<?php
$site_a['text'] = " wort 1 täglich wort 2";
preg_match('/<title>(.*?)<\/title>/is', $site_a['text'], $title);
if(isset($title[1])) {
$title = $title[1];
$title = preg_replace('/[^a-z0-9\.-üßäö]+/', ' ', $title);
}else
$title = "";
$site = preg_replace('#<script(.*?)>(.*?)</script>#is', '', $site_a['text']);
$site = preg_replace('#<style(.*?)>(.*?)</style>#is', '', $site);
$site = preg_replace('#<a(.*?)>(.*?)</a>#is', '', $site);
$site = preg_replace('#<title(.*?)>(.*?)</title>#is', '', $site);
$site = strip_tags($site);
$site = preg_replace('/[\?]+\s/', '. ', $site);
$site = preg_replace('/[\!]+\s/', '. ', $site);
$site = preg_replace('/\s\s+/', ' ', $site);
$site = strtolower ( $site );
$site = html_entity_decode($site, ENT_QUOTES, "UTF-8");
//$site = html_entity_decode($site, ENT_QUOTES, "ISO-8859-1");
print_r($site);
exit;
$site = preg_replace('/[^a-z0-9\.\?-üßäö\s]+/', ' ', $site);
$search = array("[", "]", "{", "}", ":");
$text = str_replace($search, "", $site);
$text = utf8_encode ($text);
$site = explode(". ", $text);
if(is_array($site))
foreach ($site AS $key => $satz){
$satz = preg_replace('/[^a-z0-9-üßäö]+\s/', ' ', $satz);
$satz = preg_replace('/[^a-z0-9-üßäö\s]+/', '', $satz);
$site[$key] = explode(" ", $satz);
}
$paragraph = array();
if(is_array($site))
foreach ($site AS $key => $satz){
$paragraph[] = array("sentence" => $satz);
}
$json = array("titel" => $title, "id" => "id", "link" => "link", "context" => array(array("paragraph" => $paragraph)) );
$json = json_encode($json);
print_r($json);
preferences:
38.7 ms | 402 KiB | 5 Q