Leitgedanken/fetch_bibel/#func_get_lut1984_diebibel.php

<?php
require_once("config.inc.php");
header("Content-Type: text/html; charset=utf-8");
/*
create table bibel_chapter_1984_html
as
SELECT DISTINCT anz_buch, buch, kapitel, NULL as verarbeitet  FROM `bibel_lut_1984`;
ALTER TABLE `bibel_lut_1984_html` ADD PRIMARY KEY(`bid`);
ALTER TABLE `bibel_lut_1984_html` CHANGE `bid` `bid` INT(11) NOT NULL AUTO_INCREMENT;
ALTER TABLE `bibel_chapter_1984` CHANGE `verarbeitet` `verarbeitet` VARCHAR(1) NULL DEFAULT NULL;
ALTER TABLE `bibel_lut_1984_html` CHANGE `anz_buch` `anz_buch` VARCHAR(2) CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL, CHANGE `buch` `buch` VARCHAR(100) CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL, CHANGE `vers` `vers` VARCHAR(100) CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL, CHANGE `bibelstelle` `bibelstelle` VARCHAR(100) CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL, CHANGE `inhalt` `inhalt` TEXT CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL;
*/

  $db = dbconnect();
  $db->query("SET NAMES 'utf8'");


   $query = "SELECT cid, anz_buch, buch, kapitel, link
                     FROM `bibel_chapter_1984_html`
                    WHERE verarbeitet IS NULL
                    ORDER BY cid ASC
             ";
             
#   $query = "SELECT cid, anz_buch, buch, kapitel, link
#                     FROM `bibel_chapter_1984_html`
#                    WHERE cid =1084
#             ";
             

   $result = $db->query( $query)
                   or die ("Cannot execute query: result");

      while ($row = $result->fetch_array()){
       
       #$url= "https://www.die-bibel.de/bibeln/online-bibeln/lutherbibel-1984/bibeltext/bibel/text/lesen/stelle/58/10001/19999/";
       
       $handle = file_get_contents($row['link']);
         
       $handle = strstr($handle, '<div class="bible-text-container">'); 
       $handle = strstr($handle, '<nav class="bible-navigation bible-navigation--simple">', true); 

       # Alle Zeilenumbrüche entfernen
       $handle = preg_replace('/\\r/', '', $handle);
       $handle = preg_replace('/\\n/', '', $handle);
       
       # Mehrere Leerzeichen entfernen
       $handle= preg_replace('/\s{2,}/sm',' ',$handle,PREG_SET_ORDER); //Mehr als zwei leerzeichen entfernen
       $handle = preg_replace ('#\s+#' , ' ' , $handle);

       # Zeilenumbrüche bei Verse einfügen
       $handle = str_replace("<span class=\"verse\"", "\n<span class=\"verse\"", $handle);



       # Überschrift extrahieren <h1>
       $handle = preg_replace('#(<li class="scripture">).*?(</li>)#', '', $handle);
       $handle = preg_replace('#(<li class="name">)(.*?)(</li>)#', '<h1>$2</h1>', $handle);
       

       # Teilüberschrift extrahieren <h3>
       $handle = preg_replace('#(<h1 id=\"h[0-9]\">)(.*?)(</h1>)#', '<h3>$2</h3>', $handle);
       $handle = str_replace("</h3>","</h3>\n",$handle);
       $handle = str_replace("<h3>","\n<h3>",$handle);

       # Kapitel entfernen
       $handle = preg_replace('#(<span class="chapter">)(.*?)(</span>)#', '', $handle);
       
       # Tags entfernen
       $handle = preg_replace('#(<span class="verse".*?>)(.*?)(</span>)#', '$2', $handle);
       $handle = preg_replace('#(<p>)(.*?)(</p>)#', '$2', $handle);
       $handle = preg_replace('#(<div class="linebreak"></div>)#', '{LINEBREAK}', $handle);
       
       # Hervorhebung des Worttes: HERR oder HERRN in besonder Schrift erhalten
       $handle = preg_replace('#(<span class="name-of-deity">)(.*?)(</span>)#', '{NAMEOFDEITY}$2{/NAMEOFDEITY}', $handle);


       # Tags entfernen
       $handle = strip_tags($handle, '<h3><h1><strong><em>');
       
       

       # Linebreak wieder hinzufügen
       $handle = preg_replace('#({LINEBREAK})#', '<div class="linebreak"></div>', $handle);
       $handle = preg_replace('#({/NAMEOFDEITY})#', '</span>', $handle);
       $handle = preg_replace('#({NAMEOFDEITY})#', '<span class="name-of-deity">', $handle);
       
       # Leerzeichen nach div-Tags entfernen
       $handle = str_replace("</div> ","</div>",$handle);
       
       # Doppeltes Fett löschen: Matth 6 z.B.
       $handle = str_replace("</strong><strong>"," ",$handle);
       
       # Doppelte Leerzeichen entfernen, wie oben, falls beim Strong entfernen doppelte dazukommen
       $handle = str_replace ('  ' , ' ' , $handle);

       #echo $handle;
       
       # Mehrere Zeilenumbrüche enternen
       $handle = preg_replace('/(?:[ \t]*(?:\n|\r\n?)){2,}/', "\n", $handle);
       
       
       # Bei Sirach gibt es Konstellationen wie 8&nbsp;\n[7] -> Das ist aber kein Zeilenumbruch, sondern gehört zu Vers 8 zb
       $handle = preg_replace('#(\&nbsp\;)(\\n)(\[)#', '$1$3', $handle);
#echo $handle;       
      
       
       $data = explode("\n", $handle); // preg_split('#\n#', $data); Please don't
       
     #  print_r($data);
       
       for($i=1; $i < count($data)-1; $i++){
        $inhalt = explode('&nbsp;', $data[$i]);
        $bibelstelle = "$row[anz_buch] $row[buch] $row[kapitel]";
        
         if(isset($inhalt[1])){
           $vers = trim($inhalt[0]);
           $inhalt_neu = trim(addslashes(html_entity_decode ($inhalt[1],ENT_QUOTES)));
           $bibelstelle .= ", $vers";
         }else{
           $vers = '';
           $inhalt_neu = trim(addslashes(html_entity_decode($inhalt[0],ENT_QUOTES)));
         }

         $daten[$i][0] = $vers;
         $daten[$i][1] = $inhalt_neu;

         
           	$sql1 = $db->query("INSERT INTO bibel_lut_1984_html ( anz_buch
	   						, buch
	   						, kapitel
	   						, vers
	   						, bibelstelle
	   						, inhalt
	   					       )
	   			    VALUES
	   					       ( '$row[anz_buch]'
	   					       , '$row[buch]'
	   					       , '$row[kapitel]'
	   					       , '$vers'
	   					       , '$bibelstelle'
	   					       , '$inhalt_neu'
	   					       )"
  			  );
       }
      
      
        $sql2 = $db->query("UPDATE bibel_chapter_1984_html
                               SET verarbeitet='Y'
                             WHERE anz_buch='$row[anz_buch]'
                               AND buch = '$row[buch]'
                               AND kapitel = '$row[kapitel]'
                           ");
        
        #print_r($daten);
         
        # Zufälltige Anzahl Sekunden pausieren
        $random = rand(3,10);                            
        sleep($random);
        
        echo "UPDATE bibel_chapter_1984_html SET verarbeitet='Y' WHERE anz_buch='$row[anz_buch]' AND buch = '$row[buch]' AND kapitel = '$row[kapitel]'\t ->\t $random <br>";

      }
?>