aboutsummaryrefslogblamecommitdiffhomepage
path: root/inc/3rdparty/libraries/content-extractor/ContentExtractor.php
blob: 21e693e7db6ed0c7bbb30f6a0ba885c79ebe1f9d (plain) (tree)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
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
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727






















































































































































































































































































































































































































































































































































































































































































































































                                                                                                                                                                                                                                                                                 
<?php
/**
 * Content Extractor
 * 
 * Uses patterns specified in site config files and auto detection (hNews/PHP Readability) 
 * to extract content from HTML files.
 * 
 * @version 1.0
 * @date 2013-02-05
 * @author Keyvan Minoukadeh
 * @copyright 2013 Keyvan Minoukadeh
 * @license http://www.gnu.org/licenses/agpl-3.0.html AGPL v3
 */

class ContentExtractor
{
	protected static $tidy_config = array(
				 'clean' => true,
				 'output-xhtml' => true,
				 'logical-emphasis' => true,
				 'show-body-only' => false,
				 'new-blocklevel-tags' => 'article, aside, footer, header, hgroup, menu, nav, section, details, datagrid',
				 'new-inline-tags' => 'mark, time, meter, progress, data',
				 'wrap' => 0,
				 'drop-empty-paras' => true,
				 'drop-proprietary-attributes' => false,
				 'enclose-text' => true,
				 'enclose-block-text' => true,
				 'merge-divs' => true,
				 'merge-spans' => true,
				 'char-encoding' => 'utf8',
				 'hide-comments' => true
				 );
	protected $html;
	protected $config;
	protected $title;
	protected $author = array();
	protected $language;
	protected $date;
	protected $body;
	protected $success = false;
	protected $nextPageUrl;
	public $allowedParsers = array('libxml', 'html5lib');
	public $fingerprints = array();
	public $readability;
	public $debug = false;
	public $debugVerbose = false;

	function __construct($path, $fallback=null) {
		SiteConfig::set_config_path($path, $fallback);	
	}
	
	protected function debug($msg) {
		if ($this->debug) {
			$mem = round(memory_get_usage()/1024, 2);
			$memPeak = round(memory_get_peak_usage()/1024, 2);
			echo '* ',$msg;
			if ($this->debugVerbose) echo ' - mem used: ',$mem," (peak: $memPeak)";
			echo "\n";
			ob_flush();
			flush();
		}
	}
	
	public function reset() {
		$this->html = null;
		$this->readability = null;
		$this->config = null;
		$this->title = null;
		$this->body = null;
		$this->author = array();
		$this->language = null;
		$this->date = null;
		$this->nextPageUrl = null;
		$this->success = false;
	}

	public function findHostUsingFingerprints($html) {
		$this->debug('Checking fingerprints...');
		$head = substr($html, 0, 8000);
		foreach ($this->fingerprints as $_fp => $_fphost) {
			$lookin = 'html';
			if (is_array($_fphost)) {
				if (isset($_fphost['head']) && $_fphost['head']) {
					$lookin = 'head';
				}
				$_fphost = $_fphost['hostname'];
			}
			if (strpos($$lookin, $_fp) !== false) {
				$this->debug("Found match: $_fphost");
				return $_fphost;
			}
		}
		$this->debug('No fingerprint matches');
		return false;
	}
	
	// returns SiteConfig instance (joined in order: exact match, wildcard, fingerprint, global, default)
	public function buildSiteConfig($url, $html='', $add_to_cache=true) {
		// extract host name
		$host = @parse_url($url, PHP_URL_HOST);
		$host = strtolower($host);
		if (substr($host, 0, 4) == 'www.') $host = substr($host, 4);
		// is merged version already cached?
		if (SiteConfig::is_cached("$host.merged")) {
			$this->debug("Returning cached and merged site config for $host");
			return SiteConfig::build("$host.merged");
		}
		// let's build from site_config/custom/ and standard/
		$config = SiteConfig::build($host);
		if ($add_to_cache && $config && !SiteConfig::is_cached("$host")) {
			SiteConfig::add_to_cache($host, $config);
		}
		// if no match, use defaults
		if (!$config) $config = new SiteConfig();
		// load fingerprint config?
		if ($config->autodetect_on_failure()) {
			// check HTML for fingerprints
			if (!empty($this->fingerprints) && ($_fphost = $this->findHostUsingFingerprints($html))) {
				if ($config_fingerprint = SiteConfig::build($_fphost)) {
					$this->debug("Appending site config settings from $_fphost (fingerprint match)");
					$config->append($config_fingerprint);
					if ($add_to_cache && !SiteConfig::is_cached($_fphost)) {
						//$config_fingerprint->cache_in_apc = true;
						SiteConfig::add_to_cache($_fphost, $config_fingerprint);
					}
				}
			}
		}
		// load global config?
		if ($config->autodetect_on_failure()) {
			if ($config_global = SiteConfig::build('global', true)) {
				$this->debug('Appending site config settings from global.txt');
				$config->append($config_global);
				if ($add_to_cache && !SiteConfig::is_cached('global')) {
					//$config_global->cache_in_apc = true;
					SiteConfig::add_to_cache('global', $config_global);
				}
			}
		}
		// store copy of merged config
		if ($add_to_cache) {
			// do not store in APC if wildcard match
			$use_apc = ($host == $config->cache_key);
			$config->cache_key = null;
			SiteConfig::add_to_cache("$host.merged", $config, $use_apc);
		}
		return $config;
	}
	
	// returns true on success, false on failure
	// $smart_tidy indicates that if tidy is used and no results are produced, we will
	// try again without it. Tidy helps us deal with PHP's patchy HTML parsing most of the time
	// but it has problems of its own which we try to avoid with this option.
	public function process($html, $url, $smart_tidy=true) {
		$this->reset();
		$this->config = $this->buildSiteConfig($url, $html);
		
		// do string replacements
		if (!empty($this->config->find_string)) {
			if (count($this->config->find_string) == count($this->config->replace_string)) {
				$html = str_replace($this->config->find_string, $this->config->replace_string, $html, $_count);
				$this->debug("Strings replaced: $_count (find_string and/or replace_string)");
			} else {
				$this->debug('Skipped string replacement - incorrect number of find-replace strings in site config');
			}
			unset($_count);
		}
		
		// use tidy (if it exists)?
		// This fixes problems with some sites which would otherwise
		// trouble DOMDocument's HTML parsing. (Although sometimes it
		// makes matters worse, which is why you can override it in site config files.)
		$tidied = false;
		if ($this->config->tidy() && function_exists('tidy_parse_string') && $smart_tidy) {
			$this->debug('Using Tidy');
			$tidy = tidy_parse_string($html, self::$tidy_config, 'UTF8');
			if (tidy_clean_repair($tidy)) {
				$original_html = $html;
				$tidied = true;
				$html = $tidy->value;
			}
			unset($tidy);
		}
		
		// load and parse html
		$_parser = $this->config->parser();
		if (!in_array($_parser, $this->allowedParsers)) {
			$this->debug("HTML parser $_parser not listed, using libxml instead");
			$_parser = 'libxml';
		}
		$this->debug("Attempting to parse HTML with $_parser");
		$this->readability = new Readability($html, $url, $_parser);
		
		// we use xpath to find elements in the given HTML document
		// see http://en.wikipedia.org/wiki/XPath_1.0
		$xpath = new DOMXPath($this->readability->dom);

		// try to get next page link
		foreach ($this->config->next_page_link as $pattern) {
			$elems = @$xpath->evaluate($pattern, $this->readability->dom);
			if (is_string($elems)) {
				$this->nextPageUrl = trim($elems);
				break;
			} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
				foreach ($elems as $item) {
					if ($item instanceof DOMElement && $item->hasAttribute('href')) {
						$this->nextPageUrl = $item->getAttribute('href');
						break 2;
					} elseif ($item instanceof DOMAttr && $item->value) {
						$this->nextPageUrl = $item->value;
						break 2;
					}
				}
			}
		}
		
		// try to get title
		foreach ($this->config->title as $pattern) {
			// $this->debug("Trying $pattern");
			$elems = @$xpath->evaluate($pattern, $this->readability->dom);
			if (is_string($elems)) {
				$this->title = trim($elems);
				$this->debug('Title expression evaluated as string: '.$this->title);
				$this->debug("...XPath match: $pattern");
				break;
			} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
				$this->title = $elems->item(0)->textContent;
				$this->debug('Title matched: '.$this->title);
				$this->debug("...XPath match: $pattern");
				// remove title from document
				try {
					@$elems->item(0)->parentNode->removeChild($elems->item(0));
				} catch (DOMException $e) {
					// do nothing
				}
				break;
			}
		}
		
		// try to get author (if it hasn't already been set)
		if (empty($this->author)) {
			foreach ($this->config->author as $pattern) {
				$elems = @$xpath->evaluate($pattern, $this->readability->dom);
				if (is_string($elems)) {
					if (trim($elems) != '') {
						$this->author[] = trim($elems);
						$this->debug('Author expression evaluated as string: '.trim($elems));
						$this->debug("...XPath match: $pattern");
						break;
					}
				} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
					foreach ($elems as $elem) {
						if (!isset($elem->parentNode)) continue;
						$this->author[] = trim($elem->textContent);
						$this->debug('Author matched: '.trim($elem->textContent));
					}
					if (!empty($this->author)) {
						$this->debug("...XPath match: $pattern");
						break;
					}
				}
			}
		}
		
		// try to get language
		$_lang_xpath = array('//html[@lang]/@lang', '//meta[@name="DC.language"]/@content');
		foreach ($_lang_xpath as $pattern) {
			$elems = @$xpath->evaluate($pattern, $this->readability->dom);
			if (is_string($elems)) {
				if (trim($elems) != '') {
					$this->language = trim($elems);
					$this->debug('Language matched: '.$this->language);
					break;
				}
			} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
				foreach ($elems as $elem) {
					if (!isset($elem->parentNode)) continue;
					$this->language = trim($elem->textContent);
					$this->debug('Language matched: '.$this->language);					
				}
				if ($this->language) break;
			}
		}
		
		// try to get date
		foreach ($this->config->date as $pattern) {
			$elems = @$xpath->evaluate($pattern, $this->readability->dom);
			if (is_string($elems)) {
				$this->date = strtotime(trim($elems, "; \t\n\r\0\x0B"));				
			} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
				$this->date = $elems->item(0)->textContent;
				$this->date = strtotime(trim($this->date, "; \t\n\r\0\x0B"));
				// remove date from document
				// $elems->item(0)->parentNode->removeChild($elems->item(0));
			}
			if (!$this->date) {
				$this->date = null;
			} else {
				$this->debug('Date matched: '.date('Y-m-d H:i:s', $this->date));
				$this->debug("...XPath match: $pattern");
				break;
			}
		}

		// strip elements (using xpath expressions)
		foreach ($this->config->strip as $pattern) {
			$elems = @$xpath->query($pattern, $this->readability->dom);
			// check for matches
			if ($elems && $elems->length > 0) {
				$this->debug('Stripping '.$elems->length.' elements (strip)');
				for ($i=$elems->length-1; $i >= 0; $i--) {
					$elems->item($i)->parentNode->removeChild($elems->item($i));
				}
			}
		}
		
		// strip elements (using id and class attribute values)
		foreach ($this->config->strip_id_or_class as $string) {
			$string = strtr($string, array("'"=>'', '"'=>''));
			$elems = @$xpath->query("//*[contains(@class, '$string') or contains(@id, '$string')]", $this->readability->dom);
			// check for matches
			if ($elems && $elems->length > 0) {
				$this->debug('Stripping '.$elems->length.' elements (strip_id_or_class)');
				for ($i=$elems->length-1; $i >= 0; $i--) {
					$elems->item($i)->parentNode->removeChild($elems->item($i));
				}
			}
		}
		
		// strip images (using src attribute values)
		foreach ($this->config->strip_image_src as $string) {
			$string = strtr($string, array("'"=>'', '"'=>''));
			$elems = @$xpath->query("//img[contains(@src, '$string')]", $this->readability->dom);
			// check for matches
			if ($elems && $elems->length > 0) {
				$this->debug('Stripping '.$elems->length.' image elements');
				for ($i=$elems->length-1; $i >= 0; $i--) {
					$elems->item($i)->parentNode->removeChild($elems->item($i));
				}
			}
		}
		// strip elements using Readability.com and Instapaper.com ignore class names
		// .entry-unrelated and .instapaper_ignore
		// See https://www.readability.com/publishers/guidelines/#view-plainGuidelines
		// and http://blog.instapaper.com/post/730281947
		$elems = @$xpath->query("//*[contains(concat(' ',normalize-space(@class),' '),' entry-unrelated ') or contains(concat(' ',normalize-space(@class),' '),' instapaper_ignore ')]", $this->readability->dom);
		// check for matches
		if ($elems && $elems->length > 0) {
			$this->debug('Stripping '.$elems->length.' .entry-unrelated,.instapaper_ignore elements');
			for ($i=$elems->length-1; $i >= 0; $i--) {
				$elems->item($i)->parentNode->removeChild($elems->item($i));
			}
		}
		
		// strip elements that contain style="display: none;"
		$elems = @$xpath->query("//*[contains(@style,'display:none')]", $this->readability->dom);
		// check for matches
		if ($elems && $elems->length > 0) {
			$this->debug('Stripping '.$elems->length.' elements with inline display:none style');
			for ($i=$elems->length-1; $i >= 0; $i--) {
				$elems->item($i)->parentNode->removeChild($elems->item($i));
			}
		}
		
		// try to get body
		foreach ($this->config->body as $pattern) {
			$elems = @$xpath->query($pattern, $this->readability->dom);
			// check for matches
			if ($elems && $elems->length > 0) {
				$this->debug('Body matched');
				$this->debug("...XPath match: $pattern");
				if ($elems->length == 1) {				
					$this->body = $elems->item(0);
					// prune (clean up elements that may not be content)
					if ($this->config->prune()) {
						$this->debug('...pruning content');
						$this->readability->prepArticle($this->body);
					}
					break;
				} else {
					$this->body = $this->readability->dom->createElement('div');
					$this->debug($elems->length.' body elems found');
					foreach ($elems as $elem) {
						if (!isset($elem->parentNode)) continue;
						$isDescendant = false;
						foreach ($this->body->childNodes as $parent) {
							if ($this->isDescendant($parent, $elem)) {
								$isDescendant = true;
								break;
							}
						}
						if ($isDescendant) {
							$this->debug('...element is child of another body element, skipping.');
						} else {
							// prune (clean up elements that may not be content)
							if ($this->config->prune()) {
								$this->debug('Pruning content');
								$this->readability->prepArticle($elem);
							}
							$this->debug('...element added to body');
							$this->body->appendChild($elem);
						}
					}
					if ($this->body->hasChildNodes()) break;
				}
			}
		}		
		
		// auto detect?
		$detect_title = $detect_body = $detect_author = $detect_date = false;
		// detect title?
		if (!isset($this->title)) {
			if (empty($this->config->title) || $this->config->autodetect_on_failure()) {
				$detect_title = true;
			}
		}
		// detect body?
		if (!isset($this->body)) {
			if (empty($this->config->body) || $this->config->autodetect_on_failure()) {
				$detect_body = true;
			}
		}
		// detect author?
		if (empty($this->author)) {
			if (empty($this->config->author) || $this->config->autodetect_on_failure()) {
				$detect_author = true;
			}
		}
		// detect date?
		if (!isset($this->date)) {
			if (empty($this->config->date) || $this->config->autodetect_on_failure()) {
				$detect_date = true;
			}
		}

		// check for hNews
		if ($detect_title || $detect_body) {
			// check for hentry
			$elems = @$xpath->query("//*[contains(concat(' ',normalize-space(@class),' '),' hentry ')]", $this->readability->dom);
			if ($elems && $elems->length > 0) {
				$this->debug('hNews: found hentry');
				$hentry = $elems->item(0);
				
				if ($detect_title) {
					// check for entry-title
					$elems = @$xpath->query(".//*[contains(concat(' ',normalize-space(@class),' '),' entry-title ')]", $hentry);
					if ($elems && $elems->length > 0) {
						$this->title = $elems->item(0)->textContent;
						$this->debug('hNews: found entry-title: '.$this->title);
						// remove title from document
						$elems->item(0)->parentNode->removeChild($elems->item(0));
						$detect_title = false;
					}
				}
				
				if ($detect_date) {
					// check for time element with pubdate attribute
					$elems = @$xpath->query(".//time[@pubdate] | .//abbr[contains(concat(' ',normalize-space(@class),' '),' published ')]", $hentry);
					if ($elems && $elems->length > 0) {
						$this->date = strtotime(trim($elems->item(0)->textContent));
						// remove date from document
						//$elems->item(0)->parentNode->removeChild($elems->item(0));
						if ($this->date) {
							$this->debug('hNews: found publication date: '.date('Y-m-d H:i:s', $this->date));
							$detect_date = false;
						} else {
							$this->date = null;
						}
					}
				}

				if ($detect_author) {
					// check for time element with pubdate attribute
					$elems = @$xpath->query(".//*[contains(concat(' ',normalize-space(@class),' '),' vcard ') and (contains(concat(' ',normalize-space(@class),' '),' author ') or contains(concat(' ',normalize-space(@class),' '),' byline '))]", $hentry);
					if ($elems && $elems->length > 0) {
						$author = $elems->item(0);
						$fn = @$xpath->query(".//*[contains(concat(' ',normalize-space(@class),' '),' fn ')]", $author);
						if ($fn && $fn->length > 0) {
							foreach ($fn as $_fn) {
								if (trim($_fn->textContent) != '') {
									$this->author[] = trim($_fn->textContent);
									$this->debug('hNews: found author: '.trim($_fn->textContent));
								}
							}
						} else {
							if (trim($author->textContent) != '') {
								$this->author[] = trim($author->textContent);
								$this->debug('hNews: found author: '.trim($author->textContent));
							}
						}
						$detect_author = empty($this->author);
					}
				}
				
				// check for entry-content.
				// according to hAtom spec, if there are multiple elements marked entry-content,
				// we include all of these in the order they appear - see http://microformats.org/wiki/hatom#Entry_Content
				if ($detect_body) {
					$elems = @$xpath->query(".//*[contains(concat(' ',normalize-space(@class),' '),' entry-content ')]", $hentry);
					if ($elems && $elems->length > 0) {
						$this->debug('hNews: found entry-content');
						if ($elems->length == 1) {
							// what if it's empty? (some sites misuse hNews - place their content outside an empty entry-content element)
							$e = $elems->item(0);
							if (($e->tagName == 'img') || (trim($e->textContent) != '')) {
								$this->body = $elems->item(0);
								// prune (clean up elements that may not be content)
								if ($this->config->prune()) {
									$this->debug('Pruning content');
									$this->readability->prepArticle($this->body);
								}
								$detect_body = false;
							} else {
								$this->debug('hNews: skipping entry-content - appears not to contain content');
							}
							unset($e);
						} else {
							$this->body = $this->readability->dom->createElement('div');
							$this->debug($elems->length.' entry-content elems found');
							foreach ($elems as $elem) {
								if (!isset($elem->parentNode)) continue;
								$isDescendant = false;
								foreach ($this->body->childNodes as $parent) {
									if ($this->isDescendant($parent, $elem)) {
										$isDescendant = true;
										break;
									}
								}
								if ($isDescendant) {
									$this->debug('Element is child of another body element, skipping.');
								} else {
									// prune (clean up elements that may not be content)
									if ($this->config->prune()) {
										$this->debug('Pruning content');
										$this->readability->prepArticle($elem);
									}								
									$this->debug('Element added to body');									
									$this->body->appendChild($elem);
								}
							}
							$detect_body = false;
						}
					}
				}
			}
		}

		// check for elements marked with instapaper_title
		if ($detect_title) {
			// check for instapaper_title
			$elems = @$xpath->query("//*[contains(concat(' ',normalize-space(@class),' '),' instapaper_title ')]", $this->readability->dom);
			if ($elems && $elems->length > 0) {
				$this->title = $elems->item(0)->textContent;
				$this->debug('Title found (.instapaper_title): '.$this->title);
				// remove title from document
				$elems->item(0)->parentNode->removeChild($elems->item(0));
				$detect_title = false;
			}
		}
		// check for elements marked with instapaper_body
		if ($detect_body) {
			$elems = @$xpath->query("//*[contains(concat(' ',normalize-space(@class),' '),' instapaper_body ')]", $this->readability->dom);
			if ($elems && $elems->length > 0) {
				$this->debug('body found (.instapaper_body)');
				$this->body = $elems->item(0);
				// prune (clean up elements that may not be content)
				if ($this->config->prune()) {
					$this->debug('Pruning content');
					$this->readability->prepArticle($this->body);
				}
				$detect_body = false;
			}
		}
		
		// Find author in rel="author" marked element
		// We only use this if there's exactly one.
		// If there's more than one, it could indicate more than
		// one author, but it could also indicate that we're processing
		// a page listing different articles with different authors.
		if ($detect_author) {
			$elems = @$xpath->query("//a[contains(concat(' ',normalize-space(@rel),' '),' author ')]", $this->readability->dom);
			if ($elems && $elems->length == 1) {
				$author = trim($elems->item(0)->textContent);
				if ($author != '') {
					$this->debug("Author found (rel=\"author\"): $author");
					$this->author[] = $author;
					$detect_author = false;
				}
			}
		}

		// Find date in pubdate marked time element
		// For the same reason given above, we only use this
		// if there's exactly one element.
		if ($detect_date) {
			$elems = @$xpath->query("//time[@pubdate]", $this->readability->dom);
			if ($elems && $elems->length == 1) {
				$this->date = strtotime(trim($elems->item(0)->textContent));
				// remove date from document
				//$elems->item(0)->parentNode->removeChild($elems->item(0));
				if ($this->date) {
					$this->debug('Date found (pubdate marked time element): '.date('Y-m-d H:i:s', $this->date));
					$detect_date = false;
				} else {
					$this->date = null;
				}
			}
		}

		// still missing title or body, so we detect using Readability
		if ($detect_title || $detect_body) {
			$this->debug('Using Readability');
			// clone body if we're only using Readability for title (otherwise it may interfere with body element)
			if (isset($this->body)) $this->body = $this->body->cloneNode(true);
			$success = $this->readability->init();
		}
		if ($detect_title) {
			$this->debug('Detecting title');
			$this->title = $this->readability->getTitle()->textContent;
		}
		if ($detect_body && $success) {
			$this->debug('Detecting body');
			$this->body = $this->readability->getContent();
			if ($this->body->childNodes->length == 1 && $this->body->firstChild->nodeType === XML_ELEMENT_NODE) {
				$this->body = $this->body->firstChild;
			}
			// prune (clean up elements that may not be content)
			if ($this->config->prune()) {
				$this->debug('Pruning content');
				$this->readability->prepArticle($this->body);
			}
		}
		if (isset($this->body)) {
			// remove scripts
			$this->readability->removeScripts($this->body);
			// remove any h1-h6 elements that appear as first thing in the body
			// and which match our title
			if (isset($this->title) && ($this->title != '')) {
				$firstChild = $this->body->firstChild;
				while ($firstChild->nodeType && ($firstChild->nodeType !== XML_ELEMENT_NODE)) {
					$firstChild = $firstChild->nextSibling;
				}
				if (($firstChild->nodeType === XML_ELEMENT_NODE)
					&& in_array(strtolower($firstChild->tagName), array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))
					&& (strtolower(trim($firstChild->textContent)) == strtolower(trim($this->title)))) {
						$this->body->removeChild($firstChild);
				}
			}
			// prevent self-closing iframes
			$elems = $this->body->getElementsByTagName('iframe');
			for ($i = $elems->length-1; $i >= 0; $i--) {
				$e = $elems->item($i);
				if (!$e->hasChildNodes()) {
					$e->appendChild($this->body->ownerDocument->createTextNode('[embedded content]'));
				}
			}
			// remove image lazy loading - WordPress plugin http://wordpress.org/extend/plugins/lazy-load/
			// the plugin replaces the src attribute to point to a 1x1 gif and puts the original src
			// inside the data-lazy-src attribute. It also places the original image inside a noscript element 
			// next to the amended one.
			$elems = @$xpath->query("//img[@data-lazy-src]", $this->body);
			for ($i = $elems->length-1; $i >= 0; $i--) {
				$e = $elems->item($i);
				// let's see if we can grab image from noscript
				if ($e->nextSibling !== null && $e->nextSibling->nodeName === 'noscript') {
					$_new_elem = $e->ownerDocument->createDocumentFragment();
					@$_new_elem->appendXML($e->nextSibling->innerHTML);
					$e->nextSibling->parentNode->replaceChild($_new_elem, $e->nextSibling);
					$e->parentNode->removeChild($e);
				} else {
					// Use data-lazy-src as src value
					$e->setAttribute('src', $e->getAttribute('data-lazy-src'));
					$e->removeAttribute('data-lazy-src');
				}
			}
		
			$this->success = true;
		}
		
		// if we've had no success and we've used tidy, there's a chance
		// that tidy has messed up. So let's try again without tidy...
		if (!$this->success && $tidied && $smart_tidy) {
			$this->debug('Trying again without tidy');
			$this->process($original_html, $url, false);
		}

		return $this->success;
	}
	
	private function isDescendant(DOMElement $parent, DOMElement $child) {
		$node = $child->parentNode;
		while ($node != null) {
			if ($node->isSameNode($parent))	return true;
			$node = $node->parentNode;
		}
		return false;
	}

	public function getContent() {
		return $this->body;
	}
	
	public function getTitle() {
		return $this->title;
	}
	
	public function getAuthors() {
		return $this->author;
	}
	
	public function getLanguage() {
		return $this->language;
	}
	
	public function getDate() {
		return $this->date;
	}
	
	public function getSiteConfig() {
		return $this->config;
	}
	
	public function getNextPageUrl() {
		return $this->nextPageUrl;
	}
}