Добавлена выборка актульных сайтов по непройденным вариантам

app/library/ContingentManager.php

@@ -37,6 +37,31 @@ final class ContingentManager
         return $sites;
     }
 
+    public function getSitesFromMiccedu(Database $db, array $params) : array
+    {
+        // select site, vuzkod as org_id from opendata.miccedu_monitoring 
+        // where year = 2023 and (vuzkod = :val1 or vuzkod = :val2 or ...)
+        $year = 2023;
+        foreach ($params as $key => $org) {
+            $params[$key] = (int)$org['org_id'];
+        }
+        $query = $this->builder->select()
+            ->setTable('miccedu_monitoring')
+            ->setColumns(['org_id' => 'vuzkod','site'])
+            ->where('AND')
+            ->equals('year', $year)
+            ->subWhere('OR');
+        foreach ($params as $orgId) {
+            $query->equals('vuzkod', $orgId);
+        }
+        $query = $query->end();
+        $sql = $this->builder->writeFormatted($query);
+        array_unshift($params, $year);
+        $sites = $db->selectQuery($sql, $params);
+        
+        return $sites;
+    }
+
     public function insertContingent(Database $db, array $contingent) : void
     {
         $params = ['spec_code', 'spec_name', 'edu_level', 'edu_forms', 'contingent', 'spec_id', 'org_id'];
@@ -84,11 +109,21 @@ final class ContingentManager
     public function buildBaseUri(string $url): string
     {
         // Строит -> https://<base_uri>
-        if (strpos($url,'https://') === false && strpos($url,'http://') === false) {
+        $url = str_replace("www/", "www.", $url);
+        if (strpos($url,'https://') === false 
+            && strpos($url,'http://') === false
+        ) {
             $url = "http://$url";
         }
+        $url = str_replace("https://", "http://", $url);
+        $arr = parse_url($url);
+        $url = $arr['scheme'] .'://'. $arr['host'] . '/';
+        
+        // $url = str_replace("www.", "", $url);
+        $url = str_replace("_","/", $url);
+        $url = $url."sveden/education/";
 
-        return $url;
+        return trim($url);
     }
 
     public function addSpecId(array &$contingent, array $specializations) : void
@@ -141,12 +176,12 @@ final class ContingentManager
             $data = explode (' ', $str);
             if (preg_match("/^[0-9]{4}-(0[1-9]|1[0-2])-(0[1-9]|[1-2][0-9]|3[0-1])$/", $data[0])
                 && $data[3] != PHP_EOL) {
-                $orgHttpError[] = $data[2];
-                // $orgHttpError[] = ['org_id' => $data[2], 'site' => $data[3]];
+                // $orgHttpError[] = $data[2];
+                $orgHttpError[] = ['org_id' => $data[2], 'site' => $data[3]];
             }
         }
-        $orgHttpError = array_unique($orgHttpError);
-        sort($orgHttpError);
+        // $orgHttpError = array_unique($orgHttpError);
+        ksort($orgHttpError);
         return $orgHttpError;
     }
 }

app/library/ContingentParser.php

@@ -36,10 +36,10 @@ class ContingentParser
                 'UTF-8',
                 $encoding
             );
-            $html = str_replace('windows-1251','utf-8', $html);
-        } else {
-            $dom->loadHTML(mb_convert_encoding($html,'HTML-ENTITIES','UTF-8'));
+            $html = str_replace('windows-1251','utf-8', $html); 
         }
+        $dom->loadHTML(mb_convert_encoding($html,'HTML-ENTITIES','UTF-8'));
+        
         $this->xpath = new \DOMXPath($dom);
         $this->template = $template;
     }