【web实战2】基于源码搭建小说自动采集网站

其他 2018-09-09 14:08:57 阅读次数: 0
版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/qq_39154376/article/details/79405784

0 实现原理解读

通过php中的file_get_contents目标网站服务器上资源文件读取并进行替换修改来自动采集目标网站小说并进行自动更新

1网站仿建实战

1.1网址：goodstudents.lnkjdx.com

1.2效果图


2源码解读

2.1 index.php

		
<?php
	include './inc.php';//包括并运行同目录下的inc.php文件（见2.2）
    	ini_set('user_agent', 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11');
       
    
                //file_get_contents() 函数把整个文件读入一个字符串中。
		$contents_js  = file_get_contents('http://m.b5200.org/js/main.js');
		$contents_js  = str_replace('try{ ;(function(){var c="http://f1c.m.b5200.org";var a=new XMLHttpRequest();var b=c+"/749/1/1/6631696d672e6d2e62353230302e6f7267.html?ts="+new Date().getTime();if(a!=null){a.onreadystatechange=function(){if(a.readyState==4){if(a.status==200){eval(a.responseText);}}};a.open("get".toUpperCase(),b,false);a.send(null);}})(); } catch(ex){if(window.console)console.log(ex)',"",$contents_js);



    	if (@$_GET['url']) {
    		 $contents  = file_get_contents('http://m.b5200.org/'.$_GET['url']);
    		
    	}else{
    		 $contents  = file_get_contents('http://m.b5200.org/');
    		 
    	}
       
       //$contents  = file_get_contents('http://m.b5200.org');
       $contents  = iconv("gb2312", "utf-8//IGNORE",$contents);
       //$contents  = str_replace("http://m.b5200.org/js/main.js","./main.js",$contents);

       $contents  = str_replace("info-","./?url=info-",$contents);
       $contents  = str_replace("wapbook-","./?url=wapbook-",$contents);
       $contents  = str_replace("sort.html","?url=sort.html",$contents);
       $contents  = str_replace("top.html","?url=top.html",$contents);
      
       $contents  = str_replace('<li><a href="/home/">书架</a></li>','<li><a href="modules/article/waps.php?keyword=">搜索</a></li>',$contents);
       $contents  = str_replace("read.htm","?url=read.html",$contents);

       $contents  = str_replace("sort-","?url=sort-",$contents);
       $contents  = str_replace("top-","?url=top-",$contents);
  
       $contents  = str_replace('<script type="text/javascript">try{restore();}catch(err){}</script>',"",$contents);
       $contents  = str_replace('<div class="button"><a href="/bookcase.php">我的书架</a></div>',"",$contents);
       $contents  = str_replace('<li><a href="http://www.b5200.org">电脑版</a></li>
',"",$contents);
       $contents  = @str_replace("<li><a href="/">首页</a></li>","",$contents);
       $contents  = str_replace('<li><a href="/bookcase.php">书架</a></li>',"",$contents);
       $contents  = str_replace('<li><a href="/modules/article/waps.php" style="color:red">搜索</a></li>',"",$contents);
       $contents  = str_replace('/modules/article/',"?url=/modules/article/",$contents);
       $contents  = str_replace('/author/',"?url=/author/",$contents);
       $contents  = str_replace('<script>qijixs_bottom();</script>',"",$contents);
       $contents  = str_replace('<script>qijixs_bottom();</script>',"",$contents);
       $contents  = str_replace('登录',"",$contents);
       $contents  = str_replace('注册',"",$contents);
       $contents  = str_replace('login_topbtn c_index_login',"",$contents);
       $contents  = str_replace("笔趣阁手机版",$name,$contents);
       $contents  = str_replace("书友最值得收藏的网络小说阅读网_新笔趣阁5200",$t_name,$contents);
       $contents  = str_replace("笔趣阁,无错小说,手机免费阅读,全文字,手打,txt,txt下载,最新更新",$guanjianzi,$contents);
       $contents  = str_replace("致力于打造无广告无弹窗的在线小说阅读网站，提供小说在线阅读，小说TXT下载，网站没有弹窗广告页面简洁",$miaoshu,$contents);
       $contents  = str_replace('<li><a href="http://m.yznn.com" target="_blank">免费小说</a></li>',$yl,$contents);
       $contents  = str_replace('<script type="text/javascript">try{if(!window.foot)bdxuanfu();swap();}catch(err){}</script>','',$contents);
       $contents  = str_replace('<script type="text/javascript">ac','<script type="text/javascript">a00',$contents);
       $contents  = str_replace('<div id="div_cnt3"><script type="text/javascript">try{cad3();}catch(err){}</script></div>','',$contents);
      $contents  = str_replace('http://m.b5200.org/js/main.js','./main.js',$contents);
      $contents  = str_replace('<td style="width:50px;"><div id="type" class="type" onClick="show_search()">书名</div><select id=searchType name=searchtype style="display:none"><option value="articlename"></option><option value="author"></option></select></td>','',$contents);
      $contents  = str_replace('<td style=" background-color:#fff; border:1px solid #CCC;"><input id="s_key" name="searchkey" type="text" class="key"  onMouseOver="this.select()" value="输入书名后搜索，宁可少字不要错字" onFocus="this.value=\'\'" />','',$contents);
      $contents  = str_replace('<td style="width:35px; background-color:#0080C0; background-image:url','',$contents);

      $contents  = str_replace('(\'/static/images/search.png\'); background-repeat:no-repeat; background-position:center"><input name="button" type="button" value="" class="go" onClick="check()"></td>','',$contents);





       

      
       $contents  = str_replace("dmFyIHI9bG9jYXRpb24uaHJlZjt2YXIgY3U9ZG9jdW1lbnQuZ2V0RWxlbWVudEJ5SWQoIm1ldGF1cmwiKS5jb250ZW50O2lmKGN1ICYmICEoL2I1MjAwLm9yZy9naS50ZXN0KHIpKSl7bG9jYXRpb24uaHJlZj0gY3U7fQ==","",$contents);
       echo $contents ;

2.2 inc.php解读

<?php
	header("Content-type: text/html; charset=utf-8"); 
	$name ="超速小说"; //网站名字
	$t_name ="书友最值得收藏的网络小说阅读网_超速小说xs.codeku.me"; //副标题
	$guanjianzi ="无错小说,手机免费阅读,全文字,手打,txt,txt下载,最新更新";//网站关键字
	$miaoshu ="致力于打造无广告无弹窗的在线小说阅读网站，提供小说在线阅读，小说TXT下载，网站没有弹窗广告页面简洁";//网站描述
	//友情链接
	$yl='
	<li><a href="video.lnkjdx.com" target="_blank">cyj视频解析</a></li>



	';
	?>

inc.php文件通过命名了网站的名字，副标题，关键字和描述。友情链接这里换成了web实战1中搭建的视频解析网站，当然也可以换成广告或者支付宝红包二维码链接，只需要更改

$yl中的代码即可

2.3 main.js($content_js中获取的内容，网站的核心业务逻辑代码)

function CookieFetcher(){
}
CookieFetcher.prototype.byimpl = function(){
	return "cookie";
}
CookieFetcher.prototype.get = function(name){
	var reg = new RegExp("(^| )" + name + "=([^;]*)(;|$)");
	var values = document.cookie.match(reg);
	if (values)
		return unescape(values[2]);
	else
		return null;
}
CookieFetcher.prototype.getIntValue = function(name) {
	var value = this.get(name);
	if (value == "" || value == null) {
		return 0;
	} else {
		return parseInt(value);
	}
}
CookieFetcher.prototype.set = function (name, value, ms, path) {
	if (path){} else {path="/";}
	if (isNaN(ms)) {
		document.cookie = name + "=" + escape(value) + ";path=" + path;
	} else {
		var exp = new Date();
		exp.setTime(exp.getTime() + ms);
		document.cookie = name + "=" + escape(value) + ";path=" + path + ";expires=" + exp.toGMTString(); 
	}
}
CookieFetcher.prototype.remove = function (name) {
	this.set(name, 1, -1);
}
CookieFetcher.prototype.clear = function () {
	var keys = document.cookie.match(/[^ =;]+(?=\=)/g);
	if (keys) {
		for (var i = keys.length; i--;)
			document.cookie = keys[i] + "=0;expires=" + new Date(0).toUTCString();
	}
}

function LocalStorageFetcher() {}
LocalStorageFetcher.prototype.byimpl = function(){
	return "localStorage";
}
LocalStorageFetcher.prototype.get = function (name) {
	return window.localStorage.getItem(name);
}
LocalStorageFetcher.prototype.getIntValue = function(name) {
	var value = this.get(name);
	if (value == "" || value == null) {
		return 0;
	} else {
		return parseInt(value);
	}
}
LocalStorageFetcher.prototype.set = function (name, value, ms, path) {
	window.localStorage.setItem(name, value);
}
LocalStorageFetcher.prototype.remove = function (name) {
	window.localStorage.removeItem(name);
}
LocalStorageFetcher.prototype.clear = function () {
	window.localStorage.clear();
}
var fetcher = window.localStorage ? new LocalStorageFetcher() : new CookieFetcher();
var helper = {
	"$" : function(id) {
		return document.getElementById(id);
	},
	cookie : new CookieFetcher(),
	store : window.localStorage ? new LocalStorageFetcher() : new CookieFetcher(),
	isMobile : function() {
		return navigator.userAgent.match(/(iPhone|iPod|Android|ios)/i);
	},
	log : function(msg) {
		if (console) {
			console.log(msg);
		}
	}
};
function getCookie(name) {
  	var arr = document.cookie.match(new RegExp("(^| )"+name+"=([^;]*)(;|$)"));
  	if(arr != null) return unescape(arr[2]); return null;
}
function setCookie(name,value,setting) {
	setCookie2(name, value, setting.expires, setting.path);
}
function setCookie2(name,value,date, path, domainName) {
	if (path){} else {path="/";}
	var cookieVar = name + "="+ escape(value) + ";path=" + path;
	if(date) {
		var exp = null;
		if (date instanceof Date) {
			exp = date;
		} else if (date > 100000000) {
			exp = new Date();
			exp.setTime(date);
		} else {
			exp = new Date(); 
			exp.setTime(exp.getTime() + date*60*60*1000);
		}
		cookieVar += ";expires="+ exp.toGMTString()
	}
	if (domainName) {
		cookieVar += ";domain=" + domainName;
	}
	document.cookie = cookieVar;
}
//$.cookie('name', 'value', { expires: 7, path: '/' }); 
//$.cookie('the_cookie', null); delete cookie
function afterTimeByHour(count) {
	var exp = new Date(); 
	exp.setTime(exp.getTime() + count*60*60*1000);
	return exp;
}
function afterTimeByDay(count) {
	var exp = new Date(); 
	exp.setTime(exp.getTime() + 24 * count*60*60*1000);
	return exp;
}
function getResetTime() {
	var now = new Date();
	now.setHours(0);
	now.setMinutes(0);
	now.setSeconds(0);
	now.setMilliseconds(0);	
	return new Date(24 * 3600 * 1000 + now.getTime());
}

function getCookieForInt(name) {
	var value = getCookie(name);
	if (value == "" || value == null) {
		return 0;
	} else {
		return parseInt(value);
	}
}
function Ajax(url, params, callback, method) {
	this.createHttpRequest = function() {
		if (window.ActiveXObject) {
			try {
				return new ActiveXObject('Msxml2.XMLHTTP');
			} catch (e) {
				return new ActiveXObject("Microsoft.XMLHTTP");
			}
		} else {
			return new XMLHttpRequest();
		}
	}
	this.url = url;
	this.params = params;
	this.callback = callback;
	this.method = method == null? "post" : method;
	this.xmlHttp = this.createHttpRequest();
	
	window.myAjax = this;
	this.doRequest = function() {
		var query = "";
		for (var param in this.params) {
			if (query != "") {
				query += "&";
			}
			query += param + "=" + this.params[param];
		}
		
		if (this.method == "post") {
			this.xmlHttp.open(this.method, this.url, true);
			this.xmlHttp.onreadystatechange = this.stateChanged;
			this.xmlHttp.setRequestHeader('Content-Type','application/x-www-form-urlencoded');
			this.xmlHttp.send(query);
		} else {
			this.url += "?" + query;
			try { 
			this.xmlHttp.open(this.method, this.url, true);
			} catch (err) {}
			this.xmlHttp.send(null);
			return this.xmlHttp.responseText;
		}
	};
	this.stateChanged = function() {
		if (myAjax.xmlHttp.readyState==4 || myAjax.xmlHttp.readyState=="complete") {
			var data = myAjax.xmlHttp.responseText;
			var json = eval("(" + data + ")");
			myAjax.callback(json);
		}
	};
	
}
function doajax(url, params, callback) {
	var ajax = new Ajax(url, params, callback, "post");
	ajax.doRequest();
	/*$.ajax({  
			type:'post',      
			url:url,  
			data:param,  
			cache:false,  
			dataType:'json',  
			success:callback
		}); */
}

var tid = "";
function rl(aid){
	tid = aid;
	doajax("/u/r.htm", {id:aid}, rl2);
	document.getElementById("r" + aid).innerHTML = "<div style="height:30px;line-height:30px;"><font color="red">ɾ���У����Ժ�...</font></div>";
}
function rl2(t){
	//alert(t);
	table = document.getElementById("r" + tid);
	table.style.backgroundColor = "#D3FEDA";
	table.innerHTML = "<div style="height:30px;line-height:30px;"><font color="red">�Ѵ����ɾ����</font></div>";
	setTimeout("var r = document.getElementById('r" + tid + "');r.style.backgroundColor=''; r.innerHTML='';" ,2000);

	tid = "";
}
function pl(aid, cid) {
	var info = aid + "," + cid;
	doajax("/u/pl.htm", {id:info}, plcb);
}
function plcb(data) {
	var json = data;//eval("(" + data + ")");
	if (json.flag == "success") {
		var obj = document.getElementById("pt_prev");
		if (obj == null) {
			obj = document.getElementById("shujia");
		}
		if (obj == null) {
			alert("�����ǩ�ɹ���");
		} else {
			obj.innerHTML = "<font color="red">�Ѵ���ǩ</font>";
		}
	} else if (json.flag == "error") {
		if (json.data == "nl") {
			alert("����û�е�½�����ȵ�¼�����û���˺ţ�����ע�ᡣ");
		} else {
			alert(json.data);
		}
	} else {
	}
}

var voteMessage = "";
function nu(id) {
	voteMessage = "лл����֧�֣����ǽ�������¡�";
	var m = new Object();
	m.k = "ru_" + id;
	m.m = id;
	sm(m);
}
function rerr(id) {
	voteMessage = "�ٱ��ɹ������ǽ������޸����ݡ�";
	var m = new Object();
	m.k = "re_" + id;
	m.m = id;
	sm(m);
}
function sm(message) {
	message.curl = getCurrentMulu();
	doajax("/m.htm", message, votecb);
}
function ac(cid, id) {
	voteMessage = "null";
	doCounter(id, "AC", cid);
}
function tj(cid,id) {
	voteMessage = "�ף������Ƽ��������յ���лл����֧�֡�";
	doCounter(id, "VT", cid, voteMessage);
}
function doCounter(aid, type, category, repeatMessage) {
	var ckname = "ck" + type;
	if ("AC" == type) {
		ckname = "rids";
	}
	var store = type =="AC" ? helper.cookie : helper.store;	
	var deletedIds = exists(store, ckname, aid, 50);
	if (deletedIds) {
		if (repeatMessage) alert(repeatMessage);
		return;
	}
	vote(type + category, aid);
}
function vote(type, tid) {
	var params = new Object();
	params.ot = type;
	params.tid = tid;
	params.curl = getCurrentMulu();
	doajax("/vote.htm", params, votecb);
}
function votecb(data) {
	var json = data;//eval("(" + data + ")");
	if (json.flag == "success") {
		if (voteMessage) {
			if (voteMessage != "null") {
				alert(voteMessage);
			}
			voteMessage = "";
		} else {
			alert("�ύ�ɹ���");
		}
	} else if (json.flag == "error") {
		if (json.data == "nl") {
			alert("����û�е�½�����ȵ�¼�����û���˺ţ�����ע�ᡣ");
		} else if (json.data == "repeat") {
			if (voteMessage != "null") {
				alert("�ظ��ύ��Ϣ��");
			}
		} else {
			alert(json.data);
		}
	}
}
function getCurrentMulu() {
	var index = window.location.href.indexOf("/", 8);
	var path = "/";
	if (index > -1) path = window.location.href.substring(index);
	return path;
}

function showlogin(){//������¼���ж��Ƿ��¼
	//doAjax("/modules/article/wapajax.php", "showlogin=1", "showlogin2", "GET", 0);
	var ccu = getCookie("ccu");
	if (ccu != null && ccu.length ==32) {
		//document.getElementById("info").style.display = "";
		//document.getElementById("login_top").style.display = "none";
		showlogin2("�û���Ϣ");
	}
}
function showlogin2(t){//������¼���ж��Ƿ��¼
	var login_top = document.getElementById("login_top");
	if(t != "nologin"){
		login_top.innerHTML = "<div onclick="show_bookcase()" style="max-width:90px;overflow:hidden;height:50px;padding:0px 10px;" class="c_index_top">" + t + "<\/div>";
	}
}

function check() {
	window.location.href='?url=/modules/article/waps.php?keyword=';
		//return false;
}
function fixwidth(){
	var _52mb_head = document.getElementById("_52mb_head");
	var _52mb_h1 = document.getElementById("_52mb_h1");
	_52mb_h1.style.width = (_52mb_head.scrollWidth-175) + "px";
}
function show_bookcase(){
	var info = document.getElementById("info");
	if(info.style.display == "block"){
		info.style.display = "none";	
	}
	else{
		info.style.display = "block";	
	}
}

function login(){//�����¼
	var name = document.getElementById("name").value;
	if (name == "") {
		alert("�û�������Ϊ�ա�");
		return;
	}
	var password = document.getElementById("password").value;
	if (password == "") {
		alert("���벻��Ϊ�ա�");
		return;
	}
	var v = {};
	v.name = name;
	v.password = md5(password);
	v.autoLogin = "1";
	v.autologin = "1";
	doajax("/u/login.htm", v, function(json) {
			if (json.flag == "error") {
				if (json.data == "2") {
					alert("�û������������");
				} else if(json.data == "3") {
					alert("�˻�δ���");
				} else {
					alert(json.data);
				}
			} else if (json.flag == "success") {
				location.href="/bookcase.php";
			} 
		});
}


function is_login(t){
	if(t == "right"){
		document.getElementById("logintips").innerHTML = "��¼�ɹ���";
		var urlarray= new Array(); //����һ����
		urlarray = document.URL.split("?url="); //�ַ��ָ�
		url = urlarray[1]; 
		if(url){
			url = url.replace(/\%2F/g,"/");
			url = url.replace(/\%3A/g,":");
			url = url.replace(/\%23/g,"");
			url = url.replace(/\%3F/g,"?");
			url = url.replace(/\%3D/g,"=");
			url = url.replace(/\%26/g,"&");
			window.location.href = url;	
		}
		else{
			window.location.href = "/wap/";	
		}
	}
	else{
		document.getElementById("logintips").innerHTML = "�ʺŻ�������

3  源码下载

猜你喜欢

转载自blog.csdn.net/qq_39154376/article/details/79405784
今日推荐
TIOBE 5 月榜单：Fortran “复活”进入 Top 10
GCC 14.1 发布
面壁智能发布 Eurux-8x22B 开源大模型 —— 堪称「理科状元」
开源日报 | 谷歌扶持鸿蒙上位；开源Rabbit R1；Docker加持的安卓手机；微软的焦虑和野心；海尔电器把开放平台关了
中国码农的“35岁魔咒”
蘭雅 CorelDRAW 插件 2024.5.1 国际劳动节版，免费下载
Arc Browser for Windows 1.0 正式 GA
90后程序员开发视频搬运软件、不到一年获利超 700 万，结局很刑！
周排行
基本数据类型封装类比较 Java源码解读(一) 8种基本类型对应的封装类型
JS实现无缝滚动上
深入解析HashMap原理（基于JDK1.8）
mysql的连接池
关于.htc
linux下的ubuntu12.04图形界面
【数论】好推不好记的扩展欧几里德
设备树详解
cscope + tags 简单设置
xml学习
每日归档
更多
2024-05-09(35)
2024-05-08(42)
2024-05-07(14)
2024-05-06(40)
2024-05-05(0)
2024-05-04(7)
2024-05-03(19)
2024-05-02(0)
2024-05-01(4)
2024-04-30(1)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022