sveden-parser/app/app.php

<?php
namespace App;

use GuzzleHttp\Exception\ClientException;
use GuzzleHttp\Exception\ConnectException;
use GuzzleHttp\Exception\RequestException;
use GuzzleHttp\Exception\ServerException;
use GuzzleHttp\RequestOptions;
use NilPortugues\Sql\QueryBuilder\Builder\GenericBuilder;
use App\Library\ContingentParser;
use App\Library\Database;
use GuzzleHttp\Client;
use GuzzleHttp\Psr7\Request;

$dbconfig = [
    "host" => "10.90.1.201",
    "database1" => "opendata",
    "database2" => "niimko",
    "user" => "niimko_user",
    "password" => "MOhA17FeboXE"
];

$dbOpendata = new Database(
    "mysql:host={$dbconfig['host']};dbname={$dbconfig['database1']}", 
    $dbconfig['user'],
    $dbconfig['password']
);

$dbNiimko = new Database(
    "mysql:host={$dbconfig['host']};dbname={$dbconfig['database2']}", 
    $dbconfig['user'],
    $dbconfig['password']
);

$builder = new GenericBuilder();

// select kod as org_id, site from niimko.s_vuzes
// where ootype = 'vuz' and deleted = 'n' and fake = 'n'
$params = ['vuz', 'n', 'n'];
$query = $builder->select()
    ->setTable('s_vuzes')
    ->setColumns(['org_id' => 'kod', 'site'])
    ->where('AND')
    ->equals('ootype', 'vuz')
    ->equals('deleted', 'n')
    ->equals('fake', 'n')
    ->end();
$sql = $builder->write($query);
$sites = $dbNiimko->executeQuery($sql, $params);

// select id, kod from niimko.s_specs where oopkodes = 'gos3p'
$params = ['gos3p'];
$query = $builder->select()
    ->setTable('s_specs')
    ->setColumns(['id', 'kod'])
    ->where()
    ->equals('oopkodes','gos3p')
    ->end();
$sql = $builder->write($query);
$specializations = $dbNiimko->executeQuery($sql, $params);

// print_r($sites);
// print_r($specializations);

// $sites = [ ['site' => "http://marsu.ru"], ['site' => "http://voenmeh.ru"], ['site' => "http://angtu.ru"] ];
$i = 0;
$succes = 0;
foreach ($sites as $site) {
    try {
        $client = new Client([
            RequestOptions::ALLOW_REDIRECTS => [
                'max'             => 10,        // allow at most 10 redirects.
                'strict'          => true,      // use "strict" RFC compliant redirects.
                'referer'         => true,      // add a Referer header
                'track_redirects' => true,
            ],
        ]);

        $route = "{$site['site']}/sveden/education/";
        $route = str_replace("http","https", $route);
        $route = str_replace("www.","", $route);
        print(++$i.". Current url: $route\n");

        $response = $client->get($route);
        print("StatusCode: ".$response->getStatusCode() . "\n");

        $html = $response->getBody()->getContents();
        $parser = new ContingentParser($html, '//tr[@itemprop="eduChislen"]//');
        $contingent = $parser->getDataTable();

        // Добавляем поле spec_id по spec_code
        foreach ($contingent as $key => $con) {
            $needle = $con['spec_code'];
            foreach ($specializations as $spec) {
                if ($needle == $spec['kod']) {
                    $con['spec_id'] = $spec['id'];
                }
            }
            $contingent[$key]['spec_id'] = $con['spec_id'];
        }

        // Добавляем поле org_id
        foreach ($contingent as $key => $spec) {
            $contingent[$key]['org_id'] = $site['org_id'];
        }

        print_r($contingent);
        if ($response->getStatusCode() == 200 && !empty($contingent)){
            print("Succes: ".++$succes."\n");
        }
    } catch (ClientException $e) {
        $response = $e->getCode();
    } catch (RequestException $e) {
        $response = $e->getCode();
    } catch (ConnectException $e) {
        $response = $e->getCode();
    } catch (ServerException $e) {
        $response = $e->getCode();
    }
}

// Чтобы не дублировались в базе
// $dbOpendata->insert('sveden_education_contingent', $data);
// $dbOpendata->update('sveden_education_contingent', $specializations);
// $data = $dbOpendata->select('sveden_education_contingent');