop_geo.width(), desktop_geo.height()
        self.move(width / 2 - self.width() / 2, height / 2 - self.height() / 2)


        # 设置文本
        self.label = QLabel(self)
        self.label.setText("测试按钮被按下")
        self.label.resize(200, 200)
        self.label.move(100, 100)

        self.setUI()

    def setUI(self):
        # 实例化浏览器引擎视图
        self.web_view = QWebEngineView(self)
        self.web_view.setFixedWidth(900)
        self.web_view.setFixedHeight(800)

        # 创建http请求
        self.req = QWebEngineHttpRequest()
        # 设置请求的url
        self.url = url = "http://localhost:5050/chart/add"
        # 解析url
        parsed_url = urlparse(url)
        self.domain = parsed_url.scheme + "://" + parsed_url.netloc
        #  ParseResult(scheme='http', netloc='localhost:5050', path='', params='', query='', fragment='')
        # parsed_url.scheme  获取协议
        # parsed_url.netloc 获取域名
        self.req.setUrl(QUrl(url))  # 请求对象设置url

        # 设置cookie
        self.set_cookie()
        # 浏览器引擎  加载请求对象 or QUrl
        self.web_view.page().load(self.req)

    def set_cookie(self, cookie=None):
        # cookie
        cookie = "session=.eJwlzjEOwjAMQNG7ZGawHdeJuQyKY1sgVSC1MCHuThHj01_-u1xyi_1azs_tFadyuXk5F1MwH45jCiGHDRRvSjUNK6BOqY0RewKRUZqJ-kAE0STEITlFlzo6M2NlbRO8mmqD9N6FG_0SUgQ34FxkkLCmTYGExbtpOUZee2z_Gzy4PuZY40Dcy-cLGa8yPQ.ZEU0jA.XhyzfsXhTxQC0j0UmphlC8nRe5Q"
        # 解析cookie 并导入
        cookie_dict = self.parse_cookie(cookie)
        for key, value in cookie_dict.items():
            # 生成单个cookie
            key_bytes = QByteArray(key.encode())
            val_bytes = QByteArray(value.encode())
            cookie_str = QNetworkCookie(key_bytes, val_bytes)
            print("cookie:", cookie_str)
            # 设置cookie 及 对应的网站域名
            self.web_view.page().profile().cookieStore().setCookie(cookie_str, self.domain)

        # 设置cookie持久化
        self.web_view.page().profile().setPersistentCookiesPolicy(
            QWebEngineProfile.PersistentCookiesPolicy.AllowPersistentCookies)

    def parse_cookie(self, cookie_str):
        """解析cookie"""
        c_list = cookie_str.split(";")
        c_dict = dict()
        for i in c_list:
            key, val = i.split('=')
            c_dict[key] = val
        return c_dict


"""
	# 也可以如下设置：
	my_cookie = QNetworkCookie()
	my_cookie.setName(key.encode())
	my_cookie.setValue(values.encode())
	my_cookie.setDomain('xx.xx.com')
	xxx.setCookie(c, domain)
"""

if __name__ == '__main__':

    # 窗口应用程序
    app = QApplication(sys.argv)

    window = Window()
    window.show()

    status_code = app.exec_()
    sys.exit(status_code)

存储数据

程序自己存入db
爬虫请求api 添加数据集（表名信息）


# GET
url2 = "http://localhost:5050/explore/"
headers = {
    "Host": "localhost:5050",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36",
    "Accept-Encoding": "gzip, deflate, br",
    "Accept": "*/*",
    "Connection": "keep-alive",
    "Cookie": "session=.eJwlzjEOwjAMQNG7ZGawHdeJuQyKY1sgVSC1MCHuThHj01_-u1xyi_1azs_tFadyuXk5F1MwH45jCiGHDRRvSjUNK6BOqY0RewKRUZqJ-kAE0STEITlFlzo6M2NlbRO8mmqD9N6FG_0SUgQ34FxkkLCmTYGExbtpOUZee2z_Gzy4PuZY40Dcy-cLGa8yPQ.ZEU0jA.XhyzfsXhTxQC0j0UmphlC8nRe5Q"
}
params = {
    "form_data_key": "jiB0jEm4eDbdMs0cbkkT6d4aPUOm5NYKShbl0664CYXkuiNYPOutF626jTwTkucO",
    "datasource_type": "table",
    "datasource_id": 3
}
def get_dataset(url, headers, params):
    res = requests.get(url, headers=headers, params=params)
    print("响应状态：", res.status_code)
    print("响应的数据:", res.text)


# 删除
# http://localhost:5050/api/v1/dataset/
# ?q=(order_column:changed_on_delta_humanized,order_direction:desc,page:0,page_size:25)


# 添加dataset
add_url = "http://localhost:5050/api/v1/dataset/"
# post
payload = {
    "database": 1,  # 自身数据库
    "schema": "superset",
    "table_name": "ttt"  # 表名
    }

def add_dataset(url, headers, data):
    res = requests.post(url, headers=headers, json=data) # 服务端要求json格式
    print("add response:", res.status_code)


if __name__ == "__main__":

    """
    请求头
    Host: localhost:5050

    User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36

    Accept-Encoding: gzip, deflate, br

    Accept: */*

    Connection: keep-alive

    Cookie: session=.eJwlzjESAjEIAMC_UFsAISTcZ25CCKPtnVc5_l0d6232BXse67zD9jyudYP9EbCBG3qMoDGVSZYP0mjGJZ0Kkk0tTYh6IrNzuqvFIEK1ZKKhOdVqGV1EqIi1iVHcrGFG7yqNf0S8ljSUrDpYxdKnYmKN7gbfyHWu478heH8Ad3suDA.ZEU0hw.5N9yfwPep8tDGT-Y9wxfLXR3Ohw
    
    """
    # 添加数据到tables中（自己添加不行，uuid无法给值）
    add_dataset(add_url, headers=headers, data=payload)