用C#+Selenium+ChromeDriver 爬取網頁,完美模擬真實的用戶瀏覽行爲

背景

 Selenium是一個用於Web應用程序測試的工具。Selenium測試直接運行在瀏覽器中,就像真正的用戶在操做同樣。而對於爬蟲來講,使用Selenium操控瀏覽器來爬取網上的數據那麼確定是爬蟲中的殺手武器。這裏,我將介紹selenium + 谷歌瀏覽器的通常使用。html

需求

在日常的爬蟲開發中,有時候網頁是一堆js堆起來的代碼,涉及不少異步計算,若是是普通的http 控制檯請求,那麼獲得的源文件是一堆js ,須要本身在去組裝數據,很費力;可是採用Selenium+ChromeDriver能夠達到所見即所得的完美效果。chrome

實現方式

項目結構:爲了方便使用,用的winform程序,附nuget包瀏覽器

 

 

 如下是form1.cs的代碼,這裏就只放關鍵方法代碼了。須要安裝最新的chrome瀏覽器+代碼中使用的chromedriver是 v2.9.248315less

 1    private void crawlingWebFunc()
 2         {
 3             SetText("\r\n開始嘗試...");
 4             List<testfold> surls = new List<testfold>();
 5             string path = System.Environment.CurrentDirectory + "\\圖片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("\r\n第" + a.ToString() + "");
40                         driver.Navigate().GoToUrl(itemsurls.picurl);
41                         //登陸
42                         if (driver.Url.Contains("login.1688.com"))
43                         {
44                             SetText("\r\n須要登陸,開始嘗試...");
45                             trylogin(driver); //嘗試登陸完成
46                                               //再試試
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                                 //沒辦法退出
52                                 SetText("\r\n退出,換ip重試...");
53                                 return;
54                             }
55                         }
56 
57                         //鼠標放上去的內容由於頁面自帶只能顯示一個的緣由 沒辦法作到所有顯示 而後在下載 只能是其餘方式下載
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\", \"測試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.詳情);
77                             SetText("\r\n第" + a.ToString() + "-" + i.ToString() + "");
78                             Thread.Sleep(500);
79                             i++;
80                         }
81                     }
82                 }
83                 catch (Exception ex)
84                 {
85                     CloseChromeDriver(driver);
86                     throw;
87                 }
88             }
89         }
 1  #region 異常  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         /// 獲取窗口句柄
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         /// 關閉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 異常  退出chromedriver

 

 

 

 

總結

說一下思路:curl

1.跳轉到指定的網頁driver.Navigate().GoToUrl異步

2.肯定數據源,從driver.PageSource讀取數據編輯器

3.對html數據進行解析ide

相關文章
相關標籤/搜索