XOOPS /
XoopsCore
| Total Complexity | 166 |
| Total Lines | 969 |
| Duplicated Lines | 0 % |
| Changes | 1 | ||
| Bugs | 0 | Features | 0 |
Complex classes like Snoopy often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use Snoopy, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 29 | class Snoopy |
||
| 30 | { |
||
| 31 | /**** Public variables ****/ |
||
| 32 | |||
| 33 | /* user definable vars */ |
||
| 34 | |||
| 35 | var $scheme = 'http'; // http or https |
||
| 36 | var $host = "www.php.net"; // host name we are connecting to |
||
| 37 | var $port = 80; // port we are connecting to |
||
| 38 | var $proxy_host = ""; // proxy host to use |
||
| 39 | var $proxy_port = ""; // proxy port to use |
||
| 40 | var $proxy_user = ""; // proxy user to use |
||
| 41 | var $proxy_pass = ""; // proxy password to use |
||
| 42 | |||
| 43 | var $agent = "Snoopy v2.0.0"; // agent we masquerade as |
||
| 44 | var $referer = ""; // referer info to pass |
||
| 45 | var $cookies = array(); // array of cookies to pass |
||
| 46 | // $cookies["username"]="joe"; |
||
| 47 | var $rawheaders = array(); // array of raw headers to send |
||
| 48 | // $rawheaders["Content-type"]="text/html"; |
||
| 49 | |||
| 50 | var $maxredirs = 5; // http redirection depth maximum. 0 = disallow |
||
| 51 | var $lastredirectaddr = ""; // contains address of last redirected address |
||
| 52 | var $offsiteok = true; // allows redirection off-site |
||
| 53 | var $maxframes = 0; // frame content depth maximum. 0 = disallow |
||
| 54 | var $expandlinks = true; // expand links to fully qualified URLs. |
||
| 55 | // this only applies to fetchlinks() |
||
| 56 | // submitlinks(), and submittext() |
||
| 57 | var $passcookies = true; // pass set cookies back through redirects |
||
| 58 | // NOTE: this currently does not respect |
||
| 59 | // dates, domains or paths. |
||
| 60 | |||
| 61 | var $user = ""; // user for http authentication |
||
| 62 | var $pass = ""; // password for http authentication |
||
| 63 | |||
| 64 | // http accept types |
||
| 65 | var $accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*"; |
||
| 66 | |||
| 67 | var $results = ""; // where the content is put |
||
| 68 | |||
| 69 | var $error = ""; // error messages sent here |
||
| 70 | var $response_code = ""; // response code returned from server |
||
| 71 | var $headers = array(); // headers returned from server sent here |
||
| 72 | var $maxlength = 500000; // max return data length (body) |
||
| 73 | var $read_timeout = 0; // timeout on read operations, in seconds |
||
| 74 | // supported only since PHP 4 Beta 4 |
||
| 75 | // set to 0 to disallow timeouts |
||
| 76 | var $timed_out = false; // if a read operation timed out |
||
| 77 | var $status = 0; // http request status |
||
| 78 | |||
| 79 | var $temp_dir = "/tmp"; // temporary directory that the webserver |
||
| 80 | // has permission to write to. |
||
| 81 | // under Windows, this should be C:\temp |
||
| 82 | |||
| 83 | var $curl_path = false; |
||
| 84 | // deprecated, snoopy no longer uses curl for https requests, |
||
| 85 | // but instead requires the openssl extension. |
||
| 86 | |||
| 87 | // send Accept-encoding: gzip? |
||
| 88 | var $use_gzip = true; |
||
| 89 | |||
| 90 | // file or directory with CA certificates to verify remote host with |
||
| 91 | var $cafile; |
||
| 92 | var $capath; |
||
| 93 | |||
| 94 | /**** Private variables ****/ |
||
| 95 | |||
| 96 | var $_maxlinelen = 4096; // max line length (headers) |
||
| 97 | |||
| 98 | var $_httpmethod = "GET"; // default http request method |
||
| 99 | var $_httpversion = "HTTP/1.0"; // default http request version |
||
| 100 | var $_submit_method = "POST"; // default submit method |
||
| 101 | var $_submit_type = "application/x-www-form-urlencoded"; // default submit type |
||
| 102 | var $_mime_boundary = ""; // MIME boundary for multipart/form-data submit type |
||
| 103 | var $_redirectaddr = false; // will be set if page fetched is a redirect |
||
| 104 | var $_redirectdepth = 0; // increments on an http redirect |
||
| 105 | var $_frameurls = array(); // frame src urls |
||
| 106 | var $_framedepth = 0; // increments on frame depth |
||
| 107 | |||
| 108 | var $_isproxy = false; // set if using a proxy server |
||
| 109 | var $_fp_timeout = 30; // timeout for socket connection |
||
| 110 | |||
| 111 | /*======================================================================*\ |
||
| 112 | Function: fetch |
||
| 113 | Purpose: fetch the contents of a web page |
||
| 114 | (and possibly other protocols in the |
||
| 115 | future like ftp, nntp, gopher, etc.) |
||
| 116 | Input: $URI the location of the page to fetch |
||
| 117 | Output: $this->results the output text from the fetch |
||
| 118 | \*======================================================================*/ |
||
| 119 | |||
| 120 | function fetch($URI) |
||
|
|
|||
| 121 | { |
||
| 122 | |||
| 123 | $URI_PARTS = parse_url($URI); |
||
| 124 | if (!empty($URI_PARTS["user"])) |
||
| 125 | $this->user = $URI_PARTS["user"]; |
||
| 126 | if (!empty($URI_PARTS["pass"])) |
||
| 127 | $this->pass = $URI_PARTS["pass"]; |
||
| 128 | if (empty($URI_PARTS["query"])) |
||
| 129 | $URI_PARTS["query"] = ''; |
||
| 130 | if (empty($URI_PARTS["path"])) |
||
| 131 | $URI_PARTS["path"] = ''; |
||
| 132 | |||
| 133 | $fp = null; |
||
| 134 | |||
| 135 | switch (strtolower($URI_PARTS["scheme"])) { |
||
| 136 | case "https": |
||
| 137 | if (!extension_loaded('openssl')) { |
||
| 138 | trigger_error("openssl extension required for HTTPS", E_USER_ERROR); |
||
| 139 | exit; |
||
| 140 | } |
||
| 141 | $this->port = 443; |
||
| 142 | case "http": |
||
| 143 | $this->scheme = strtolower($URI_PARTS["scheme"]); |
||
| 144 | $this->host = $URI_PARTS["host"]; |
||
| 145 | if (!empty($URI_PARTS["port"])) |
||
| 146 | $this->port = $URI_PARTS["port"]; |
||
| 147 | if ($this->_connect($fp)) { |
||
| 148 | if ($this->_isproxy) { |
||
| 149 | // using proxy, send entire URI |
||
| 150 | $this->_httprequest($URI, $fp, $URI, $this->_httpmethod); |
||
| 151 | } else { |
||
| 152 | $path = $URI_PARTS["path"] . ($URI_PARTS["query"] ? "?" . $URI_PARTS["query"] : ""); |
||
| 153 | // no proxy, send only the path |
||
| 154 | $this->_httprequest($path, $fp, $URI, $this->_httpmethod); |
||
| 155 | } |
||
| 156 | |||
| 157 | $this->_disconnect($fp); |
||
| 158 | |||
| 159 | if ($this->_redirectaddr) { |
||
| 160 | /* url was redirected, check if we've hit the max depth */ |
||
| 161 | if ($this->maxredirs > $this->_redirectdepth) { |
||
| 162 | // only follow redirect if it's on this site, or offsiteok is true |
||
| 163 | if (preg_match("|^https?://" . preg_quote($this->host) . "|i", $this->_redirectaddr) || $this->offsiteok) { |
||
| 164 | /* follow the redirect */ |
||
| 165 | $this->_redirectdepth++; |
||
| 166 | $this->lastredirectaddr = $this->_redirectaddr; |
||
| 167 | $this->fetch($this->_redirectaddr); |
||
| 168 | } |
||
| 169 | } |
||
| 170 | } |
||
| 171 | |||
| 172 | if ($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) { |
||
| 173 | $frameurls = $this->_frameurls; |
||
| 174 | $this->_frameurls = array(); |
||
| 175 | |||
| 176 | while (list(, $frameurl) = each($frameurls)) { |
||
| 177 | if ($this->_framedepth < $this->maxframes) { |
||
| 178 | $this->fetch($frameurl); |
||
| 179 | $this->_framedepth++; |
||
| 180 | } else |
||
| 181 | break; |
||
| 182 | } |
||
| 183 | } |
||
| 184 | } else { |
||
| 185 | return false; |
||
| 186 | } |
||
| 187 | return $this; |
||
| 188 | break; |
||
| 189 | default: |
||
| 190 | // not a valid protocol |
||
| 191 | $this->error = 'Invalid protocol "' . $URI_PARTS["scheme"] . '"\n'; |
||
| 192 | return false; |
||
| 193 | break; |
||
| 194 | } |
||
| 195 | return $this; |
||
| 196 | } |
||
| 197 | |||
| 198 | /*======================================================================*\ |
||
| 199 | Function: submit |
||
| 200 | Purpose: submit an http(s) form |
||
| 201 | Input: $URI the location to post the data |
||
| 202 | $formvars the formvars to use. |
||
| 203 | format: $formvars["var"] = "val"; |
||
| 204 | $formfiles an array of files to submit |
||
| 205 | format: $formfiles["var"] = "/dir/filename.ext"; |
||
| 206 | Output: $this->results the text output from the post |
||
| 207 | \*======================================================================*/ |
||
| 208 | |||
| 209 | function submit($URI, $formvars = "", $formfiles = "") |
||
| 210 | { |
||
| 211 | unset($postdata); |
||
| 212 | |||
| 213 | $postdata = $this->_prepare_post_body($formvars, $formfiles); |
||
| 214 | |||
| 215 | $URI_PARTS = parse_url($URI); |
||
| 216 | if (!empty($URI_PARTS["user"])) |
||
| 217 | $this->user = $URI_PARTS["user"]; |
||
| 218 | if (!empty($URI_PARTS["pass"])) |
||
| 219 | $this->pass = $URI_PARTS["pass"]; |
||
| 220 | if (empty($URI_PARTS["query"])) |
||
| 221 | $URI_PARTS["query"] = ''; |
||
| 222 | if (empty($URI_PARTS["path"])) |
||
| 223 | $URI_PARTS["path"] = ''; |
||
| 224 | |||
| 225 | switch (strtolower($URI_PARTS["scheme"])) { |
||
| 226 | case "https": |
||
| 227 | if (!extension_loaded('openssl')) { |
||
| 228 | trigger_error("openssl extension required for HTTPS", E_USER_ERROR); |
||
| 229 | exit; |
||
| 230 | } |
||
| 231 | $this->port = 443; |
||
| 232 | case "http": |
||
| 233 | $this->scheme = strtolower($URI_PARTS["scheme"]); |
||
| 234 | $this->host = $URI_PARTS["host"]; |
||
| 235 | if (!empty($URI_PARTS["port"])) |
||
| 236 | $this->port = $URI_PARTS["port"]; |
||
| 237 | if ($this->_connect($fp)) { |
||
| 238 | if ($this->_isproxy) { |
||
| 239 | // using proxy, send entire URI |
||
| 240 | $this->_httprequest($URI, $fp, $URI, $this->_submit_method, $this->_submit_type, $postdata); |
||
| 241 | } else { |
||
| 242 | $path = $URI_PARTS["path"] . ($URI_PARTS["query"] ? "?" . $URI_PARTS["query"] : ""); |
||
| 243 | // no proxy, send only the path |
||
| 244 | $this->_httprequest($path, $fp, $URI, $this->_submit_method, $this->_submit_type, $postdata); |
||
| 245 | } |
||
| 246 | |||
| 247 | $this->_disconnect($fp); |
||
| 248 | |||
| 249 | if ($this->_redirectaddr) { |
||
| 250 | /* url was redirected, check if we've hit the max depth */ |
||
| 251 | if ($this->maxredirs > $this->_redirectdepth) { |
||
| 252 | if (!preg_match("|^" . $URI_PARTS["scheme"] . "://|", $this->_redirectaddr)) |
||
| 253 | $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr, $URI_PARTS["scheme"] . "://" . $URI_PARTS["host"]); |
||
| 254 | |||
| 255 | // only follow redirect if it's on this site, or offsiteok is true |
||
| 256 | if (preg_match("|^https?://" . preg_quote($this->host) . "|i", $this->_redirectaddr) || $this->offsiteok) { |
||
| 257 | /* follow the redirect */ |
||
| 258 | $this->_redirectdepth++; |
||
| 259 | $this->lastredirectaddr = $this->_redirectaddr; |
||
| 260 | if (strpos($this->_redirectaddr, "?") > 0) |
||
| 261 | $this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get |
||
| 262 | else |
||
| 263 | $this->submit($this->_redirectaddr, $formvars, $formfiles); |
||
| 264 | } |
||
| 265 | } |
||
| 266 | } |
||
| 267 | |||
| 268 | if ($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) { |
||
| 269 | $frameurls = $this->_frameurls; |
||
| 270 | $this->_frameurls = array(); |
||
| 271 | |||
| 272 | while (list(, $frameurl) = each($frameurls)) { |
||
| 273 | if ($this->_framedepth < $this->maxframes) { |
||
| 274 | $this->fetch($frameurl); |
||
| 275 | $this->_framedepth++; |
||
| 276 | } else |
||
| 277 | break; |
||
| 278 | } |
||
| 279 | } |
||
| 280 | |||
| 281 | } else { |
||
| 282 | return false; |
||
| 283 | } |
||
| 284 | return $this; |
||
| 285 | break; |
||
| 286 | default: |
||
| 287 | // not a valid protocol |
||
| 288 | $this->error = 'Invalid protocol "' . $URI_PARTS["scheme"] . '"\n'; |
||
| 289 | return false; |
||
| 290 | break; |
||
| 291 | } |
||
| 292 | return $this; |
||
| 293 | } |
||
| 294 | |||
| 295 | /*======================================================================*\ |
||
| 296 | Function: fetchlinks |
||
| 297 | Purpose: fetch the links from a web page |
||
| 298 | Input: $URI where you are fetching from |
||
| 299 | Output: $this->results an array of the URLs |
||
| 300 | \*======================================================================*/ |
||
| 301 | |||
| 302 | function fetchlinks($URI) |
||
| 303 | { |
||
| 304 | if ($this->fetch($URI) !== false) { |
||
| 305 | if ($this->lastredirectaddr) |
||
| 306 | $URI = $this->lastredirectaddr; |
||
| 307 | if (is_array($this->results)) { |
||
| 308 | for ($x = 0; $x < count($this->results); $x++) |
||
| 309 | $this->results[$x] = $this->_striplinks($this->results[$x]); |
||
| 310 | } else |
||
| 311 | $this->results = $this->_striplinks($this->results); |
||
| 312 | |||
| 313 | if ($this->expandlinks) |
||
| 314 | $this->results = $this->_expandlinks($this->results, $URI); |
||
| 315 | return $this; |
||
| 316 | } else |
||
| 317 | return false; |
||
| 318 | } |
||
| 319 | |||
| 320 | /*======================================================================*\ |
||
| 321 | Function: fetchform |
||
| 322 | Purpose: fetch the form elements from a web page |
||
| 323 | Input: $URI where you are fetching from |
||
| 324 | Output: $this->results the resulting html form |
||
| 325 | \*======================================================================*/ |
||
| 326 | |||
| 327 | function fetchform($URI) |
||
| 328 | { |
||
| 329 | |||
| 330 | if ($this->fetch($URI) !== false) { |
||
| 331 | |||
| 332 | if (is_array($this->results)) { |
||
| 333 | for ($x = 0; $x < count($this->results); $x++) |
||
| 334 | $this->results[$x] = $this->_stripform($this->results[$x]); |
||
| 335 | } else |
||
| 336 | $this->results = $this->_stripform($this->results); |
||
| 337 | |||
| 338 | return $this; |
||
| 339 | } else |
||
| 340 | return false; |
||
| 341 | } |
||
| 342 | |||
| 343 | |||
| 344 | /*======================================================================*\ |
||
| 345 | Function: fetchtext |
||
| 346 | Purpose: fetch the text from a web page, stripping the links |
||
| 347 | Input: $URI where you are fetching from |
||
| 348 | Output: $this->results the text from the web page |
||
| 349 | \*======================================================================*/ |
||
| 350 | |||
| 351 | function fetchtext($URI) |
||
| 352 | { |
||
| 353 | if ($this->fetch($URI) !== false) { |
||
| 354 | if (is_array($this->results)) { |
||
| 355 | for ($x = 0; $x < count($this->results); $x++) |
||
| 356 | $this->results[$x] = $this->_striptext($this->results[$x]); |
||
| 357 | } else |
||
| 358 | $this->results = $this->_striptext($this->results); |
||
| 359 | return $this; |
||
| 360 | } else |
||
| 361 | return false; |
||
| 362 | } |
||
| 363 | |||
| 364 | /*======================================================================*\ |
||
| 365 | Function: submitlinks |
||
| 366 | Purpose: grab links from a form submission |
||
| 367 | Input: $URI where you are submitting from |
||
| 368 | Output: $this->results an array of the links from the post |
||
| 369 | \*======================================================================*/ |
||
| 370 | |||
| 371 | function submitlinks($URI, $formvars = "", $formfiles = "") |
||
| 372 | { |
||
| 373 | if ($this->submit($URI, $formvars, $formfiles) !== false) { |
||
| 374 | if ($this->lastredirectaddr) |
||
| 375 | $URI = $this->lastredirectaddr; |
||
| 376 | if (is_array($this->results)) { |
||
| 377 | for ($x = 0; $x < count($this->results); $x++) { |
||
| 378 | $this->results[$x] = $this->_striplinks($this->results[$x]); |
||
| 379 | if ($this->expandlinks) |
||
| 380 | $this->results[$x] = $this->_expandlinks($this->results[$x], $URI); |
||
| 381 | } |
||
| 382 | } else { |
||
| 383 | $this->results = $this->_striplinks($this->results); |
||
| 384 | if ($this->expandlinks) |
||
| 385 | $this->results = $this->_expandlinks($this->results, $URI); |
||
| 386 | } |
||
| 387 | return $this; |
||
| 388 | } else |
||
| 389 | return false; |
||
| 390 | } |
||
| 391 | |||
| 392 | /*======================================================================*\ |
||
| 393 | Function: submittext |
||
| 394 | Purpose: grab text from a form submission |
||
| 395 | Input: $URI where you are submitting from |
||
| 396 | Output: $this->results the text from the web page |
||
| 397 | \*======================================================================*/ |
||
| 398 | |||
| 399 | function submittext($URI, $formvars = "", $formfiles = "") |
||
| 400 | { |
||
| 401 | if ($this->submit($URI, $formvars, $formfiles) !== false) { |
||
| 402 | if ($this->lastredirectaddr) |
||
| 403 | $URI = $this->lastredirectaddr; |
||
| 404 | if (is_array($this->results)) { |
||
| 405 | for ($x = 0; $x < count($this->results); $x++) { |
||
| 406 | $this->results[$x] = $this->_striptext($this->results[$x]); |
||
| 407 | if ($this->expandlinks) |
||
| 408 | $this->results[$x] = $this->_expandlinks($this->results[$x], $URI); |
||
| 409 | } |
||
| 410 | } else { |
||
| 411 | $this->results = $this->_striptext($this->results); |
||
| 412 | if ($this->expandlinks) |
||
| 413 | $this->results = $this->_expandlinks($this->results, $URI); |
||
| 414 | } |
||
| 415 | return $this; |
||
| 416 | } else |
||
| 417 | return false; |
||
| 418 | } |
||
| 419 | |||
| 420 | |||
| 421 | /*======================================================================*\ |
||
| 422 | Function: set_submit_multipart |
||
| 423 | Purpose: Set the form submission content type to |
||
| 424 | multipart/form-data |
||
| 425 | \*======================================================================*/ |
||
| 426 | function set_submit_multipart() |
||
| 427 | { |
||
| 428 | $this->_submit_type = "multipart/form-data"; |
||
| 429 | return $this; |
||
| 430 | } |
||
| 431 | |||
| 432 | |||
| 433 | /*======================================================================*\ |
||
| 434 | Function: set_submit_normal |
||
| 435 | Purpose: Set the form submission content type to |
||
| 436 | application/x-www-form-urlencoded |
||
| 437 | \*======================================================================*/ |
||
| 438 | function set_submit_normal() |
||
| 439 | { |
||
| 440 | $this->_submit_type = "application/x-www-form-urlencoded"; |
||
| 441 | return $this; |
||
| 442 | } |
||
| 443 | |||
| 444 | |||
| 445 | |||
| 446 | |||
| 447 | /*======================================================================*\ |
||
| 448 | Private functions |
||
| 449 | \*======================================================================*/ |
||
| 450 | |||
| 451 | |||
| 452 | /*======================================================================*\ |
||
| 453 | Function: _striplinks |
||
| 454 | Purpose: strip the hyperlinks from an html document |
||
| 455 | Input: $document document to strip. |
||
| 456 | Output: $match an array of the links |
||
| 457 | \*======================================================================*/ |
||
| 458 | |||
| 459 | function _striplinks($document) |
||
| 460 | { |
||
| 461 | preg_match_all("'<\s*a\s.*?href\s*=\s* # find <a href= |
||
| 462 | ([\"\'])? # find single or double quote |
||
| 463 | (?(1) (.*?)\\1 | ([^\s\>]+)) # if quote found, match up to next matching |
||
| 464 | # quote, otherwise match up to next space |
||
| 465 | 'isx", $document, $links); |
||
| 466 | |||
| 467 | |||
| 468 | // catenate the non-empty matches from the conditional subpattern |
||
| 469 | |||
| 470 | while (list($key, $val) = each($links[2])) { |
||
| 471 | if (!empty($val)) |
||
| 472 | $match[] = $val; |
||
| 473 | } |
||
| 474 | |||
| 475 | while (list($key, $val) = each($links[3])) { |
||
| 476 | if (!empty($val)) |
||
| 477 | $match[] = $val; |
||
| 478 | } |
||
| 479 | |||
| 480 | // return the links |
||
| 481 | return $match; |
||
| 482 | } |
||
| 483 | |||
| 484 | /*======================================================================*\ |
||
| 485 | Function: _stripform |
||
| 486 | Purpose: strip the form elements from an html document |
||
| 487 | Input: $document document to strip. |
||
| 488 | Output: $match an array of the links |
||
| 489 | \*======================================================================*/ |
||
| 490 | |||
| 491 | function _stripform($document) |
||
| 492 | { |
||
| 493 | preg_match_all("'<\/?(FORM|INPUT|SELECT|TEXTAREA|(OPTION))[^<>]*>(?(2)(.*(?=<\/?(option|select)[^<>]*>[\r\n]*)|(?=[\r\n]*))|(?=[\r\n]*))'Usi", $document, $elements); |
||
| 494 | |||
| 495 | // catenate the matches |
||
| 496 | $match = implode("\r\n", $elements[0]); |
||
| 497 | |||
| 498 | // return the links |
||
| 499 | return $match; |
||
| 500 | } |
||
| 501 | |||
| 502 | |||
| 503 | /*======================================================================*\ |
||
| 504 | Function: _striptext |
||
| 505 | Purpose: strip the text from an html document |
||
| 506 | Input: $document document to strip. |
||
| 507 | Output: $text the resulting text |
||
| 508 | \*======================================================================*/ |
||
| 509 | |||
| 510 | function _striptext($document) |
||
| 511 | { |
||
| 512 | |||
| 513 | // I didn't use preg eval (//e) since that is only available in PHP 4.0. |
||
| 514 | // so, list your entities one by one here. I included some of the |
||
| 515 | // more common ones. |
||
| 516 | |||
| 517 | $search = array("'<script[^>]*?>.*?</script>'si", // strip out javascript |
||
| 518 | "'<[\/\!]*?[^<>]*?>'si", // strip out html tags |
||
| 519 | "'([\r\n])[\s]+'", // strip out white space |
||
| 520 | "'&(quot|#34|#034|#x22);'i", // replace html entities |
||
| 521 | "'&(amp|#38|#038|#x26);'i", // added hexadecimal values |
||
| 522 | "'&(lt|#60|#060|#x3c);'i", |
||
| 523 | "'&(gt|#62|#062|#x3e);'i", |
||
| 524 | "'&(nbsp|#160|#xa0);'i", |
||
| 525 | "'&(iexcl|#161);'i", |
||
| 526 | "'&(cent|#162);'i", |
||
| 527 | "'&(pound|#163);'i", |
||
| 528 | "'&(copy|#169);'i", |
||
| 529 | "'&(reg|#174);'i", |
||
| 530 | "'&(deg|#176);'i", |
||
| 531 | "'&(#39|#039|#x27);'", |
||
| 532 | "'&(euro|#8364);'i", // europe |
||
| 533 | "'&a(uml|UML);'", // german |
||
| 534 | "'&o(uml|UML);'", |
||
| 535 | "'&u(uml|UML);'", |
||
| 536 | "'&A(uml|UML);'", |
||
| 537 | "'&O(uml|UML);'", |
||
| 538 | "'&U(uml|UML);'", |
||
| 539 | "'ß'i", |
||
| 540 | ); |
||
| 541 | $replace = array("", |
||
| 542 | "", |
||
| 543 | "\\1", |
||
| 544 | "\"", |
||
| 545 | "&", |
||
| 546 | "<", |
||
| 547 | ">", |
||
| 548 | " ", |
||
| 549 | chr(161), |
||
| 550 | chr(162), |
||
| 551 | chr(163), |
||
| 552 | chr(169), |
||
| 553 | chr(174), |
||
| 554 | chr(176), |
||
| 555 | chr(39), |
||
| 556 | chr(128), |
||
| 557 | "ä", |
||
| 558 | "ö", |
||
| 559 | "ü", |
||
| 560 | "Ä", |
||
| 561 | "Ö", |
||
| 562 | "Ü", |
||
| 563 | "ß", |
||
| 564 | ); |
||
| 565 | |||
| 566 | $text = preg_replace($search, $replace, $document); |
||
| 567 | |||
| 568 | return $text; |
||
| 569 | } |
||
| 570 | |||
| 571 | /*======================================================================*\ |
||
| 572 | Function: _expandlinks |
||
| 573 | Purpose: expand each link into a fully qualified URL |
||
| 574 | Input: $links the links to qualify |
||
| 575 | $URI the full URI to get the base from |
||
| 576 | Output: $expandedLinks the expanded links |
||
| 577 | \*======================================================================*/ |
||
| 578 | |||
| 579 | function _expandlinks($links, $URI) |
||
| 580 | { |
||
| 581 | |||
| 582 | preg_match("/^[^\?]+/", $URI, $match); |
||
| 583 | |||
| 584 | $match = preg_replace("|/[^\/\.]+\.[^\/\.]+$|", "", $match[0]); |
||
| 585 | $match = preg_replace("|/$|", "", $match); |
||
| 586 | $match_part = parse_url($match); |
||
| 587 | $match_root = |
||
| 588 | $match_part["scheme"] . "://" . $match_part["host"]; |
||
| 589 | |||
| 590 | $search = array("|^http://" . preg_quote($this->host) . "|i", |
||
| 591 | "|^(\/)|i", |
||
| 592 | "|^(?!http://)(?!mailto:)|i", |
||
| 593 | "|/\./|", |
||
| 594 | "|/[^\/]+/\.\./|" |
||
| 595 | ); |
||
| 596 | |||
| 597 | $replace = array("", |
||
| 598 | $match_root . "/", |
||
| 599 | $match . "/", |
||
| 600 | "/", |
||
| 601 | "/" |
||
| 602 | ); |
||
| 603 | |||
| 604 | $expandedLinks = preg_replace($search, $replace, $links); |
||
| 605 | |||
| 606 | return $expandedLinks; |
||
| 607 | } |
||
| 608 | |||
| 609 | /*======================================================================*\ |
||
| 610 | Function: _httprequest |
||
| 611 | Purpose: go get the http(s) data from the server |
||
| 612 | Input: $url the url to fetch |
||
| 613 | $fp the current open file pointer |
||
| 614 | $URI the full URI |
||
| 615 | $body body contents to send if any (POST) |
||
| 616 | Output: |
||
| 617 | \*======================================================================*/ |
||
| 618 | |||
| 619 | function _httprequest($url, $fp, $URI, $http_method, $content_type = "", $body = "") |
||
| 620 | { |
||
| 621 | $cookie_headers = ''; |
||
| 622 | if ($this->passcookies && $this->_redirectaddr) |
||
| 623 | $this->setcookies(); |
||
| 624 | |||
| 625 | $URI_PARTS = parse_url($URI); |
||
| 626 | if (empty($url)) |
||
| 627 | $url = "/"; |
||
| 628 | $headers = $http_method . " " . $url . " " . $this->_httpversion . "\r\n"; |
||
| 629 | if (!empty($this->host) && !isset($this->rawheaders['Host'])) { |
||
| 630 | $headers .= "Host: " . $this->host; |
||
| 631 | if (!empty($this->port) && $this->port != '80') |
||
| 632 | $headers .= ":" . $this->port; |
||
| 633 | $headers .= "\r\n"; |
||
| 634 | } |
||
| 635 | if (!empty($this->agent)) |
||
| 636 | $headers .= "User-Agent: " . $this->agent . "\r\n"; |
||
| 637 | if (!empty($this->accept)) |
||
| 638 | $headers .= "Accept: " . $this->accept . "\r\n"; |
||
| 639 | if ($this->use_gzip) { |
||
| 640 | // make sure PHP was built with --with-zlib |
||
| 641 | // and we can handle gzipp'ed data |
||
| 642 | if (function_exists('gzinflate')) { |
||
| 643 | $headers .= "Accept-encoding: gzip\r\n"; |
||
| 644 | } else { |
||
| 645 | trigger_error( |
||
| 646 | "use_gzip is on, but PHP was built without zlib support." . |
||
| 647 | " Requesting file(s) without gzip encoding.", |
||
| 648 | E_USER_NOTICE); |
||
| 649 | } |
||
| 650 | } |
||
| 651 | if (!empty($this->referer)) |
||
| 652 | $headers .= "Referer: " . $this->referer . "\r\n"; |
||
| 653 | if (!empty($this->cookies)) { |
||
| 654 | if (!is_array($this->cookies)) |
||
| 655 | $this->cookies = (array)$this->cookies; |
||
| 656 | |||
| 657 | reset($this->cookies); |
||
| 658 | if (count($this->cookies) > 0) { |
||
| 659 | $cookie_headers .= 'Cookie: '; |
||
| 660 | foreach ($this->cookies as $cookieKey => $cookieVal) { |
||
| 661 | $cookie_headers .= $cookieKey . "=" . urlencode($cookieVal) . "; "; |
||
| 662 | } |
||
| 663 | $headers .= substr($cookie_headers, 0, -2) . "\r\n"; |
||
| 664 | } |
||
| 665 | } |
||
| 666 | if (!empty($this->rawheaders)) { |
||
| 667 | if (!is_array($this->rawheaders)) |
||
| 668 | $this->rawheaders = (array)$this->rawheaders; |
||
| 669 | while (list($headerKey, $headerVal) = each($this->rawheaders)) |
||
| 670 | $headers .= $headerKey . ": " . $headerVal . "\r\n"; |
||
| 671 | } |
||
| 672 | if (!empty($content_type)) { |
||
| 673 | $headers .= "Content-type: $content_type"; |
||
| 674 | if ($content_type == "multipart/form-data") |
||
| 675 | $headers .= "; boundary=" . $this->_mime_boundary; |
||
| 676 | $headers .= "\r\n"; |
||
| 677 | } |
||
| 678 | if (!empty($body)) |
||
| 679 | $headers .= "Content-length: " . strlen($body) . "\r\n"; |
||
| 680 | if (!empty($this->user) || !empty($this->pass)) |
||
| 681 | $headers .= "Authorization: Basic " . base64_encode($this->user . ":" . $this->pass) . "\r\n"; |
||
| 682 | |||
| 683 | //add proxy auth headers |
||
| 684 | if (!empty($this->proxy_user)) |
||
| 685 | $headers .= 'Proxy-Authorization: ' . 'Basic ' . base64_encode($this->proxy_user . ':' . $this->proxy_pass) . "\r\n"; |
||
| 686 | |||
| 687 | |||
| 688 | $headers .= "\r\n"; |
||
| 689 | |||
| 690 | // set the read timeout if needed |
||
| 691 | if ($this->read_timeout > 0) |
||
| 692 | socket_set_timeout($fp, $this->read_timeout); |
||
| 693 | $this->timed_out = false; |
||
| 694 | |||
| 695 | fwrite($fp, $headers . $body, strlen($headers . $body)); |
||
| 696 | |||
| 697 | $this->_redirectaddr = false; |
||
| 698 | unset($this->headers); |
||
| 699 | |||
| 700 | // content was returned gzip encoded? |
||
| 701 | $is_gzipped = false; |
||
| 702 | |||
| 703 | while ($currentHeader = fgets($fp, $this->_maxlinelen)) { |
||
| 704 | if ($this->read_timeout > 0 && $this->_check_timeout($fp)) { |
||
| 705 | $this->status = -100; |
||
| 706 | return false; |
||
| 707 | } |
||
| 708 | |||
| 709 | if ($currentHeader == "\r\n") |
||
| 710 | break; |
||
| 711 | |||
| 712 | // if a header begins with Location: or URI:, set the redirect |
||
| 713 | if (preg_match("/^(Location:|URI:)/i", $currentHeader)) { |
||
| 714 | // get URL portion of the redirect |
||
| 715 | preg_match("/^(Location:|URI:)[ ]+(.*)/i", chop($currentHeader), $matches); |
||
| 716 | // look for :// in the Location header to see if hostname is included |
||
| 717 | if (!preg_match("|\:\/\/|", $matches[2])) { |
||
| 718 | // no host in the path, so prepend |
||
| 719 | $this->_redirectaddr = $URI_PARTS["scheme"] . "://" . $this->host . ":" . $this->port; |
||
| 720 | // eliminate double slash |
||
| 721 | if (!preg_match("|^/|", $matches[2])) |
||
| 722 | $this->_redirectaddr .= "/" . $matches[2]; |
||
| 723 | else |
||
| 724 | $this->_redirectaddr .= $matches[2]; |
||
| 725 | } else |
||
| 726 | $this->_redirectaddr = $matches[2]; |
||
| 727 | } |
||
| 728 | |||
| 729 | if (preg_match("|^HTTP/|", $currentHeader)) { |
||
| 730 | if (preg_match("|^HTTP/[^\s]*\s(.*?)\s|", $currentHeader, $status)) { |
||
| 731 | $this->status = $status[1]; |
||
| 732 | } |
||
| 733 | $this->response_code = $currentHeader; |
||
| 734 | } |
||
| 735 | |||
| 736 | if (preg_match("/Content-Encoding: gzip/", $currentHeader)) { |
||
| 737 | $is_gzipped = true; |
||
| 738 | } |
||
| 739 | |||
| 740 | $this->headers[] = $currentHeader; |
||
| 741 | } |
||
| 742 | |||
| 743 | $results = ''; |
||
| 744 | do { |
||
| 745 | $_data = fread($fp, $this->maxlength); |
||
| 746 | if (strlen($_data) == 0) { |
||
| 747 | break; |
||
| 748 | } |
||
| 749 | $results .= $_data; |
||
| 750 | } while (true); |
||
| 751 | |||
| 752 | // gunzip |
||
| 753 | if ($is_gzipped) { |
||
| 754 | // per http://www.php.net/manual/en/function.gzencode.php |
||
| 755 | $results = substr($results, 10); |
||
| 756 | $results = gzinflate($results); |
||
| 757 | } |
||
| 758 | |||
| 759 | if ($this->read_timeout > 0 && $this->_check_timeout($fp)) { |
||
| 760 | $this->status = -100; |
||
| 761 | return false; |
||
| 762 | } |
||
| 763 | |||
| 764 | // check if there is a a redirect meta tag |
||
| 765 | |||
| 766 | if (preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i", $results, $match)) { |
||
| 767 | $this->_redirectaddr = $this->_expandlinks($match[1], $URI); |
||
| 768 | } |
||
| 769 | |||
| 770 | // have we hit our frame depth and is there frame src to fetch? |
||
| 771 | if (($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i", $results, $match)) { |
||
| 772 | $this->results[] = $results; |
||
| 773 | for ($x = 0; $x < count($match[1]); $x++) |
||
| 774 | $this->_frameurls[] = $this->_expandlinks($match[1][$x], $URI_PARTS["scheme"] . "://" . $this->host); |
||
| 775 | } // have we already fetched framed content? |
||
| 776 | elseif (is_array($this->results)) |
||
| 777 | $this->results[] = $results; |
||
| 778 | // no framed content |
||
| 779 | else |
||
| 780 | $this->results = $results; |
||
| 781 | |||
| 782 | return $this; |
||
| 783 | } |
||
| 784 | |||
| 785 | /*======================================================================*\ |
||
| 786 | Function: setcookies() |
||
| 787 | Purpose: set cookies for a redirection |
||
| 788 | \*======================================================================*/ |
||
| 789 | |||
| 790 | function setcookies() |
||
| 791 | { |
||
| 792 | for ($x = 0; $x < count($this->headers); $x++) { |
||
| 793 | if (preg_match('/^set-cookie:[\s]+([^=]+)=([^;]+)/i', $this->headers[$x], $match)) |
||
| 794 | $this->cookies[$match[1]] = urldecode($match[2]); |
||
| 795 | } |
||
| 796 | return $this; |
||
| 797 | } |
||
| 798 | |||
| 799 | |||
| 800 | /*======================================================================*\ |
||
| 801 | Function: _check_timeout |
||
| 802 | Purpose: checks whether timeout has occurred |
||
| 803 | Input: $fp file pointer |
||
| 804 | \*======================================================================*/ |
||
| 805 | |||
| 806 | function _check_timeout($fp) |
||
| 807 | { |
||
| 808 | if ($this->read_timeout > 0) { |
||
| 809 | $fp_status = socket_get_status($fp); |
||
| 810 | if ($fp_status["timed_out"]) { |
||
| 811 | $this->timed_out = true; |
||
| 812 | return true; |
||
| 813 | } |
||
| 814 | } |
||
| 815 | return false; |
||
| 816 | } |
||
| 817 | |||
| 818 | /*======================================================================*\ |
||
| 819 | Function: _connect |
||
| 820 | Purpose: make a socket connection |
||
| 821 | Input: $fp file pointer |
||
| 822 | \*======================================================================*/ |
||
| 823 | |||
| 824 | function _connect(&$fp) |
||
| 825 | { |
||
| 826 | if (!empty($this->proxy_host) && !empty($this->proxy_port)) { |
||
| 827 | $this->_isproxy = true; |
||
| 828 | |||
| 829 | $host = $this->proxy_host; |
||
| 830 | $port = $this->proxy_port; |
||
| 831 | |||
| 832 | if ($this->scheme == 'https') { |
||
| 833 | trigger_error("HTTPS connections over proxy are currently not supported", E_USER_ERROR); |
||
| 834 | exit; |
||
| 835 | } |
||
| 836 | } else { |
||
| 837 | $host = $this->host; |
||
| 838 | $port = $this->port; |
||
| 839 | } |
||
| 840 | |||
| 841 | $this->status = 0; |
||
| 842 | |||
| 843 | $context_opts = array(); |
||
| 844 | |||
| 845 | if ($this->scheme == 'https') { |
||
| 846 | // if cafile or capath is specified, enable certificate |
||
| 847 | // verification (including name checks) |
||
| 848 | if (isset($this->cafile) || isset($this->capath)) { |
||
| 849 | $context_opts['ssl'] = array( |
||
| 850 | 'verify_peer' => true, |
||
| 851 | 'CN_match' => $this->host, |
||
| 852 | 'disable_compression' => true, |
||
| 853 | ); |
||
| 854 | |||
| 855 | if (isset($this->cafile)) |
||
| 856 | $context_opts['ssl']['cafile'] = $this->cafile; |
||
| 857 | if (isset($this->capath)) |
||
| 858 | $context_opts['ssl']['capath'] = $this->capath; |
||
| 859 | } |
||
| 860 | |||
| 861 | $host = 'ssl://' . $host; |
||
| 862 | } |
||
| 863 | |||
| 864 | $context = stream_context_create($context_opts); |
||
| 865 | |||
| 866 | if (version_compare(PHP_VERSION, '5.0.0', '>')) { |
||
| 867 | if($this->scheme == 'http') |
||
| 868 | $host = "tcp://" . $host; |
||
| 869 | $fp = stream_socket_client( |
||
| 870 | "$host:$port", |
||
| 871 | $errno, |
||
| 872 | $errmsg, |
||
| 873 | $this->_fp_timeout, |
||
| 874 | STREAM_CLIENT_CONNECT, |
||
| 875 | $context); |
||
| 876 | } else { |
||
| 877 | $fp = fsockopen( |
||
| 878 | $host, |
||
| 879 | $port, |
||
| 880 | $errno, |
||
| 881 | $errstr, |
||
| 882 | $this->_fp_timeout, |
||
| 883 | $context); |
||
| 884 | } |
||
| 885 | |||
| 886 | if ($fp) { |
||
| 887 | // socket connection succeeded |
||
| 888 | return true; |
||
| 889 | } else { |
||
| 890 | // socket connection failed |
||
| 891 | $this->status = $errno; |
||
| 892 | switch ($errno) { |
||
| 893 | case -3: |
||
| 894 | $this->error = "socket creation failed (-3)"; |
||
| 895 | case -4: |
||
| 896 | $this->error = "dns lookup failure (-4)"; |
||
| 897 | case -5: |
||
| 898 | $this->error = "connection refused or timed out (-5)"; |
||
| 899 | default: |
||
| 900 | $this->error = "connection failed (" . $errno . ")"; |
||
| 901 | } |
||
| 902 | return false; |
||
| 903 | } |
||
| 904 | } |
||
| 905 | |||
| 906 | /*======================================================================*\ |
||
| 907 | Function: _disconnect |
||
| 908 | Purpose: disconnect a socket connection |
||
| 909 | Input: $fp file pointer |
||
| 910 | \*======================================================================*/ |
||
| 911 | |||
| 912 | function _disconnect($fp) |
||
| 913 | { |
||
| 914 | return (fclose($fp)); |
||
| 915 | } |
||
| 916 | |||
| 917 | |||
| 918 | /*======================================================================*\ |
||
| 919 | Function: _prepare_post_body |
||
| 920 | Purpose: Prepare post body according to encoding type |
||
| 921 | Input: $formvars - form variables |
||
| 922 | $formfiles - form upload files |
||
| 923 | Output: post body |
||
| 924 | \*======================================================================*/ |
||
| 925 | |||
| 926 | function _prepare_post_body($formvars, $formfiles) |
||
| 927 | { |
||
| 928 | settype($formvars, "array"); |
||
| 929 | settype($formfiles, "array"); |
||
| 930 | $postdata = ''; |
||
| 931 | |||
| 932 | if (count($formvars) == 0 && count($formfiles) == 0) |
||
| 933 | return; |
||
| 934 | |||
| 935 | switch ($this->_submit_type) { |
||
| 936 | case "application/x-www-form-urlencoded": |
||
| 937 | reset($formvars); |
||
| 938 | while (list($key, $val) = each($formvars)) { |
||
| 939 | if (is_array($val) || is_object($val)) { |
||
| 940 | while (list($cur_key, $cur_val) = each($val)) { |
||
| 941 | $postdata .= urlencode($key) . "[]=" . urlencode($cur_val) . "&"; |
||
| 942 | } |
||
| 943 | } else |
||
| 944 | $postdata .= urlencode($key) . "=" . urlencode($val) . "&"; |
||
| 945 | } |
||
| 946 | break; |
||
| 947 | |||
| 948 | case "multipart/form-data": |
||
| 949 | $this->_mime_boundary = "Snoopy" . md5(uniqid(microtime())); |
||
| 950 | |||
| 951 | reset($formvars); |
||
| 952 | while (list($key, $val) = each($formvars)) { |
||
| 953 | if (is_array($val) || is_object($val)) { |
||
| 954 | while (list($cur_key, $cur_val) = each($val)) { |
||
| 955 | $postdata .= "--" . $this->_mime_boundary . "\r\n"; |
||
| 956 | $postdata .= "Content-Disposition: form-data; name=\"$key\[\]\"\r\n\r\n"; |
||
| 957 | $postdata .= "$cur_val\r\n"; |
||
| 958 | } |
||
| 959 | } else { |
||
| 960 | $postdata .= "--" . $this->_mime_boundary . "\r\n"; |
||
| 961 | $postdata .= "Content-Disposition: form-data; name=\"$key\"\r\n\r\n"; |
||
| 962 | $postdata .= "$val\r\n"; |
||
| 963 | } |
||
| 964 | } |
||
| 965 | |||
| 966 | reset($formfiles); |
||
| 967 | while (list($field_name, $file_names) = each($formfiles)) { |
||
| 968 | settype($file_names, "array"); |
||
| 969 | while (list(, $file_name) = each($file_names)) { |
||
| 970 | if (!is_readable($file_name)) continue; |
||
| 971 | |||
| 972 | $fp = fopen($file_name, "r"); |
||
| 973 | $file_content = fread($fp, filesize($file_name)); |
||
| 974 | fclose($fp); |
||
| 975 | $base_name = basename($file_name); |
||
| 976 | |||
| 977 | $postdata .= "--" . $this->_mime_boundary . "\r\n"; |
||
| 978 | $postdata .= "Content-Disposition: form-data; name=\"$field_name\"; filename=\"$base_name\"\r\n\r\n"; |
||
| 979 | $postdata .= "$file_content\r\n"; |
||
| 980 | } |
||
| 981 | } |
||
| 982 | $postdata .= "--" . $this->_mime_boundary . "--\r\n"; |
||
| 983 | break; |
||
| 984 | } |
||
| 985 | |||
| 986 | return $postdata; |
||
| 987 | } |
||
| 988 | |||
| 989 | /*======================================================================*\ |
||
| 990 | Function: getResults |
||
| 991 | Purpose: return the results of a request |
||
| 992 | Output: string results |
||
| 993 | \*======================================================================*/ |
||
| 994 | |||
| 995 | function getResults() |
||
| 998 | } |
||
| 999 | } |
||
| 1000 | |||
| 1001 | ?> |
||
| 1002 |
Loading history...
Adding explicit visibility (
private,protected, orpublic) is generally recommend to communicate to other developers how, and from where this method is intended to be used.