Install-Package HtmlAgilityPack

public struct HotWord{public int Rank;//排行public string Word;public string JumpLink; //相关链接public int HotDegree; //热度}

XML 实例文档

我们将在下面的例子中使用这个 XML 文档。

<?xml version="1.0" encoding="ISO-8859-1"?><bookstore><book><title lang="eng">Harry Potter</title><price>29.99</price>
</book><book><title lang="eng">Learning XML</title><price>39.95</price>
</book></bookstore>

选取节点

XPath 使用路径表达式在 XML 文档中选取节点。节点是通过沿着路径或者 step 来选取的。

下面列出了最有用的路径表达式：

实例

在下面的表格中，我们已列出了一些路径表达式以及表达式的结果：

谓语（Predicates）

谓语用来查找某个特定的节点或者包含某个指定的值的节点。

谓语被嵌在方括号中。

实例

在下面的表格中，我们列出了带有谓语的一些路径表达式，以及表达式的结果：

选取未知节点

XPath 通配符可用来选取未知的 XML 元素。

实例

在下面的表格中，我们列出了一些路径表达式，以及这些表达式的结果：

  /// <summary>/// 指定header参数的HTTP Get方法/// </summary>/// <param name="headers"></param>/// <param name="url"></param>/// <returns>respondse</returns>public string Get(WebHeaderCollection headers, string url ,string responseEncoding="UTF-8",bool isUseCookie = false){string responseText = "";try{var request = (HttpWebRequest)WebRequest.Create(url);request.Method = "GET";foreach (string key in headers.Keys){switch (key.ToLower()){case "user-agent":request.UserAgent = headers[key];break;case "referer":request.Referer = headers[key];break;case "host":request.Host = headers[key];break;case "contenttype":request.ContentType = headers[key];break;case "accept":request.Accept = headers[key];break;default:break;}}if (string.IsNullOrEmpty(request.Referer)){request.Referer = "http://weixin.sogou.com/";};if (string.IsNullOrEmpty(request.Host)){request.Host = "weixin.sogou.com";};if (string.IsNullOrEmpty(request.UserAgent)){Random r = new Random();int index = r.Next(WechatSogouBasic._agent.Count - 1);request.UserAgent = WechatSogouBasic._agent[index];}if (isUseCookie){CookieCollection cc = Tools.LoadCookieFromCache();request.CookieContainer = new CookieContainer();request.CookieContainer.Add(cc);}HttpWebResponse response = (HttpWebResponse)request.GetResponse();if (isUseCookie && response.Cookies.Count >0){var cookieCollection = response.Cookies;WechatCache cache = new WechatCache(Config.CacheDir, 3000);if (!cache.Add("cookieCollection", cookieCollection, 3000)) { cache.Update("cookieCollection", cookieCollection, 3000); };}// Get the stream containing content returned by the server.Stream dataStream = response.GetResponseStream();//如果response是图片，则返回以base64方式返回图片内容，否则返回html内容if (response.Headers.Get("Content-Type") == "image/jpeg" || response.Headers.Get("Content-Type") == "image/jpg"){Image img = Image.FromStream(dataStream, true);using (MemoryStream ms = new MemoryStream()){// Convert Image to byte[]//img.Save("myfile.jpg");
                        img.Save(ms,System.Drawing.Imaging.ImageFormat.Jpeg);byte[] imageBytes = ms.ToArray();// Convert byte[] to Base64 Stringstring base64String = Convert.ToBase64String(imageBytes);responseText = base64String;}}else //read response string
                {// Open the stream using a StreamReader for easy access.
                    Encoding encoding;switch (responseEncoding.ToLower()){case "utf-8":encoding = Encoding.UTF8;break;case "unicode":encoding = Encoding.Unicode;break;case "ascii":encoding = Encoding.ASCII;break;default:encoding = Encoding.Default;break;}StreamReader reader = new StreamReader(dataStream, encoding);//System.Text.Encoding.Default// Read the content.if (response.StatusCode == HttpStatusCode.OK){responseText = reader.ReadToEnd();if (responseText.Contains("用户您好，您的访问过于频繁，为确认本次访问为正常用户行为，需要您协助验证")){_vcode_url = url;throw new Exception("weixin.sogou.com verification code");}}else{logger.Error("requests status_code error" + response.StatusCode);throw new Exception("requests status_code error");}reader.Close();}dataStream.Close();response.Close();}catch (Exception e){logger.Error(e);}return responseText;}

public List<OfficialAccount> SearchOfficialAccount(string keyword, int page = 1){List<OfficialAccount> accountList = new List<OfficialAccount>();string text = this._SearchAccount_Html(keyword, page);//返回了一个搜索页面的html代码HtmlDocument pageDoc = new HtmlDocument();pageDoc.LoadHtml(text);HtmlNodeCollection targetArea = pageDoc.DocumentNode.SelectNodes("//ul[@class='news-list2']/li");if (targetArea != null){foreach (HtmlNode node in targetArea){try{OfficialAccount accountInfo = new OfficialAccount();//链接中包含了&amp; html编码符，要用htmdecode，不是urldecodeaccountInfo.AccountPageurl = WebUtility.HtmlDecode(node.SelectSingleNode("div/div[@class='img-box']/a").GetAttributeValue("href", ""));//accountInfo.ProfilePicture = node.SelectSingleNode("div/div[1]/a/img").InnerHtml;accountInfo.ProfilePicture = WebUtility.HtmlDecode(node.SelectSingleNode("div/div[@class='img-box']/a/img").GetAttributeValue("src", ""));accountInfo.Name = node.SelectSingleNode("div/div[2]/p[1]").InnerText.Trim().Replace("<!--red_beg-->", "").Replace("<!--red_end-->", "");accountInfo.WeChatId = node.SelectSingleNode("div/div[2]/p[2]/label").InnerText.Trim();accountInfo.QrCode = WebUtility.HtmlDecode(node.SelectSingleNode("div/div[3]/span/img").GetAttributeValue("src", ""));accountInfo.Introduction = node.SelectSingleNode("dl[1]/dd").InnerText.Trim().Replace("<!--red_beg-->","").Replace("<!--red_end-->", "");//早期的账号认证和后期的认证显示不一样？，对比 bitsea 和 NUAA_1952 两个账号//现在改为包含该script的即认证了if (node.InnerText.Contains("document.write(authname('2'))")){accountInfo.IsAuth = true;}else{accountInfo.IsAuth = false;}accountList.Add(accountInfo);}catch (Exception e){logger.Warn(e);}}}return accountList; }

CookieCollection cc = Tools.LoadCookieFromCache();
request.CookieContainer = new CookieContainer();
request.CookieContainer.Add(cc);