如何截取html的子字符串作为内容摘要代码,Asp.Net代码库,德仔网

代码语言
代码分类
【Asp.Net】如何截取html的子字符串作为内容摘要
作者:Dezai.CN / 发布于2012/2/15/ 448
<div>
<div class="container">
<div class="line number1 index0 alt2">"csharp keyword">public  "csharp keyword">static "csharp keyword">string "csharp plain">HtmlSummary("csharp keyword">string "csharp plain">content,  "csharp keyword">int "csharp plain">length) </div>
<div class="line number2 index1 alt1">"csharp plain">{ </div>
<div class="line number3 index2 alt2">"csharp spaces">    "csharp comments">//如果输入字符串长度小于截取长度，直接返回 </div>
<div class="line number4 index3 alt1">"csharp spaces">    "csharp keyword">if "csharp plain">(content.Length <= length) "csharp keyword">return "csharp plain">content;  </div>
<div class="line number5 index4 alt2">"csharp spaces">    "csharp comments">//如果输入字符串竟未包含html代码，那就直接截取 </div>
<div class="line number6 index5 alt1">"csharp spaces">    "csharp keyword">if "csharp plain">(!content.Contains("csharp string">"<""csharp plain">)) "csharp keyword">return "csharp plain">content.Substring(0, length); </div>
<div class="line number7 index6 alt2">"csharp spaces">    "csharp comments">//如果输入字符串中包含手动截取标记，则返回标记前的内容 </div>
<div class="line number8 index7 alt1">"csharp spaces">    "csharp keyword">if "csharp plain">(content.Contains("csharp string">"<!-- summary end -->""csharp plain">)) "csharp keyword">return "csharp plain">Regex.Split(content, "csharp string">"<!-- summary end -->""csharp plain">)[0]; </div>
<div class="line number9 index8 alt2"></div>
<div class="line number10 index9 alt1">"csharp spaces">    "csharp plain">var IsTag =  "csharp keyword">false"csharp plain">;  "csharp comments">//当前字符是否在标签中 </div>
<div class="line number11 index10 alt2">"csharp spaces">    "csharp plain">var Summary =  String.Empty; "csharp comments">//截取的子字符串 </div>
<div class="line number12 index11 alt1">"csharp spaces">    "csharp plain">var TagName =  String.Empty; "csharp comments">//当前标签名称 </div>
<div class="line number13 index12 alt2">"csharp spaces">    "csharp plain">var TagArray =  "csharp keyword">new "csharp plain">{ Left  = "csharp keyword">new "csharp plain">ArrayList(), Right = "csharp keyword">new "csharp plain">ArrayList() };  "csharp comments">//左标签数组、右标签数组 </div>
<div class="line number14 index13 alt1"></div>
<div class="line number15 index14 alt2">"csharp spaces">    "csharp plain">content =  FixHtml(content); </div>
<div class="line number16 index15 alt1"></div>
<div class="line number17 index16 alt2">"csharp spaces">    "csharp keyword">foreach  "csharp plain">(var current "csharp keyword">in "csharp plain">content)  </div>
<div class="line number18 index17 alt1">"csharp spaces">    "csharp plain">{ </div>
<div class="line number19 index18 alt2">"csharp spaces">        "csharp keyword">if  "csharp plain">(length <= 0) "csharp keyword">break"csharp plain">; "csharp comments">//在截取长度>0的情况下，循环遍历html字符 </div>
<div class="line number20 index19 alt1"></div>
<div class="line number21 index20 alt2">"csharp spaces">        "csharp keyword">if  "csharp plain">(current == "csharp string">'<'"csharp plain">) "csharp comments">//当前字符为<，进入html标签 </div>
<div class="line number22 index21 alt1">"csharp spaces">        "csharp plain">{ </div>
<div class="line number23 index22 alt2">"csharp spaces">            "csharp plain">IsTag =  "csharp keyword">true"csharp plain">;  </div>
<div class="line number24 index23 alt1">"csharp spaces">        "csharp plain">} </div>
<div class="line number25 index24 alt2">"csharp spaces">        "csharp keyword">else  "csharp keyword">if "csharp plain">(current ==  "csharp string">'>'"csharp plain">)  "csharp comments">//当前字符为>，移出html标签 </div>
<div class="line number26 index25 alt1">"csharp spaces">        "csharp plain">{ </div>
<div class="line number27 index26 alt2">"csharp spaces">            "csharp comments">//如果当前标签名称以/开头，则此标签为闭合标签，应加入右标签数组 </div>
<div class="line number28 index27 alt1">"csharp spaces">            "csharp keyword">if  "csharp plain">(TagName.Trim().StartsWith("csharp string">"/""csharp plain">)) </div>
<div class="line number29 index28 alt2">"csharp spaces">                "csharp plain">TagArray.Right.Add(TagName); </div>
<div class="line number30 index29 alt1">"csharp spaces">            "csharp comments">//否则应加入左标签数组，但应考虑自闭合标签不加入闭合标签数组 </div>
<div class="line number31 index30 alt2">"csharp spaces">            "csharp keyword">else "csharp keyword">if "csharp plain">(!TagName.Trim().EndsWith("csharp string">"/""csharp plain">) &&  !"csharp string">"img|br|input""csharp plain">.Split("csharp string">'|'"csharp plain">).Contains(TagName.ToLower())) </div>
<div class="line number32 index31 alt1">"csharp spaces">                "csharp plain">TagArray.Left.Add(TagName.Trim().ToLower().Split("csharp string">' '"csharp plain">)[0]); </div>
<div class="line number33 index32 alt2"></div>
<div class="line number34 index33 alt1">"csharp spaces">            "csharp plain">IsTag =  "csharp keyword">false"csharp plain">;  "csharp comments">//标记已移出html标签 </div>
<div class="line number35 index34 alt2">"csharp spaces">            "csharp plain">TagName =  String.Empty; "csharp comments">//完成标签加入标签数组后，应重置此变量  </div>
<div class="line number36 index35 alt1">"csharp spaces">        "csharp plain">} </div>
<div class="line number37 index36 alt2">"csharp spaces">        "csharp keyword">else</div>
<div class="line number38 index37 alt1">"csharp spaces">        "csharp plain">{ </div>
<div class="line number39 index38 alt2">"csharp spaces">            "csharp keyword">if  "csharp plain">(IsTag) "csharp comments">//如果在html标签中，则拼积当前标签名称 </div>
<div class="line number40 index39 alt1">"csharp spaces">                "csharp plain">TagName  += current; </div>
<div class="line number41 index40 alt2">"csharp spaces">            "csharp keyword">else "csharp comments">//否则为纯文本内容，计数器开始自减，直到减为0，循环退出 </div>
<div class="line number42 index41 alt1">"csharp spaces">                "csharp plain">length--; </div>
<div class="line number43 index42 alt2">"csharp spaces">        "csharp plain">} </div>
<div class="line number44 index43 alt1"></div>
<div class="line number45 index44 alt2">"csharp spaces">        "csharp plain">Summary +=  current; "csharp comments">//拼积截取的子字符串 </div>
<div class="line number46 index45 alt1">"csharp spaces">    "csharp plain">} </div>
<div class="line number47 index46 alt2"></div>
<div class="line number48 index47 alt1">"csharp spaces">    "csharp plain">Summary =  Summary.Trim(); </div>
<div class="line number49 index48 alt2"></div>
<div class="line number50 index49 alt1">"csharp spaces">    "csharp comments">//从左标签数组中移除已闭合的标签  </div>
<div class="line number51 index50 alt2">"csharp spaces">    "csharp comments">//TagArray.Left.RemoveRange(0, TagArray.Right.Count);  </div>
<div class="line number52 index51 alt1">"csharp spaces">    "csharp keyword">while "csharp plain">(TagArray.Right.Count > 0) </div>
<div class="line number53 index52 alt2">"csharp spaces">    "csharp plain">{ </div>
<div class="line number54 index53 alt1">"csharp spaces">        "csharp plain">TagArray.Left.RemoveAt(TagArray.Left.IndexOf(TagArray.Right[0].ToString().Replace("csharp string">"/""csharp plain">,"csharp string">"""csharp plain">))); </div>
<div class="line number55 index54 alt2">"csharp spaces">        "csharp plain">TagArray.Right.RemoveAt(0); </div>
<div class="line number56 index55 alt1">"csharp spaces">    "csharp plain">} </div>
<div class="line number57 index56 alt2"></div>
<div class="line number58 index57 alt1">"csharp spaces">        "csharp comments">//剩余标签未闭合，逆序以html闭合标签格式拼接至截取的子字符串末尾 </div>
<div class="line number59 index58 alt2">"csharp spaces">        "csharp keyword">if  "csharp plain">(TagArray.Left.Count > 0) </div>
<div class="line number60 index59 alt1">"csharp spaces">            "csharp keyword">for  "csharp plain">(var i = TagArray.Left.Count - 1; i >= 0; i--)  </div>
<div class="line number61 index60 alt2">"csharp spaces">            "csharp plain">{  </div>
<div class="line number62 index61 alt1">"csharp spaces">                "csharp plain">Summary  += String.Format("csharp string">"</{0}>""csharp plain">, TagArray.Left[i].ToString()); </div>
<div class="line number63 index62 alt2">"csharp spaces">            "csharp plain">}  </div>
<div class="line number64 index63 alt1"></div>
<div class="line number65 index64 alt2">"csharp spaces">    "csharp keyword">return  "csharp plain">Summary; </div>
<div class="line number66 index65 alt1">"csharp plain">}</div>
</div>
</div>
试试其它关键字
　windvoice　
同语言下
可能有用的
Dezai.CN贡献的其它代码(4037)