Question

我只是在尝试使用Selenium Webdriver，我遇到了一些问题，所有这些问题似乎都需要我解决，然后再继续。当我运行粘贴在底部的代码时，Selenium永远需要用浏览器执行任何操作，并且显示“等待[在此处插入站点]”一段时间。完成这些操作后，它最终将找到元素并与页面进行交互。有时我会遇到各种各样的错误，并且这些错误并不一致（但是这些错误不会破坏代码，直到Selenium遵照我的要求进行处理才花更长的时间）。有时我的防病毒软件会弹出来，说它阻止了网站（global.ymtracking.com），因为它是恶意软件。我觉得这可能与网页上的广告以及Selenium如何加载网页有关，但我真的不知道，因为我对此并不陌生。我从访问此网站就从未遇到过任何问题。

using System;
using System.Collections.Generic;
using System.Drawing;
using System.IO;
using OpenQA.Selenium;
using OpenQA.Selenium.Chrome;

namespace WebScrappingTesting
{
    class Program
    {
        static IWebDriver driver;
        static Dictionary<string, Dictionary<string, float>> hockeyStats = new Dictionary<string, Dictionary<string, float>>();
        static string TeamName ="";
        static float TeamAge;
        static float Wins;
        static float Losses;

        static void Main(string[] args)
        {
            driver = new ChromeDriver();

            driver.Navigate().GoToUrl("https://www.hockey-reference.com/leagues/NHL_2019.html");

            using (StreamWriter file = new StreamWriter(@"C:\Users\hockeyData.csv", false))
            {
                file.WriteLine("Team Name,Avg Age,Wins,Losses");
            }

            for (var year = 2019; year > 2015; year--)
            {
                Console.WriteLine($"Getting data for {year}");

                var rowsOfData = driver.FindElements(By.CssSelector("#stats > tbody > tr"));

                for (var i = 1; i <= rowsOfData.Count; i++)
                {
                    TeamName = driver.FindElement(By.CssSelector($"#stats > tbody > tr:nth-child({i}) > td.left > a")).Text;
                    float.TryParse(driver.FindElement(By.CssSelector($"#stats > tbody > tr:nth-child({i}) > td:nth-child(3)")).Text, out TeamAge);
                    float.TryParse(driver.FindElement(By.CssSelector($"#stats > tbody > tr:nth-child({i}) > td:nth-child(5)")).Text, out Wins);
                    float.TryParse(driver.FindElement(By.CssSelector($"#stats > tbody > tr:nth-child({i}) > td:nth-child(6)")).Text, out Losses);
                    // TODO: need to change this to a 3 dim dictionary or an object to be able to also record the year of the data
                    hockeyStats[TeamName] = new Dictionary<string, float>() {
                        { "Age", TeamAge },
                        { "Wins", Wins },
                        { "Losses", Losses }
                    };
                }

                foreach (var item in hockeyStats)
                {
                    Console.WriteLine("=============================================================");
                    Console.WriteLine($"Team Name: {item.Key}, Avg Age: {item.Value["Age"]}");
                    Console.WriteLine($"Wins {item.Value["Wins"]}, Losses {item.Value["Losses"]}");
                }

                using (StreamWriter file = new StreamWriter(@"C:\Users\hockeyData.csv", true))
                {
                    foreach (var item in hockeyStats)
                    {
                        file.WriteLine($"{item.Key},{item.Value["Age"]},{item.Value["Wins"]},{item.Value["Losses"]}");
                    }
                }


                driver.FindElement(By.LinkText("Previous Season")).Click();
                //driver.FindElement(By.CssSelector($"[href*=/leagues/NHL_{year - 1}.html]"));


            }

            Console.WriteLine("=============================================================");
            Console.WriteLine("=============================================================");
            Console.WriteLine(@"You file has been saved to C:\Users\hockeyData.csv");
            Console.WriteLine("=============================================================");
            Console.WriteLine("=============================================================");

            driver.Close();
            driver.Dispose();
        }
    }
}

Answer 1

它似乎与网站有关。我运行了提琴手，该网站的后台发生了很多事情。

Selenium Webdriver C＃页面加载

1 个答案: