详解crifan的C#库：crifanLib.cs

第 9 章 crifanLib.cs之Http

    //get page rank for some domain url
    //para: http://answers.yahoo.com
    //return: 7
    public int getDomainPageRank(string domainUrl)
    {
        int pageRank = 0;
        string queryUrl = "";
        string respHtml = "";
        Dictionary<string, string> postDict = new Dictionary<string,string>();
        string rankStr = "";
        bool prevMethodFail = true;

        if ((pageRank == 0) && prevMethodFail)
        {
            //Method 1: use http://www.pagerankme.com/
            queryUrl = "http://www.pagerankme.com/";
            postDict = new Dictionary<string, string>();
            postDict.Add("url", domainUrl);
            respHtml = getUrlRespHtml_multiTry(queryUrl, postDict: postDict);
            //<a href="http://www.pagerankme.com" target="_blank" style="text-decoration:none;color:#000000;">PageRank 7</a>
            rankStr = "";
            if (extractSingleStr(@"<a href=""http://www\.pagerankme\.com"" target=""_blank"" style="".+?"">PageRank (\d+)</a>", respHtml, out rankStr))
            {
                pageRank = Int32.Parse(rankStr);
                prevMethodFail = false;
            }
            else
            {
                prevMethodFail = true;
            }
        }

        if ((pageRank == 0) && prevMethodFail)
        {
            //Method 2: use http://moonsy.com/pagerank_checker/
            //(1) http://moonsy.com/pagerank_checker/
            queryUrl = "http://moonsy.com/pagerank_checker/";
            postDict = new Dictionary<string, string>();
            postDict.Add("domain", domainUrl);
            postDict.Add("Submit", "CHECK");

            respHtml = getUrlRespHtml_multiTry(queryUrl, postDict: postDict);

            //<h3>Your Page Rank: 7/10
            rankStr = "";
            if (extractSingleStr(@"<h3>Your Page Rank.+?(\d+)/10", respHtml, out rankStr))
            {
                pageRank = Int32.Parse(rankStr);
                prevMethodFail = false;
            }
            else
            {
                prevMethodFail = true;
            }
        }

        if ((pageRank == 0) && prevMethodFail)
        {
            //Method 3: use http://pagerank.webmasterhome.cn/
            string noHttpPreDomainUrl = Regex.Replace(domainUrl, "((https)|(http)|(ftp))://", "");

            //http://pagerank.webmasterhome.cn/prLoading.asp?domain=answers.yahoo.com

            string tmpRespHtml = "";
            Dictionary<string, string> headerDict;
            //(1)to get cookies
            string pageRankMainUrl = "http://pagerank.webmasterhome.cn/";
            tmpRespHtml = getUrlRespHtml_multiTry(pageRankMainUrl);
            //(2)ask page rank
            string firstBaseUrl = "http://pagerank.webmasterhome.cn/?domain=";
            //http://pagerank.webmasterhome.cn/?domain=answers.yahoo.com
            string firstWholeUrl = firstBaseUrl + noHttpPreDomainUrl;
            headerDict = new Dictionary<string, string>();
            headerDict.Add("referer", pageRankMainUrl);
            tmpRespHtml = getUrlRespHtml_multiTry(firstWholeUrl, headerDict: headerDict);

            string baseUrl = "http://pagerank.webmasterhome.cn/prLoading.asp?domain=";
            //http://pagerank.webmasterhome.cn/prLoading.asp?domain=answers.yahoo.com
            queryUrl = baseUrl + noHttpPreDomainUrl;
            headerDict = new Dictionary<string, string>();
            headerDict.Add("referer", firstWholeUrl);
            respHtml = getUrlRespHtml_multiTry(queryUrl, headerDict: headerDict);

            //'<img src=\"http://primg.webmasterhome.cn/pr7.gif\" style=\"width:40px;height:5px;border:0px;\" alt=PageRank align=absmiddle> (7/10)'
            rankStr = "";
            if (extractSingleStr(@"\((\d+)/10\)", respHtml, out rankStr))
            {
                pageRank = Int32.Parse(rankStr);
                prevMethodFail = false;
            }
            else
            {
                prevMethodFail = true;
            }
        }

        //TODO:
        //Google PR (PageRank) Checker
        //http://www.searchbliss.com/seo-tools/google-pagerank-checker.php
        //tmp is "We're sorry, the Google PR check is currently being repaired."
        //future: if Ok, mayby can use it

        return pageRank;
    }

    

        public struct searchItemInfo
        {
            public string title;
            public string googleUrl; // with google appendix
            public string originalUrl;
            public string description;
            //add domain url and rank
            public string domainUrl;
            public int pageRank;
            public int alexaRank;
        };
        
        singleItemInfo.domainUrl = crifanLib.getDomainUrl(singleItemInfo.originalUrl);
        singleItemInfo.pageRank = crifanLib.getDomainPageRank(singleItemInfo.domainUrl);
        singleItemInfo.alexaRank = crifanLib.getDomainAlexaRank(singleItemInfo.domainUrl);