using System.Text.RegularExpressions;
/// <summary> /// 执行正则提取出值 /// </summary> /// <param name="RegexString">正则表达式</param> /// <param name="HtmlCode">HtmlCode源代码</param> /// <returns>数组</returns> public static string[] GetRegValueAarry(string RegexString, string HtmlCode) { string[] MatchVale = new String[30];//初始化数组 int i = 0; Regex r = new Regex(RegexString);
for (Match m = r.Match(HtmlCode); m.Success; m = m.NextMatch()) { MatchVale[i] = m.Value.ToString(); i++; }
return MatchVale; }
/// <summary> /// 获取标签内的内容(只取出第一个) /// </summary> /// <param name="code"></param> /// <param name="wordsBegin"></param> /// <param name="wordsEnd"></param> /// <returns></returns> public static string SniffwebCode(string code, string wordsBegin, string wordsEnd) { string NewsTitle = ""; Regex regex1 = new Regex("" + wordsBegin + @"(?<content>[\s\S]+?)" + wordsEnd + "", RegexOptions.Compiled | RegexOptions.IgnoreCase); for (Match match1 = regex1.Match(code); match1.Success; match1 = match1.NextMatch()) { NewsTitle += match1.Groups["content"].ToString(); break; } return NewsTitle; }
// <summary> /// 获取标签内的内容并用~连上 /// </summary> /// <param name="code"></param> /// <param name="wordsBegin"></param> /// <param name="wordsEnd"></param> /// <returns></returns> public static string SniffwebCodeSplit(string code, string wordsBegin, string wordsEnd) { string NewsTitle = ""; Regex regex1 = new Regex("" + wordsBegin + @"(?<content>[\s\S]+?)" + wordsEnd + "", RegexOptions.Compiled | RegexOptions.IgnoreCase); for (Match match1 = regex1.Match(code); match1.Success; match1 = match1.NextMatch()) { NewsTitle += match1.Groups["content"].ToString() + "~"; } return NewsTitle; }
|
请发表评论