微信公众号文章列表抓取

waft

最近需要做一个公众号文章阅读奖励积分的功能，首先就得获取到文章列表，网上查了资料后，感觉微信公众平台图文编辑那的限制会少一点，可以满足需求，现在记录一下

一：首先创建一个登陆表单，包含账户和密码，点击登陆后台请求对应接口获得一个二维码图片，然后js循环刷新显示二维码直到扫码成功（账号密码为微信公众平台的账号密码）

<!DOCTYPE HTML>
<html>
<head>
    <meta charset="utf-8">
</head>
<body>
    <input id="name" type="text" placeholder="账户">
    <input id="pwd" type="password" placeholder="密码"> 
    <input onclick="showimg()" type="button" value="登录">
    <div id="showimg" style="display:none">正在获取...</div>
<script  src="http://libs.baidu.com/jquery/1.7.2/jquery.min.js"></script>
<script>
    function showimg() {
        $("#showimg").show();
        name = $("#name").val();
        pwd = $("#pwd").val();
        t = setInterval("img()", 3000);
        $.post("./wx.php?method=login", {\'name\':name, \'pwd\':pwd},function(rsg){
            data = jQuery.parseJSON(rsg);
            if(!data.code) {
                window.location.href = "./wx.php?method=getwx";
            }else{
                $("#showimg").hide();
                alert(data.msg);
            }
        })
    }
    function img() {
        num = Math.round(Math.random());
        $("#showimg").html("<img src=\'./wx/qrcode_tmall.png?"+num+"\'>")
    }
</script>
</body>
</html>

二：控制器接收请求处理（Wx.php）

<?php
namespace app;

use app\Wxlogin;

class Wx
{
    //登陆
    function login() {
        $name = $_POST[\'name\'];
        if(!$name)
            return $this->ajax([\'code\'=>2, \'msg\'=>\'账号不能为空\']);
        $pwd = $_POST[\'pwd\'];
        if(!$pwd)
            return $this->ajax([\'code\'=>2, \'msg\'=>\'密码不能为空\']);
        $arr = array(
          \'account\'  => $name,
          \'password\' => $pwd,
          \'key\'    => "tmall",
        );
        $wx = new Wxlogin();
        $wx->init($arr);
        if(!$wx->getToken()){
            return $this->ajax([\'code\'=>1, \'msg\'=>\'登陆失败\'], );
        }
        return $this->ajax([\'code\'=>0, \'msg\'=>\'登陆成功\']);
    }

    //搜索公众号（备用，只查看单个公众号无需使用，fackid固定即可；搜索公众号查看会用到此方法，然后需要把getwx里的获取fackid更改一下【session或者参数形式都可以】）
    function getfackid(){
        $search = isset($_GET[\'search\']) ? $_GET[\'search\'] : \'内涵段子\';
        $wx = new Wxlogin();
        $arr = array(
          \'key\'    => "tmall",
        );
        //没有token就去登陆扫码
        if(!$wx->getToken()){
            header(\'location:/\');
        }
        //开始位置
        $size = 5;
        $nowpage = isset($_GET[\'page\']) ? $_GET[\'page\'] : 1;
        $nowpage = $nowpage<1?1:$nowpage;
        $begin = ($nowpage-1)*$size;
        //初始化并获取数据
        $wx->init($arr);
        $data = $wx->getfackid($begin, $search);if($data[\'base_resp\'][\'ret\'] != 0) {
            file_put_contents("./wx/token.txt", \'\');
            switch ($data[\'base_resp\'][\'ret\']) {
                case \'200013\':
                    echo \'请求太频繁了\';
                    break;
                case \'200003\':
                    echo \'无效会话\';
                    break;
                default:
                    echo \'请求错误\';
                    break;
            }
            return;
        }else{
            //总页数
            $psum = ceil($data[\'app_msg_cnt\']/$size);
            $list = $data[\'app_msg_list\'];
        }
        return $this->ajax($list);
    }

    //获取列表（分页，页面条数不足的代表发布者删除过一些）
    function getwx(){
        $wx = new Wxlogin();
        $arr = array(
          \'key\'    => "tmall",
        );
        //没有token就去登陆扫码
        if(!$wx->getToken()){
            header(\'location:/\');
        }
        //登陆成功删除二维码
        if(file_exists(\'./wx/qrcode_tmall.png\')) {
            unlink(\'./wx/qrcode_tmall.png\');
        }
        //开始位置
        $size = 5;
        $nowpage = isset($_GET[\'page\']) ? $_GET[\'page\'] : 1;
        $nowpage = $nowpage<1?1:$nowpage;
        $begin = ($nowpage-1)*$size;
        //初始化并获取数据
        $wx->init($arr);
        $search = isset($_GET[\'search\']) ? $_GET[\'search\'] : 1;
        $data = $wx->getwx($begin, $search);
        if($data[\'base_resp\'][\'ret\'] != 0) {
            file_put_contents("./wx/token.txt", \'\');
            switch ($data[\'base_resp\'][\'ret\']) {
                case \'200013\':
                    echo \'请求太频繁了\';
                    break;
                case \'200003\':
                    echo \'无效会话\';
                    break;
                default:
                    echo \'请求错误\';
                    break;
            }
            return;
        }else{
            //总页数
            $psum = ceil($data[\'app_msg_cnt\']/$size);
            $list = $data[\'app_msg_list\'];
        }
        return $this->ajax([$data[\'app_msg_cnt\'], $search, $nowpage, $psum, $list]);
    }

    function ajax($data)
    {
        return json_encode($data, JSON_UNESCAPED_UNICODE);
    }

}

//自动加载
spl_autoload_register(function ($class) {
    $arr = explode(\'\\\', $class);
    if(array_shift($arr) == \'app\') {
        include implode(\'\\\', $arr) . \'.php\';
    }
});

$wx = new Wx();
$method = $_GET[\'method\'];
echo $wx->$method();

 

三：请求微信接口，供Wx.php调用（Wxlogin.php）

<?php
namespace app;

class Wxlogin
{
    //--------------------------------------------------------LOGIN START
    private $_apis = [
        "host" => "https://mp.weixin.qq.com",
        "login" => "https://mp.weixin.qq.com/cgi-bin/bizlogin?action=startlogin",
        "qrcode" => "https://mp.weixin.qq.com/cgi-bin/loginqrcode?action=getqrcode&m=4300",
        "loginqrcode" => "https://mp.weixin.qq.com/cgi-bin/loginqrcode?action=ask&token=&lang=zh_CN&f=json&ajax=1",
        "loginask" => "https://mp.weixin.qq.com/cgi-bin/loginqrcode?action=ask&token=&lang=zh_CN&f=json&ajax=1&random=",
        "loginauth" => "https://mp.weixin.qq.com/cgi-bin/loginauth?action=ask&token=&lang=zh_CN&f=json&ajax=1",
        "bizlogin" => "https://mp.weixin.qq.com/cgi-bin/bizlogin?action=login&lang=zh_CN"
    ];
    public $fakeid = "MzIxMTU3MDA4Ng==";
    private $_redirect_url = "";
    private $_key = "";

    //获取cookie保存文件，用于访问接口
    private function _getCookieFile(){
        return "./wx/cookie_{$this->_key}.text";
    }

    //获取二维码路径
    private function _getSavePath(){
        return \'./wx/\'.$this->_qrcodeName();
    }

    //获取二维码名称
    private function _qrcodeName(){
        return "qrcode_{$this->_key}.png";
    }

    //记录日志
    private function _log($log_content){
        $log_filename = \'./wx\';
        !is_dir($log_filename) && mkdir($log_filename, 0755, true);

        file_put_contents($log_filename.\'/wx.log\', \'[\'.date("Y-m-d H:i:s").\']\' .PHP_EOL . $log_content . PHP_EOL."------------------------ --------------------------".PHP_EOL, FILE_APPEND);
    }

    public function getToken(){
        return file_get_contents("./wx/token.txt");
    }
    public function setToken($token){
        file_put_contents("./wx/token.txt", $token);
    }
    public function init($options){
        if(!isset($options["key"])){
            die("Key is Null!");
        }
        $this->_key = $options["key"];
        if($this->getToken()){
            $this->_log("HAS Token !");
            return;
        }else{
            $this->fetch("https://mp.weixin.qq.com/","","text");
            $this->_log("start login!!");
            $this->start_login($options);
        }
    }
    private function start_login($options){
        $_res = $this->_login($options["account"],$options["password"]);
        if($_res["code"]){
            $this->_log($_res["msg"]);
            return;
        }
        //保存二维码
        $this->_saveQRcode();
        $_ask_api = $this->_apis["loginask"];
        $_input["refer"] = $this->_redirect_url;
        $_index = 1;
        while(true){
            if($_index>20){
                $this->_log("超时");
                break;
            }
            $_res = $this->fetch($_ask_api.$this->getWxRandomNum(),$_input);
            $_status = $_res["status"];
            if($_status==1){
                if($_res["user_category"]==1){
                    $_ask_api = $this->_apis["loginauth"];
                }else{
                    $this->_log("Login success");
                    break;
                }
            }else if($_status==4){
                $this->_log("已经扫码");
            }else if($_status==2){
                $this->_log("管理员拒绝");
                break;
            }else if($_status==3){
                $this->_log("登录超时");
                break;
            }else{
                if($_ask_api==$this->_apis["loginask"]){
                    $this->_log("请打开test.jpg，用微信扫码");
                }else{
                    $this->_log("等待确认");
                }
            }
            sleep(2);
            $_index++;
        }
        $this->_log("开始验证");
        $_input["post"] = ["lang"=>"zh_CN","f"=>"json","ajax"=>1,"random"=>$this->getWxRandomNum(),"token"=>""];
        $_input["refer"] = $this->_redirect_url;
        $_res = $this->fetch($this->_apis["bizlogin"],$_input);
        $this->_log(print_r($_res,true));
        if($_res["base_resp"]["ret"]!=0){
            $this->_log("error = ".$_res["base_resp"]["err_msg"]);
            return ;
        }
        $redirect_url = $_res["redirect_url"];//跳转路径
        if(preg_match(\'/token=([\d]+)/i\', $redirect_url,$match)){//获取cookie
            $this->setToken($match[1]);
        }
        $this->_log("验证成功,token: ".$this->getToken());
    }
    //下载二维码
    private function _saveQRcode(){
        $_input["refer"] = $this->_redirect_url;
        $_res = $this->fetch($this->_apis["qrcode"],$_input,"text");
        $fp = fopen($this->_getSavePath(), "wb+") or die("open fails");
        fwrite($fp,$_res) or die("fwrite fails");
        fclose($fp);
    }

    private function _login($_username,$_password){
        $_input["post"] = array(
            \'username\' => $_username,
            \'pwd\' => md5($_password),
            \'f\' => \'json\',
            \'imgcode\' => ""
        );
        $_input["refer"] = "https://mp.weixin.qq.com";
        $_res = $this->fetch($this->_apis["login"],$_input);
        if($_res["base_resp"]["ret"]!==0){
            return [\'code\'=>\'1\', \'msg\'=>$_res["base_resp"]["err_msg"]];
        }
        $this->_redirect_url = "https://mp.weixin.qq.com".$_res["redirect_url"];//跳转路径
        return [\'code\'=>\'0\', \'msg\'=>\'ok\'];
    }

    function getWxRandomNum(){
        return "0.".mt_rand(1000000000000000,9999999999999999);
    }

    function getfackid($begin, $search){
        $url = "https://mp.weixin.qq.com/cgi-bin/searchbiz?action=search_biz&begin=$begin&count=5&query=$search&token=".$this->getToken()."&lang=zh_CN&f=json&ajax=1";
        return $this->fetch($url);
    }

    function getwx($begin, $search){
        $url = "https://mp.weixin.qq.com/cgi-bin/appmsg?action=list_ex&begin=$begin&count=5&fakeid=".$this->fakeid."&type=9&query={$search}&token=".$this->getToken()."&lang=zh_CN&f=json&ajax=1";
        return $this->fetch($url);
    }

    /**
    * @param $url
    * @param null $_input
    * @param string $data_type
    * @return mixed
    * $_input= ["post"=>[],"refer"=>"",cookiefile=\'\']
    */
    function fetch( $url, $_input=null, $data_type=\'json\') {
        $ch = curl_init();
        $useragent = isset($_input[\'useragent\']) ? $_input[\'useragent\'] : \'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:10.0.2) Gecko/20100101 Firefox/10.0.2\';
        curl_setopt( $ch, CURLOPT_URL, $url );
        curl_setopt( $ch, CURLOPT_RETURNTRANSFER, true );
        curl_setopt( $ch, CURLOPT_AUTOREFERER, true );
        curl_setopt( $ch, CURLOPT_FOLLOWLOCATION, true );
        curl_setopt( $ch, CURLOPT_POST, isset($_input[\'post\']) );
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false); //不验证证书
        curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false); //不验证证书
        if( isset($_input[\'post\']) ) curl_setopt( $ch, CURLOPT_POSTFIELDS, $_input[\'post\'] );
        if( isset($_input[\'refer\']) ) curl_setopt( $ch, CURLOPT_REFERER, $_input[\'refer\'] );
        curl_setopt( $ch, CURLOPT_USERAGENT, $useragent );
        curl_setopt( $ch, CURLOPT_CONNECTTIMEOUT, ( isset($_input[\'timeout\']) ? $_input[\'timeout\'] : 5 ) );
        curl_setopt( $ch, CURLOPT_COOKIEJAR, ( isset($_input[\'cookiefile\']) ? $_input[\'cookiefile\'] : $this->_getCookieFile() ));
        curl_setopt( $ch, CURLOPT_COOKIEFILE, ( isset($_input[\'cookiefile\']) ? $_input[\'cookiefile\'] : $this->_getCookieFile() ));
        $result = curl_exec( $ch );
        curl_close( $ch );
        if ($data_type == \'json\') {
            $result = json_decode($result,true);
        }
        return $result;
    }
}

 注：fakeid是要抓去的公众号的标识（调用本文的getfackid也可以），也可在公众平台的图文编辑里获取，步骤如下：

1：草稿箱内的写新图文

 

 

2：先打开浏览器的开发者工具（要从请求中查看），然后点击超链接，输入要查询的公众号，点击搜索

3：在开发者工具中查看Network一栏中点击searchbiz...这一栏查看fakeid

补充：

因为我是获取单个公众号，所以没有用getfackid方法，有做公众号搜索模式的，可以调用上面的getfackid方法获取公众号fackid
思路：获取到公众号列表后展现给前端，前端点击选择提交给后端，后端将对应的fackid存入session,然后获取文章列表的接口判断是否存在session,存在则获取文章列表

分类：

技术点：

相关文章：

猜你喜欢
相关资源
相似解决方案
热门标签
Java Python linux javascript Mysql C# Docker 算法 前端 SpringBoot Redis Vue spring 设计模式 .net core .net kubernetes c++ 数据库 数据结构 大数据 js 机器学习 微服务 Android Go 程序员 面试 JVM ASP.net core 云原生 人工智能 后端 PHP git CSS golang k8s Nginx Django mybatis 深度学习 多线程 React 架构 devops 爬虫 云计算 Spring Boot LeetCode