整理两个 在C#中,用正则表达式 获取网页源代码标签的属性或值的方法 :
1、获取标签中的值: string str="<a href=\"www.csdn.net\" class=\"main\" >CSDN</a>" 结果:CSDN
调用例子:string name=GetTitleContent(str,"a");
/// <summary> /// 获取字符中指定标签的值 /// </summary> /// <param name="str">字符串</param> /// <param name="title">标签</param> /// <returns>值</returns> public static string GetTitleContent(string str, string title) { string tmpStr = string.Format("<{0}[^>]*?>(?<Text>[^<]*)</{1}>", title, title); //获取<title>之间内容
Match TitleMatch = Regex.Match(str, tmpStr, RegexOptions.IgnoreCase);
string result = TitleMatch.Groups["Text"].Value; return result; }
2、获取标签中的属性: string str="<a href=\"www.csdn.net\" class=\"main\">CSDN</a>" 获取 “href” 的结果:www.csdn.net
调用例子:string href=GetTitleContent(str,"a","href");
/// <summary> /// 获取字符中指定标签的值 /// </summary> /// <param name="str">字符串</param> /// <param name="title">标签</param> /// <param name="attrib">属性名</param> /// <returns>属性</returns> public static string GetTitleContent(string str, string title,string attrib) {
string tmpStr = string.Format("<{0}[^>]*?{1}=(['\"\"]?)(?<url>[^'\"\"\\s>]+)\\1[^>]*>", title, attrib); //属性值
Match TitleMatch = Regex.Match(str, tmpStr, RegexOptions.IgnoreCase);
string result = TitleMatch.Groups["url"].Value; return result; }
注:以上方法为获取字符串中第一个结果的值。可以使用Foreach读取TitileMath中所有的匹配属性或值。
3。获取 <div class="brand_items"> 跟 </div> 之间的内容,<div class="brand_items"> 跟 </div> 可以重复出现
比如 :
<div class="cont_left"> |
|
<div class="cont_left_items"><a href="left.php?cid=QDE=" class="ma">数码手机</a></div>
|
|
<div class="cont_left_items"><a href="left.php?cid=QTE=" class="ma">整机电教</a></div>
|
|
<div class="cont_left_items"><a href="left.php?cid=QjE=" class="ma">办公耗材</a></div>
|
|
<div class="cont_left_items2"><a href="left.php?cid=RDE=" class="ma2">硬件周边</a></div>
|
|
<div class="cont_left_items"><a href="left.php?cid=RTE=" class="ma">网络通讯</a></div>
|
|
<div class="cont_left_items"><a href="left.php?cid=RzE=" class="ma">安防监控</a></div>
|
|
<div class="cont_left_items"><a href="left.php?cid=QDFAMQ==" class="ma">IT综合</a></div>
|
|
</div> |
|
<div class="cont_right"> |
|
<div class="cont_right_items2"><a href="prod_list.php?cid=RDE=&sid=SDE=" class="ma3" target="_parent">摄像头</a></div>
|
|
<div class="rg_brand_list"> <div class="brand_items"><a href="prod_list.php?bid=QDFBMUYx&cid=RDE=&sid=SDE=" target="_parent" class="ma2">罗技</a></div>
|
|
<div class="brand_items"><a href="prod_list.php?bid=QDFCMUQx&cid=RDE=&sid=SDE=" target="_parent" class="ma2">新贵</a></div>
|
|
<div class="brand_items"><a href="prod_list.php?bid=QDFDMUYx&cid=RDE=&sid=SDE=" target="_parent" class="ma2">清华紫光</a></div>
|
|
|
|
|
|
<div class="brand_items"><a href="prod_list.php?bid=QDFDMUUx&cid=RDE=&sid=SDE=" target="_parent" class="ma2">达克浩思</a></div>
|
|
<div class="brand_items"><a href="prod_list.php?bid=QDFGMUYxPzFBMQ==&cid=RDE=&sid=SDE=" target="_parent" class="ma2">ASJ奥视嘉</a></div>
|
|
<div class="brand_items"><a href="prod_list.php?bid=RzE/MUUxRDFHMQ==&cid=RDE=&sid=SDE=" target="_parent" class="ma2">百视通</a></div>
|
|
<div class="brand_items"><a href="prod_list.php?bid=RzE/MUgxSDE/MQ==&cid=RDE=&sid=SDE=" target="_parent" class="ma2">创新</a></div>
|
|
<div class="brand_items"><a href="prod_list.php?bid=RzFAMT8xPzE/MQ==&cid=RDE=&sid=SDE=" target="_parent" class="ma2">海畅</a></div>
|
|
<div class="brand_items"><a href="prod_list.php?bid=RzFAMT8xQDFEMQ==&cid=RDE=&sid=SDE=" target="_parent" class="ma2">昂达</a></div>
|
|
<div class="brand_items"><a href="prod_list.php?bid=RzFAMT8xQjFAMQ==&cid=RDE=&sid=SDE=" target="_parent" class="ma2">网眼</a></div>
|
|
<div class="brand_items"><a href="prod_list.php?bid=RzFBMUMxPzFAMQ==&cid=RDE=&sid=SDE=" target="_parent" class="ma2">网缘</a></div>
|
|
<div class="brand_items"><a href="prod_list.php?bid=RzFDMUUxQjFGMQ==&cid=RDE=&sid=SDE=" target="_parent" class="ma2">黑石</a></div>
|
|
<div class="brand_items"><a href="prod_list.php?bid=QDFBMUgx&cid=RDE=&sid=SDE=" target="_parent" class="ma2">奥尼ANC</a></div>
|
|
<div class="brand_items"><a href="prod_list.php?bid=QDFCMUYx&cid=RDE=&sid=SDE=" target="_parent" class="ma2">鼎易</a></div>
|
|
|
|
<div class="brand_items"><a href="prod_list.php?bid=RzFCMUcxQDE/MQ==&cid=RDE=&sid=SDE=" target="_parent" class="ma2">清华同方</a></div>
|
|
</div> <div class="cont_right_items"><a href="prod_list.php?cid=RDE=&sid=QzFBMQ==" class="ma3" target="_parent">液晶显示器</a></div>
|
|
<div class="cont_right_items"><a href="prod_list.php?cid=RDE=&sid=RDE/MQ==" class="ma3" target="_parent">主板</a></div>
|
|
<div class="cont_right_items"><a href="prod_list.php?cid=RDE=&sid=RDFAMQ==" class="ma3" target="_parent">显卡</a></div>
|
|
<div class="cont_right_items"><a href="prod_list.php?cid=RDE=&sid=RDFBMQ==" class="ma3" target="_parent">CPU</a></div>
|
|
|
|
<div class="cont_right_items"><a href="prod_list.php?cid=RDE=&sid=RTFAMQ==" class="ma3" target="_parent">散热器</a></div>
|
|
<div class="cont_right_items"><a href="prod_list.php?cid=RDE=&sid=RzFDMQ==" class="ma3" target="_parent">键盘</a></div>
|
Regex regex = new Regex("(?<=(<div class=\"brand_items\">))[.\\s\\S]*?(?=(</div>))", RegexOptions.IgnoreCase);
for (Match match = regex.Match(content); match.Success; match = match.NextMatch())
{
string d=match.Groups[0].ToString();//每个<div class="brand_items"> </div>里的内容
}
获取<div class="info_mid_left"> 跟 <div class="endarea"> 之间的内容,唯一性 <div class="info_mid_left"> 跟 <div class="endarea"> 不重复出现
Regex regex1 = new Regex("(?<=(<div class=\"info_mid_left\">))[.\\s\\S]*?(?=(<div class=\"endarea\">))", RegexOptions.IgnoreCase);
string Pcontent = regex1.Match(content).Groups[0].Value;
获取 <td class="paramFontS2" style="text-align:center; font-size:13px;">技嘉 H61M-DS2DVI </td> td里的Text内容,td有多种不确定属性的时候
Regex regex2 = new Regex("<td[^>]*?>(?<Text>[^<]*)</td>", RegexOptions.IgnoreCase);
for (Match match2 = regex2.Match(d1); match2.Success; match2 = match2.NextMatch())
{
name = match2.Groups["Text"].Value;
}
获取input控件的value值
public string FindValueByName(string str, string inputname) { //string reg = @"<input name=""(?<name>.*?)"" [\s\S]*?value=""(?<value>.*?)"" [\s\S]*?>"; string reg = "<input[^>]+name=\"*(?<name>[^\\s\">]+)\"*[^>]*value=\"*(?<value>[^\\s\">]+)\"*[^>]*>"; Regex r = new Regex(reg, RegexOptions.None); Match match = r.Match(str); string aa = ""; while (match.Success) { string name = match.Groups["name"].ToString(); string value = match.Groups["value"].ToString(); if (name == inputname) { return value; } else { match = match.NextMatch(); } } return aa; }
清除所有a标签:string str1 = Regex.Replace(str, @"</?a[^>]*>", "");
清除所有script 包括script里面的代码 str1 = Regex.Replace(str, @"<script[^>]*>([\s\S](?!<script))*?</script>", "");
|
请发表评论