1 #region 解析HTML

2 ///

3 ///获取网页标签内容4 ///

5 public static string[] RegexHtmlToFormat(string as_Html, stringtags)6 {7 List list = new List();8 Regex regex = new Regex("]*?>[\\s\\S]*?", RegexOptions.IgnoreCase |RegexOptions.Multiline);9 if(regex.IsMatch(as_Html))10 {11 MatchCollection matchCollection =regex.Matches(as_Html);12 foreach (Match match inmatchCollection)13 {14 list.Add(match.Value);//获取到的

15 }16 }17 returnlist.ToArray();18 }19 ///

20 ///取得HTML中所有图片的 URL。21 ///

22 /// HTML代码

23 /// 图片的URL列表

24 public static string[] GetHtmlImageUrlList(stringsHtmlText)25 {26 //定义正则表达式用来匹配 img 标签

27 Regex regImg = new Regex(@"]*?\bsrc[\s\t\r\n]*=[\s\t\r\n]*[""‘]?[\s\t\r\n]*(?[^\s\t\r\n""‘<>]*)[^<>]*?/?[\s\t\r\n]*>", RegexOptions.IgnoreCase);28

29 //搜索匹配的字符串

30 MatchCollection matches =regImg.Matches(sHtmlText);31 int i = 0;32 string[] sUrlList = new string[matches.Count];33

34 //取得匹配项列表

35 foreach (Match match inmatches)36 sUrlList[i++] = match.Groups["imgUrl"].Value;37 returnsUrlList;38 }39 ///

40 ///获取页面内所有漫画图片地址41 ///

42 public static string[] RegexHtmlDiv(string as_Html, stringclassName)43 {44 List list = new List();45 Regex regex = new Regex("

", RegexOptions.IgnoreCase |RegexOptions.Multiline);46 if(regex.IsMatch(as_Html))47 {48 MatchCollection matchCollection =regex.Matches(as_Html);49 foreach (Match match inmatchCollection)50 {51 string ls_rc =match.Value;52 list.Add(ls_rc);//获取到的

53 }54 }55 returnlist.ToArray();56 }57

58 ///

59 ///解析HTML60 /// 示例代码

61 ///

62 public static string RegexHTMLList(stringas_Html)63 {64 as_Html = as_Html.Replace("\t", "");65 as_Html = as_Html.Replace(" ", "");66 string ls_rc = "";67 Regex regex = new Regex("

(?.*?)", RegexOptions.IgnoreCase |RegexOptions.Multiline);68 if(regex.IsMatch(as_Html))69 {70 MatchCollection matchCollection =regex.Matches(as_Html);71 foreach (Match match inmatchCollection)72 {73 ls_rc += match.Value;//获取到的

74 }75 }76 returnls_rc;77 }78

79 ///

80 ///获取字符中指定标签的值81 ///

82 /// 字符串

83 /// 标签

84 /// 属性名

85 /// 属性

86 public static string GetTitleContent(string str, string title, stringattrib)87 {88 string tmpStr = string.Format("]*?{1}=([‘\"\"]?)(?[^‘\"\"\\s>]+)\\1[^>]*>", title, attrib); //获取之间内容

89 Match TitleMatch =Regex.Match(str, tmpStr, RegexOptions.IgnoreCase);90 string result = TitleMatch.Groups["url"].Value;91 returnresult;92 }93 ///

94 ///解析控件的属性返回键值对95 ///

96 ///

97 ///

98 public static System.Collections.Hashtable getAttrs(stringHtmlElement)99 {100 System.Collections.Hashtable ht = newSystem.Collections.Hashtable();101 MatchCollection mc = Regex.Matches(HtmlElement, "(?[\\S^=]+)\\s*=\\s*\"(?[^\"\"]+)\"|(?[\\S^=]+)\\s*=\\s*‘(?[^‘‘]+)‘|(?\\w+)=(?[^\"])(?=[\\s])");102 foreach (Match m inmc)103 {104 ht[m.Groups[1].Value] = m.Groups[2].Value;105 }106 returnht;107 }108 #endregion