正好有时间所以用C#写了一段正则表达式,作用是删除 Page 里面Code 中的 HTML标签,这在做采集信息,消除其中的HTML很有用处。
以下是引用片段: public string checkStr(string html) { System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"<script[\s\S]+</script *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex(@" href *= *[\s\S]*script *:", System.Text.RegularExpressions.RegexOptions.IgnoreCase); System.Text.RegularExpressions.Regex regex3 = new System.Text.RegularExpressions.Regex(@" no[\s\S]*=", System.Text.RegularExpressions.RegexOptions.IgnoreCase); System.Text.RegularExpressions.Regex regex4 = new System.Text.RegularExpressions.Regex(@"<iframe[\s\S]+</iframe *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); System.Text.RegularExpressions.Regex regex5 = new System.Text.RegularExpressions.Regex(@"<frameset[\s\S]+</frameset *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); System.Text.RegularExpressions.Regex regex6 = new System.Text.RegularExpressions.Regex(@"\<img[^\>]+\>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); System.Text.RegularExpressions.Regex regex7 = new System.Text.RegularExpressions.Regex(@"</p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); System.Text.RegularExpressions.Regex regex8 = new System.Text.RegularExpressions.Regex(@"<p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); System.Text.RegularExpressions.Regex regex9 = new System.Text.RegularExpressions.Regex(@"<[^>]*>", System.Text.RegularExpressions.RegexOptions.IgnoreCase); html = regex1.Replace(html, ""); //过滤<script></script>标记 html = regex2.Replace(html, ""); //过滤href=javascript: (<A>) 属性 html = regex3.Replace(html, " _disibledevent="); //过滤其它控件的on事件 html = regex4.Replace(html, ""); //过滤iframe html = regex5.Replace(html, ""); //过滤frameset html = regex6.Replace(html, ""); //过滤frameset html = regex7.Replace(html, ""); //过滤frameset html = regex8.Replace(html, ""); //过滤frameset html = regex9.Replace(html, ""); html = html.Replace(" ", ""); html = html.Replace("</strong>", ""); html = html.Replace("<strong>", ""); return html; } |