'; echo ''; echo ''; echo ''; echo 'https://www.deutschlandfunk.de/kalenderblatt.870.de.html'; echo 'Das Kalenderblatt stellt historische Ereignisse von Bedeutung oder von Relevanz in anschaulicher Weise dar.'; echo ''.$xml->channel->category.''; echo ''.$xml->channel->copyright.''; echo ''.$xml->channel->language.''; echo ''.$xml->channel->pubDate.''; echo ''.$xml->channel->lastBuildDate.''; echo ''.$xml->channel->ttl.''; echo ''; echo ' https://'.$_SERVER['HTTP_HOST'].dirname($_SERVER['SCRIPT_NAME']).'/image.png'; echo ' '; echo ' '.$xml->channel->image->link.''; echo ' '.$xml->channel->image->description.''; echo ''; echo ''; echo 'Die Beiträge zur Sendung'; echo ''; echo 'https://'.$_SERVER['HTTP_HOST'].$_SERVER['REQUEST_URI'].''; echo ''; echo ' Redaktion deutschlandradio.de'; echo ' podcast@deutschlandradio.de'; echo ''; echo 'Deutschlandfunk'; echo 'No'; echo ''; // Write podcast episodes $containing = array(); foreach ($xml->channel->item as $item) { $content = getPageContent($item->link); // Only add episode to feed if media file is available if ($content[0] != 'XXX') { $id = md5($item->guid); $filename = ''; $filetype = ''; if (str_ends_with($content[1], '.mp3')) { $filename = $id.'.mp3'; $filetype = 'audio/mpeg'; if (!file_exists($downloads.'/'.$filename)) { downloadSingleMediaFile($content[1], $id, $downloads); } } else { $filename = $id.'.aac'; $filetype = 'audio/aac'; // Download episode if not yet done if (!file_exists($downloads.'/'.$filename)) { foreach (glob($temp.'/*') as $file) { if (is_file($file)) { unlink($file); } } downloadMediaFile($content[1], $id, $temp, $downloads); } } array_push($containing, $downloads.'/'.$filename); // Write episode to podcast feed echo ''; echo ' '; echo ' https://'.$_SERVER['HTTP_HOST'].dirname($_SERVER['SCRIPT_NAME']).'/'.$downloads.'/'.$filename.''; echo ' '.str_replace("www.deutschlandfunk.de,", "", strip_tags($item->description)).''; echo ' '.$item->pubDate.''; echo ' '.$item->guid.''; echo ' '; echo ' '.$content[0].''; echo ' '.$content[2].''; echo ''; } } // Remove unused episode media files foreach (glob($downloads.'/*') as $file) { if(is_file($file) && !in_array($file, $containing)) { unlink($file); } } // Write podcast feed end echo ''; echo ''; ///// --- FUNCTIONS --- \\\\\ // Get selected content from episode website function getPageContent($site) { $dom = new DomDocument(); $dom->loadHTML(download($site)); $xpath = new DOMXpath($dom); $player = $xpath->query("//button[@data-audio-series='Kalenderblatt']"); $author = $xpath->query("//p[@class='article-header-author']"); if ($player->length == 0) { return array('XXX'); } $authorname = str_replace('Von ', '', $author->item(0)->nodeValue); $authorname = trim(substr($authorname , 0, strpos($authorname, '|'))); $minutes = intdiv(intval($player->item(0)->getAttribute('data-audio-duration')), 60); $seconds = intval($player->item(0)->getAttribute('data-audio-duration')) % 60; $duration = $minutes.':'.sprintf('%02d', $seconds); // Returns array [episode author name | media file url | episode duration] return array($authorname, $player->item(0)->getAttribute('data-audio-src'), $duration); } // Download episode media file function downloadMediaFile($url, $id, $temp, $downloads) { $regex = "/([^\n\r]+)/m"; // Download first playlist and get "inner" playlist preg_match_all($regex, download($url), $lines); $playlist = getUrlBase($url).(array_values(array_filter($lines[1], "isNotCommentLine"))[0]); // Download contents of "inner" playlist preg_match_all($regex, download($playlist), $urls); // Download all media file segments $counter = 0; foreach (array_filter($urls[1], "isNotCommentLine") as $url) { $outfile = fopen($temp.'/'.$counter.'.ts', 'wb') or exit('File open failed'); $curl = curl_init(); curl_setopt($curl, CURLOPT_FILE, $outfile); curl_setopt($curl, CURLOPT_HEADER, 0); curl_setopt($curl, CURLOPT_URL, getUrlBase($playlist).$url); curl_exec($curl); curl_close($curl); fclose($outfile); file_put_contents($temp.'/list.txt', 'file '.$counter.'.ts'."\n", FILE_APPEND); $counter++; } // Concatenate segments to media file $ffmpeg = './ffmpeg -f concat -i '.$temp.'/list.txt -c copy -bsf:a aac_adtstoasc '.$downloads.'/'.$id.'.aac'; exec($ffmpeg); } // Download episode media file function downloadSingleMediaFile($url, $id, $downloads) { $outfile = fopen($downloads.'/'.$id.'.mp3', 'wb') or exit('File open failed'); $curl = curl_init(); curl_setopt($curl, CURLOPT_FILE, $outfile); curl_setopt($curl, CURLOPT_HEADER, 0); curl_setopt($curl, CURLOPT_URL, $url); curl_exec($curl); curl_close($curl); fclose($outfile); } // Download URL and return content function download($url) { $curl = curl_init(); curl_setopt($curl, CURLOPT_URL, $url); curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true); $download = curl_exec($curl); curl_close($curl); return $download; } // Check if a string does not look like a comment line function isNotCommentLine($var) { return (strcmp( substr( $var , 0, 1 ) , '#' ) !== 0); } // Get the base of an URL (= URL without last element) function getUrlBase($url) { return substr($url, 0, strripos($url, '/') + 1); } ?>