首页 > 代码库 > [PHP] 网盘搜索引擎-采集爬取百度网盘分享文件实现网盘搜索(二)

[PHP] 网盘搜索引擎-采集爬取百度网盘分享文件实现网盘搜索(二)

前情提要:最近使用PHP实现了简单的网盘搜索程序,并且关联了微信公众平台,名字是网盘小说。用户可以通过公众号输入关键字,公众号会返回相应的网盘下载地址。就是这么一个简单的功能,类似很多的网盘搜索类网站,我这个采集和搜索程序都是PHP实现的,全文和分词搜索部分使用到了开源软件xunsearch。

上一篇([PHP] 网盘搜索引擎-采集爬取百度网盘分享文件实现网盘搜索)中我重点介绍了怎样去获取一大批的百度网盘用户,这一篇介绍怎样获得指定网盘用户的分享列表。同样的原理,也是找到百度获取分享列表的接口,然后去循环就可以了。

 

查找分享接口

随便找一个网盘用户的分享页面,点击最下面的分页链接,可以看到发起的请求接口,这个就是获取分享列表的接口。

技术分享

整个的请求url是这个 https://pan.baidu.com/pcloud/feed/getsharelist?t=1493892795526&category=0&auth_type=1&request_location=share_home&start=60&limit=60&query_uk=4162539356&channel=chunlei&clienttype=0&web=1&logid=MTQ5Mzg5Mjc5NTUyNzAuOTEwNDc2NTU1NTgyMTM1OQ==&bdstoken=bc329b0677cad94231e973953a09b46f

 

调用接口获取数据

使用PHP的CURL去请求这个接口,看看是否能够获取到数据。测试后发现,返回的是{"errno":2,"request_id":1775381927},并没有获取到数据。这是因为百度对header头信息里面的Referer进行了限制,我把Referer改成http://www.baidu.com,就可以获取到数据了。接口的参数也可以进行简化成 https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start=60&limit=60&query_uk=4162539356

测试代码如下:

<?php/** 获取分享列表*/class TextsSpider{    /**    * 发送请求    */    public function sendRequest($url,$data = null,$header=null){        $curl = curl_init();        curl_setopt($curl, CURLOPT_URL, $url);        curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, FALSE);        curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, FALSE);        if (!empty($data)){            curl_setopt($curl, CURLOPT_POST, 1);            curl_setopt($curl, CURLOPT_POSTFIELDS, $data);        }        if (!empty($header)){            curl_setopt($curl, CURLOPT_HTTPHEADER, $header);        }        curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);        $output = curl_exec($curl);        curl_close($curl);        return $output;    }}$textsSpider=new TextsSpider();$header=array(    ‘Referer:http://www.baidu.com‘);$str=$textsSpider->sendRequest("https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start=60&limit=60&query_uk=4162539356",null,$header);echo $str;

分享列表的json结果如下:

{    "errno": 0,    "request_id": 1985680203,    "total_count": 1025,    "records": [        {            "feed_type": "share",            "category": 6,            "public": "1",            "shareid": "98963537",            "data_id": "1799945104803474515",            "title": "《通灵少女》2017.同步台视(完结待删)",            "third": 0,            "clienttype": 0,            "filecount": 1,            "uk": 4162539356,            "username": "a20****3762",            "feed_time": 1493626027308,            "desc": "",            "avatar_url": "https://ss0.bdstatic.com/7Ls0a8Sm1A5BphGlnYG/sys/portrait/item/01f8831f.jpg",            "dir_cnt": 1,            "filelist": [                {                    "server_filename": "《通灵少女》2017.同步台视(完结待删)",                    "category": 6,                    "isdir": 1,                    "size": 1024,                    "fs_id": 98994643773159,                    "path": "%2F%E3%80%8A%E9%80%9A%E7%81%B5%E5%B0%91%E5%A5%B3%E3%80%8B2017.%E5%90%8C%E6%AD%A5%E5%8F%B0%E8%A7%86%EF%BC%88%E5%AE%8C%E7%BB%93%E5%BE%85%E5%88%A0%EF%BC%89",                    "md5": "0",                    "sign": "86de8a14f72e6e3798d525c689c0e4575b1a7728",                    "time_stamp": 1493895381                }            ],            "source_uid": "528742401",            "source_id": "98963537",            "shorturl": "1pKPCF0J",            "vCnt": 356,            "dCnt": 29,            "tCnt": 184        },        {            "source_uid": "528742401",            "source_id": "152434783",            "shorturl": "1qYdhFkC",            "vCnt": 1022,            "dCnt": 29,            "tCnt": 345        }    ]}

还是和上次一样,综合性的搜索站,可以把有用的数据都留下存住,我只是做个最简单的,就只要了标题title和shareid

每个分享文件的下载页面url是这样的:http://pan.baidu.com/share/link?shareid={$shareId}&uk={$uk} ,只需要用户编号和分享id就可以拼出下载url。

 

生成分页接口URL

假设用户最多分享了30000个,每页60个,可以分500页,这样url可以这样生成

<?php/** 获取分享列表*/class TextsSpider{    private $pages=500;//分页数    private $start=60;//每页个数    /**    * 生成分页接口的url    */    public function makeUrl($rootUk){        $urls=array();        for($i=0;$i<=$this->pages;$i++){            $start=$this->start*$i;            $url="https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start={$start}&limit={$this->start}&query_uk={$rootUk}";            $urls[]=$url;        }        return $urls;    }}$textsSpider=new TextsSpider();$urls=$textsSpider->makeUrl(4162539356);print_r($urls);

分页的url结果是这样的

Array(    [0] => https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start=0&limit=60&query_uk=4162539356    [1] => https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start=60&limit=60&query_uk=4162539356    [2] => https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start=120&limit=60&query_uk=4162539356    [3] => https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start=180&limit=60&query_uk=4162539356    [4] => https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start=240&limit=60&query_uk=4162539356    [5] => https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start=300&limit=60&query_uk=4162539356    [6] => https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start=360&limit=60&query_uk=4162539356    [7] => https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start=420&limit=60&query_uk=4162539356    [8] => https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start=480&limit=60&query_uk=4162539356    [9] => https://pan.baidu.com/pcloud/feed/getsharelist?&auth_type=1&request_location=share_home&start=540&limit=60&query_uk=4162539356

 

数据表存储结构

CREATE TABLE `texts` (  `id` int(10) unsigned NOT NULL AUTO_INCREMENT,  `title` varchar(255) NOT NULL DEFAULT ‘‘,  `url` varchar(255) NOT NULL DEFAULT ‘‘,  `time` int(10) unsigned NOT NULL DEFAULT 0,  PRIMARY KEY (`id`),  KEY `title` (`title`(250))) ENGINE=MyISAM

 

 循环读取的时候,应该注意,每次间隔一定的时间,防止被封。

下一篇主要介绍xunsearch分词和全文搜索和这次的完整代码

演示地址,关注微信公众号:网盘小说,或者扫描下面的二维码

技术分享

上一篇循环获取uk并存入数据库的完整代码如下:

<?php/** 获取订阅者*/class UkSpider{    private $pages;//分页数    private $start=24;//每页个数    private $db=null;//数据库    public function __construct($pages=100){        $this->pages=$pages;        $this->db = new PDO("mysql:host=localhost;dbname=pan","root","root");        $this->db->query(‘set names utf8‘);    }    /**    * 生成分页接口的url    */    public function makeUrl($rootUk){        $urls=array();        for($i=0;$i<=$this->pages;$i++){            $start=$this->start*$i;            $url="https://pan.baidu.com/pcloud/friend/getfollowlist?query_uk={$rootUk}&limit={$this->start}&start={$start}";            $urls[]=$url;        }        return $urls;    }    /**    * 根据URL获取订阅用户id    */    public function getFollowsByUrl($url){        $result=$this->sendRequest($url);        $arr=json_decode($result,true);        if(empty($arr)||!isset($arr[‘follow_list‘])){            return;        }        $ret=array();        foreach($arr[‘follow_list‘] as $fan){            $ret[]=$fan[‘follow_uk‘];        }                return $ret;    }    /**    * 发送请求    */    public function sendRequest($url,$data = null,$header=null){        $curl = curl_init();        curl_setopt($curl, CURLOPT_URL, $url);        curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, FALSE);        curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, FALSE);        if (!empty($data)){            curl_setopt($curl, CURLOPT_POST, 1);            curl_setopt($curl, CURLOPT_POSTFIELDS, $data);        }        if (!empty($header)){            curl_setopt($curl, CURLOPT_HTTPHEADER, $header);        }        curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);        $output = curl_exec($curl);        curl_close($curl);        return $output;    }    /*    获取到的uks存入数据    */    public function addUks($uks){        foreach($uks as $uk){            $sql="insert into uks (uk)values({$uk})";            $this->db->prepare($sql)->execute();        }    }    /*    获取某个用户的所有订阅并入库    */    public function sleepGetByUk($uk){        $urls=$this->makeUrl($uk);        //$this->updateUkFollow($uk);        //循环分页url        foreach($urls as $url){            echo "loading:".$url."\r\n";            //随机睡眠7到11秒            $second=rand(7,11);            echo "sleep...{$second}s\r\n";            sleep($second);            //发起请求            $followList=$this->getFollowsByUrl($url);            //如果已经没有数据了,要停掉请求            if(empty($followList)){                break;            }            $this->addUks($followList);        }    }    /*从数据库取get_follow=0的uk*/    public function getUksFromDb(){        $sth = $this->db->prepare("select * from uks where get_follow=0");        $sth->execute();        $uks = $sth->fetchAll(PDO::FETCH_ASSOC);        $result=array();        foreach ($uks as $key => $uk) {            $result[]=$uk[‘uk‘];        }        return $result;    }    /*已经取过follow的置为1*/    public function updateUkFollow($uk){        $sql="UPDATE uks SET get_follow=1 where uk={$uk}";        $this->db->prepare($sql)->execute();    }}$ukSpider=new UkSpider();$uks=$ukSpider->getUksFromDb();foreach($uks as $uk){    $ukSpider->sleepGetByUk($uk);}

 

[PHP] 网盘搜索引擎-采集爬取百度网盘分享文件实现网盘搜索(二)