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
|
<form action="" method="post">
<input type="text" name="page" value="http://" />
<input type="submit" />
</form>
<?php
/******************************************************************
Projectname: Automatic Keyword Generator
Version: 0.2
Author: Ver Pangonilo <smp_AT_itsp.info>
Last modified: 21 July 2006
Copyright (C): 2006 Ver Pangonilo, All Rights Reserved
* GNU General Public License (Version 2, June 1991)
*
* This program is free software; you can redistribute
* it and/or modify it under the terms of the GNU
* General Public License as published by the Free
* Software Foundation; either version 2 of the License,
* or (at your option) any later version.
*
* This program is distributed in the hope that it will
* be useful, but WITHOUT ANY WARRANTY; without even the
* implied warranty of MERCHANTABILITY or FITNESS FOR A
* PARTICULAR PURPOSE. See the GNU General Public License
* for more details.
Description:
This class can generates automatically META Keywords for your
web pages based on the contents of your articles. This will
eliminate the tedious process of thinking what will be the best
keywords that suits your article. The basis of the keyword
generation is the number of iterations any word or phrase
occured within an article.
This automatic keyword generator will create single words,
two word phrase and three word phrases. Single words will be
filtered from a common words list.
Change Log:
===========
0.2 Ver Pangonilo - 22 July 2005
================================
Added user configurable parameters and commented codes
for easier end user understanding.
0.3 Vasilich (vasilich_AT_grafin.kiev.ua) - 26 July 2006
=========================================================
Added encoding parameter to work with UTF texts, min number
of the word/phrase occurrences,
******************************************************************/
class autokeyword {
//declare variables
//the site contents
var $contents;
var $encoding;
//the generated keywords
var $keywords;
//minimum word length for inclusion into the single word
//metakeys
var $wordLengthMin;
var $wordOccuredMin;
//minimum word length for inclusion into the 2 word
//phrase metakeys
var $word2WordPhraseLengthMin;
var $phrase2WordLengthMinOccur;
//minimum word length for inclusion into the 3 word
//phrase metakeys
var $word3WordPhraseLengthMin;
//minimum phrase length for inclusion into the 2 word
//phrase metakeys
var $phrase2WordLengthMin;
var $phrase3WordLengthMinOccur;
//minimum phrase length for inclusion into the 3 word
//phrase metakeys
var $phrase3WordLengthMin;
function autokeyword($params, $encoding) {
//get parameters
$this->encoding = $encoding;
mb_internal_encoding($encoding);
$this->contents = $this->replace_chars($params['content']);
// single word
$this->wordLengthMin = $params['min_word_length'];
$this->wordOccuredMin = $params['min_word_occur'];
// 2 word phrase
$this->word2WordPhraseLengthMin = $params['min_2words_length'];
$this->phrase2WordLengthMin = $params['min_2words_phrase_length'];
$this->phrase2WordLengthMinOccur = $params['min_2words_phrase_occur'];
// 3 word phrase
$this->word3WordPhraseLengthMin = $params['min_3words_length'];
$this->phrase3WordLengthMin = $params['min_3words_phrase_length'];
$this->phrase3WordLengthMinOccur = $params['min_3words_phrase_occur'];
//parse single, two words and three words
}
function get_keywords() {
$keywords = $this->parse_words() . $this->parse_2words() . $this->parse_3words();
$keywords = array_unique(explode(' ',$keywords));
//$keywords = mb_substr($keywords, 0, 230, 'utf-8');
return implode(', ',$keywords);
}
//turn the site contents into an array
//then replace common html tags.
function replace_chars($content) {
//convert all characters to lower case
$content = mb_strtolower($content);
//$content = mb_strtolower($content, "UTF-8");
$content = strip_tags($content);
$punctuations = array("\r\n", "\n", ' ', 'gettime', 'http', "document", "write", "unescape", "script", "protocol", "location", '"', '»', '%3e', '%3c', ' ', '|', ',', ')', '(', '.', "'", '"', '<', '>', ';', '!', '?', '/', '-', '_', '[', ']', ':', '+', '=', '#', '$', '"', '©', '>', '<', chr(10), chr(13), chr(9));
$content = str_replace($punctuations, " ", $content);
// replace multiple gaps
$content = preg_replace('/ {2,}/si', " ", $content);
return $content;
}
//single words META KEYWORDS
function parse_words() {
//list of commonly used words
// this can be edited to suit your needs
$common = array("able", "about", "above", "act", "add", "afraid", "after", "again", "against", "age", "ago", "agree", "all", "almost", "alone", "along", "already", "also", "although", "always", "am", "amount", "an", "and", "anger", "angry", "animal", "another", "answer", "any", "appear", "apple", "are", "arrive", "arm", "arms", "around", "arrive", "as", "ask", "at", "attempt", "aunt", "away", "back", "bad", "bag", "bay", "be", "became", "because", "become", "been", "before", "began", "begin", "behind", "being", "bell", "belong", "below", "beside", "best", "better", "between", "beyond", "big", "body", "bone", "born", "borrow", "both", "bottom", "box", "boy", "break", "bring", "brought", "bug", "built", "busy", "but", "buy", "by", "call", "came", "can", "cause", "choose", "close", "close",
"consider", "come", "consider", "considerable", "contain", "continue", "could", "cry", "cut", "dare", "dark", "deal", "dear", "decide", "deep", "did", "die", "do", "does", "dog", "done", "doubt", "down", "during", "each", "ear", "early", "eat", "effort", "either", "else", "end", "enjoy", "enough", "enter", "even", "ever", "every", "except", "expect", "explain", "fail", "fall", "far", "fat", "favor", "fear", "feel", "feet", "fell", "felt", "few", "fill", "find", "fit", "fly", "follow", "for", "forever", "forget", "from", "front", "gave", "get", "gives", "goes", "gone", "good", "got", "gray", "great", "green", "grew", "grow", "guess", "had", "half", "hang", "happen", "has", "hat", "have", "he", "hear", "heard", "held", "hello", "help", "her", "here", "hers", "high", "hill", "him", "his",
"hit", "hold", "hot", "how", "however", "I", "if", "ill", "in", "indeed", "instead", "into", "iron", "is", "it", "its", "just", "keep", "kept", "knew", "know", "known", "late", "least", "led", "left", "lend", "less", "let", "like", "likely", "likr", "lone", "long", "look", "lot", "make", "many", "may", "me", "mean", "met", "might", "mile", "mine", "moon", "more", "most", "move", "much", "must", "my", "near", "nearly", "necessary", "neither", "never", "next", "no", "none", "nor", "not", "note", "nothing", "now", "number", "of", "off", "often", "oh", "on", "once", "only", "or", "other", "ought", "our", "out", "please", "prepare", "probable", "pull", "pure", "push", "put", "raise", "ran", "rather", "reach", "realize", "reply", "require", "rest", "run", "said", "same", "sat", "saw", "say",
"see", "seem", "seen", "self", "sell", "sent", "separate", "set", "shall", "she", "should", "side", "sign", "since", "so", "sold", "some", "soon", "sorry", "stay", "step", "stick", "still", "stood", "such", "sudden", "suppose", "take", "taken", "talk", "tall", "tell", "ten", "than", "thank", "that", "the", "their", "them", "then", "there", "therefore", "these", "they", "this", "those", "though", "through", "till", "to", "today", "told", "tomorrow", "too", "took", "tore", "tought", "toward", "tried", "tries", "trust", "try", "turn", "two", "under", "until", "up", "upon", "us", "use", "usual", "various", "verb", "very", "visit", "want", "was", "we", "well", "went", "were", "what", "when", "where", "whether", "which", "while", "white", "who", "whom", "whose", "why", "will", "with", "within",
"without", "would", "yes", "yet", "you", "young", "your", "br", "img", "p", "lt", "gt", "quot", "copy", "Akmenė", "Alytus", "Anykščiai", "Ariogala", "Baltoji", "Vokė", "Birštonas", "Biržai", "Daugai", "Druskininkai", "Dusetos", "Dūkštas", "Eišiškės", "Elektrėnai", "Ežerėlis", "Gargždai", "Garliava", "Gelgaudiškis", "Grigiškės", "Ignalina", "Jieznas", "Jonava", "Joniškis", "Joniškėlis", "Jurbarkas", "Kaišiadorys", "Kalvarija", "Kaunas", "Kavarskas", "Kazlų", "Rūda", "Kelmė", "Klaipėda", "Kretinga", "Kudirkos", "Naumiestis", "Kupiškis", "Kuršėnai", "Kybartai", "Kėdainiai", "Lazdijai", "Lentvaris", "Linkuva", "Marijampolė", "Mažeikiai", "Molėtai", "Naujoji", "Akmenė", "Nemenčinė", "Neringa", "Neringos", "sav.", "Obeliai", "Pabradė", "Pagėgiai", "Pakruojis", "Palanga", "Pandėlys", "Panemunė",
"Panevėžys", "Pasvalys", "Plungė", "Priekulė", "Prienai", "Radviliškis", "Ramygala", "Raseiniai", "Rietavas", "Rokiškis", "Rūdiškės", "Salantai", "Seda", "Simnas", "Skaudvilė", "Skuodas", "Smalininkai", "Subačius", "Tauragė", "Telšiai", "Trakai", "Troškūnai", "Tytuvėnai", "Ukmergė", "Utena", "Užventis", "Vabalninkas", "Varniai", "Varėna", "Veisiejai", "Venta", "Viekšniai", "Vievis", "Vilkaviškis", "Vilkija", "Vilnius", "Virbalis", "Visaginas", "Zarasai", "Šakiai", "Šalčininkai", "Šeduva", "Šiauliai", "Šilalė", "Šilutė", "Širvintos", "Švenčionys", "Švenčionėliai", "Žagarė", "Žiežmariai", "-------------", "Germany", "Ireland", "Lietuva", "Russian", "Federation", "Spain", "United", "Kingdom", "United", "States", "Lietuva", "United", "States", "United", "Kingdom", "Russian", "Federation",
"Spain", "Germany", "Ireland", "-------------", "Afghanistan", "Albania", "Algeria", "American", "Samoa", "Andorra", "Angola", "Anguilla", "Antarctica", "Antigua", "And", "Barbuda", "Argentina", "Armenia", "Aruba", "Australia", "Austria", "Azerbaijan", "Bahamas", "Bahrain", "Bangladesh", "Barbados", "Belarus", "Belgium", "Belize", "Benin", "Bermuda", "Bhutan", "Bolivia", "Bosnia", "And", "Herzegowina", "Botswana", "Bouvet", "Island", "Brazil", "British", "Indian", "Ocean", "Territory", "Brunei", "Darussalam", "Bulgaria", "Burkina", "Faso", "Burundi", "Cambodia", "Cameroon", "Canada", "Cape", "Verde", "Cayman", "Islands", "Central", "African", "Republic", "Chad", "Chile", "China", "Christmas", "Island", "Cocos", "(Keeling)", "Islands", "Colombia", "Comoros", "Congo", "Cook", "Islands",
"Costa", "Rica", "Cote", "D'Ivoire", "Croatia", "Cuba", "Cyprus", "Czech", "Republic", "Denmark", "Djibouti", "Dominica", "Dominican", "Republic", "East", "Timor", "Ecuador", "Egypt", "El", "Salvador", "Equatorial", "Guinea", "Eritrea", "Estonia", "Ethiopia", "Falkland", "Islands", "Faroe", "Islands", "Fiji", "Finland", "France", "France,", "Metropolitan", "French", "Guiana", "French", "Polynesia", "French", "Southern", "Territories", "Gabon", "Gambia", "Georgia", "Ghana", "Gibraltar", "Greece", "Greenland", "Grenada", "Guadeloupe", "Guam", "Guatemala", "Guinea", "Guinea-Bissau", "Guyana", "Haiti", "Heard", "And", "Mc", "Donald", "Islands", "Honduras", "Hong", "Kong", "Hungary", "Iceland", "India", "Indonesia", "International", "Iran", "Iraq", "Israel", "Italy", "Jamaica", "Japan",
"Jordan", "Kazakhstan", "Kenya", "Kiribati", "Kuwait", "Kyrgyzstan", "Lao", "People's", "Republic", "Latvia", "Lebanon", "Lesotho", "Liberia", "Libyan", "Arab", "Jamahiriya", "Liechtenstein", "Luxembourg", "Macau", "Macedonia", "Madagascar", "Malawi", "Malaysia", "Maldives", "Mali", "Malta", "Marshall", "Islands", "Martinique", "Mauritania", "Mauritius", "Mayotte", "Mexico", "Micronesia", "Moldova", "Monaco", "Mongolia", "Montserrat", "Morocco", "Mozambique", "Myanmar", "Namibia", "Nauru", "Nepal", "Netherlands", "Netherlands", "Antilles", "New", "Caledonia", "New", "Zealand", "Nicaragua", "Niger", "Nigeria", "Niue", "Norfolk", "Island", "North", "Korea", "Northern", "Mariana", "Islands", "Norway", "Oman", "Pakistan", "Palau", "Panama", "Papua", "New", "Guinea", "Paraguay", "Peru",
"Philippines", "Pitcairn", "Poland", "Portugal", "Puerto", "Rico", "Qatar", "Reunion", "Romania", "Rwanda", "Saint", "Kitts", "And", "Nevis", "Saint", "Lucia", "Saint", "Vincent", "And", "The", "Grenadin", "Samoa", "San", "Marino", "Sao", "Tome", "And", "Principe", "Saudi", "Arabia", "Senegal", "Serbia", "Seychelles", "Sierra", "Leone", "Singapore", "Slovakia", "Slovenia", "Solomon", "Islands", "Somalia", "South", "Africa", "South", "Georgia", "And", "The", "South", "Sa", "South", "Korea", "Sri", "Lanka", "St", "Helena", "St", "Pierre", "and", "Miquelon", "Sudan", "Suriname", "Svalbard", "And", "Jan", "Mayen", "Islands", "Swaziland", "Sweden", "Switzerland", "Syrian", "Arab", "Republic", "Taiwan", "Tajikistan", "Tanzania", "Thailand", "Togo", "Tokelau", "Tonga", "Trinidad", "And", "Tobago",
"Tunisia", "Turkey", "Turkmenistan", "Turks", "And", "Caicos", "Islands", "Tuvalu", "Uganda", "Ukraine", "United", "Arab", "Emirates", "United", "States", "Minor", "Outlying", "I", "Uruguay", "Uzbekistan", "Vanuatu", "Vatican", "City", "State", "Venezuela", "Viet", "Nam", "Virgin", "Islands", "(British)", "Virgin", "Islands", "(U.S.)", "Wallis", "And", "Futuna", "Islands", "Western", "Sahara", "Yemen", "Zaire", "Zambia", "Zimbabwe");
$common = mb_strtolower($common, "utf-8");
//create an array out of the site contents
$s = str_replace($common, '', $this->contents);
$s = split(" ", $this->contents);
//initialize array
$k = array();
//iterate inside the array
foreach ($s as $key => $val) {
//delete single or two letter words and
//Add it to the list if the word is not
//contained in the common words list.
if (mb_strlen(trim($val)) >= $this->wordLengthMin && !in_array(trim($val), $common) && !is_numeric(trim($val))) {
$k[] = trim($val);
}
}
//count the words
$k = array_count_values($k);
//sort the words from
//highest count to the
//lowest.
$occur_filtered = $this->occure_filter($k, $this->wordOccuredMin);
arsort($occur_filtered);
$imploded = $this->implode(" ", $occur_filtered);
//release unused variables
unset($k);
unset($s);
return $imploded;
}
function parse_2words() {
//create an array out of the site contents
$x = split(" ", $this->contents);
//initilize array
//$y = array();
for ($i = 0; $i < count($x) - 1; $i++) {
//delete phrases lesser than 5 characters
if ((mb_strlen(trim($x[$i])) >= $this->word2WordPhraseLengthMin) && (mb_strlen(trim($x[$i + 1])) >= $this->word2WordPhraseLengthMin)) {
$y[] = trim($x[$i]) . " " . trim($x[$i + 1]);
}
}
//count the 2 word phrases
$y = array_count_values($y);
$occur_filtered = $this->occure_filter($y, $this->phrase2WordLengthMinOccur);
//sort the words from highest count to the lowest.
arsort($occur_filtered);
$imploded = $this->implode(" ", $occur_filtered);
//release unused variables
unset($y);
unset($x);
return $imploded;
}
function parse_3words() {
//create an array out of the site contents
$a = split(" ", $this->contents);
//initilize array
$b = array();
for ($i = 0; $i < count($a) - 2; $i++) {
//delete phrases lesser than 5 characters
if ((mb_strlen(trim($a[$i])) >= $this->word3WordPhraseLengthMin) && (mb_strlen(trim($a[$i + 1])) > $this->word3WordPhraseLengthMin) && (mb_strlen(trim($a[$i + 2])) > $this->word3WordPhraseLengthMin) && (mb_strlen(trim($a[$i]) . trim($a[$i + 1]) . trim($a[$i + 2])) > $this->phrase3WordLengthMin)) {
$b[] = trim($a[$i]) . " " . trim($a[$i + 1]) . " " . trim($a[$i + 2]);
}
}
//count the 3 word phrases
$b = array_count_values($b);
//sort the words from
//highest count to the
//lowest.
$occur_filtered = $this->occure_filter($b, $this->phrase3WordLengthMinOccur);
arsort($occur_filtered);
$imploded = $this->implode(" ", $occur_filtered);
//release unused variables
unset($a);
unset($b);
return $imploded;
}
function occure_filter($array_count_values, $min_occur) {
$occur_filtered = array();
foreach ($array_count_values as $word => $occured) {
if ($occured >= $min_occur) {
$occur_filtered[$word] = $occured;
}
}
return $occur_filtered;
}
function implode($gule, $array) {
$c = "";
foreach ($array as $key => $val) {
@$c .= $key . $gule;
}
return $c;
}
function content() {
return $this->contents;
}
}
/******************************************************************
Projectname: Autolink Keywords Application Script 1
Version: 0.1
Author: Ver Pangonilo <smp@limbofreak.com>
Last modified: 05 January 2007
Copyright (C): 2007 Ver Pangonilo, All Rights Reserved
* GNU General Public License (Version 2, June 1991)
*
* This program is free software; you can redistribute
* it and/or modify it under the terms of the GNU
* General Public License as published by the Free
* Software Foundation; either version 2 of the License,
* or (at your option) any later version.
*
* This program is distributed in the hope that it will
* be useful, but WITHOUT ANY WARRANTY; without even the
* implied warranty of MERCHANTABILITY or FITNESS FOR A
* PARTICULAR PURPOSE. See the GNU General Public License
* for more details.
Description:
============
Note: This class uses the output Automatic Keyword Generator.
This class can automatically create keywords link within an articles
if the keyword is found on a predetermined list of linked words.
The predetermined list could contain words and links to other
websites like advertisers or simply a link to other articles
in within your website.
Replacement Type:
=================
Since the autokeyword generator class produces only lower case words
and phrases, this example uses Case Sensitive string replacement.
******************************************************************/
if (isset($_POST) && !empty($_POST['page']) && $_POST['page'] != 'http://') {
$data = file_get_contents($_POST['page']);
$data = preg_replace('%<script[^>]*>(.*?)</script>%si', '', $data);
$data = preg_replace('%<style[^>]*>(.*?)</style>%si', '', $data);
$data = trim(strip_tags($data));
$data = trim(preg_replace('/\[(.*)\]/i', '', $data));
$data = trim(preg_replace('/\B"\b([^"\x84\x93\x94\r\n]+)\b"\B/', '\1', $data)); //Quates
$search = array('«', " ", ' ', " ", '|', "\t", ',');
$data = trim(str_replace($search, ' ', $data));
$data = mb_strtolower($data, "utf-8");
//$data = preg_replace('/[\W]/m', "\n", $data);
//$data = trim(preg_replace('/^[ \t]*$/m', '', $data)); //remove blank lines
$data = preg_replace("`\s+`", "\n", $data);
//$data = preg_replace("/\n+/s","\n",$data);
$common = array("Akmenė", "Alytus", "Anykščiai", "Ariogala", "Baltoji", "Vokė", "Birštonas", "Biržai", "Daugai", "Druskininkai", "Dusetos", "Dūkštas", "Eišiškės", "Elektrėnai", "Ežerėlis", "Gargždai", "Garliava", "Gelgaudiškis", "Grigiškės", "Ignalina", "Jieznas", "Jonava", "Joniškis", "Joniškėlis", "Jurbarkas", "Kaišiadorys", "Kalvarija", "Kaunas", "Kavarskas", "Kazlų", "Rūda", "Kelmė", "Klaipėda", "Kretinga", "Kudirkos", "Naumiestis", "Kupiškis", "Kuršėnai", "Kybartai", "Kėdainiai", "Lazdijai", "Lentvaris", "Linkuva", "Marijampolė", "Mažeikiai", "Molėtai", "Naujoji", "Akmenė", "Nemenčinė", "Neringa", "Neringos", "sav.", "Obeliai", "Pabradė", "Pagėgiai", "Pakruojis", "Palanga", "Pandėlys", "Panemunė",
"Panevėžys", "Pasvalys", "Plungė", "Priekulė", "Prienai", "Radviliškis", "Ramygala", "Raseiniai", "Rietavas", "Rokiškis", "Rūdiškės", "Salantai", "Seda", "Simnas", "Skaudvilė", "Skuodas", "Smalininkai", "Subačius", "Tauragė", "Telšiai", "Trakai", "Troškūnai", "Tytuvėnai", "Ukmergė", "Utena", "Užventis", "Vabalninkas", "Varniai", "Varėna", "Veisiejai", "Venta", "Viekšniai", "Vievis", "Vilkaviškis", "Vilkija", "Vilnius", "Virbalis", "Visaginas", "Zarasai", "Šakiai", "Šalčininkai", "Šeduva", "Šiauliai", "Šilalė", "Šilutė", "Širvintos", "Švenčionys", "Švenčionėliai", "Žagarė", "Žiežmariai", "-------------", "Germany", "Ireland", "Lietuva", "Russian", "Federation", "Spain", "United", "Kingdom", "United", "States", "Lietuva", "United", "States", "United", "Kingdom", "Russian", "Federation",
"Spain", "Germany", "Ireland", "Afghanistan", "Albania", "Algeria", "American", "Samoa", "Andorra", "Angola", "Anguilla", "Antarctica", "Antigua", "And", "Barbuda", "Argentina", "Armenia", "Aruba", "Australia", "Austria", "Azerbaijan", "Bahamas", "Bahrain", "Bangladesh", "Barbados", "Belarus", "Belgium", "Belize", "Benin", "Bermuda", "Bhutan", "Bolivia", "Bosnia", "And", "Herzegowina", "Botswana", "Bouvet", "Island", "Brazil", "British", "Indian", "Ocean", "Territory", "Brunei", "Darussalam", "Bulgaria", "Burkina", "Faso", "Burundi", "Cambodia", "Cameroon", "Canada", "Cape", "Verde", "Cayman", "Islands", "Central", "African", "Republic", "Chad", "Chile", "China", "Christmas", "Island", "Cocos", "(Keeling)", "Islands", "Colombia", "Comoros", "Congo", "Cook", "Islands",
"Costa", "Rica", "Cote", "D'Ivoire", "Croatia", "Cuba", "Cyprus", "Czech", "Republic", "Denmark", "Djibouti", "Dominica", "Dominican", "Republic", "East", "Timor", "Ecuador", "Egypt", "El", "Salvador", "Equatorial", "Guinea", "Eritrea", "Estonia", "Ethiopia", "Falkland", "Islands", "Faroe", "Islands", "Fiji", "Finland", "France", "France,", "Metropolitan", "French", "Guiana", "French", "Polynesia", "French", "Southern", "Territories", "Gabon", "Gambia", "Georgia", "Ghana", "Gibraltar", "Greece", "Greenland", "Grenada", "Guadeloupe", "Guam", "Guatemala", "Guinea", "Guinea-Bissau", "Guyana", "Haiti", "Heard", "And", "Mc", "Donald", "Islands", "Honduras", "Hong", "Kong", "Hungary", "Iceland", "India", "Indonesia", "International", "Iran", "Iraq", "Israel", "Italy", "Jamaica", "Japan",
"Jordan", "Kazakhstan", "Kenya", "Kiribati", "Kuwait", "Kyrgyzstan", "Lao", "People's", "Republic", "Latvia", "Lebanon", "Lesotho", "Liberia", "Libyan", "Arab", "Jamahiriya", "Liechtenstein", "Luxembourg", "Macau", "Macedonia", "Madagascar", "Malawi", "Malaysia", "Maldives", "Mali", "Malta", "Marshall", "Islands", "Martinique", "Mauritania", "Mauritius", "Mayotte", "Mexico", "Micronesia", "Moldova", "Monaco", "Mongolia", "Montserrat", "Morocco", "Mozambique", "Myanmar", "Namibia", "Nauru", "Nepal", "Netherlands", "Netherlands", "Antilles", "New", "Caledonia", "New", "Zealand", "Nicaragua", "Niger", "Nigeria", "Niue", "Norfolk", "Island", "North", "Korea", "Northern", "Mariana", "Islands", "Norway", "Oman", "Pakistan", "Palau", "Panama", "Papua", "New", "Guinea", "Paraguay", "Peru",
"Philippines", "Pitcairn", "Poland", "Portugal", "Puerto", "Rico", "Qatar", "Reunion", "Romania", "Rwanda", "Saint", "Kitts", "And", "Nevis", "Saint", "Lucia", "Saint", "Vincent", "Grenadin", "Samoa", "Marino", "Principe", "Saudi", "Arabia", "Senegal", "Serbia", "Seychelles", "Sierra", "Leone", "Singapore", "Slovakia", "Slovenia", "Solomon", "Islands", "Somalia", "South", "Africa", "South", "Georgia", "South", "Korea", "Sri", "Lanka", "Helena", "Pierre", "Miquelon", "Sudan", "Suriname", "Svalbard", "And", "Jan", "Mayen", "Islands", "Swaziland", "Sweden", "Switzerland", "Syrian", "Arab", "Republic", "Taiwan", "Tajikistan", "Tanzania", "Thailand", "Togo", "Tokelau", "Tonga", "Trinidad", "And", "Tobago",
"Tunisia", "Turkey", "Turkmenistan", "Turks", "And", "Caicos", "Islands", "Tuvalu", "Uganda", "Ukraine", "United", "Arab", "Emirates", "United", "States", "Minor", "Outlying", "Uruguay", "Uzbekistan", "Vanuatu", "Vatican", "City", "State", "Venezuela", "Viet", "Nam", "Virgin", "Islands", "(British)", "Virgin", "Islands", "(U.S.)", "Wallis", "And", "Futuna", "Islands", "Western", "Sahara", "Yemen", "Zaire", "Zambia", "Zimbabwe");
$common = array_unique($common);
$common = mb_strtolower(implode(' ',$common), "utf-8");
//create an array out of the site contents
$data = str_replace(explode(' ',$common), '', $data);
//echo "<pre>$data</pre>";
/**********************************************
This is the automatice keyword generator class
***********************************************/
//this the actual application.
echo "<H1>Keywords:</H1>";
//echo $data;
$params['content'] = $data; //page content
//set the length of keywords you like
$params['min_word_length'] = 5; //minimum length of single words
$params['min_word_occur'] = 2; //minimum occur of single words
$params['min_2words_length'] = 5; //minimum length of words for 2 word phrases
$params['min_2words_phrase_length'] = 10; //minimum length of 2 word phrases
$params['min_2words_phrase_occur'] = 2; //minimum occur of 2 words phrase
$params['min_3words_length'] = 5; //minimum length of words for 3 word phrases
$params['min_3words_phrase_length'] = 10; //minimum length of 3 word phrases
$params['min_3words_phrase_occur'] = 2; //minimum occur of 3 words phrase
$keyword = new autokeyword($params, "utf-8");
$keywords = $keyword->get_keywords();
echo $keywords;
echo "<h1>Content</h1>";
echo $keyword->content();
}
?>
|