- A+
所属分类：.NET技术
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
1 private void crawlingWebFunc() 2 { 3 SetText("rn开始尝试..."); 4 List<testfold> surls = new List<testfold>(); 5 string path = System.Environment.CurrentDirectory + "\图片url\"; 6 DirectoryInfo root = new DirectoryInfo(path); 7 DirectoryInfo[] dics = root.GetDirectories(); 8 foreach (var itemdic in dics) 9 { 10 string txt = ""; 11 StreamReader sr = new StreamReader(itemdic.FullName + "\data.txt"); 12 while (!sr.EndOfStream) 13 { 14 string str = sr.ReadLine(); 15 txt += str;// + "n"; 16 } 17 sr.Close(); 18 surls.Add(new testfold() { key = itemdic.FullName, picurl = txt }); 19 } 20 21 ChromeDriverService service = ChromeDriverService.CreateDefaultService(System.Environment.CurrentDirectory); 22 // service.HideCommandPromptWindow = true; 23 24 ChromeOptions options = new ChromeOptions(); 25 options.AddArguments("--test-type", "--ignore-certificate-errors"); 26 options.AddArgument("enable-automation"); 27 // options.AddArgument("headless"); 28 // options.AddArguments("--proxy-server=http://user:password@yourProxyServer.com:8080"); 29 30 using (IWebDriver driver = new OpenQA.Selenium.Chrome.ChromeDriver(service, options, TimeSpan.FromSeconds(120))) 31 { 32 driver.Url = "https://www.1688.com/"; 33 Thread.Sleep(200); 34 try 35 { 36 int a = 1; 37 foreach (var itemsurls in surls) 38 { 39 SetText("rn第" + a.ToString() + "个"); 40 driver.Navigate().GoToUrl(itemsurls.picurl); 41 //登录 42 if (driver.Url.Contains("login.1688.com")) 43 { 44 SetText("rn需要登录，开始尝试..."); 45 trylogin(driver); //尝试登录完成 46 //再试试 47 driver.Navigate().GoToUrl("https://s.1688.com/youyuan/index.htm?tab=imageSearch&imageType=oss&imageAddress=cbuimgsearch/eWXC7XHHPN1607529600000&spm="); 48 49 if (driver.Url.Contains("login.1688.com")) 50 { 51 //没办法退出 52 SetText("rn退出，换ip重试..."); 53 return; 54 } 55 } 56 57 //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 58 // var elements = document.getElementsByClassName('hover-container'); 59 // Array.prototype.forEach.call(elements, function(element) { 60 // element.style.display = "block"; 61 // console.log(element); 62 // }); 63 64 // IJavaScriptExecutor js = (IJavaScriptExecutor)driver; 65 66 // 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); });"); 67 68 Thread.Sleep(500); 69 var responseModel = Write(itemsurls.key, driver.PageSource, Pagetypeenum.列表); 70 Thread.Sleep(500); 71 int i = 1; 72 foreach (var offer in responseModel?.data?.offerList ?? new List<OfferItemModel>()) 73 { 74 driver.Navigate().GoToUrl(offer.information.detailUrl); 75 string responseDatadetail = driver.PageSource; 76 Write(itemsurls.key, driver.PageSource, Pagetypeenum.详情); 77 SetText("rn第" + a.ToString() + "-" + i.ToString() + "个"); 78 Thread.Sleep(500); 79 i++; 80 } 81 } 82 } 83 catch (Exception ex) 84 { 85 CloseChromeDriver(driver); 86 throw; 87 } 88 } 89 }
1 #region 异常 退出chromedriver 2 3 [DllImport("user32.dll", EntryPoint = "FindWindow")] 4 private extern static IntPtr FindWindow(string lpClassName, string lpWindowName); 5 6 [DllImport("user32.dll", EntryPoint = "SendMessage")] 7 public static extern int SendMessage(IntPtr hWnd, int Msg, int wParam, int lParam); 8 9 public const int SW_HIDE = 0; 10 public const int SW_SHOW = 5; 11 12 [DllImport("user32.dll", EntryPoint = "ShowWindow")] 13 public static extern int ShowWindow(IntPtr hwnd, int nCmdShow); 14 15 /// <summary> 16 /// 获取窗口句柄 17 /// </summary> 18 /// <returns></returns> 19 public IntPtr GetWindowHandle() 20 { 21 string name = (Environment.CurrentDirectory + "\chromedriver.exe"); 22 IntPtr hwd = FindWindow(null, name); 23 return hwd; 24 } 25 26 /// <summary> 27 /// 关闭chromedriver窗口 28 /// </summary> 29 public void CloseWindow() 30 { 31 try 32 { 33 IntPtr hwd = GetWindowHandle(); 34 SendMessage(hwd, 0x10, 0, 0); 35 } 36 catch { } 37 } 38 39 /// <summary> 40 /// 退出chromedriver 41 /// </summary> 42 /// <param name="driver"></param> 43 public void CloseChromeDriver(IWebDriver driver) 44 { 45 try 46 { 47 driver.Quit(); 48 driver.Dispose(); 49 } 50 catch { } 51 CloseWindow(); 52 } 53 54 #endregion 异常 退出chromedriver
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
