1: <?php
   2: 
   3: /*************************************************
   4:  *
   5:  * Snoopy - the PHP net client
   6:  * Author: Monte Ohrt <monte@ohrt.com>
   7:  * Copyright (c): 1999-2014, all rights reserved
   8:  * Version: 1.2.5
   9:  * This library is free software; you can redistribute it and/or
  10:  * modify it under the terms of the GNU Lesser General Public
  11:  * License as published by the Free Software Foundation; either
  12:  * version 2.1 of the License, or (at your option) any later version.
  13:  *
  14:  * This library is distributed in the hope that it will be useful,
  15:  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  16:  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  17:  * Lesser General Public License for more details.
  18:  *
  19:  * You should have received a copy of the GNU Lesser General Public
  20:  * License along with this library; if not, write to the Free Software
  21:  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  22:  *
  23:  * You may contact the author of Snoopy by e-mail at:
  24:  * monte@ohrt.com
  25:  *
  26:  * The latest version of Snoopy can be obtained from:
  27:  * http://snoopy.sourceforge.net/
  28:  *************************************************/
  29: class Snoopy
  30: {
  31:     /**** Public variables ****/
  32: 
  33:     /* user definable vars */
  34: 
  35:     var $host = "www.php.net"; // host name we are connecting to
  36:     var $port = 80; // port we are connecting to
  37:     var $proxy_host = ""; // proxy host to use
  38:     var $proxy_port = ""; // proxy port to use
  39:     var $proxy_user = ""; // proxy user to use
  40:     var $proxy_pass = ""; // proxy password to use
  41: 
  42:     var $agent = "Snoopy v1.2.5"; // agent we masquerade as
  43:     var $referer = ""; // referer info to pass
  44:     var $cookies = array(); // array of cookies to pass
  45:     // $cookies["username"]="joe";
  46:     var $rawheaders = array(); // array of raw headers to send
  47:     // $rawheaders["Content-type"]="text/html";
  48: 
  49:     var $maxredirs = 5; // http redirection depth maximum. 0 = disallow
  50:     var $lastredirectaddr = ""; // contains address of last redirected address
  51:     var $offsiteok = true; // allows redirection off-site
  52:     var $maxframes = 0; // frame content depth maximum. 0 = disallow
  53:     var $expandlinks = true; // expand links to fully qualified URLs.
  54:     // this only applies to fetchlinks()
  55:     // submitlinks(), and submittext()
  56:     var $passcookies = true; // pass set cookies back through redirects
  57:     // NOTE: this currently does not respect
  58:     // dates, domains or paths.
  59: 
  60:     var $user = ""; // user for http authentication
  61:     var $pass = ""; // password for http authentication
  62: 
  63:     // http accept types
  64:     var $accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*";
  65: 
  66:     var $results = ""; // where the content is put
  67: 
  68:     var $error = ""; // error messages sent here
  69:     var $response_code = ""; // response code returned from server
  70:     var $headers = array(); // headers returned from server sent here
  71:     var $maxlength = 500000; // max return data length (body)
  72:     var $read_timeout = 0; // timeout on read operations, in seconds
  73:     // supported only since PHP 4 Beta 4
  74:     // set to 0 to disallow timeouts
  75:     var $timed_out = false; // if a read operation timed out
  76:     var $status = 0; // http request status
  77: 
  78:     var $temp_dir = "/tmp"; // temporary directory that the webserver
  79:     // has permission to write to.
  80:     // under Windows, this should be C:\temp
  81: 
  82:     var $curl_path = "/usr/bin/curl";
  83:     // Snoopy will use cURL for fetching
  84:     // SSL content if a full system path to
  85:     // the cURL binary is supplied here.
  86:     // set to false if you do not have
  87:     // cURL installed. See http://curl.haxx.se
  88:     // for details on installing cURL.
  89:     // Snoopy does *not* use the cURL
  90:     // library functions built into php,
  91:     // as these functions are not stable
  92:     // as of this Snoopy release.
  93: 
  94:     // send Accept-encoding: gzip?
  95:     var $use_gzip = true;
  96:     /**** Private variables ****/
  97: 
  98:     var $_maxlinelen = 4096; // max line length (headers)
  99: 
 100:     var $_httpmethod = "GET"; // default http request method
 101:     var $_httpversion = "HTTP/1.0"; // default http request version
 102:     var $_submit_method = "POST"; // default submit method
 103:     var $_submit_type = "application/x-www-form-urlencoded"; // default submit type
 104:     var $_mime_boundary = ""; // MIME boundary for multipart/form-data submit type
 105:     var $_redirectaddr = false; // will be set if page fetched is a redirect
 106:     var $_redirectdepth = 0; // increments on an http redirect
 107:     var $_frameurls = array(); // frame src urls
 108:     var $_framedepth = 0; // increments on frame depth
 109: 
 110:     var $_isproxy = false; // set if using a proxy server
 111:     var $_fp_timeout = 30; // timeout for socket connection
 112: 
 113:     /*======================================================================*\
 114:         Function:   fetch
 115:         Purpose:    fetch the contents of a web page
 116:                     (and possibly other protocols in the
 117:                     future like ftp, nntp, gopher, etc.)
 118:         Input:      $URI    the location of the page to fetch
 119:         Output:     $this->results  the output text from the fetch
 120:     \*======================================================================*/
 121: 
 122:     function fetch($URI)
 123:     {
 124: 
 125:         //preg_match("|^([^:]+)://([^:/]+)(:[\d]+)*(.*)|",$URI,$URI_PARTS);
 126:         $URI_PARTS = parse_url($URI);
 127:         if (!empty($URI_PARTS["user"]))
 128:             $this->user = $URI_PARTS["user"];
 129:         if (!empty($URI_PARTS["pass"]))
 130:             $this->pass = $URI_PARTS["pass"];
 131:         if (empty($URI_PARTS["query"]))
 132:             $URI_PARTS["query"] = '';
 133:         if (empty($URI_PARTS["path"]))
 134:             $URI_PARTS["path"] = '';
 135: 
 136:         switch (strtolower($URI_PARTS["scheme"])) {
 137:             case "http":
 138:                 $this->host = $URI_PARTS["host"];
 139:                 if (!empty($URI_PARTS["port"]))
 140:                     $this->port = $URI_PARTS["port"];
 141:                 if ($this->_connect($fp)) {
 142:                     if ($this->_isproxy) {
 143:                         // using proxy, send entire URI
 144:                         $this->_httprequest($URI, $fp, $URI, $this->_httpmethod);
 145:                     } else {
 146:                         $path = $URI_PARTS["path"] . ($URI_PARTS["query"] ? "?" . $URI_PARTS["query"] : "");
 147:                         // no proxy, send only the path
 148:                         $this->_httprequest($path, $fp, $URI, $this->_httpmethod);
 149:                     }
 150: 
 151:                     $this->_disconnect($fp);
 152: 
 153:                     if ($this->_redirectaddr) {
 154:                         /* url was redirected, check if we've hit the max depth */
 155:                         if ($this->maxredirs > $this->_redirectdepth) {
 156:                             // only follow redirect if it's on this site, or offsiteok is true
 157:                             if (preg_match("|^http://" . preg_quote($this->host) . "|i", $this->_redirectaddr) || $this->offsiteok) {
 158:                                 /* follow the redirect */
 159:                                 $this->_redirectdepth++;
 160:                                 $this->lastredirectaddr = $this->_redirectaddr;
 161:                                 $this->fetch($this->_redirectaddr);
 162:                             }
 163:                         }
 164:                     }
 165: 
 166:                     if ($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) {
 167:                         $frameurls = $this->_frameurls;
 168:                         $this->_frameurls = array();
 169: 
 170:                         while (list(, $frameurl) = each($frameurls)) {
 171:                             if ($this->_framedepth < $this->maxframes) {
 172:                                 $this->fetch($frameurl);
 173:                                 $this->_framedepth++;
 174:                             } else
 175:                                 break;
 176:                         }
 177:                     }
 178:                 } else {
 179:                     return false;
 180:                 }
 181:                 return true;
 182:                 break;
 183:             case "https":
 184:                 if (!$this->curl_path)
 185:                     return false;
 186:                 if (function_exists("is_executable"))
 187:                     if (!is_executable($this->curl_path))
 188:                         return false;
 189:                 $this->host = $URI_PARTS["host"];
 190:                 if (!empty($URI_PARTS["port"]))
 191:                     $this->port = $URI_PARTS["port"];
 192:                 if ($this->_isproxy) {
 193:                     // using proxy, send entire URI
 194:                     $this->_httpsrequest($URI, $URI, $this->_httpmethod);
 195:                 } else {
 196:                     $path = $URI_PARTS["path"] . ($URI_PARTS["query"] ? "?" . $URI_PARTS["query"] : "");
 197:                     // no proxy, send only the path
 198:                     $this->_httpsrequest($path, $URI, $this->_httpmethod);
 199:                 }
 200: 
 201:                 if ($this->_redirectaddr) {
 202:                     /* url was redirected, check if we've hit the max depth */
 203:                     if ($this->maxredirs > $this->_redirectdepth) {
 204:                         // only follow redirect if it's on this site, or offsiteok is true
 205:                         if (preg_match("|^http://" . preg_quote($this->host) . "|i", $this->_redirectaddr) || $this->offsiteok) {
 206:                             /* follow the redirect */
 207:                             $this->_redirectdepth++;
 208:                             $this->lastredirectaddr = $this->_redirectaddr;
 209:                             $this->fetch($this->_redirectaddr);
 210:                         }
 211:                     }
 212:                 }
 213: 
 214:                 if ($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) {
 215:                     $frameurls = $this->_frameurls;
 216:                     $this->_frameurls = array();
 217: 
 218:                     while (list(, $frameurl) = each($frameurls)) {
 219:                         if ($this->_framedepth < $this->maxframes) {
 220:                             $this->fetch($frameurl);
 221:                             $this->_framedepth++;
 222:                         } else
 223:                             break;
 224:                     }
 225:                 }
 226:                 return true;
 227:                 break;
 228:             default:
 229:                 // not a valid protocol
 230:                 $this->error = 'Invalid protocol "' . $URI_PARTS["scheme"] . '"\n';
 231:                 return false;
 232:                 break;
 233:         }
 234:         return true;
 235:     }
 236: 
 237:     /*======================================================================*\
 238:         Function:   submit
 239:         Purpose:    submit an http form
 240:         Input:      $URI    the location to post the data
 241:                     $formvars   the formvars to use.
 242:                         format: $formvars["var"] = "val";
 243:                     $formfiles  an array of files to submit
 244:                         format: $formfiles["var"] = "/dir/filename.ext";
 245:         Output:     $this->results  the text output from the post
 246:     \*======================================================================*/
 247: 
 248:     function submit($URI, $formvars = "", $formfiles = "")
 249:     {
 250:         unset($postdata);
 251: 
 252:         $postdata = $this->_prepare_post_body($formvars, $formfiles);
 253: 
 254:         $URI_PARTS = parse_url($URI);
 255:         if (!empty($URI_PARTS["user"]))
 256:             $this->user = $URI_PARTS["user"];
 257:         if (!empty($URI_PARTS["pass"]))
 258:             $this->pass = $URI_PARTS["pass"];
 259:         if (empty($URI_PARTS["query"]))
 260:             $URI_PARTS["query"] = '';
 261:         if (empty($URI_PARTS["path"]))
 262:             $URI_PARTS["path"] = '';
 263: 
 264:         switch (strtolower($URI_PARTS["scheme"])) {
 265:             case "http":
 266:                 $this->host = $URI_PARTS["host"];
 267:                 if (!empty($URI_PARTS["port"]))
 268:                     $this->port = $URI_PARTS["port"];
 269:                 if ($this->_connect($fp)) {
 270:                     if ($this->_isproxy) {
 271:                         // using proxy, send entire URI
 272:                         $this->_httprequest($URI, $fp, $URI, $this->_submit_method, $this->_submit_type, $postdata);
 273:                     } else {
 274:                         $path = $URI_PARTS["path"] . ($URI_PARTS["query"] ? "?" . $URI_PARTS["query"] : "");
 275:                         // no proxy, send only the path
 276:                         $this->_httprequest($path, $fp, $URI, $this->_submit_method, $this->_submit_type, $postdata);
 277:                     }
 278: 
 279:                     $this->_disconnect($fp);
 280: 
 281:                     if ($this->_redirectaddr) {
 282:                         /* url was redirected, check if we've hit the max depth */
 283:                         if ($this->maxredirs > $this->_redirectdepth) {
 284:                             if (!preg_match("|^" . $URI_PARTS["scheme"] . "://|", $this->_redirectaddr))
 285:                                 $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr, $URI_PARTS["scheme"] . "://" . $URI_PARTS["host"]);
 286: 
 287:                             // only follow redirect if it's on this site, or offsiteok is true
 288:                             if (preg_match("|^http://" . preg_quote($this->host) . "|i", $this->_redirectaddr) || $this->offsiteok) {
 289:                                 /* follow the redirect */
 290:                                 $this->_redirectdepth++;
 291:                                 $this->lastredirectaddr = $this->_redirectaddr;
 292:                                 if (strpos($this->_redirectaddr, "?") > 0)
 293:                                     $this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get
 294:                                 else
 295:                                     $this->submit($this->_redirectaddr, $formvars, $formfiles);
 296:                             }
 297:                         }
 298:                     }
 299: 
 300:                     if ($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) {
 301:                         $frameurls = $this->_frameurls;
 302:                         $this->_frameurls = array();
 303: 
 304:                         while (list(, $frameurl) = each($frameurls)) {
 305:                             if ($this->_framedepth < $this->maxframes) {
 306:                                 $this->fetch($frameurl);
 307:                                 $this->_framedepth++;
 308:                             } else
 309:                                 break;
 310:                         }
 311:                     }
 312: 
 313:                 } else {
 314:                     return false;
 315:                 }
 316:                 return true;
 317:                 break;
 318:             case "https":
 319:                 if (!$this->curl_path)
 320:                     return false;
 321:                 if (function_exists("is_executable"))
 322:                     if (!is_executable($this->curl_path))
 323:                         return false;
 324:                 $this->host = $URI_PARTS["host"];
 325:                 if (!empty($URI_PARTS["port"]))
 326:                     $this->port = $URI_PARTS["port"];
 327:                 if ($this->_isproxy) {
 328:                     // using proxy, send entire URI
 329:                     $this->_httpsrequest($URI, $URI, $this->_submit_method, $this->_submit_type, $postdata);
 330:                 } else {
 331:                     $path = $URI_PARTS["path"] . ($URI_PARTS["query"] ? "?" . $URI_PARTS["query"] : "");
 332:                     // no proxy, send only the path
 333:                     $this->_httpsrequest($path, $URI, $this->_submit_method, $this->_submit_type, $postdata);
 334:                 }
 335: 
 336:                 if ($this->_redirectaddr) {
 337:                     /* url was redirected, check if we've hit the max depth */
 338:                     if ($this->maxredirs > $this->_redirectdepth) {
 339:                         if (!preg_match("|^" . $URI_PARTS["scheme"] . "://|", $this->_redirectaddr))
 340:                             $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr, $URI_PARTS["scheme"] . "://" . $URI_PARTS["host"]);
 341: 
 342:                         // only follow redirect if it's on this site, or offsiteok is true
 343:                         if (preg_match("|^http://" . preg_quote($this->host) . "|i", $this->_redirectaddr) || $this->offsiteok) {
 344:                             /* follow the redirect */
 345:                             $this->_redirectdepth++;
 346:                             $this->lastredirectaddr = $this->_redirectaddr;
 347:                             if (strpos($this->_redirectaddr, "?") > 0)
 348:                                 $this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get
 349:                             else
 350:                                 $this->submit($this->_redirectaddr, $formvars, $formfiles);
 351:                         }
 352:                     }
 353:                 }
 354: 
 355:                 if ($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) {
 356:                     $frameurls = $this->_frameurls;
 357:                     $this->_frameurls = array();
 358: 
 359:                     while (list(, $frameurl) = each($frameurls)) {
 360:                         if ($this->_framedepth < $this->maxframes) {
 361:                             $this->fetch($frameurl);
 362:                             $this->_framedepth++;
 363:                         } else
 364:                             break;
 365:                     }
 366:                 }
 367:                 return true;
 368:                 break;
 369: 
 370:             default:
 371:                 // not a valid protocol
 372:                 $this->error = 'Invalid protocol "' . $URI_PARTS["scheme"] . '"\n';
 373:                 return false;
 374:                 break;
 375:         }
 376:         return true;
 377:     }
 378: 
 379:     /*======================================================================*\
 380:         Function:   fetchlinks
 381:         Purpose:    fetch the links from a web page
 382:         Input:      $URI    where you are fetching from
 383:         Output:     $this->results  an array of the URLs
 384:     \*======================================================================*/
 385: 
 386:     function fetchlinks($URI)
 387:     {
 388:         if ($this->fetch($URI)) {
 389:             if ($this->lastredirectaddr)
 390:                 $URI = $this->lastredirectaddr;
 391:             if (is_array($this->results)) {
 392:                 for ($x = 0; $x < count($this->results); $x++)
 393:                     $this->results[$x] = $this->_striplinks($this->results[$x]);
 394:             } else
 395:                 $this->results = $this->_striplinks($this->results);
 396: 
 397:             if ($this->expandlinks)
 398:                 $this->results = $this->_expandlinks($this->results, $URI);
 399:             return true;
 400:         } else
 401:             return false;
 402:     }
 403: 
 404:     /*======================================================================*\
 405:         Function:   fetchform
 406:         Purpose:    fetch the form elements from a web page
 407:         Input:      $URI    where you are fetching from
 408:         Output:     $this->results  the resulting html form
 409:     \*======================================================================*/
 410: 
 411:     function fetchform($URI)
 412:     {
 413: 
 414:         if ($this->fetch($URI)) {
 415: 
 416:             if (is_array($this->results)) {
 417:                 for ($x = 0; $x < count($this->results); $x++)
 418:                     $this->results[$x] = $this->_stripform($this->results[$x]);
 419:             } else
 420:                 $this->results = $this->_stripform($this->results);
 421: 
 422:             return true;
 423:         } else
 424:             return false;
 425:     }
 426: 
 427: 
 428:     /*======================================================================*\
 429:         Function:   fetchtext
 430:         Purpose:    fetch the text from a web page, stripping the links
 431:         Input:      $URI    where you are fetching from
 432:         Output:     $this->results  the text from the web page
 433:     \*======================================================================*/
 434: 
 435:     function fetchtext($URI)
 436:     {
 437:         if ($this->fetch($URI)) {
 438:             if (is_array($this->results)) {
 439:                 for ($x = 0; $x < count($this->results); $x++)
 440:                     $this->results[$x] = $this->_striptext($this->results[$x]);
 441:             } else
 442:                 $this->results = $this->_striptext($this->results);
 443:             return true;
 444:         } else
 445:             return false;
 446:     }
 447: 
 448:     /*======================================================================*\
 449:         Function:   submitlinks
 450:         Purpose:    grab links from a form submission
 451:         Input:      $URI    where you are submitting from
 452:         Output:     $this->results  an array of the links from the post
 453:     \*======================================================================*/
 454: 
 455:     function submitlinks($URI, $formvars = "", $formfiles = "")
 456:     {
 457:         if ($this->submit($URI, $formvars, $formfiles)) {
 458:             if ($this->lastredirectaddr)
 459:                 $URI = $this->lastredirectaddr;
 460:             if (is_array($this->results)) {
 461:                 for ($x = 0; $x < count($this->results); $x++) {
 462:                     $this->results[$x] = $this->_striplinks($this->results[$x]);
 463:                     if ($this->expandlinks)
 464:                         $this->results[$x] = $this->_expandlinks($this->results[$x], $URI);
 465:                 }
 466:             } else {
 467:                 $this->results = $this->_striplinks($this->results);
 468:                 if ($this->expandlinks)
 469:                     $this->results = $this->_expandlinks($this->results, $URI);
 470:             }
 471:             return true;
 472:         } else
 473:             return false;
 474:     }
 475: 
 476:     /*======================================================================*\
 477:         Function:   submittext
 478:         Purpose:    grab text from a form submission
 479:         Input:      $URI    where you are submitting from
 480:         Output:     $this->results  the text from the web page
 481:     \*======================================================================*/
 482: 
 483:     function submittext($URI, $formvars = "", $formfiles = "")
 484:     {
 485:         if ($this->submit($URI, $formvars, $formfiles)) {
 486:             if ($this->lastredirectaddr)
 487:                 $URI = $this->lastredirectaddr;
 488:             if (is_array($this->results)) {
 489:                 for ($x = 0; $x < count($this->results); $x++) {
 490:                     $this->results[$x] = $this->_striptext($this->results[$x]);
 491:                     if ($this->expandlinks)
 492:                         $this->results[$x] = $this->_expandlinks($this->results[$x], $URI);
 493:                 }
 494:             } else {
 495:                 $this->results = $this->_striptext($this->results);
 496:                 if ($this->expandlinks)
 497:                     $this->results = $this->_expandlinks($this->results, $URI);
 498:             }
 499:             return true;
 500:         } else
 501:             return false;
 502:     }
 503: 
 504: 
 505:     /*======================================================================*\
 506:         Function:   set_submit_multipart
 507:         Purpose:    Set the form submission content type to
 508:                     multipart/form-data
 509:     \*======================================================================*/
 510:     function set_submit_multipart()
 511:     {
 512:         $this->_submit_type = "multipart/form-data";
 513:     }
 514: 
 515: 
 516:     /*======================================================================*\
 517:         Function:   set_submit_normal
 518:         Purpose:    Set the form submission content type to
 519:                     application/x-www-form-urlencoded
 520:     \*======================================================================*/
 521:     function set_submit_normal()
 522:     {
 523:         $this->_submit_type = "application/x-www-form-urlencoded";
 524:     }
 525: 
 526: 
 527: 
 528: 
 529:     /*======================================================================*\
 530:         Private functions
 531:     \*======================================================================*/
 532: 
 533: 
 534:     /*======================================================================*\
 535:         Function:   _striplinks
 536:         Purpose:    strip the hyperlinks from an html document
 537:         Input:      $document   document to strip.
 538:         Output:     $match      an array of the links
 539:     \*======================================================================*/
 540: 
 541:     function _striplinks($document)
 542:     {
 543:         preg_match_all("'<\s*a\s.*?href\s*=\s*          # find <a href=
 544:                         ([\"\'])?                   # find single or double quote
 545:                         (?(1) (.*?)\\1 | ([^\s\>]+))        # if quote found, match up to next matching
 546:                                                     # quote, otherwise match up to next space
 547:                         'isx", $document, $links);
 548: 
 549: 
 550:         // catenate the non-empty matches from the conditional subpattern
 551: 
 552:         while (list($key, $val) = each($links[2])) {
 553:             if (!empty($val))
 554:                 $match[] = $val;
 555:         }
 556: 
 557:         while (list($key, $val) = each($links[3])) {
 558:             if (!empty($val))
 559:                 $match[] = $val;
 560:         }
 561: 
 562:         // return the links
 563:         return $match;
 564:     }
 565: 
 566:     /*======================================================================*\
 567:         Function:   _stripform
 568:         Purpose:    strip the form elements from an html document
 569:         Input:      $document   document to strip.
 570:         Output:     $match      an array of the links
 571:     \*======================================================================*/
 572: 
 573:     function _stripform($document)
 574:     {
 575:         preg_match_all("'<\/?(FORM|INPUT|SELECT|TEXTAREA|(OPTION))[^<>]*>(?(2)(.*(?=<\/?(option|select)[^<>]*>[\r\n]*)|(?=[\r\n]*))|(?=[\r\n]*))'Usi", $document, $elements);
 576: 
 577:         // catenate the matches
 578:         $match = implode("\r\n", $elements[0]);
 579: 
 580:         // return the links
 581:         return $match;
 582:     }
 583: 
 584: 
 585:     /*======================================================================*\
 586:         Function:   _striptext
 587:         Purpose:    strip the text from an html document
 588:         Input:      $document   document to strip.
 589:         Output:     $text       the resulting text
 590:     \*======================================================================*/
 591: 
 592:     function _striptext($document)
 593:     {
 594: 
 595:         // I didn't use preg eval (//e) since that is only available in PHP 4.0.
 596:         // so, list your entities one by one here. I included some of the
 597:         // more common ones.
 598: 
 599:         $search = array("'<script[^>]*?>.*?</script>'si", // strip out javascript
 600:             "'<[\/\!]*?[^<>]*?>'si", // strip out html tags
 601:             "'([\r\n])[\s]+'", // strip out white space
 602:             "'&(quot|#34|#034|#x22);'i", // replace html entities
 603:             "'&(amp|#38|#038|#x26);'i", // added hexadecimal values
 604:             "'&(lt|#60|#060|#x3c);'i",
 605:             "'&(gt|#62|#062|#x3e);'i",
 606:             "'&(nbsp|#160|#xa0);'i",
 607:             "'&(iexcl|#161);'i",
 608:             "'&(cent|#162);'i",
 609:             "'&(pound|#163);'i",
 610:             "'&(copy|#169);'i",
 611:             "'&(reg|#174);'i",
 612:             "'&(deg|#176);'i",
 613:             "'&(#39|#039|#x27);'",
 614:             "'&(euro|#8364);'i", // europe
 615:             "'&a(uml|UML);'", // german
 616:             "'&o(uml|UML);'",
 617:             "'&u(uml|UML);'",
 618:             "'&A(uml|UML);'",
 619:             "'&O(uml|UML);'",
 620:             "'&U(uml|UML);'",
 621:             "'&szlig;'i",
 622:         );
 623:         $replace = array("",
 624:             "",
 625:             "\\1",
 626:             "\"",
 627:             "&",
 628:             "<",
 629:             ">",
 630:             " ",
 631:             chr(161),
 632:             chr(162),
 633:             chr(163),
 634:             chr(169),
 635:             chr(174),
 636:             chr(176),
 637:             chr(39),
 638:             chr(128),
 639:             "ä",
 640:             "ö",
 641:             "ü",
 642:             "Ä",
 643:             "Ö",
 644:             "Ü",
 645:             "ß",
 646:         );
 647: 
 648:         $text = preg_replace($search, $replace, $document);
 649: 
 650:         return $text;
 651:     }
 652: 
 653:     /*======================================================================*\
 654:         Function:   _expandlinks
 655:         Purpose:    expand each link into a fully qualified URL
 656:         Input:      $links          the links to qualify
 657:                     $URI            the full URI to get the base from
 658:         Output:     $expandedLinks  the expanded links
 659:     \*======================================================================*/
 660: 
 661:     function _expandlinks($links, $URI)
 662:     {
 663: 
 664:         preg_match("/^[^\?]+/", $URI, $match);
 665: 
 666:         $match = preg_replace("|/[^\/\.]+\.[^\/\.]+$|", "", $match[0]);
 667:         $match = preg_replace("|/$|", "", $match);
 668:         $match_part = parse_url($match);
 669:         $match_root =
 670:             $match_part["scheme"] . "://" . $match_part["host"];
 671: 
 672:         $search = array("|^http://" . preg_quote($this->host) . "|i",
 673:             "|^(\/)|i",
 674:             "|^(?!http://)(?!mailto:)|i",
 675:             "|/\./|",
 676:             "|/[^\/]+/\.\./|"
 677:         );
 678: 
 679:         $replace = array("",
 680:             $match_root . "/",
 681:             $match . "/",
 682:             "/",
 683:             "/"
 684:         );
 685: 
 686:         $expandedLinks = preg_replace($search, $replace, $links);
 687: 
 688:         return $expandedLinks;
 689:     }
 690: 
 691:     /*======================================================================*\
 692:         Function:   _httprequest
 693:         Purpose:    go get the http data from the server
 694:         Input:      $url        the url to fetch
 695:                     $fp         the current open file pointer
 696:                     $URI        the full URI
 697:                     $body       body contents to send if any (POST)
 698:         Output:
 699:     \*======================================================================*/
 700: 
 701:     function _httprequest($url, $fp, $URI, $http_method, $content_type = "", $body = "")
 702:     {
 703:         $cookie_headers = '';
 704:         if ($this->passcookies && $this->_redirectaddr)
 705:             $this->setcookies();
 706: 
 707:         $URI_PARTS = parse_url($URI);
 708:         if (empty($url))
 709:             $url = "/";
 710:         $headers = $http_method . " " . $url . " " . $this->_httpversion . "\r\n";
 711:         if (!empty($this->agent))
 712:             $headers .= "User-Agent: " . $this->agent . "\r\n";
 713:         if (!empty($this->host) && !isset($this->rawheaders['Host'])) {
 714:             $headers .= "Host: " . $this->host;
 715:             if (!empty($this->port) && $this->port != '80')
 716:                 $headers .= ":" . $this->port;
 717:             $headers .= "\r\n";
 718:         }
 719:         if (!empty($this->accept))
 720:             $headers .= "Accept: " . $this->accept . "\r\n";
 721:         if ($this->use_gzip) {
 722:             // make sure PHP was built with --with-zlib
 723:             // and we can handle gzipp'ed data
 724:             if (function_exists('gzinflate')) {
 725:                 $headers .= "Accept-encoding: gzip\r\n";
 726:             } else {
 727:                 trigger_error(
 728:                     "use_gzip is on, but PHP was built without zlib support." .
 729:                     "  Requesting file(s) without gzip encoding.",
 730:                     E_USER_NOTICE);
 731:             }
 732:         }
 733:         if (!empty($this->referer))
 734:             $headers .= "Referer: " . $this->referer . "\r\n";
 735:         if (!empty($this->cookies)) {
 736:             if (!is_array($this->cookies))
 737:                 $this->cookies = (array)$this->cookies;
 738: 
 739:             reset($this->cookies);
 740:             if (count($this->cookies) > 0) {
 741:                 $cookie_headers .= 'Cookie: ';
 742:                 foreach ($this->cookies as $cookieKey => $cookieVal) {
 743:                     $cookie_headers .= $cookieKey . "=" . urlencode($cookieVal) . "; ";
 744:                 }
 745:                 $headers .= substr($cookie_headers, 0, -2) . "\r\n";
 746:             }
 747:         }
 748:         if (!empty($this->rawheaders)) {
 749:             if (!is_array($this->rawheaders))
 750:                 $this->rawheaders = (array)$this->rawheaders;
 751:             while (list($headerKey, $headerVal) = each($this->rawheaders))
 752:                 $headers .= $headerKey . ": " . $headerVal . "\r\n";
 753:         }
 754:         if (!empty($content_type)) {
 755:             $headers .= "Content-type: $content_type";
 756:             if ($content_type == "multipart/form-data")
 757:                 $headers .= "; boundary=" . $this->_mime_boundary;
 758:             $headers .= "\r\n";
 759:         }
 760:         if (!empty($body))
 761:             $headers .= "Content-length: " . strlen($body) . "\r\n";
 762:         if (!empty($this->user) || !empty($this->pass))
 763:             $headers .= "Authorization: Basic " . base64_encode($this->user . ":" . $this->pass) . "\r\n";
 764: 
 765:         //add proxy auth headers
 766:         if (!empty($this->proxy_user))
 767:             $headers .= 'Proxy-Authorization: ' . 'Basic ' . base64_encode($this->proxy_user . ':' . $this->proxy_pass) . "\r\n";
 768: 
 769: 
 770:         $headers .= "\r\n";
 771: 
 772:         // set the read timeout if needed
 773:         if ($this->read_timeout > 0)
 774:             socket_set_timeout($fp, $this->read_timeout);
 775:         $this->timed_out = false;
 776: 
 777:         fwrite($fp, $headers . $body, strlen($headers . $body));
 778: 
 779:         $this->_redirectaddr = false;
 780:         unset($this->headers);
 781: 
 782:         // content was returned gzip encoded?
 783:         $is_gzipped = false;
 784: 
 785:         while ($currentHeader = fgets($fp, $this->_maxlinelen)) {
 786:             if ($this->read_timeout > 0 && $this->_check_timeout($fp)) {
 787:                 $this->status = -100;
 788:                 return false;
 789:             }
 790: 
 791:             if ($currentHeader == "\r\n")
 792:                 break;
 793: 
 794:             // if a header begins with Location: or URI:, set the redirect
 795:             if (preg_match("/^(Location:|URI:)/i", $currentHeader)) {
 796:                 // get URL portion of the redirect
 797:                 preg_match("/^(Location:|URI:)[ ]+(.*)/i", chop($currentHeader), $matches);
 798:                 // look for :// in the Location header to see if hostname is included
 799:                 if (!preg_match("|\:\/\/|", $matches[2])) {
 800:                     // no host in the path, so prepend
 801:                     $this->_redirectaddr = $URI_PARTS["scheme"] . "://" . $this->host . ":" . $this->port;
 802:                     // eliminate double slash
 803:                     if (!preg_match("|^/|", $matches[2]))
 804:                         $this->_redirectaddr .= "/" . $matches[2];
 805:                     else
 806:                         $this->_redirectaddr .= $matches[2];
 807:                 } else
 808:                     $this->_redirectaddr = $matches[2];
 809:             }
 810: 
 811:             if (preg_match("|^HTTP/|", $currentHeader)) {
 812:                 if (preg_match("|^HTTP/[^\s]*\s(.*?)\s|", $currentHeader, $status)) {
 813:                     $this->status = $status[1];
 814:                 }
 815:                 $this->response_code = $currentHeader;
 816:             }
 817: 
 818:             if (preg_match("/Content-Encoding: gzip/", $currentHeader)) {
 819:                 $is_gzipped = true;
 820:             }
 821: 
 822:             $this->headers[] = $currentHeader;
 823:         }
 824: 
 825:         $results = '';
 826:         do {
 827:             $_data = fread($fp, $this->maxlength);
 828:             if (strlen($_data) == 0) {
 829:                 break;
 830:             }
 831:             $results .= $_data;
 832:         } while (true);
 833: 
 834:         // gunzip
 835:         if ($is_gzipped) {
 836:             // per http://www.php.net/manual/en/function.gzencode.php
 837:             $results = substr($results, 10);
 838:             $results = gzinflate($results);
 839:         }
 840: 
 841:         if ($this->read_timeout > 0 && $this->_check_timeout($fp)) {
 842:             $this->status = -100;
 843:             return false;
 844:         }
 845: 
 846:         // check if there is a a redirect meta tag
 847: 
 848:         if (preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i", $results, $match)) {
 849:             $this->_redirectaddr = $this->_expandlinks($match[1], $URI);
 850:         }
 851: 
 852:         // have we hit our frame depth and is there frame src to fetch?
 853:         if (($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i", $results, $match)) {
 854:             $this->results[] = $results;
 855:             for ($x = 0; $x < count($match[1]); $x++)
 856:                 $this->_frameurls[] = $this->_expandlinks($match[1][$x], $URI_PARTS["scheme"] . "://" . $this->host);
 857:         } // have we already fetched framed content?
 858:         elseif (is_array($this->results))
 859:             $this->results[] = $results;
 860:         // no framed content
 861:         else
 862:             $this->results = $results;
 863: 
 864:         return true;
 865:     }
 866: 
 867:     /*======================================================================*\
 868:         Function:   _httpsrequest
 869:         Purpose:    go get the https data from the server using curl
 870:         Input:      $url        the url to fetch
 871:                     $URI        the full URI
 872:                     $body       body contents to send if any (POST)
 873:         Output:
 874:     \*======================================================================*/
 875: 
 876:     function _httpsrequest($url, $URI, $http_method, $content_type = "", $body = "")
 877:     {
 878:         if ($this->passcookies && $this->_redirectaddr)
 879:             $this->setcookies();
 880: 
 881:         $headers = array();
 882: 
 883:         $URI_PARTS = parse_url($URI);
 884:         if (empty($url))
 885:             $url = "/";
 886:         // GET ... header not needed for curl
 887:         //$headers[] = $http_method." ".$url." ".$this->_httpversion;
 888:         if (!empty($this->agent))
 889:             $headers[] = "User-Agent: " . $this->agent;
 890:         if (!empty($this->host))
 891:             if (!empty($this->port))
 892:                 $headers[] = "Host: " . $this->host . ":" . $this->port;
 893:             else
 894:                 $headers[] = "Host: " . $this->host;
 895:         if (!empty($this->accept))
 896:             $headers[] = "Accept: " . $this->accept;
 897:         if (!empty($this->referer))
 898:             $headers[] = "Referer: " . $this->referer;
 899:         if (!empty($this->cookies)) {
 900:             if (!is_array($this->cookies))
 901:                 $this->cookies = (array)$this->cookies;
 902: 
 903:             reset($this->cookies);
 904:             if (count($this->cookies) > 0) {
 905:                 $cookie_str = 'Cookie: ';
 906:                 foreach ($this->cookies as $cookieKey => $cookieVal) {
 907:                     $cookie_str .= $cookieKey . "=" . urlencode($cookieVal) . "; ";
 908:                 }
 909:                 $headers[] = substr($cookie_str, 0, -2);
 910:             }
 911:         }
 912:         if (!empty($this->rawheaders)) {
 913:             if (!is_array($this->rawheaders))
 914:                 $this->rawheaders = (array)$this->rawheaders;
 915:             while (list($headerKey, $headerVal) = each($this->rawheaders))
 916:                 $headers[] = $headerKey . ": " . $headerVal;
 917:         }
 918:         if (!empty($content_type)) {
 919:             if ($content_type == "multipart/form-data")
 920:                 $headers[] = "Content-type: $content_type; boundary=" . $this->_mime_boundary;
 921:             else
 922:                 $headers[] = "Content-type: $content_type";
 923:         }
 924:         if (!empty($body))
 925:             $headers[] = "Content-length: " . strlen($body);
 926:         if (!empty($this->user) || !empty($this->pass))
 927:             $headers[] = "Authorization: BASIC " . base64_encode($this->user . ":" . $this->pass);
 928: 
 929:         for ($curr_header = 0; $curr_header < count($headers); $curr_header++) {
 930:             $safer_header = strtr($headers[$curr_header], "\"", " ");
 931:             $cmdline_params .= " -H \"" . $safer_header . "\"";
 932:         }
 933: 
 934:         if (!empty($body))
 935:             $cmdline_params .= " -d \"$body\"";
 936: 
 937:         if ($this->read_timeout > 0)
 938:             $cmdline_params .= " -m " . $this->read_timeout;
 939: 
 940:         $headerfile = tempnam($temp_dir, "sno");
 941: 
 942:         exec($this->curl_path . " -k -D \"$headerfile\"" . $cmdline_params . " " . escapeshellarg($URI), $results, $return);
 943: 
 944:         if ($return) {
 945:             $this->error = "Error: cURL could not retrieve the document, error $return.";
 946:             return false;
 947:         }
 948: 
 949: 
 950:         $results = implode("\r\n", $results);
 951: 
 952:         $result_headers = file("$headerfile");
 953: 
 954:         $this->_redirectaddr = false;
 955:         unset($this->headers);
 956: 
 957:         for ($currentHeader = 0; $currentHeader < count($result_headers); $currentHeader++) {
 958: 
 959:             // if a header begins with Location: or URI:, set the redirect
 960:             if (preg_match("/^(Location: |URI: )/i", $result_headers[$currentHeader])) {
 961:                 // get URL portion of the redirect
 962:                 preg_match("/^(Location: |URI:)\s+(.*)/", chop($result_headers[$currentHeader]), $matches);
 963:                 // look for :// in the Location header to see if hostname is included
 964:                 if (!preg_match("|\:\/\/|", $matches[2])) {
 965:                     // no host in the path, so prepend
 966:                     $this->_redirectaddr = $URI_PARTS["scheme"] . "://" . $this->host . ":" . $this->port;
 967:                     // eliminate double slash
 968:                     if (!preg_match("|^/|", $matches[2]))
 969:                         $this->_redirectaddr .= "/" . $matches[2];
 970:                     else
 971:                         $this->_redirectaddr .= $matches[2];
 972:                 } else
 973:                     $this->_redirectaddr = $matches[2];
 974:             }
 975: 
 976:             if (preg_match("|^HTTP/|", $result_headers[$currentHeader])) {
 977:                 $this->response_code = $result_headers[$currentHeader];
 978:                 if (preg_match("|^HTTP/[^\s]*\s(.*?)\s|", $this->response_code, $match)) {
 979:                     $this->status = $match[1];
 980:                 }
 981:             }
 982: 
 983:             $this->headers[] = $result_headers[$currentHeader];
 984:         }
 985: 
 986:         // check if there is a a redirect meta tag
 987: 
 988:         if (preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i", $results, $match)) {
 989:             $this->_redirectaddr = $this->_expandlinks($match[1], $URI);
 990:         }
 991: 
 992:         // have we hit our frame depth and is there frame src to fetch?
 993:         if (($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i", $results, $match)) {
 994:             $this->results[] = $results;
 995:             for ($x = 0; $x < count($match[1]); $x++)
 996:                 $this->_frameurls[] = $this->_expandlinks($match[1][$x], $URI_PARTS["scheme"] . "://" . $this->host);
 997:         } // have we already fetched framed content?
 998:         elseif (is_array($this->results))
 999:             $this->results[] = $results;
1000:         // no framed content
1001:         else
1002:             $this->results = $results;
1003: 
1004:         unlink("$headerfile");
1005: 
1006:         return true;
1007:     }
1008: 
1009:     /*======================================================================*\
1010:         Function:   setcookies()
1011:         Purpose:    set cookies for a redirection
1012:     \*======================================================================*/
1013: 
1014:     function setcookies()
1015:     {
1016:         for ($x = 0; $x < count($this->headers); $x++) {
1017:             if (preg_match('/^set-cookie:[\s]+([^=]+)=([^;]+)/i', $this->headers[$x], $match))
1018:                 $this->cookies[$match[1]] = urldecode($match[2]);
1019:         }
1020:     }
1021: 
1022: 
1023:     /*======================================================================*\
1024:         Function:   _check_timeout
1025:         Purpose:    checks whether timeout has occurred
1026:         Input:      $fp file pointer
1027:     \*======================================================================*/
1028: 
1029:     function _check_timeout($fp)
1030:     {
1031:         if ($this->read_timeout > 0) {
1032:             $fp_status = socket_get_status($fp);
1033:             if ($fp_status["timed_out"]) {
1034:                 $this->timed_out = true;
1035:                 return true;
1036:             }
1037:         }
1038:         return false;
1039:     }
1040: 
1041:     /*======================================================================*\
1042:         Function:   _connect
1043:         Purpose:    make a socket connection
1044:         Input:      $fp file pointer
1045:     \*======================================================================*/
1046: 
1047:     function _connect(&$fp)
1048:     {
1049:         if (!empty($this->proxy_host) && !empty($this->proxy_port)) {
1050:             $this->_isproxy = true;
1051: 
1052:             $host = $this->proxy_host;
1053:             $port = $this->proxy_port;
1054:         } else {
1055:             $host = $this->host;
1056:             $port = $this->port;
1057:         }
1058: 
1059:         $this->status = 0;
1060: 
1061:         if ($fp = fsockopen(
1062:             $host,
1063:             $port,
1064:             $errno,
1065:             $errstr,
1066:             $this->_fp_timeout
1067:         )
1068:         ) {
1069:             // socket connection succeeded
1070: 
1071:             return true;
1072:         } else {
1073:             // socket connection failed
1074:             $this->status = $errno;
1075:             switch ($errno) {
1076:                 case -3:
1077:                     $this->error = "socket creation failed (-3)";
1078:                 case -4:
1079:                     $this->error = "dns lookup failure (-4)";
1080:                 case -5:
1081:                     $this->error = "connection refused or timed out (-5)";
1082:                 default:
1083:                     $this->error = "connection failed (" . $errno . ")";
1084:             }
1085:             return false;
1086:         }
1087:     }
1088: 
1089:     /*======================================================================*\
1090:         Function:   _disconnect
1091:         Purpose:    disconnect a socket connection
1092:         Input:      $fp file pointer
1093:     \*======================================================================*/
1094: 
1095:     function _disconnect($fp)
1096:     {
1097:         return (fclose($fp));
1098:     }
1099: 
1100: 
1101:     /*======================================================================*\
1102:         Function:   _prepare_post_body
1103:         Purpose:    Prepare post body according to encoding type
1104:         Input:      $formvars  - form variables
1105:                     $formfiles - form upload files
1106:         Output:     post body
1107:     \*======================================================================*/
1108: 
1109:     function _prepare_post_body($formvars, $formfiles)
1110:     {
1111:         settype($formvars, "array");
1112:         settype($formfiles, "array");
1113:         $postdata = '';
1114: 
1115:         if (count($formvars) == 0 && count($formfiles) == 0)
1116:             return;
1117: 
1118:         switch ($this->_submit_type) {
1119:             case "application/x-www-form-urlencoded":
1120:                 reset($formvars);
1121:                 while (list($key, $val) = each($formvars)) {
1122:                     if (is_array($val) || is_object($val)) {
1123:                         while (list($cur_key, $cur_val) = each($val)) {
1124:                             $postdata .= urlencode($key) . "[]=" . urlencode($cur_val) . "&";
1125:                         }
1126:                     } else
1127:                         $postdata .= urlencode($key) . "=" . urlencode($val) . "&";
1128:                 }
1129:                 break;
1130: 
1131:             case "multipart/form-data":
1132:                 $this->_mime_boundary = "Snoopy" . md5(uniqid(microtime()));
1133: 
1134:                 reset($formvars);
1135:                 while (list($key, $val) = each($formvars)) {
1136:                     if (is_array($val) || is_object($val)) {
1137:                         while (list($cur_key, $cur_val) = each($val)) {
1138:                             $postdata .= "--" . $this->_mime_boundary . "\r\n";
1139:                             $postdata .= "Content-Disposition: form-data; name=\"$key\[\]\"\r\n\r\n";
1140:                             $postdata .= "$cur_val\r\n";
1141:                         }
1142:                     } else {
1143:                         $postdata .= "--" . $this->_mime_boundary . "\r\n";
1144:                         $postdata .= "Content-Disposition: form-data; name=\"$key\"\r\n\r\n";
1145:                         $postdata .= "$val\r\n";
1146:                     }
1147:                 }
1148: 
1149:                 reset($formfiles);
1150:                 while (list($field_name, $file_names) = each($formfiles)) {
1151:                     settype($file_names, "array");
1152:                     while (list(, $file_name) = each($file_names)) {
1153:                         if (!is_readable($file_name)) continue;
1154: 
1155:                         $fp = fopen($file_name, "r");
1156:                         $file_content = fread($fp, filesize($file_name));
1157:                         fclose($fp);
1158:                         $base_name = basename($file_name);
1159: 
1160:                         $postdata .= "--" . $this->_mime_boundary . "\r\n";
1161:                         $postdata .= "Content-Disposition: form-data; name=\"$field_name\"; filename=\"$base_name\"\r\n\r\n";
1162:                         $postdata .= "$file_content\r\n";
1163:                     }
1164:                 }
1165:                 $postdata .= "--" . $this->_mime_boundary . "--\r\n";
1166:                 break;
1167:         }
1168: 
1169:         return $postdata;
1170:     }
1171: }
1172: 
1173: ?>
1174: