在以下应用程序中,我使用HTML敏捷包从给定的URL中提取HTML文档。现在我需要知道如何使用HTML文档中的元素ID并在字段中输入文本,最后点击SUBMIT按钮提交表单。
protected void Button1_Click(object sender, EventArgs e)
{
string Url = "https://something.com/login.asp";
HtmlWeb web = new HtmlWeb();
HtmlAgilityPack.HtmlDocument doc = web.Load(Url);
}
当前应用程序自动化Web数据输入。
答案 0 :(得分:0)
HtmlAgilityPack不能那样工作。您只是拥有一个表示HTML文档中节点的数据结构,您没有托管Web浏览器或客户端的实例。
soliutin将遍历HtmlDocument实例并找到正确的<form>
元素,然后提取相应的子<input />
元素。您需要创建自己的HttpWebRequest对象,并使用适当编码的键/值对手动填充其RequestStream
(假设它是POST表单而不是GET表单)。
如果您要提交的表单是静态的并且不会更改,那么您根本不需要使用HtmlAgilityPack,只需将表单名称和值硬编码到HttpWebRequest中。
答案 1 :(得分:0)
我正在做类似的事情,但我手动获取页面html。
// do webrequest stuff and return raw html
string html = DemoDoHttpGet(url, cookieContainer);
// I'm hitting an asp.net page so I have to repeat a bunch of values back to the server
// key is the "name" attribute of an element i want to find in the html
// i gathered these manually by watching a normal exchange with fiddler
var fields = new Dictionary<string, string>();
fields.Add(System.Web.HttpUtility.UrlDecode("__LASTFOCUS"), string.Empty);
fields.Add(System.Web.HttpUtility.UrlDecode("__EVENTTARGET"), string.Empty);
fields.Add(System.Web.HttpUtility.UrlDecode("__EVENTARGUMENT"), string.Empty);
fields.Add(System.Web.HttpUtility.UrlDecode("__VIEWSTATE"), string.Empty);
fields.Add(System.Web.HttpUtility.UrlDecode("__EVENTVALIDATION"), string.Empty);
fields.Add(System.Web.HttpUtility.UrlDecode("ctl00%24ContentPlaceHolder1%24Login1%24LoginButton"), string.Empty);
// this method searches the html for elements with the given names and updates
// the value for each item in the field collection with the value sent from the server
Scraper.GetFieldValues(fields, html);
/* looks kind of like this
var doc = new HtmlAgilityPack.HtmlDocument();
doc.LoadHtml(html);
var names = new List<string>();
foreach (var ditem in fields)
{
names.Add(ditem.Key);
}
foreach (var nitem in names)
{
// find items, read value
string xpath = string.Format("//*[@name=\"{0}\"]", (nitem));
var nodes = doc.DocumentNode.SelectNodes(xpath);
// if node found read whatever attribute is appropriate,
// write value back to fields collection
*/
// here i'm manually providing values for login username/password
fields.Add(System.Web.HttpUtility.UrlDecode(
"ctl00%24ContentPlaceHolder1%24Login1%24UserName"), "my@email.aaa");
fields.Add(System.Web.HttpUtility.UrlDecode(
"ctl00%24ContentPlaceHolder1%24Login1%24Password"), "mypassword");
// another webrequest to post back to the server
var request2 = (HttpWebRequest)WebRequest.Create(url);
request2.CookieContainer = cookieContainer;
request2.Method = "POST";
request2.ContentType = "application/x-www-form-urlencoded";
var args = new StringBuilder();
foreach (var item in fields)
{
args.Append(System.Web.HttpUtility.UrlEncode(item.Key));
args.Append("=");
args.Append(System.Web.HttpUtility.UrlEncode(item.Value));
args.Append("&");
}
using (System.IO.StreamWriter writer =
new System.IO.StreamWriter(request2.GetRequestStream()))
{
writer.Write(args.ToString().TrimEnd('&'));
}
string html;
using (var response2 = (System.Net.HttpWebResponse)request2.GetResponse())
using (var rdr2 = new System.IO.StreamReader(response2.GetResponseStream()))
{
html = rdr2.ReadToEnd();
}
答案 2 :(得分:0)
protected void Button1_Click(object sender, EventArgs e)
{
IWebDriver driver =
new InternetExplorerDriver(@"C:\.....\IEDriverServer_Win32_2.25.2");
driver.Navigate().GoToUrl("https://website.com/login.asp");
// Find the text input element by its name
// username
IWebElement name_ID = driver.FindElement(By.Name("name_ID"));
name_ID.SendKeys("xyzw");
// password
IWebElement pwd_PW = driver.FindElement(By.Name("pwd_PW"));
pwd_PW.SendKeys("fasdfasfdasdf");
// submit login form
IWebElement sSubmit = driver.FindElement(By.Name("submit"));
submit.Submit();
System.Threading.Thread.Sleep(5000);
driver.Quit();
}