`
JerryWang_SAP
  • 瀏覽: 527337 次
  • 性別: Icon_minigender_1
  • 來自: 西安
文章分類
社區版塊
存檔分類
最新評論

我自己開發的工具,打印出百度貼吧某用戶發表過的所有帖子

閱讀更多
<html>
<meta charset="UTF-8"/> 
<style>
a {
    color: green;
    font-family: arial;
    font-weight: bold
}
</style>
<body>
    <div id="container"></div>
</body>
<script src="jquery1.7.1.js">
/* Jerry 2017-02-06 14:58PM update
 should use C:\MyApp\Chrome\Application\chrome.exe --user-data-dir="C:/yaas" --disable-web-security
 and then FIRST LOG ON BAIDU successfully!!!!

*/

</script>
<script>
/* Jerry 2017-02-05 5:54PM
這個警告的意思是說:請求的資源可能會被(擴展/或其他什么機制)屏蔽掉。

之所以會出現這個警告,是因為去獲取該資源的請求其實并(還)沒有真的發生,所以 Header 里顯示的是偽信息,直到服務器真的有響應返回,這里的 Header 信息才會被更新為真實的。不過這一切也可能不會發生,因為該請求可能會被屏蔽。比如說 AdBlock 什么的,當然了不全是瀏覽器擴展,具體情況具體分析了。

對了,別忘了用 chrome://net-internals 來幫助你查找被屏蔽的請求以及可能的原因。
*/

var PREFIX = "http://tieba.baidu.com";
var START = "http://tieba.baidu.com/i/i/my_tie";
//var START = "http://www.baidu.com";
var POST = {};
var TOTAL = 0;
var SORTED = [];

function getTotalCount(collection){
    var count = 0;
    for( bar in collection){
        if( !collection.hasOwnProperty(bar))
            continue;
        var postList = collection[bar];
        count += postList.length;
    }
    return count;
}

function shouldEnd(previousCount) {
    TOTAL = getTotalCount(POST);
    console.log("pre: " + previousCount + " total: " + TOTAL);
    return ( previousCount == TOTAL );
}

function main() {
    var html = getPostByAJAX(START);
    handleLiChildren(html);
    var page = 2;
    while(1){
        var prevCount = getTotalCount(POST);
        var task = START + "?&pn=" + page;
        var html = getPostByAJAX(task);
        handleLiChildren(html);
        page++;
        /*
        if( page >=2 )
            break;*/
        if( shouldEnd(prevCount) )
            break;
    }
    sort();
    generate();
}

function handleLiChildren(resultString){
    var htmlDom = $(resultString);
    var liChildren = $("li", htmlDom);
    $.each( liChildren, function(i, value) {
        // if( value.className.indexOf("nav_item") != -1 )
        if( value.className)
            return true;
        if( value.innerText == "我回復的" || value.innerText == "我的精品")
            return true;
        var detail = parseDetail(value);
        insertPost(detail);
    });
}

/*
<ul>
    <li>
        <cite>2016</cite>
         <a href="/f?kw=%E5%A4%A7%E9%82%91" >尿素氮</a>
    </li>
    <li>
        <cite>2015</cite>
         <a href="/f?kw=%E5%A4%A7%E9%82%91" >尿素氮2</a>
    </li>
</ul>
*/

function getpostSource(post) {
    var source = "<li><cite>";
    source += post.date + "/<cite>";
    source += '<a href="' + post.url + '">' + post.postTitle + "</a></li>";
    return source; 
}

function getBarPostsSource(barName, posts) {
    var source = '<h1>' + barName + ': ' + posts.length + '個</h1>';
    source += "<ul>";
    for( var i = 0; i < posts.length; i++){
        var post = posts[i];
        source += getpostSource(post);
    }
    source += "</ul>";
    return source;
}

function sortNumber(a,b){
    return b.size - a.size; 
}

function sort() {
    for( barName in POST) {
        if( !POST.hasOwnProperty(barName))
            continue;
        var post = {
            name: barName,
            size: POST[barName].length
        };
        SORTED.push(post);
    }
    SORTED.sort(sortNumber);
}

function generate(){
    var div = document.getElementById("container");
    var source = "總共帖子: " + TOTAL + "個";
    for( var i = 0; i < SORTED.length; i++){
        var posts = POST[SORTED[i].name];
        source += getBarPostsSource(SORTED[i].name, posts);
    }
    div.innerHTML = source;
}

$(function(){ 
    main();
}); 


function getPostByAJAX(requestURL){
   var html = $.ajax({
    url: requestURL,
    xhrFields: {
    // The 'xhrFields' property sets additional fields on the XMLHttpRequest.
    // This can be used to set the 'withCredentials' property.
    // Set the value to 'true' if you'd like to pass cookies to the server.
    // If this is enabled, your server must respond with the header
    // 'Access-Control-Allow-Credentials: true'.
    withCredentials: true
  },
    async: false}).responseText; 
   debugger;
   return html;
}

/*
function getPostByAJAX(requestURL){
 var settings = {
        type: "GET",
        crossOrigin: true,
        url:requestURL,
        error: function(XHR,textStatus,errorThrown) {
            alert ("XHR="+XHR+"\ntextStatus="+textStatus+"\nerrorThrown=" + errorThrown);
        },
        success: function(data,textStatus) {
            debugger;
        },
        headers: {
            "Access-Control-Allow-Origin":"http://tieba.baidu.com",
            "Access-Control-Allow-Headers":"X-Requested-With"
        }
    };
    $.ajax(settings);
}
*/
/*
function getPostByAJAX(requestURL){
   var html = $.ajax({
    url: requestURL,
    dataType:"jsonp",
    xhrFields: {
    // The 'xhrFields' property sets additional fields on the XMLHttpRequest.
    // This can be used to set the 'withCredentials' property.
    // Set the value to 'true' if you'd like to pass cookies to the server.
    // If this is enabled, your server must respond with the header
    // 'Access-Control-Allow-Credentials: true'.
    withCredentials: true
  },
    async: false}).responseText; 
   return html;
}
*/
function insertPost(postDetail){
    if( !POST[postDetail.barName]){
        POST[postDetail.barName] = [];
    }
    POST[postDetail.barName].push(postDetail);
}

function parseDetail(liNode) {
    var cite = $("cite", liNode);
    var date = cite[0].innerHTML; // value1
    var tds = $("td", liNode);
    var a1 = $("a", tds[0]);
    var barName = a1[0].innerHTML; // value2
    var a2 = $("a", tds[1]);
    var postTitle = a2[0].innerHTML; // value3
    var url = PREFIX + a2.attr("href");
    return {
        date: date,
        barName: barName,
        postTitle: postTitle,
        url: url
    }
}
function getTestData(){
    return '<!DOCTYPE html><html><body><div class="wrap1"><div class="wrap2"><div ' + 
    ' id="main_wrapper" class="main_wrapper"><div id="main_back_img"><div ' + 
    ' id="main_back_bottom"><div id="container" class="ibody clearfix"><div><div ' + 
    ' id="content"><div class="simple_block_container"><ul><li><cite>2-16</cite>' + 
    '<div class="wrap_container"><table><tr><td class="nowrap">在<a style="" ' +
    ' href="/f?kw=%E5%A4%A7%E9%82%91" target="_blank">ANDROID吧</a> 發貼</td><td class="wrap">' + 
    '<a href="/p/4356641476?pid=84106363194&amp;cid=0#841063631" class="thread_title"  target="_blank">硬盤</a></td>' +
    '</tr></table></div><div class="clear"></div></li>' + 
    '<li></li><li></li></ul></div></div></div></div></div></div></div></div></body></html>';
}
</script>
</html>
0
0
分享到:
評論
Global site tag (gtag.js) - Google Analytics 开心农场种蔬菜赚钱 极速赛车下 金牛配资网是否合法 武汉晃晃最新版下载 可以赚钱的网页游戏 2018长期投资股 喜迎棋牌游戏官网 码和不码是啥意思 原油下跌利好哪些股 幸运赛车计划神器 单机捕鱼达人2旧版 长春手机科乐麻将挂免费版 pk10最牛稳赚计划软件 网上怎么做兼职赚钱 天津麻将游戏 白小l姐资料图库 今日大盘股市分析