时间:2021-07-01 10:21:17 帮助过:15人阅读
使用asp.net或者asp检查某个url地址,某篇文章是否被搜索引擎,如百度,谷歌,搜狗收录。
实现原理:直接搜索你那篇文章的url地址(不带协议,但上协议也行,代码会自动去掉协议内容),如果被索引会返回搜索结果,否则会提示找不到信息。
Asp.Net检查百度,谷歌,搜狗搜索引擎是否收录文章网址源代码:
using System; using System.Net; using System.Text; using System.IO; using System.Web; public class SearchEngineIndex { public static string[] urls = { //搜索引擎检查地址 "http://www.baidu.com/s?ie=utf-8&wd=",//百度索引url检查地址 "https://www.google.com.hk/search?q=",//谷歌索引url检查地址 "http://www.sogou.com/web?ie=utf8&query="//搜狗索引url检查地址 } , noFindKeyword = { "抱歉,没有找到与", "找不到和您的查询", "未收录?" };//搜索引擎未索引url地址时的关键字 /// <summary> /// 获取响应的编码 /// </summary> /// <param name="contenttype"></param> /// <returns></returns> private static Encoding GetEncoding(string contenttype) { if (!string.IsNullOrEmpty(contenttype)) { contenttype = contenttype.ToLower(); if (contenttype.IndexOf("gb2312") != -1 || contenttype.IndexOf("gbk") != -1) return Encoding.GetEncoding(936); if (contenttype.IndexOf("big5") != -1) return Encoding.GetEncoding(950); } return Encoding.UTF8; } /// <summary> /// 使用HttpWebRequest对象,自动识别字符集 /// </summary> /// <param name="url"></param> /// <param name="addUseragent">是否添加UserAgent,采集其他网站时防止被拦截</param> /// <returns></returns> public static string GetHtml(string url, bool addUseragent) { HttpWebRequest request = (HttpWebRequest)HttpWebRequest.Create(url); if (addUseragent) request.UserAgent = "Googlebot|Feedfetcher-Google|Baiduspider"; string html = null; try { HttpWebResponse response = (HttpWebResponse)request.GetResponse(); StreamReader srd = new StreamReader(response.GetResponseStream(), GetEncoding(response.ContentType)); html = srd.ReadToEnd(); srd.Close(); response.Close(); } catch { } return html; } /// <summary> /// 检查某个url是否被搜索引擎索引 /// </summary> /// <param name="url">url地址</param> /// <param name="engin">0:百度 1:谷歌 2:搜狗,其他搜索引擎如bing和360直接查网址显示的结果不是直接得到网址的,有些出入,不做检查</param> /// <returns></returns> public static bool CheckIndex(string url, int engin) { if (string.IsNullOrEmpty(url)) return false; if (engin < 0 || engin > 2) engin = 0; url = urls[engin] + HttpUtility.UrlEncode(url.ToLower().Replace("http://", "").Replace("https://", "")); bool r = true; string html = GetHtml(url, true); if (html == null || html.IndexOf(noFindKeyword[engin]) != -1) r = false; return r; } } //调用方法示例 SearchEngineIndex.CheckIndex("www.gxlcms.com/article/20101014/2902.aspx", 0);//检查百度索引 SearchEngineIndex.CheckIndex("www.gxlcms.com/article/20101014/2902.aspx", 1);//检查谷歌索引 SearchEngineIndex.CheckIndex("www.gxlcms.com/article/20101014/2902.aspx", 2);//检查搜狗索引
Asp检查百度,谷歌,搜狗搜索引擎是否收录文章网址源代码:
<% class SearchEnginIndex dim urls,noFindKeyword private sub Class_Initialize '百度,谷歌,搜狗url地址索引查询地址 urls=array("http://www.baidu.com/s?ie=utf-8&wd=","https://www.google.com.hk/search?q=","http://www.sogou.com/web?ie=utf8&query=") '搜索引擎未索引url地址时的关键字 NoFindKeyword=array("抱歉,没有找到与", "找不到和您的查询", "未收录?") End sub private function GetEncoding(contenttype) contenttype=lcase(contenttype) if instr(contenttype,"gb2312")<>0 and instr(contenttype,"gbk")<>0 then GetEncoding="gb2312" elseif instr(contenttype,"big5")<>0 then GetEncoding="big5" else GetEncoding="utf-8" end if end function private function BinToString(bin,encoding)'将2进制流数据依据编码转为对应的字符串内容 dim obj set obj=Server.CreateObject("Adodb.Stream") obj.Type=1:obj.Mode=3:obj.Open obj.Write bin obj.Position=0:obj.Type=2:obj.Charset=encoding BinToString=obj.ReadText obj.Close:set obj=nothing end function public function GetHtml(url) dim xhr set xhr=server.CreateObject("microsoft.xmlhttp") xhr.open "get",url,false xhr.send encoding=GetEncoding(xhr.getResponseHeader("content-type")) response.CharSet=encoding GetHtml=BinToString(xhr.responsebody,encoding) set xhr=nothing end function public function CheckIndex(url,engin) if len(url)=0 then exit function if engin<0 or engin>2 then engin=1 url=urls(engin)&server.URLEncode(url) dim html html=GetHtml(url) CheckIndex=instr(html,NoFindKeyword(engin))=0 End function end Class set sei=new SearchEnginIndex response.Write sei.CheckIndex("www.gxlcms.com/article/20101014/2902.aspx",0)'百度索引 response.Write sei.CheckIndex("www.gxlcms.com/article/20101014/2902.aspx",1)'谷歌索引 response.Write sei.CheckIndex("www.gxlcms.com/article/20101014/2902.aspx",2)'搜狗索引 set sei=nothing %>