一、背景 ! Z8 H" L5 x6 v; A& t ^* A! H 在1688官网里面有很多信息是需要登录才能看得到的，比如商家的联系电话等等。那么我们在抓取它的网页的时候，肯定是需要维持登录状态才能得到对应的内容。这里面就会涉及到自动登录的问题。) O. J- ?3 Z+ ^3 m: P- p' D* J 登录地址：https://login.1688.com/member/signin.htm ' S% h K% Q1 q+ P- E
. Q+ f6 @7 M9 c% g 二、自动登录方法 5 ^9 \3 J7 t$ g$ N; G" X 1、找到对应的元素，账号、密码框。6 y/ W0 I% z) u! @ H
; a* J( N9 L$ T7 R, E: k9 l) F 0 o3 `' L8 d' `! `5 s; s; x ~ List<string> logininfolist = new List<string>();
string file = "1688Account.json";
if (!File.Exists(file))
{
throw new ArgumentException("1688Account not found");
}
string data = File.ReadAllText(file, Encoding.UTF8);
var account1688list = JsonConvert.DeserializeObject<List<Account1688Item>>(data);
logininfolist.AddRange(account1688list.Select(o => o.AccountPassword).ToList());
Random rdinfo = new Random();
int indexinfo = rdinfo.Next(logininfolist.Count);
var modelinfo = logininfolist[indexinfo];
driver.FindElement(By.Id("fm-login-id")).SendKeys(modelinfo.Split('+')[0]);
driver.FindElement(By.Id("fm-login-password")).SendKeys(modelinfo.Split('+')[1]);5 c. }3 ^- b( X; m // Thread.Sleep(1000 * 30); //30时间操作
driver.FindElement(By.ClassName("password-login")).Click();
Thread.Sleep(1000 * 30);//30时间操作9 @9 T4 Y i# o5 G0 @% C driver.Navigate().GoToUrl("https://work.1688.com/?tracelog=login_target_is_blank_1688");
Thread.Sleep(1000 * 5);
if (driver.Url.Contains("login.1688.com"))
{
Console.WriteLine("登录失败");
CookieHelp.DeleteCookies();
Console.WriteLine("2");
throw new Exception("重新登录");
}
driver.Navigate().Refresh();
CookieHelp.WriteCookies(driver.Manage().Cookies.AllCookies);' i9 a y+ o" F" h driver.Navigate().GoToUrl("https://www.1688.com/");
driver.Manage().Cookies.DeleteAllCookies();
var listCookie = CookieHelp.GetCookie();
if (listCookie != null)
{
logintry = 0;
Console.WriteLine("有现成cookies" + DateTime.UtcNow);
foreach (var item in listCookie)
{
driver.Manage().Cookies.AddCookie(new Cookie(item.Name, item.Value, item.Domain, item.Path, item.Expiry));
}
Thread.Sleep(2000);
driver.Navigate().GoToUrl("https://work.1688.com/?tracelog=login_target_is_blank_1688");
Thread.Sleep(1000 * 2);三、完整代码 0 ]: n0 v0 ~& H* D) I# O4 y4 S4 M3 W /// <summary>
/// 登录 todo
/// </summary>
/// <param name="_reptilesImageSearchService"></param>
/// <param name="options"></param>
/// <param name="driver"></param>
public void Implement(IReptilesImageSearchService _reptilesImageSearchService, IWebDriver driver)
{
driver.Navigate().GoToUrl("https://www.1688.com/");
driver.Manage().Cookies.DeleteAllCookies();
var listCookie = CookieHelp.GetCookie();
if (listCookie != null)
{
logintry = 0;
Console.WriteLine("有现成cookies" + DateTime.UtcNow);
foreach (var item in listCookie)
{
driver.Manage().Cookies.AddCookie(new Cookie(item.Name, item.Value, item.Domain, item.Path, item.Expiry));
}
Thread.Sleep(2000);
driver.Navigate().GoToUrl("https://work.1688.com/?tracelog=login_target_is_blank_1688");
Thread.Sleep(1000 * 2);
if (driver.Url.Contains("login.1688.com"))
{
Console.WriteLine("cookies过期了");
CookieHelp.DeleteCookies();
Console.WriteLine("1");
throw new Exception("重新登录");
}
}
else
{
if (logintry > 4)
{
Console.WriteLine("登陆次数超出：" + logintry);
throw new Exception("登陆次数超出,退出");
}
logintry++;
Console.WriteLine("无现成cookies" + DateTime.UtcNow);
driver.Navigate().GoToUrl("https://login.1688.com/member/signin.htm");
#region 登录动作
driver.SwitchTo().Frame(0);
IJavaScriptExecutor js = (IJavaScriptExecutor)driver;
////// string returnjs = (string)js.ExecuteScript("Object.defineProperties(navigator, {webdriver:{get:()=>undefined}});");
string jsfile = File.ReadAllText("stealth.min.js", Encoding.UTF8);
string returnjs = (string)js.ExecuteScript(jsfile);
List<string> logininfolist = new List<string>();
string file = "1688Account.json";
if (!File.Exists(file))
{
throw new ArgumentException("1688Account not found");
}
string data = File.ReadAllText(file, Encoding.UTF8);
var account1688list = JsonConvert.DeserializeObject<List<Account1688Item>>(data);
logininfolist.AddRange(account1688list.Select(o => o.AccountPassword).ToList());
Random rdinfo = new Random();
int indexinfo = rdinfo.Next(logininfolist.Count);
var modelinfo = logininfolist[indexinfo];
driver.FindElement(By.Id("fm-login-id")).SendKeys(modelinfo.Split('+')[0]);
driver.FindElement(By.Id("fm-login-password")).SendKeys(modelinfo.Split('+')[1]);
// Thread.Sleep(1000 * 30); //30时间操作
driver.FindElement(By.ClassName("password-login")).Click();
Thread.Sleep(1000 * 30);//30时间操作
#endregion 登录动作
driver.Navigate().GoToUrl("https://work.1688.com/?tracelog=login_target_is_blank_1688");
Thread.Sleep(1000 * 5);
if (driver.Url.Contains("login.1688.com"))
{
Console.WriteLine("登录失败");
CookieHelp.DeleteCookies();
Console.WriteLine("2");
throw new Exception("重新登录");
}
driver.Navigate().Refresh();
CookieHelp.WriteCookies(driver.Manage().Cookies.AllCookies);
}
Thread.Sleep(1000);
}四、注意事项 * O0 {5 k: s- S2 l " @, Q8 B5 x2 c1 i 2、使用这段代码本身就是模拟真实用户的行为，最大限度的减少验证码出现的几率。0 [+ F. E, E* g8 O! I IJavaScriptExecutor js = (IJavaScriptExecutor)driver;
////// string returnjs = (string)js.ExecuteScript("Object.defineProperties(navigator, {webdriver:{get:()=>undefined}});");
string jsfile = File.ReadAllText("stealth.min.js", Encoding.UTF8);
string returnjs = (string)js.ExecuteScript(jsfile); 
|手机版|小黑屋|paopaomj.COM
( 
渝ICP备18007172号|
渝公网安备50010502503914号 )
发表于 2022-4-12 07:51:04
