C# + Selenium + ChromeDriver 爬取网页

转自：UP技术控

cnblogs.com/lyl6796910/p/14166876.html

背景

Selenium是一个用于Web应用程序测试的工具。Selenium测试直接运行在浏览器中，就像真正的用户在操作一样。而对于爬虫来说，使用Selenium操控浏览器来爬取网上的数据那么肯定是爬虫中的杀手武器。这里，我将介绍selenium + 谷歌浏览器的一般使用。

需求

在平常的爬虫开发中，有时候网页是一堆js堆起来的代码，涉及很多异步计算，如果是普通的http 控制台请求，那么得到的源文件是一堆js ，需要自己在去组装数据，很费力；但是采用Selenium+ChromeDriver可以达到所见即所得的完美效果。

实现方式

项目结构：为了方便使用，用的winform程序，附nuget包

以下是form1.cs的代码，这里就只放关键方法代码了。需要安装最新的chrome浏览器+代码中使用的chromedriver是 v2.9.248315

private void crawlingWebFunc()
{
    SetText("\r\n开始尝试...");
    List<testfold> surls = new List<testfold>();
    string path = System.Environment.CurrentDirectory + "\\图片url\\";
    DirectoryInfo root = new DirectoryInfo(path);
    DirectoryInfo[] dics = root.GetDirectories();
    foreach (var itemdic in dics)
    {
        string txt = "";
        StreamReader sr = new StreamReader(itemdic.FullName + "\\data.txt");
        while (!sr.EndOfStream)
        {
            string str = sr.ReadLine();
            txt += str;// + "\n";
        }
        sr.Close();
        surls.Add(new testfold() { key = itemdic.FullName, picurl = txt });
    }
    ChromeDriverService service = ChromeDriverService.CreateDefaultService(System.Environment.CurrentDirectory);
    //  service.HideCommandPromptWindow = true;
    ChromeOptions options = new ChromeOptions();
    options.AddArguments("--test-type", "--ignore-certificate-errors");
    options.AddArgument("enable-automation");
    //   options.AddArgument("headless");
    //  options.AddArguments("--proxy-server=http://user:password@yourProxyServer.com:8080");
    using (IWebDriver driver = new OpenQA.Selenium.Chrome.ChromeDriver(service, options, TimeSpan.FromSeconds(120)))
    {
        driver.Url = "https://www.1688.com/";
        Thread.Sleep(200);
        try
        {
            int a = 1;
            foreach (var itemsurls in surls)
            {
                SetText("\r\n第" + a.ToString() + "个");
                driver.Navigate().GoToUrl(itemsurls.picurl);
                //登录
                if (driver.Url.Contains("login.1688.com"))
                {
                    SetText("\r\n需要登录，开始尝试...");
                    trylogin(driver); //尝试登录完成
                                      //再试试        driver.Navigate().GoToUrl("https://s.1688.com/youyuan/index.htm?tab=imageSearch&imageType=oss&imageAddress=cbuimgsearch/eWXC7XHHPN1607529600000&spm=");
                    if (driver.Url.Contains("login.1688.com"))
                    {
                        //没办法退出
                        SetText("\r\n退出，换ip重试...");
                        return;
                    }
                }
                //鼠标放上去的内容因为页面自带只能显示一个的原因 没办法做到全部显示 然后在下载 只能是其他方式下载
                //  var elements = document.getElementsByClassName('hover-container');
                //  Array.prototype.forEach.call(elements, function(element) {
                //  element.style.display = "block";
                //   console.log(element);
                //  });
                //   IJavaScriptExecutor js = (IJavaScriptExecutor)driver;
                //    var sss = js.ExecuteScript(" var elements = document.getElementsByClassName('hover-container');  Array.prototype.forEach.call(elements, function(element) {  console.log(element); element.setAttribute(\"class\", \"测试title\");  element.style.display = \"block\";  console.log(element); });");
                Thread.Sleep(500);
                var responseModel = Write(itemsurls.key, driver.PageSource, Pagetypeenum.列表);
                Thread.Sleep(500);
                int i = 1;
                foreach (var offer in responseModel?.data?.offerList ?? new List<OfferItemModel>())
                { driver.Navigate().GoToUrl(offer.information.detailUrl);
                    string responseDatadetail = driver.PageSource;
                    Write(itemsurls.key, driver.PageSource, Pagetypeenum.详情);
                    SetText("\r\n第" + a.ToString() + "-" + i.ToString() + "个");
                    Thread.Sleep(500);
                    i++;
                }
            }
        }
        catch (Exception ex)
        {
            CloseChromeDriver(driver);
            throw;
        }
    }
}


#region 异常  退出chromedriver
[DllImport("user32.dll", EntryPoint = "FindWindow")]
private extern static IntPtr FindWindow(string lpClassName, string lpWindowName);
[DllImport("user32.dll", EntryPoint = "SendMessage")]
public static extern int SendMessage(IntPtr hWnd, int Msg, int wParam, int lParam);
public const int SW_HIDE = 0;
public const int SW_SHOW = 5;
[DllImport("user32.dll", EntryPoint = "ShowWindow")]
public static extern int ShowWindow(IntPtr hwnd, int nCmdShow);

/// <summary>
/// 获取窗口句柄
/// </summary>
/// <returns></returns>
public IntPtr GetWindowHandle()
{
    string name = (Environment.CurrentDirectory + "\\chromedriver.exe");
    IntPtr hwd = FindWindow(null, name);
    return hwd;
}

/// <summary>
/// 关闭chromedriver窗口
/// </summary>
public void CloseWindow()
{
    try
    {
        IntPtr hwd = GetWindowHandle();
        SendMessage(hwd, 0x10, 0, 0);
    }
    catch { }
}
/// <summary>
/// 退出chromedriver
/// </summary>
/// <param name="driver"></param>
public void CloseChromeDriver(IWebDriver driver)
{
    try
    {
        driver.Quit();
        driver.Dispose();
    }
    catch { }
    CloseWindow();
}

总结

说一下思路:

1、跳转到指定的网页driver.Navigate().GoToUrl

2、确定数据源，从driver.PageSource读取数据

3、对html数据进行解析

- EOF -

技术群：添加小编微信dotnet999

公众号：dotnet讲堂