为了网站做SEO的需要，统计网站的页面收录率，写个小工具，目前虽然还不完善，但很想跟大家分享一下。
使用方法，可以先用sitemapX软件，生成网站链接的列表，这个列表比较靠谱，因为网站内部能链接到的网站基本都是比较重要的页面。
把生成的列表粘贴进小工具，查询即可。--目前如果一次请求过多，会出现被百度屏蔽的情况，目前还没解决，大家有啥好的方案可以分享来哈！
测试地址：http://zhidong10.com/site_rs_baidu/baidu.php
以后会增加：收录、未收录筛选，手动设置请求参数，数据导出，未收录重新检测等。2013-03-23
废话不多说，上代码。
发送请求、数据展现：
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> <html xmlns="http://www.w3.org/1999/xhtml"> <head> <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <title>百度收录查询</title> <link href="css/reset.css" rel="stylesheet" type="text/css" /> <link href="css/ui.css" rel="stylesheet" type="text/css" /> <script type="text/javascript" src="js/jquery-1.7.1.min.js"></script> </head> <body> <h1 class="tit">百度收录查询</h1> <div class="enterbox"> <textarea id="TextBox1" ></textarea> </div> <div class="sub_btn"><a href="javascript: testGG()" >提交</a></div> <div class="resutl_tit">查询结果：</div> <div id="maindiv"> <div id="div3" style=" 750px;"><!--<a href="javascript:void(0);" title="点击重新查询"><img src="image/rst.gif"></a><span id="rehome">←重新查询</span>--> <!--<div onclick="_export()" id="div_export"></div>--> <div id="div4"><span id="num_total">总:</span><span id="num_total2">0</span><span id="num_sl">收录:</span><span id="num_sl2">0</span><span id="num_nosl">未收录:</span><span id="num_nosl2">0</span><span id="percent">收录率:</span><span id="num_pct"></span></div> </div> <table class="tb1"> <colgroup> <col id="col1"> <col id="col2" /> <col id="col3" /> <col id="col4" /> <col id="col5" /> </colgroup> <thead id="thead"> <tr> <th scope="col"><span>No.</span></th> <th scope="col"><span>标题</span></th> <th scope="col"><span>网址</span></th> <th scope="col" class="th2"><div id="div5"><img src="image/sort.gif" id="s1"></div> <span id="sp">收录</span></th> <th style="border-bottom:1px solid #a5a5a5;border-right:1px solid #a5a5a5" scope="col" class="kz"><span>快照</span></th> </tr> </thead> </table> </div> <script type="text/javascript"> var count = { total:0, time : '', url_list:"", star:0 }; function get_rs(url, num){ var url =url; var num =num; $.ajax({ url: "rs.php?site="+url+"&time="+ new Date().getTime(), dataType:"json", success: function(data){ var title = $("#tr"+num).find(".title"); var rs = $("#tr"+num).find(".yo div"); var kz = $("#tr"+num).find(".kz div"); if(!data) { title.html("数据异常"); console.log("data:"+data) return; } if(data.error == 1){ title.html(data.title); rs.attr("class","iconwarn"); kz.attr("class",""); kz.html("-"); } if(data.error == 0){ title.html(data.title); rs.attr("class","iconok"); kz.attr("class",""); kz.html(data.date); } $("#num_sl2").html($(".yo .iconok").length); $("#num_nosl2").html($(".yo .iconwarn").length); var per = Math.floor(($(".yo .iconok").length/count.total)*100) $("#num_pct").html(per+"%") }, error:function(){ } }); } function testGG(){ //清除旧数据 $(".tb1 tbody tr").remove(); count = { total:0, time : '', url_list:"", star:0 }; $("#num_total2").html("0"); $("#num_sl2").html("0"); $("#num_nosl2").html("0"); $("#num_pct").html(""); var txt = document.getElementById("TextBox1"); count.url_list = txt.value.split("\n"); count.total = count.total + count.url_list.length; $("#num_total2").html(count.total); count.time = setInterval(function(){ run(); }, 1000);//1000毫秒执行一次，防止百度屏蔽攻击 } function run(){ var len = count.url_list.length; if(count.star < len){ var order = (count.star%2==0?"odd1":"odd"); var url = $.trim(count.url_list[count.star]); url = url.substr(0,7).toLowerCase()=="http://"?url:"http://"+url; var str = ''; str = '<tr class="'+order+'" id="tr'+count.star+'"> <td class="num">'+(count.star+1)+'</td><td class="title">-</td><td class="url2"><a href="'+url+'" target="_blank">'+url+'</a></td><td class="yo"><div class="iconloading"></div></td><td class="kz" style="border:1px;"><div class="iconloading"> </div></td></tr>'; $(".tb1").append(str); get_rs(url,count.star); count.star++; }else{ clearInterval(count.time); } } </script> </body> </html>
请求处理
<?php //$site = 'http://xsh.changyou.com/dhsh/events/events.shtml'; $site = $_GET['site']; function fs($r, $t) {//无法匹配到时，返回 $finfo = array('error' => 1, 'title' => $t); $fInfo = json_encode($finfo); if (!$r) { return $fInfo; } if (!$r[0]) { return $fInfo; } if (!$r[0][0]) { return $fInfo; } } function str_substr($start, $end, $str) { // 字符串截取函数 $temp = explode($start, $str, 2); $content = explode($end, $temp[1], 2); return $content[0]; } function curl_file_get_contents($durl) { $ch = curl_init(); curl_setopt($ch, CURLOPT_URL, $durl); curl_setopt($ch, CURLOPT_TIMEOUT, 20); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); $rs = curl_exec($ch); curl_close($ch); return $rs; } //$buffer = @file_get_contents("http://www.baidu.com/s?wd=" . $site); $buffer = @file_get_contents("http://www.baidu.com/s?wd=" . $site); //返回输出文本流 $d = @file_get_contents($site); if (!$d) { $s = "路径不存在"; $finfo = array('error' => 1, 'title' => $s); $fInfo = json_encode($finfo); echo $fInfo; return; } else { $s = str_substr("<title>", "</title>", $d); } preg_match_all("/<table[^>]+>.+?<\/table>/", $buffer, $r); $tmp = fs($r, $s); if ($tmp) { echo $tmp; return; } preg_match_all("/<span[^>]+>.+?<\/span>/", $r[0][0], $r); $tmp = fs($r, $s); if ($tmp) { echo $tmp; return; } //$txt = '<span class="g"> <b>xsh.changyou.com</b>/<b>dhsh</b>/<b>events</b>/events... 2013-1-27 </span>'; //echo $txt; preg_match_all("/(\d{4}-\d+-\d+)/", $r[0][0], $r); $tmp = fs($r, $s); if ($tmp) { echo $tmp; return; } $info = array('error' => 0, 'date' => $r[0][0], 'title' => $s); $userinfo = json_encode($info); echo $userinfo; ?>
svn: http://php-rss-ajax.googlecode.com/svn/trunk/site_rs_baidu
源码下载：猛击此处
反馈可以留言拍砖，或者发邮箱里：zhidong10@foxmail.com