我正在尝试使用 Rohit Agarwal 的 BrowserSession与 HtmlAgilityPack 一起上课以登录并随后在 Facebook 周围导航。

我以前通过编写自己的 HttpWebRequest 来设法做到这一点。但是，它只有在我每次从浏览器中手动获取 cookie 并在每次执行新的“ session ”时向请求中插入一个新的 cookie 字符串时才有效。现在我正在尝试使用 BrowserSession 来获得更智能的导航。

这是当前代码:

BrowserSession b = new BrowserSession();

b.Get(@"http://www.facebook.com/login.php");
b.FormElements["email"] = "some@email.com";
b.FormElements["pass"] = "xxxxxxxx";
b.FormElements["lsd"] = "qDhIH";
b.FormElements["trynum"] = "1";
b.FormElements["persistent_inputcheckbox"] = "1";

var response = b.Post(@"https://login.facebook.com/login.php?login_attempt=1");

以上工作正常。当我尝试再次使用此 BrowserSession 来获取另一个页面时，问题就来了。我这样做是因为 BrowserSession 保存了上次响应中的 cookie 并将它们插入到下一个请求中，因此我不必再手动插入从浏览器中获取的 cookie 数据。

但是，当我尝试做这样的事情时:

var profilePage = b.Get(@"https://m.facebook.com/profile.php?id=1111111111");

我取回的文档是空的。对于我做错的任何意见，我将不胜感激。

最佳答案

如果有人关心，我会解决这个问题的根本原因。结果是 cookie 被保存在 REQUEST 对象的 CookieContainer 中，而不是响应对象中。我还添加了下载文件的功能(前提是该文件是基于字符串的)。代码绝对不是线程安全的，但对象一开始就不是线程安全的:

public class BrowserSession
{
    private bool _isPost;
    private bool _isDownload;
    private HtmlDocument _htmlDoc;
    private string _download;

    /// <summary>
    /// System.Net.CookieCollection. Provides a collection container for instances of Cookie class 
    /// </summary>
    public CookieCollection Cookies { get; set; }

    /// <summary>
    /// Provide a key-value-pair collection of form elements 
    /// </summary>
    public FormElementCollection FormElements { get; set; }

    /// <summary>
    /// Makes a HTTP GET request to the given URL
    /// </summary>
    public string Get(string url)
    {
        _isPost = false;
        CreateWebRequestObject().Load(url);
        return _htmlDoc.DocumentNode.InnerHtml;
    }

    /// <summary>
    /// Makes a HTTP POST request to the given URL
    /// </summary>
    public string Post(string url)
    {
        _isPost = true;
        CreateWebRequestObject().Load(url, "POST");
        return _htmlDoc.DocumentNode.InnerHtml;
    }

    public string GetDownload(string url)
    {
        _isPost = false;
        _isDownload = true;
        CreateWebRequestObject().Load(url);
        return _download;
    }

    /// <summary>
    /// Creates the HtmlWeb object and initializes all event handlers. 
    /// </summary>
    private HtmlWeb CreateWebRequestObject()
    {
        HtmlWeb web = new HtmlWeb();
        web.UseCookies = true;
        web.PreRequest = new HtmlWeb.PreRequestHandler(OnPreRequest);
        web.PostResponse = new HtmlWeb.PostResponseHandler(OnAfterResponse);
        web.PreHandleDocument = new HtmlWeb.PreHandleDocumentHandler(OnPreHandleDocument);
        return web;
    }

    /// <summary>
    /// Event handler for HtmlWeb.PreRequestHandler. Occurs before an HTTP request is executed.
    /// </summary>
    protected bool OnPreRequest(HttpWebRequest request)
    {
        AddCookiesTo(request);               // Add cookies that were saved from previous requests
        if (_isPost) AddPostDataTo(request); // We only need to add post data on a POST request
        return true;
    }

    /// <summary>
    /// Event handler for HtmlWeb.PostResponseHandler. Occurs after a HTTP response is received
    /// </summary>
    protected void OnAfterResponse(HttpWebRequest request, HttpWebResponse response)
    {
        SaveCookiesFrom(request, response); // Save cookies for subsequent requests

        if (response != null && _isDownload)
        {
            Stream remoteStream = response.GetResponseStream();
            var sr = new StreamReader(remoteStream);
            _download = sr.ReadToEnd();
        }
    }

    /// <summary>
    /// Event handler for HtmlWeb.PreHandleDocumentHandler. Occurs before a HTML document is handled
    /// </summary>
    protected void OnPreHandleDocument(HtmlDocument document)
    {
        SaveHtmlDocument(document);
    }

    /// <summary>
    /// Assembles the Post data and attaches to the request object
    /// </summary>
    private void AddPostDataTo(HttpWebRequest request)
    {
        string payload = FormElements.AssemblePostPayload();
        byte[] buff = Encoding.UTF8.GetBytes(payload.ToCharArray());
        request.ContentLength = buff.Length;
        request.ContentType = "application/x-www-form-urlencoded";
        System.IO.Stream reqStream = request.GetRequestStream();
        reqStream.Write(buff, 0, buff.Length);
    }

    /// <summary>
    /// Add cookies to the request object
    /// </summary>
    private void AddCookiesTo(HttpWebRequest request)
    {
        if (Cookies != null && Cookies.Count > 0)
        {
            request.CookieContainer.Add(Cookies);
        }
    }

    /// <summary>
    /// Saves cookies from the response object to the local CookieCollection object
    /// </summary>
    private void SaveCookiesFrom(HttpWebRequest request, HttpWebResponse response)
    {
        //save the cookies ;)
        if (request.CookieContainer.Count > 0 || response.Cookies.Count > 0)
        {
            if (Cookies == null)
            {
                Cookies = new CookieCollection();
            }

            Cookies.Add(request.CookieContainer.GetCookies(request.RequestUri));
            Cookies.Add(response.Cookies);
        }
    }

    /// <summary>
    /// Saves the form elements collection by parsing the HTML document
    /// </summary>
    private void SaveHtmlDocument(HtmlDocument document)
    {
        _htmlDoc = document;
        FormElements = new FormElementCollection(_htmlDoc);
    }
}

/// <summary>
/// Represents a combined list and collection of Form Elements.
/// </summary>
public class FormElementCollection : Dictionary<string, string>
{
    /// <summary>
    /// Constructor. Parses the HtmlDocument to get all form input elements. 
    /// </summary>
    public FormElementCollection(HtmlDocument htmlDoc)
    {
        var inputs = htmlDoc.DocumentNode.Descendants("input");
        foreach (var element in inputs)
        {
            string name = element.GetAttributeValue("name", "undefined");
            string value = element.GetAttributeValue("value", "");

            if (!this.ContainsKey(name))
            {
                if (!name.Equals("undefined"))
                {
                    Add(name, value);
                }
            }
        }
    }

    /// <summary>
    /// Assembles all form elements and values to POST. Also html encodes the values.  
    /// </summary>
    public string AssemblePostPayload()
    {
        StringBuilder sb = new StringBuilder();
        foreach (var element in this)
        {
            string value = System.Web.HttpUtility.UrlEncode(element.Value);
            sb.Append("&" + element.Key + "=" + value);
        }
        return sb.ToString().Substring(1);
    }
}

关于c# - 使用 BrowserSession 和 HtmlAgilityPack 通过 .NET 登录 Facebook，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/3471893/