Searchengine.php 13.6 KB
Newer Older
1
2
<?php

3
namespace App\Models;
4
use App\MetaGer;
5
6
use Log;
use Redis;
7

8
abstract class Searchengine
9
10
{

11
	protected $ch; 	# Curl Handle zum erhalten der Ergebnisse
12
	public $fp;
13
14
15
16
	protected $getString = "";
	protected $engine;
    protected $counter = 0;
    protected $socketNumber = null;
17
    public $enabled = true;
18
	public $results = [];
19
20
21
	public $ads = [];
	public $write_time = 0;
	public $connection_time = 0;
22

23
	function __construct(\SimpleXMLElement $engine, MetaGer $metager)
24
25
26
27
	{
		foreach($engine->attributes() as $key => $value){
			$this->$key = $value->__toString();
		}
28
29
		if( !isset($this->homepage) )
			$this->homepage = "https://metager.de";
30
31
32
33
34
		$this->engine = $engine;

		# Wir registrieren die Benutzung dieser Suchmaschine
		$this->uses = intval(Redis::hget($this->name, "uses")) + 1;
		Redis::hset($this->name, "uses", $this->uses);
35

36
37
38
39
40
41
42
43
44
45
46
		# Eine Suchmaschine kann automatisch temporär deaktiviert werden, wenn es Verbindungsprobleme gab:
        if(isset($this->disabled) && strtotime($this->disabled) <= time() )
        {
        	# In diesem Fall ist der Timeout der Suchmaschine abgelaufen.
        	$this->enable($metager->getSumaFile(), "Die Suchmaschine " . $this->name . " wurde wieder eingeschaltet.");
        }elseif (isset($this->disabled) && strtotime($this->disabled) > time()) 
        {
        	$this->enabled = false;
        	return;
        }

47
48
49
50
51
52
53
54
		# User-Agent definieren:
		if( isset($_SERVER['HTTP_USER_AGENT']))
		{
			$this->useragent = $_SERVER['HTTP_USER_AGENT'];
		}else
		{
			$this->useragent = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:40.0) Gecko/20100101 Firefox/40.1";
		}
55
		$this->ip = $metager->getIp();
56
57
		$this->gefVon = "<a href=\"" . $this->homepage . "\" target=\"_blank\">" . $this->displayName . "</a>";
		$this->startTime = microtime();
58
59
		
		$this->getString = $this->generateGetString($metager->getQ(), $metager->getUrl(), $metager->getLanguage(), $metager->getCategory());
60
61
		$counter = 0;
		# Wir benötigen einen verfügbaren Socket, über den wir kommunizieren können:
62
		$time = microtime(true);
63
		$this->fp = $this->getFreeSocket();
64
65
66
		
		$this->setStatistic("connection_time", ((microtime(true)-$time) / 1000000));
		if(!$this->fp)
67
		{
68
69
70
71
72
73
74
75
76
77
			$this->disable($metager->getSumaFile(), "Die Suchmaschine " . $this->name . " wurde für 1h deaktiviert, weil keine Verbindung aufgebaut werden konnte");
		}else
		{
			$time = microtime(true);
			$this->writeRequest();
			$this->setStatistic("write_time", ((microtime(true)-$time) / 1000000));
		}

	}

78
	public abstract function loadResults($result);
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96

	private function writeRequest ()
	{
		$out = "GET " . $this->getString . " HTTP/1.1\r\n";
		$out .= "Host: " . $this->host . "\r\n";
		$out .= "User-Agent: " . $this->useragent . "\r\n";
		$out .= "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8\r\n";
		$out .= "Accept-Language: de,en-US;q=0.7,en;q=0.3\r\n";
		$out .= "Accept-Encoding: gzip, deflate, br\r\n";
		$out .= "Connection: keep-alive\r\n\r\n";

		# Anfrage senden:
		$sent = 0; $string = $out; $time = microtime(true);
		while(true)
		{	
			try{
				$tmp = fwrite($this->fp, $string);
			}catch(\ErrorException $e)
97
			{
98
99
100
101
102
103
104
105
106
107
108
				# Irgendwas ist mit unserem Socket passiert. Wir brauchen einen neuen:
				fclose($this->fp);
				Redis::del($this->name . "." . $this->socketNumber);
				$this->fp = $this->getFreeSocket();
				$sent = 0;
				$string = $out;
				continue;
			}
			if($tmp){
				$sent += $tmp;
				$string = substr($string, $tmp);
109
			}else
110
111
112
				abort(500, "Fehler beim schreiben.");

			if(((microtime(true) - $time) / 1000000) >= 500)
113
			{
114
				abort(500, "Konnte die Request Daten nicht an: " . $this->name . " senden");
115
			}
116
117
118
119

			if($sent >= strlen($out))
				break;
		}
120
121
	}

122
123
124
125
126
127
128
	public function rank (\App\MetaGer $metager)
	{
		foreach($this->results as $result)
		{
			$result->rank($metager);
		}
	}
129
130
131
132
133
134
135
136
137
138

	private function getFreeSocket()
	{
		# Je nach Auslastung des Servers ( gleichzeitige Abfragen ), kann es sein, dass wir mehrere Sockets benötigen um die Abfragen ohne Wartezeit beantworten zu können.
		# pfsockopen öffnet dabei einen persistenten Socket, der also auch zwischen den verschiedenen php Prozessen geteilt werden kann. 
		# Wenn der Hostname mit einem bereits erstellten Socket übereinstimmt, wird die Verbindung also aufgegriffen und fortgeführt.
		# Allerdings dürfen wir diesen nur verwenden, wenn er nicht bereits von einem anderen Prozess zur Kommunikation verwendet wird.
		# Wenn dem so ist, probieren wir den nächsten Socket zu verwenden.
		# Dies festzustellen ist komplizierter, als man sich das vorstellt. Folgendes System sollte funktionieren:
		# 1. Stelle fest, ob dieser Socket neu erstellt wurde, oder ob ein existierender geöffnet wurde.
139
		$counter = 0; $fp = null;
140
141
		do
		{
142
143
			
			if( intval(Redis::exists($this->host . ".$counter")) === 0 )              
144
			{
145
146
				Redis::set($this->host . ".$counter", 1);
				Redis::expire($this->host . ".$counter", 5);
147
148
149
150
151
152
153
				$this->socketNumber = $counter;

				try
				{
					$fp = pfsockopen($this->getHost() . ":" . $this->port . "/$counter", $this->port, $errstr, $errno, 1);
				}catch(\ErrorException $e)
				{
154
					break;
155
				}
156
157
158
				# Wir gucken, ob der Lesepuffer leer ist:
				stream_set_blocking($fp, 0);
				if(fgets($fp, BUFFER_LENGTH) !== false)
159
				{
160
					Log::error("Der Lesepuffer von: " . $this->name . " war nach dem Erstellen nicht leer. Musste den Socket neu starten.");
161
					fclose($fp);
162
					$fp = pfsockopen($this->getHost() . ":" . $this->port . "/$counter", $this->port, $errstr, $errno, 1);
163
				}
164
165
				header($this->name . ": " . $counter . "_" . $this->getHost());
				break;
166
			}
167
168
169
170
171
172
			$counter++;
		}while(true);

		return $fp;
	}

173
	private function setStatistic($key, $val)
174
	{
175

176
177
178
179
		$oldVal = floatval(Redis::hget($this->name, $key)) * $this->uses;
		$newVal = ($oldVal + max($val, 0)) / $this->uses;
		Redis::hset($this->name, $key, $newVal);
		$this->$key = $newVal;
180
181
	}

182
	public function disable($sumaFile, $message)
183
184
185
	{
		Log::info($message);
		$xml = simplexml_load_file($sumaFile);
186
187
188
189
		$xml->xpath("//sumas/suma[@name='" . $this->name . "']")['0']['disabled'] = date(DATE_RFC822, mktime(date("H")+1,date("i"), date("s"), date("m"), date("d"), date("Y")));
		$xml->saveXML($sumaFile);
	}

190
	public function enable($sumaFile, $message)
191
192
193
194
	{
		Log::info($message);
		$xml = simplexml_load_file($sumaFile);
		unset($xml->xpath("//sumas/suma[@name='" . $this->name . "']")['0']['disabled']);
195
196
197
198
199
200
201
202
203
204
		$xml->saveXML($sumaFile);
	}

	public function closeFp()
	{
		fclose($this->fp);
	}

	public function retrieveResults()
	{
205
		$time = microtime(true);
206
207
208
209
210
211
212
213
		$headers = '';
		$body = '';
		$length = 0;
		if(!$this->fp)
		{
			return;
		}
		// get headers FIRST
214
215
		$c = 0;
		stream_set_blocking($this->fp, 0);
216
217
218
219
220
221
		do
		{
    		// use fgets() not fread(), fgets stops reading at first newline
   			// or buffer which ever one is reached first
    		$data = fgets($this->fp, BUFFER_LENGTH);
    		// a sincle CRLF indicates end of headers
222
    		if ($data === false || $data == CRLF || feof($this->fp) || ((microtime()-$time)/1000000) > 100 ) {
223
224
225
226
227
        		// break BEFORE OUTPUT
        		break;
    		}
    		if( sizeof(($tmp = explode(": ", $data))) === 2 )
    			$headers[trim($tmp[0])] = trim($tmp[1]);
228
    		$c++;
229
230
231
		}
		while (true);
		// end of headers
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
		if(sizeof($headers) > 1){
			$bodySize = 0;
			if( isset($headers["Transfer-Encoding"]) && $headers["Transfer-Encoding"] === "chunked" )
			{
				$body = $this->readChunked();
				
			}elseif( isset($headers['Content-Length']) )
			{
				$length = trim($headers['Content-Length']);
				if(is_numeric($length) && $length >= 1)
					$body = $this->readBody($length);
				$bodySize = strlen($body);
			}else
			{
				die("Konnte nicht herausfinden, wie ich die Serverantwort von: " . $this->name . " auslesen soll. Header war: " . print_r($headers));
			}
248
249
250
		}else
		{
			fclose($this->fp);
251
252
		}

253
254
		Redis::del($this->host . "." . $this->socketNumber);
		$this->setStatistic("read_time", ((microtime(true)-$time) / 1000000));
255
256
257
258
		if( isset($headers["Content-Encoding"]) && $headers['Content-Encoding'] === "gzip")
		{
			$body = $this->gunzip($body);
		}
259

260
261
262
263
		#print_r($headers);
		#print($body);
		#print("\r\n". $bodySize);
		#exit;
264
265
266
267
268
		#die(print_r($headers));
		// $body and $headers should contain your stream data
		$this->loadResults($body);
		#print(print_r($headers, TRUE) . $body);
		#exit;
269
270
	}

271
	private function readBody($length)
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
	{
		$theData = '';
        $done = false;
        stream_set_blocking($this->fp, 0);
        $startTime = time();
        $lastTime = $startTime;
        while (!feof($this->fp) && !$done && (($startTime + 1) > time()) && $length !== 0)
        {
            usleep(100);
            $theNewData = fgets($this->fp, BUFFER_LENGTH);
            $theData .= $theNewData;
            $length -= strlen($theNewData);
            $done = (trim($theNewData) === '0');

        }
        return $theData;
	}

290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
	private function readChunked()
	{
		$body = '';
		// read from chunked stream
		// loop though the stream
		do
		{
	    	// NOTE: for chunked encoding to work properly make sure
	    	// there is NOTHING (besides newlines) before the first hexlength

	    	// get the line which has the length of this chunk (use fgets here)
	    	$line = fgets($this->fp, BUFFER_LENGTH);

	    	// if it's only a newline this normally means it's read
	    	// the total amount of data requested minus the newline
	    	// continue to next loop to make sure we're done
	    	if ($line == CRLF) {
	        	continue;
	    	}

	    	// the length of the block is sent in hex decode it then loop through
	    	// that much data get the length
	    	// NOTE: hexdec() ignores all non hexadecimal chars it finds
	    	$length = hexdec($line);

	    	if (!is_int($length)) {
	        	trigger_error('Most likely not chunked encoding', E_USER_ERROR);
	    	}

		    // zero is sent when at the end of the chunks
		    // or the end of the stream or error
		    if ($line === false || $length < 1 || feof($this->fp)) {
		    	if($length <= 0)
		            	fgets($this->fp, BUFFER_LENGTH);
		        // break out of the streams loop
		        break;
		    }

		    // loop though the chunk
		    do
		    {
		        // read $length amount of data
		        // (use fread here)
		        $data = fread($this->fp, $length);

		        // remove the amount received from the total length on the next loop
		        // it'll attempt to read that much less data
		        $length -= strlen($data);

		        // PRINT out directly
		        #print $data;
		        #flush();
		        // you could also save it directly to a file here

		        // store in string for later use
		        $body .= $data;

		        // zero or less or end of connection break
		        if ($length <= 0 || feof($this->fp))
		        {
		            // break out of the chunk loop
		            if($length <= 0)
		            	fgets($this->fp, BUFFER_LENGTH);
		            break;
		        }
		    }
		    while (true);
		    // end of chunk loop
		}
		while (true);
		// end of stream loop
		return $body;
	}

	private function gunzip($zipped) {
      $offset = 0;
      if (substr($zipped,0,2) == "\x1f\x8b")
         $offset = 2;
      if (substr($zipped,$offset,1) == "\x08")  
      {
      	try
      	{
         return gzinflate(substr($zipped, $offset + 8));
      	} catch (\Exception $e)
      	{
      		abort(500, "Fehler beim unzip des Ergebnisses von folgendem Anbieter: " . $this->name);
      	}
      }
      return "Unknown Format";
   }  

	protected function getHost()
	{
		$return = "";
		if( $this->port === "443" )
		{
			$return .= "tls://";
		}else
		{
			$return .= "tcp://";
		}
		$return .= $this->host;
		return $return;
	}
394

395
396
397
398
399
	public function getCurlInfo()
	{
		return curl_getinfo($this->ch);
	}

400
401
402
403
404
	public function getCurlErrors()
	{
		return curl_errno($this->ch);
	}

405
406
407
	public function addCurlHandle ($mh)
	{
		curl_multi_add_handle($mh, $this->ch);
408
409
	}

410
411
412
413
414
	public function removeCurlHandle ($mh)
	{
		curl_multi_remove_handle($mh, $this->ch);
	}

415
	private function generateGetString($query, $url, $language, $category)
416
417
	{
		$getString = "";
418

419
		# Skript:
420
421
422
423
		if(strlen($this->skript) > 0)
			$getString .= $this->skript;
		else
			$getString .= "/";
424
		# FormData:
425
426
		if(strlen($this->formData) > 0)
			$getString .= "?" . $this->formData;
427
428
429
430
431
432
433
434

		# Wir müssen noch einige Platzhalter in dem GET-String ersetzen:
		if( strpos($getString, "<<USERAGENT>>") ){
			$getString = str_replace("<<USERAGENT>>", $this->urlEncode($this->useragent), $getString);
		}

		if( strpos($getString, "<<QUERY>>") )
		{
435
			$getString = str_replace("<<QUERY>>", $this->urlEncode($query), $getString);
436
437
438
439
		}

		if( strpos($getString, "<<IP>>") )
		{
440
			$getString = str_replace("<<IP>>", $this->urlEncode($this->ip), $getString);
441
442
443
444
		}

		if( strpos($getString, "<<LANGUAGE>>") )
		{
445
			$getString = str_replace("<<LANGUAGE>>", $this->urlEncode($language), $getString);
446
447
448
449
		}

		if( strpos($getString, "<<CATEGORY>>") )
		{
450
			$getString = str_replace("<<CATEGORY>>", $this->urlEncode($category), $getString);
451
		}
452
453
454

		if( strpos($getString, "<<AFFILDATA>>") )
		{
455
			$getString = str_replace("<<AFFILDATA>>", $this->getOvertureAffilData($url), $getString);
456
		}
457
458
459
		return $getString;
	}

460
	protected function urlEncode($string)
461
462
463
464
465
466
467
468
469
470
	{
		if(isset($this->inputEncoding))
		{
			return urlencode(mb_convert_encoding($string, $this->inputEncoding));
		}else
		{
			return urlencode($string);
		}
	}

471
	private function getOvertureAffilData($url)
472
	{
473
	    $affil_data = 'ip=' . $this->ip;
474
475
476
	    $affil_data .= '&ua=' . $this->useragent;  
	    if ( isset($_SERVER['HTTP_X_FORWARDED_FOR']) ) {
	       $affil_data .= '&xfip=' . $_SERVER['HTTP_X_FORWARDED_FOR'];
477
	    }
478
	    $affilDataValue = $this->urlEncode($affil_data);
479
		# Wir benötigen die ServeUrl:
480
		$serveUrl = $this->urlEncode($url);
481

482
483
		return "&affilData=" . $affilDataValue . "&serveUrl=" . $serveUrl;
	}
484
485
486
487
488

	public function isEnabled ()
	{
		return $this->enabled;
	}
489
}