一、编写采集入库脚本接口

新建2个php文件：

1. 目录./api/下新建caiji.php，代码：

<?php
 
/**
 * 数据采集
 */
 
define('IS_API', basename(__FILE__, '.php')); // 项目标识
define('SELF', pathinfo(__FILE__, PATHINFO_BASENAME)); // 该文件的名称
require('../index.php'); // 引入主文件

2. 目录 ./dayrui/My/Api/下，如果没有就新建个目录，新建caiji.php，代码如下：

<?php


$this->_module_init('news'); // news 是模块目录

if ($_GET['action'] == 'category') {
    // 显示栏目

    foreach ($this->module['category'] as $t) {
        if ($t['child'] == 0 && $t['tid'] == 1) {
            echo '<h1>'.$t['name'].'<=>'.$t['id'].'</h1>'.PHP_EOL;
        }
    }

} else {
    // 入库数据

    $data = $_REQUEST;

    // 发布者id 1
    $data['uid'] = 1;

    // 发布者账号 admin
    $data['author'] = 'admin';

    // 主表字段
    $fields[1] = $this->get_cache('table-'.SITE_ID, $this->content_model->dbprefix(SITE_ID.'_'.MOD_DIR));
    $cache = $this->get_cache('table-'.SITE_ID, $this->content_model->dbprefix(SITE_ID.'_'.MOD_DIR.'_category_data'));
    $cache && $fields[1] = array_merge($fields[1], $cache);

    // 附表字段
    $fields[0] = $this->get_cache('table-'.SITE_ID, $this->content_model->dbprefix(SITE_ID.'_'.MOD_DIR.'_data_0'));
    $cache = $this->get_cache('table-'.SITE_ID, $this->content_model->dbprefix(SITE_ID.'_'.MOD_DIR.'_category_data_0'));
    $cache && $fields[0] = array_merge($fields[0], $cache);

    // 去重复
    $fields[0] = array_unique($fields[0]);
    $fields[1] = array_unique($fields[1]);

    $save = [];

    // 主表附表归类
    foreach ($fields as $ismain => $field) {
        foreach ($field as $name) {
            isset($data[$name]) && $save[$ismain][$name] = $data[$name];
        }
    }
        if (!$data['catid']) {
            exit('栏目为空');
        }

/*随机发栏目，下面的数字是栏目id
$arr_1 = array("44","45","46","47","48","49","50","51","52","53","54","55","56","57","58","59","60","61","62","63","64","65","66","67","68","69","70","71","72","73","74","75","76","77","78","79","80","81","82","83","84","85");

$randarr= mt_rand(0,count($arr_1)-1);

$data['catid'] = $arr_1[$randarr];
*/



    $save[1]['uid'] = $save[0]['uid'] = $data['uid'];
    $save[1]['catid'] = $save[0]['catid'] = $data['catid'];
// 提取内容中第一张图作为缩略图
  
    $save[1]['url'] = '';
    $save[1]['status'] = 9; //9表示正常发布，1表示审核里面
     $save[1]['hits'] = random_int(50,900);
    $save[1]['displayorder'] = 0;
    $save[1]['link_id'] = 0;
    //$save[1]['comments'] = 0;
  //  $save[1]['avgsort'] = 0;
    $save[1]['inputtime'] = $save[1]['updatetime'] = SYS_TIME + rand(0, 7200);
    $save[1]['inputip'] = '127.0.0.1';



function myTrim($str)

{
$search = array(" ","　","\n","\r","\t");

$replace = array("","","","","");

return str_replace($search, $replace, $str);

}


$nr=dr_clearhtml($save[0]['content']);

    
$nr=myTrim($nr);

$save[1]['description']=dr_clearhtml(substr($nr,0,400));

$value=$save[0]['content'];

   $formsite = '/'; //相对地址时候目标域名

    $value = str_replace('src="/', 'src="'.$formsite, $value);

    //exit($value);

    if (preg_match_all("/(src)=([\"|']?)([^ \"'>]+\.(gif|jpg|jpeg|png))\\2/i", $value, $imgs)) {

        foreach ($imgs[3] as $img) {

            if (strpos($img, '/api/ueditor/') !== false

                || strpos($img, '/api/umeditor/') !== false) {

                continue;

            }

            // 下载图片

            if (strpos($img, 'http') === 0) {

                // 正常下载

                // 判断域名白名单

                $arr = parse_url($img);

                $domain = $arr['host'];

                if ($domain) {

                    $sites = WRITEPATH.'config/domain_site.php';

                    if (isset($sites[$domain])) {

                        // 过滤站点域名

                    } elseif (strpos(SYS_UPLOAD_URL, $domain) !== false) {

                        // 过滤附件白名单

                    } else {

                        $zj = 0;

                        $remote = \Phpcmf\Service::C()->get_cache('attachment');

                        if ($remote) {

                            foreach ($remote as $t) {

                                if (strpos($t['url'], $domain) !== false) {

                                    $zj = 1;

                                    break;

                                }

                            }

                        }

                        if ($zj == 0) {

                            // 可以下载文件

                            // 同步模式

                            // 下载远程文件

                            $rt = \Phpcmf\Service::L('upload')->down_file([

                                'url' => $img,

                                'attachment' => \Phpcmf\Service::M('Attachment')->get_attach_info(intval($field['content']['setting']['option']['attachment'])),

                            ]);

                            if ($rt['code']) {

                                $att = \Phpcmf\Service::M('Attachment')->save_data($rt['data'], 'ueditor_down_img');

                                if ($att['code']) {

                                    // 归档成功

                                    $value = str_replace($img, $rt['data']['url'], $value);

                                    $img = $att['code'];

                                }

                            }

                            

                        }

                    }

                }

                

            }

          
        }

    }


$save[0]['content']=$value;
  $imgs = dr_get_content_img($save[0]['content']);
    $save[1]['thumb'] = (string)$imgs[0];


    // 验证标题重复
    if ($this->content_model->table(SITE_ID.'_'.MOD_DIR)->where('title', $save[1]['title'])->counts()) {
        echo '重复';exit;
    }


  //  $rt = $this->content_model->save(0, $save);
$rt = $this->content_model->save_content(0, $save);


    if ($rt['code']) {
        exit('成功');
    } else {
        exit('失败');
    }

}

exit;

二、火车采集器新建一个在线发布模块

选择迅睿发布模块-网页编码utf-8-网站地址填上首页地址，测试获取列表。

成功获取列表就说明成功了。

要发布的标签自行测试。

---