Total Complexity | 222 |
Total Lines | 1234 |
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 |
||
47 | class Snoopy |
||
48 | { |
||
49 | public function __construct() |
||
50 | { |
||
51 | $GLOBALS['xoopsLogger']->addDeprecated("Use of Snoopy in XOOPS is deprecated and has been replaced in core with XoopsHttpGet. Snoopy will be removed in future versions.."); |
||
52 | } |
||
53 | |||
54 | /**** Public variables ****/ |
||
55 | |||
56 | /* user definable vars */ |
||
57 | |||
58 | public $host = "www.php.net"; // host name we are connecting to |
||
59 | public $port = 80; // port we are connecting to |
||
60 | public $proxy_host = ""; // proxy host to use |
||
61 | public $proxy_port = ""; // proxy port to use |
||
62 | public $proxy_user = ""; // proxy user to use |
||
63 | public $proxy_pass = ""; // proxy password to use |
||
64 | |||
65 | public $agent = "Snoopy v1.2.5"; // agent we masquerade as |
||
66 | public $referer = ""; // referer info to pass |
||
67 | public $cookies = []; // array of cookies to pass |
||
68 | // $cookies["username"]="joe"; |
||
69 | public $rawheaders = []; // array of raw headers to send |
||
70 | // $rawheaders["Content-type"]="text/html"; |
||
71 | |||
72 | public $maxredirs = 5; // http redirection depth maximum. 0 = disallow |
||
73 | public $lastredirectaddr = ""; // contains address of last redirected address |
||
74 | public $offsiteok = true; // allows redirection off-site |
||
75 | public $maxframes = 0; // frame content depth maximum. 0 = disallow |
||
76 | public $expandlinks = true; // expand links to fully qualified URLs. |
||
77 | // this only applies to fetchlinks() |
||
78 | // submitlinks(), and submittext() |
||
79 | public $passcookies = true; // pass set cookies back through redirects |
||
80 | // NOTE: this currently does not respect |
||
81 | // dates, domains or paths. |
||
82 | |||
83 | public $user = ""; // user for http authentication |
||
84 | public $pass = ""; // password for http authentication |
||
85 | |||
86 | // http accept types |
||
87 | public $accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*"; |
||
88 | |||
89 | public $results = []; // where the content is put |
||
90 | |||
91 | public $error = ""; // error messages sent here |
||
92 | public $response_code = ""; // response code returned from server |
||
93 | public $headers = []; // headers returned from server sent here |
||
94 | public $maxlength = 500000; // max return data length (body) |
||
95 | public $read_timeout = 0; // timeout on read operations, in seconds |
||
96 | // supported only since PHP 4 Beta 4 |
||
97 | // set to 0 to disallow timeouts |
||
98 | public $timed_out = false; // if a read operation timed out |
||
99 | public $status = 0; // http request status |
||
100 | |||
101 | public $temp_dir = "/tmp"; // temporary directory that the webserver |
||
102 | // has permission to write to. |
||
103 | // under Windows, this should be C:\temp |
||
104 | |||
105 | public $curl_path = "/usr/bin/curl"; |
||
106 | // Snoopy will use cURL for fetching |
||
107 | // SSL content if a full system path to |
||
108 | // the cURL binary is supplied here. |
||
109 | // set to false if you do not have |
||
110 | // cURL installed. See http://curl.haxx.se |
||
111 | // for details on installing cURL. |
||
112 | // Snoopy does *not* use the cURL |
||
113 | // library functions built into php, |
||
114 | // as these functions are not stable |
||
115 | // as of this Snoopy release. |
||
116 | |||
117 | // send Accept-encoding: gzip? |
||
118 | public $use_gzip = true; |
||
119 | /**** Private variables ****/ |
||
120 | |||
121 | public $_maxlinelen = 4096; // max line length (headers) |
||
122 | |||
123 | public $_httpmethod = "GET"; // default http request method |
||
124 | public $_httpversion = "HTTP/1.0"; // default http request version |
||
125 | public $_submit_method = "POST"; // default submit method |
||
126 | public $_submit_type = "application/x-www-form-urlencoded"; // default submit type |
||
127 | public $_mime_boundary = ""; // MIME boundary for multipart/form-data submit type |
||
128 | public $_redirectaddr = false; // will be set if page fetched is a redirect |
||
129 | public $_redirectdepth = 0; // increments on an http redirect |
||
130 | public $_frameurls = []; // frame src urls |
||
131 | public $_framedepth = 0; // increments on frame depth |
||
132 | |||
133 | public $_isproxy = false; // set if using a proxy server |
||
134 | public $_fp_timeout = 30; // timeout for socket connection |
||
135 | |||
136 | /*======================================================================*\ |
||
137 | Function: fetch |
||
138 | Purpose: fetch the contents of a web page |
||
139 | (and possibly other protocols in the |
||
140 | future like ftp, nntp, gopher, etc.) |
||
141 | Input: $URI the location of the page to fetch |
||
142 | Output: $this->results the output text from the fetch |
||
143 | \*======================================================================*/ |
||
144 | |||
145 | public function fetch($URI) |
||
146 | { |
||
147 | |||
148 | //preg_match("|^([^:]+)://([^:/]+)(:[\d]+)*(.*)|",$URI,$URI_PARTS); |
||
149 | $URI_PARTS = parse_url($URI); |
||
150 | if (!empty($URI_PARTS["user"])) { |
||
151 | $this->user = $URI_PARTS["user"]; |
||
152 | } |
||
153 | if (!empty($URI_PARTS["pass"])) { |
||
154 | $this->pass = $URI_PARTS["pass"]; |
||
155 | } |
||
156 | if (empty($URI_PARTS["query"])) { |
||
157 | $URI_PARTS["query"] = ''; |
||
158 | } |
||
159 | if (empty($URI_PARTS["path"])) { |
||
160 | $URI_PARTS["path"] = ''; |
||
161 | } |
||
162 | |||
163 | switch (strtolower($URI_PARTS["scheme"])) { |
||
164 | case "http": |
||
165 | $this->host = $URI_PARTS["host"]; |
||
166 | if (!empty($URI_PARTS["port"])) { |
||
167 | $this->port = $URI_PARTS["port"]; |
||
168 | } |
||
169 | if ($this->_connect($fp)) { |
||
170 | if ($this->_isproxy) { |
||
171 | // using proxy, send entire URI |
||
172 | $this->_httprequest($URI, $fp, $URI, $this->_httpmethod); |
||
173 | } else { |
||
174 | $path = $URI_PARTS["path"] . ($URI_PARTS["query"] ? "?" . $URI_PARTS["query"] : ""); |
||
175 | // no proxy, send only the path |
||
176 | $this->_httprequest($path, $fp, $URI, $this->_httpmethod); |
||
177 | } |
||
178 | |||
179 | $this->_disconnect($fp); |
||
180 | |||
181 | if ($this->_redirectaddr) { |
||
182 | /* url was redirected, check if we've hit the max depth */ |
||
183 | if ($this->maxredirs > $this->_redirectdepth) { |
||
184 | // only follow redirect if it's on this site, or offsiteok is true |
||
185 | if (preg_match("|^http://" . preg_quote($this->host) . "|i", $this->_redirectaddr) || $this->offsiteok) { |
||
186 | /* follow the redirect */ |
||
187 | $this->_redirectdepth++; |
||
188 | $this->lastredirectaddr = $this->_redirectaddr; |
||
189 | $this->fetch($this->_redirectaddr); |
||
190 | } |
||
191 | } |
||
192 | } |
||
193 | |||
194 | if ($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) { |
||
195 | $frameurls = $this->_frameurls; |
||
196 | $this->_frameurls = []; |
||
197 | |||
198 | while (list(, $frameurl) = each($frameurls)) { |
||
199 | if ($this->_framedepth < $this->maxframes) { |
||
200 | $this->fetch($frameurl); |
||
201 | $this->_framedepth++; |
||
202 | } else { |
||
203 | break; |
||
204 | } |
||
205 | } |
||
206 | } |
||
207 | } else { |
||
208 | return false; |
||
209 | } |
||
210 | return true; |
||
211 | break; |
||
|
|||
212 | case "https": |
||
213 | if (!$this->curl_path) { |
||
214 | return false; |
||
215 | } |
||
216 | if (function_exists("is_executable")) { |
||
217 | if (!is_executable($this->curl_path)) { |
||
218 | return false; |
||
219 | } |
||
220 | } |
||
221 | $this->host = $URI_PARTS["host"]; |
||
222 | if (!empty($URI_PARTS["port"])) { |
||
223 | $this->port = $URI_PARTS["port"]; |
||
224 | } |
||
225 | if ($this->_isproxy) { |
||
226 | // using proxy, send entire URI |
||
227 | $this->_httpsrequest($URI, $URI, $this->_httpmethod); |
||
228 | } else { |
||
229 | $path = $URI_PARTS["path"] . ($URI_PARTS["query"] ? "?" . $URI_PARTS["query"] : ""); |
||
230 | // no proxy, send only the path |
||
231 | $this->_httpsrequest($path, $URI, $this->_httpmethod); |
||
232 | } |
||
233 | |||
234 | if ($this->_redirectaddr) { |
||
235 | /* url was redirected, check if we've hit the max depth */ |
||
236 | if ($this->maxredirs > $this->_redirectdepth) { |
||
237 | // only follow redirect if it's on this site, or offsiteok is true |
||
238 | if (preg_match("|^http://" . preg_quote($this->host) . "|i", $this->_redirectaddr) || $this->offsiteok) { |
||
239 | /* follow the redirect */ |
||
240 | $this->_redirectdepth++; |
||
241 | $this->lastredirectaddr = $this->_redirectaddr; |
||
242 | $this->fetch($this->_redirectaddr); |
||
243 | } |
||
244 | } |
||
245 | } |
||
246 | |||
247 | if ($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) { |
||
248 | $frameurls = $this->_frameurls; |
||
249 | $this->_frameurls = []; |
||
250 | |||
251 | while (list(, $frameurl) = each($frameurls)) { |
||
252 | if ($this->_framedepth < $this->maxframes) { |
||
253 | $this->fetch($frameurl); |
||
254 | $this->_framedepth++; |
||
255 | } else { |
||
256 | break; |
||
257 | } |
||
258 | } |
||
259 | } |
||
260 | return true; |
||
261 | break; |
||
262 | default: |
||
263 | // not a valid protocol |
||
264 | $this->error = 'Invalid protocol "' . $URI_PARTS["scheme"] . '"\n'; |
||
265 | return false; |
||
266 | break; |
||
267 | } |
||
268 | return true; |
||
269 | } |
||
270 | |||
271 | /*======================================================================*\ |
||
272 | Function: submit |
||
273 | Purpose: submit an http form |
||
274 | Input: $URI the location to post the data |
||
275 | $formvars the formvars to use. |
||
276 | format: $formvars["var"] = "val"; |
||
277 | $formfiles an array of files to submit |
||
278 | format: $formfiles["var"] = "/dir/filename.ext"; |
||
279 | Output: $this->results the text output from the post |
||
280 | \*======================================================================*/ |
||
281 | |||
282 | public function submit($URI, $formvars = "", $formfiles = "") |
||
283 | { |
||
284 | unset($postdata); |
||
285 | |||
286 | $postdata = $this->_prepare_post_body($formvars, $formfiles); |
||
287 | |||
288 | $URI_PARTS = parse_url($URI); |
||
289 | if (!empty($URI_PARTS["user"])) { |
||
290 | $this->user = $URI_PARTS["user"]; |
||
291 | } |
||
292 | if (!empty($URI_PARTS["pass"])) { |
||
293 | $this->pass = $URI_PARTS["pass"]; |
||
294 | } |
||
295 | if (empty($URI_PARTS["query"])) { |
||
296 | $URI_PARTS["query"] = ''; |
||
297 | } |
||
298 | if (empty($URI_PARTS["path"])) { |
||
299 | $URI_PARTS["path"] = ''; |
||
300 | } |
||
301 | |||
302 | switch (strtolower($URI_PARTS["scheme"])) { |
||
303 | case "http": |
||
304 | $this->host = $URI_PARTS["host"]; |
||
305 | if (!empty($URI_PARTS["port"])) { |
||
306 | $this->port = $URI_PARTS["port"]; |
||
307 | } |
||
308 | if ($this->_connect($fp)) { |
||
309 | if ($this->_isproxy) { |
||
310 | // using proxy, send entire URI |
||
311 | $this->_httprequest($URI, $fp, $URI, $this->_submit_method, $this->_submit_type, $postdata); |
||
312 | } else { |
||
313 | $path = $URI_PARTS["path"] . ($URI_PARTS["query"] ? "?" . $URI_PARTS["query"] : ""); |
||
314 | // no proxy, send only the path |
||
315 | $this->_httprequest($path, $fp, $URI, $this->_submit_method, $this->_submit_type, $postdata); |
||
316 | } |
||
317 | |||
318 | $this->_disconnect($fp); |
||
319 | |||
320 | if ($this->_redirectaddr) { |
||
321 | /* url was redirected, check if we've hit the max depth */ |
||
322 | if ($this->maxredirs > $this->_redirectdepth) { |
||
323 | if (!preg_match("|^" . $URI_PARTS["scheme"] . "://|", $this->_redirectaddr)) { |
||
324 | $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr, $URI_PARTS["scheme"] . "://" . $URI_PARTS["host"]); |
||
325 | } |
||
326 | |||
327 | // only follow redirect if it's on this site, or offsiteok is true |
||
328 | if (preg_match("|^http://" . preg_quote($this->host) . "|i", $this->_redirectaddr) || $this->offsiteok) { |
||
329 | /* follow the redirect */ |
||
330 | $this->_redirectdepth++; |
||
331 | $this->lastredirectaddr = $this->_redirectaddr; |
||
332 | if (strpos($this->_redirectaddr, "?") > 0) { |
||
333 | $this->fetch($this->_redirectaddr); |
||
334 | } // the redirect has changed the request method from post to get |
||
335 | else { |
||
336 | $this->submit($this->_redirectaddr, $formvars, $formfiles); |
||
337 | } |
||
338 | } |
||
339 | } |
||
340 | } |
||
341 | |||
342 | if ($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) { |
||
343 | $frameurls = $this->_frameurls; |
||
344 | $this->_frameurls = []; |
||
345 | |||
346 | while (list(, $frameurl) = each($frameurls)) { |
||
347 | if ($this->_framedepth < $this->maxframes) { |
||
348 | $this->fetch($frameurl); |
||
349 | $this->_framedepth++; |
||
350 | } else { |
||
351 | break; |
||
352 | } |
||
353 | } |
||
354 | } |
||
355 | |||
356 | } else { |
||
357 | return false; |
||
358 | } |
||
359 | return true; |
||
360 | break; |
||
361 | case "https": |
||
362 | if (!$this->curl_path) { |
||
363 | return false; |
||
364 | } |
||
365 | if (function_exists("is_executable")) { |
||
366 | if (!is_executable($this->curl_path)) { |
||
367 | return false; |
||
368 | } |
||
369 | } |
||
370 | $this->host = $URI_PARTS["host"]; |
||
371 | if (!empty($URI_PARTS["port"])) { |
||
372 | $this->port = $URI_PARTS["port"]; |
||
373 | } |
||
374 | if ($this->_isproxy) { |
||
375 | // using proxy, send entire URI |
||
376 | $this->_httpsrequest($URI, $URI, $this->_submit_method, $this->_submit_type, $postdata); |
||
377 | } else { |
||
378 | $path = $URI_PARTS["path"] . ($URI_PARTS["query"] ? "?" . $URI_PARTS["query"] : ""); |
||
379 | // no proxy, send only the path |
||
380 | $this->_httpsrequest($path, $URI, $this->_submit_method, $this->_submit_type, $postdata); |
||
381 | } |
||
382 | |||
383 | if ($this->_redirectaddr) { |
||
384 | /* url was redirected, check if we've hit the max depth */ |
||
385 | if ($this->maxredirs > $this->_redirectdepth) { |
||
386 | if (!preg_match("|^" . $URI_PARTS["scheme"] . "://|", $this->_redirectaddr)) { |
||
387 | $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr, $URI_PARTS["scheme"] . "://" . $URI_PARTS["host"]); |
||
388 | } |
||
389 | |||
390 | // only follow redirect if it's on this site, or offsiteok is true |
||
391 | if (preg_match("|^http://" . preg_quote($this->host) . "|i", $this->_redirectaddr) || $this->offsiteok) { |
||
392 | /* follow the redirect */ |
||
393 | $this->_redirectdepth++; |
||
394 | $this->lastredirectaddr = $this->_redirectaddr; |
||
395 | if (strpos($this->_redirectaddr, "?") > 0) { |
||
396 | $this->fetch($this->_redirectaddr); |
||
397 | } // the redirect has changed the request method from post to get |
||
398 | else { |
||
399 | $this->submit($this->_redirectaddr, $formvars, $formfiles); |
||
400 | } |
||
401 | } |
||
402 | } |
||
403 | } |
||
404 | |||
405 | if ($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) { |
||
406 | $frameurls = $this->_frameurls; |
||
407 | $this->_frameurls = []; |
||
408 | |||
409 | while (list(, $frameurl) = each($frameurls)) { |
||
410 | if ($this->_framedepth < $this->maxframes) { |
||
411 | $this->fetch($frameurl); |
||
412 | $this->_framedepth++; |
||
413 | } else { |
||
414 | break; |
||
415 | } |
||
416 | } |
||
417 | } |
||
418 | return true; |
||
419 | break; |
||
420 | |||
421 | default: |
||
422 | // not a valid protocol |
||
423 | $this->error = 'Invalid protocol "' . $URI_PARTS["scheme"] . '"\n'; |
||
424 | return false; |
||
425 | break; |
||
426 | } |
||
427 | return true; |
||
428 | } |
||
429 | |||
430 | /*======================================================================*\ |
||
431 | Function: fetchlinks |
||
432 | Purpose: fetch the links from a web page |
||
433 | Input: $URI where you are fetching from |
||
434 | Output: $this->results an array of the URLs |
||
435 | \*======================================================================*/ |
||
436 | |||
437 | public function fetchlinks($URI) |
||
438 | { |
||
439 | if ($this->fetch($URI)) { |
||
440 | if ($this->lastredirectaddr) { |
||
441 | $URI = $this->lastredirectaddr; |
||
442 | } |
||
443 | if (is_array($this->results)) { |
||
444 | for ($x = 0; $x < count($this->results); $x++) { |
||
445 | $this->results[$x] = $this->_striplinks($this->results[$x]); |
||
446 | } |
||
447 | } else { |
||
448 | $this->results = $this->_striplinks($this->results); |
||
449 | } |
||
450 | |||
451 | if ($this->expandlinks) { |
||
452 | $this->results = $this->_expandlinks($this->results, $URI); |
||
453 | } |
||
454 | return true; |
||
455 | } else { |
||
456 | return false; |
||
457 | } |
||
458 | } |
||
459 | |||
460 | /*======================================================================*\ |
||
461 | Function: fetchform |
||
462 | Purpose: fetch the form elements from a web page |
||
463 | Input: $URI where you are fetching from |
||
464 | Output: $this->results the resulting html form |
||
465 | \*======================================================================*/ |
||
466 | |||
467 | public function fetchform($URI) |
||
483 | } |
||
484 | } |
||
485 | |||
486 | |||
487 | /*======================================================================*\ |
||
488 | Function: fetchtext |
||
489 | Purpose: fetch the text from a web page, stripping the links |
||
490 | Input: $URI where you are fetching from |
||
491 | Output: $this->results the text from the web page |
||
492 | \*======================================================================*/ |
||
493 | |||
494 | public function fetchtext($URI) |
||
495 | { |
||
496 | if ($this->fetch($URI)) { |
||
497 | if (is_array($this->results)) { |
||
498 | for ($x = 0; $x < count($this->results); $x++) { |
||
499 | $this->results[$x] = $this->_striptext($this->results[$x]); |
||
500 | } |
||
501 | } else { |
||
502 | $this->results = $this->_striptext($this->results); |
||
503 | } |
||
504 | return true; |
||
505 | } else { |
||
506 | return false; |
||
507 | } |
||
508 | } |
||
509 | |||
510 | /*======================================================================*\ |
||
511 | Function: submitlinks |
||
512 | Purpose: grab links from a form submission |
||
513 | Input: $URI where you are submitting from |
||
514 | Output: $this->results an array of the links from the post |
||
515 | \*======================================================================*/ |
||
516 | |||
517 | public function submitlinks($URI, $formvars = "", $formfiles = "") |
||
518 | { |
||
519 | if ($this->submit($URI, $formvars, $formfiles)) { |
||
520 | if ($this->lastredirectaddr) { |
||
521 | $URI = $this->lastredirectaddr; |
||
522 | } |
||
523 | if (is_array($this->results)) { |
||
524 | for ($x = 0; $x < count($this->results); $x++) { |
||
525 | $this->results[$x] = $this->_striplinks($this->results[$x]); |
||
526 | if ($this->expandlinks) { |
||
527 | $this->results[$x] = $this->_expandlinks($this->results[$x], $URI); |
||
528 | } |
||
529 | } |
||
530 | } else { |
||
531 | $this->results = $this->_striplinks($this->results); |
||
532 | if ($this->expandlinks) { |
||
533 | $this->results = $this->_expandlinks($this->results, $URI); |
||
534 | } |
||
535 | } |
||
536 | return true; |
||
537 | } else { |
||
538 | return false; |
||
539 | } |
||
540 | } |
||
541 | |||
542 | /*======================================================================*\ |
||
543 | Function: submittext |
||
544 | Purpose: grab text from a form submission |
||
545 | Input: $URI where you are submitting from |
||
546 | Output: $this->results the text from the web page |
||
547 | \*======================================================================*/ |
||
548 | |||
549 | public function submittext($URI, $formvars = "", $formfiles = "") |
||
550 | { |
||
551 | if ($this->submit($URI, $formvars, $formfiles)) { |
||
552 | if ($this->lastredirectaddr) { |
||
553 | $URI = $this->lastredirectaddr; |
||
554 | } |
||
555 | if (is_array($this->results)) { |
||
556 | for ($x = 0; $x < count($this->results); $x++) { |
||
557 | $this->results[$x] = $this->_striptext($this->results[$x]); |
||
558 | if ($this->expandlinks) { |
||
559 | $this->results[$x] = $this->_expandlinks($this->results[$x], $URI); |
||
560 | } |
||
561 | } |
||
562 | } else { |
||
563 | $this->results = $this->_striptext($this->results); |
||
564 | if ($this->expandlinks) { |
||
565 | $this->results = $this->_expandlinks($this->results, $URI); |
||
566 | } |
||
567 | } |
||
568 | return true; |
||
569 | } else { |
||
570 | return false; |
||
571 | } |
||
572 | } |
||
573 | |||
574 | |||
575 | /*======================================================================*\ |
||
576 | Function: set_submit_multipart |
||
577 | Purpose: Set the form submission content type to |
||
578 | multipart/form-data |
||
579 | \*======================================================================*/ |
||
580 | public function set_submit_multipart() |
||
581 | { |
||
582 | $this->_submit_type = "multipart/form-data"; |
||
583 | } |
||
584 | |||
585 | |||
586 | /*======================================================================*\ |
||
587 | Function: set_submit_normal |
||
588 | Purpose: Set the form submission content type to |
||
589 | application/x-www-form-urlencoded |
||
590 | \*======================================================================*/ |
||
591 | public function set_submit_normal() |
||
592 | { |
||
593 | $this->_submit_type = "application/x-www-form-urlencoded"; |
||
594 | } |
||
595 | |||
596 | |||
597 | |||
598 | |||
599 | /*======================================================================*\ |
||
600 | Private functions |
||
601 | \*======================================================================*/ |
||
602 | |||
603 | |||
604 | /*======================================================================*\ |
||
605 | Function: _striplinks |
||
606 | Purpose: strip the hyperlinks from an HTML document |
||
607 | Input: $document document to strip. |
||
608 | Output: $match an array of the links |
||
609 | \*======================================================================*/ |
||
610 | |||
611 | public function _striplinks($document) |
||
636 | } |
||
637 | |||
638 | /*======================================================================*\ |
||
639 | Function: _stripform |
||
640 | Purpose: strip the form elements from an HTML document |
||
641 | Input: $document document to strip. |
||
642 | Output: $match an array of the links |
||
643 | \*======================================================================*/ |
||
644 | |||
645 | public function _stripform($document) |
||
646 | { |
||
647 | preg_match_all("'<\/?(FORM|INPUT|SELECT|TEXTAREA|(OPTION))[^<>]*>(?(2)(.*(?=<\/?(option|select)[^<>]*>[\r\n]*)|(?=[\r\n]*))|(?=[\r\n]*))'Usi", $document, $elements); |
||
648 | |||
649 | // catenate the matches |
||
650 | $match = implode("\r\n", $elements[0]); |
||
651 | |||
652 | // return the links |
||
653 | return $match; |
||
654 | } |
||
655 | |||
656 | |||
657 | /*======================================================================*\ |
||
658 | Function: _striptext |
||
659 | Purpose: strip the text from an HTML document |
||
660 | Input: $document document to strip. |
||
661 | Output: $text the resulting text |
||
662 | \*======================================================================*/ |
||
663 | |||
664 | public function _striptext($document) |
||
723 | } |
||
724 | |||
725 | /*======================================================================*\ |
||
726 | Function: _expandlinks |
||
727 | Purpose: expand each link into a fully qualified URL |
||
728 | Input: $links the links to qualify |
||
729 | $URI the full URI to get the base from |
||
730 | Output: $expandedLinks the expanded links |
||
731 | \*======================================================================*/ |
||
732 | |||
733 | public function _expandlinks($links, $URI) |
||
734 | { |
||
735 | |||
736 | preg_match("/^[^\?]+/", $URI, $match); |
||
737 | |||
738 | $match = preg_replace("|/[^\/\.]+\.[^\/\.]+$|", "", $match[0]); |
||
739 | $match = preg_replace("|/$|", "", $match); |
||
740 | $match_part = parse_url($match); |
||
741 | $match_root = |
||
742 | $match_part["scheme"] . "://" . $match_part["host"]; |
||
743 | |||
744 | $search = ["|^http://" . preg_quote($this->host) . "|i", "|^(\/)|i", "|^(?!http://)(?!mailto:)|i", "|/\./|", "|/[^\/]+/\.\./|"]; |
||
745 | |||
746 | $replace = ["", $match_root . "/", $match . "/", "/", "/"]; |
||
747 | |||
748 | $expandedLinks = preg_replace($search, $replace, $links); |
||
749 | |||
750 | return $expandedLinks; |
||
751 | } |
||
752 | |||
753 | /*======================================================================*\ |
||
754 | Function: _httprequest |
||
755 | Purpose: go get the http data from the server |
||
756 | Input: $url the url to fetch |
||
757 | $fp the current open file pointer |
||
758 | $URI the full URI |
||
759 | $body body contents to send if any (POST) |
||
760 | Output: |
||
761 | \*======================================================================*/ |
||
762 | |||
763 | public function _httprequest($url, $fp, $URI, $http_method, $content_type = "", $body = "") |
||
764 | { |
||
765 | $cookie_headers = ''; |
||
766 | if ($this->passcookies && $this->_redirectaddr) { |
||
767 | $this->setcookies(); |
||
768 | } |
||
769 | |||
770 | $URI_PARTS = parse_url($URI); |
||
771 | if (empty($url)) { |
||
772 | $url = "/"; |
||
773 | } |
||
774 | $headers = $http_method . " " . $url . " " . $this->_httpversion . "\r\n"; |
||
775 | if (!empty($this->agent)) { |
||
776 | $headers .= "User-Agent: " . $this->agent . "\r\n"; |
||
777 | } |
||
778 | if (!empty($this->host) && !isset($this->rawheaders['Host'])) { |
||
779 | $headers .= "Host: " . $this->host; |
||
780 | if (!empty($this->port) && $this->port != '80') { |
||
781 | $headers .= ":" . $this->port; |
||
782 | } |
||
783 | $headers .= "\r\n"; |
||
784 | } |
||
785 | if (!empty($this->accept)) { |
||
786 | $headers .= "Accept: " . $this->accept . "\r\n"; |
||
787 | } |
||
788 | if ($this->use_gzip) { |
||
789 | // make sure PHP was built with --with-zlib |
||
790 | // and we can handle gzipp'ed data |
||
791 | if (function_exists('gzinflate')) { |
||
792 | $headers .= "Accept-encoding: gzip\r\n"; |
||
793 | } else { |
||
794 | trigger_error( |
||
795 | "use_gzip is on, but PHP was built without zlib support." . |
||
796 | " Requesting file(s) without gzip encoding.", |
||
797 | E_USER_NOTICE, |
||
798 | ); |
||
799 | } |
||
800 | } |
||
801 | if (!empty($this->referer)) { |
||
802 | $headers .= "Referer: " . $this->referer . "\r\n"; |
||
803 | } |
||
804 | if (!empty($this->cookies)) { |
||
805 | if (!is_array($this->cookies)) { |
||
806 | $this->cookies = (array) $this->cookies; |
||
807 | } |
||
808 | |||
809 | reset($this->cookies); |
||
810 | if (count($this->cookies) > 0) { |
||
811 | $cookie_headers .= 'Cookie: '; |
||
812 | foreach ($this->cookies as $cookieKey => $cookieVal) { |
||
813 | $cookie_headers .= $cookieKey . "=" . urlencode($cookieVal) . "; "; |
||
814 | } |
||
815 | $headers .= substr($cookie_headers, 0, -2) . "\r\n"; |
||
816 | } |
||
817 | } |
||
818 | if (!empty($this->rawheaders)) { |
||
819 | if (!is_array($this->rawheaders)) { |
||
820 | $this->rawheaders = (array) $this->rawheaders; |
||
821 | } |
||
822 | while (list($headerKey, $headerVal) = each($this->rawheaders)) { |
||
823 | $headers .= $headerKey . ": " . $headerVal . "\r\n"; |
||
824 | } |
||
825 | } |
||
826 | if (!empty($content_type)) { |
||
827 | $headers .= "Content-type: $content_type"; |
||
828 | if ($content_type == "multipart/form-data") { |
||
829 | $headers .= "; boundary=" . $this->_mime_boundary; |
||
830 | } |
||
831 | $headers .= "\r\n"; |
||
832 | } |
||
833 | if (!empty($body)) { |
||
834 | $headers .= "Content-length: " . strlen($body) . "\r\n"; |
||
835 | } |
||
836 | if (!empty($this->user) || !empty($this->pass)) { |
||
837 | $headers .= "Authorization: Basic " . base64_encode($this->user . ":" . $this->pass) . "\r\n"; |
||
838 | } |
||
839 | |||
840 | //add proxy auth headers |
||
841 | if (!empty($this->proxy_user)) { |
||
842 | $headers .= 'Proxy-Authorization: ' . 'Basic ' . base64_encode($this->proxy_user . ':' . $this->proxy_pass) . "\r\n"; |
||
843 | } |
||
844 | |||
845 | |||
846 | $headers .= "\r\n"; |
||
847 | |||
848 | // set the read timeout if needed |
||
849 | if ($this->read_timeout > 0) { |
||
850 | socket_set_timeout($fp, $this->read_timeout); |
||
851 | } |
||
852 | $this->timed_out = false; |
||
853 | |||
854 | fwrite($fp, $headers . $body, strlen($headers . $body)); |
||
855 | |||
856 | $this->_redirectaddr = false; |
||
857 | unset($this->headers); |
||
858 | |||
859 | // content was returned gzip encoded? |
||
860 | $is_gzipped = false; |
||
861 | |||
862 | while ($currentHeader = fgets($fp, $this->_maxlinelen)) { |
||
863 | if ($this->read_timeout > 0 && $this->_check_timeout($fp)) { |
||
864 | $this->status = -100; |
||
865 | return false; |
||
866 | } |
||
867 | |||
868 | if ($currentHeader == "\r\n") { |
||
869 | break; |
||
870 | } |
||
871 | |||
872 | // if a header begins with Location: or URI:, set the redirect |
||
873 | if (preg_match("/^(Location:|URI:)/i", $currentHeader)) { |
||
874 | // get URL portion of the redirect |
||
875 | preg_match("/^(Location:|URI:)[ ]+(.*)/i", chop($currentHeader), $matches); |
||
876 | // look for :// in the Location header to see if hostname is included |
||
877 | if (!preg_match("|\:\/\/|", $matches[2])) { |
||
878 | // no host in the path, so prepend |
||
879 | $this->_redirectaddr = $URI_PARTS["scheme"] . "://" . $this->host . ":" . $this->port; |
||
880 | // eliminate double slash |
||
881 | if (!preg_match("|^/|", $matches[2])) { |
||
882 | $this->_redirectaddr .= "/" . $matches[2]; |
||
883 | } else { |
||
884 | $this->_redirectaddr .= $matches[2]; |
||
885 | } |
||
886 | } else { |
||
887 | $this->_redirectaddr = $matches[2]; |
||
888 | } |
||
889 | } |
||
890 | |||
891 | if (preg_match("|^HTTP/|", $currentHeader)) { |
||
892 | if (preg_match("|^HTTP/[^\s]*\s(.*?)\s|", $currentHeader, $status)) { |
||
893 | $this->status = $status[1]; |
||
894 | } |
||
895 | $this->response_code = $currentHeader; |
||
896 | } |
||
897 | |||
898 | if (preg_match("/Content-Encoding: gzip/", $currentHeader)) { |
||
899 | $is_gzipped = true; |
||
900 | } |
||
901 | |||
902 | $this->headers[] = $currentHeader; |
||
903 | } |
||
904 | |||
905 | $results = ''; |
||
906 | do { |
||
907 | $_data = fread($fp, $this->maxlength); |
||
908 | if (strlen($_data) == 0) { |
||
909 | break; |
||
910 | } |
||
911 | $results .= $_data; |
||
912 | } while (true); |
||
913 | |||
914 | // gunzip |
||
915 | if ($is_gzipped) { |
||
916 | // per https://www.php.net/manual/en/function.gzencode.php |
||
917 | $results = substr($results, 10); |
||
918 | $results = gzinflate($results); |
||
919 | } |
||
920 | |||
921 | if ($this->read_timeout > 0 && $this->_check_timeout($fp)) { |
||
922 | $this->status = -100; |
||
923 | return false; |
||
924 | } |
||
925 | |||
926 | // check if there is a a redirect meta tag |
||
927 | |||
928 | if (preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i", $results, $match)) { |
||
929 | $this->_redirectaddr = $this->_expandlinks($match[1], $URI); |
||
930 | } |
||
931 | |||
932 | // have we hit our frame depth and is there frame src to fetch? |
||
933 | if (($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i", $results, $match)) { |
||
934 | $this->results[] = $results; |
||
935 | for ($x = 0; $x < count($match[1]); $x++) { |
||
936 | $this->_frameurls[] = $this->_expandlinks($match[1][$x], $URI_PARTS["scheme"] . "://" . $this->host); |
||
937 | } |
||
938 | } // have we already fetched framed content? |
||
939 | elseif (is_array($this->results)) { |
||
940 | $this->results[] = $results; |
||
941 | } |
||
942 | // no framed content |
||
943 | else { |
||
944 | $this->results = $results; |
||
945 | } |
||
946 | |||
947 | return true; |
||
948 | } |
||
949 | |||
950 | /*======================================================================*\ |
||
951 | Function: _httpsrequest |
||
952 | Purpose: go get the https data from the server using curl |
||
953 | Input: $url the url to fetch |
||
954 | $URI the full URI |
||
955 | $body body contents to send if any (POST) |
||
956 | Output: |
||
957 | \*======================================================================*/ |
||
958 | |||
959 | public function _httpsrequest($url, $URI, $http_method, $content_type = "", $body = "") |
||
960 | { |
||
961 | if ($this->passcookies && $this->_redirectaddr) { |
||
962 | $this->setcookies(); |
||
963 | } |
||
964 | |||
965 | $headers = []; |
||
966 | |||
967 | $URI_PARTS = parse_url($URI); |
||
968 | if (empty($url)) { |
||
969 | $url = "/"; |
||
970 | } |
||
971 | // GET ... header not needed for curl |
||
972 | //$headers[] = $http_method." ".$url." ".$this->_httpversion; |
||
973 | if (!empty($this->agent)) { |
||
974 | $headers[] = "User-Agent: " . $this->agent; |
||
975 | } |
||
976 | if (!empty($this->host)) { |
||
977 | if (!empty($this->port)) { |
||
978 | $headers[] = "Host: " . $this->host . ":" . $this->port; |
||
979 | } else { |
||
980 | $headers[] = "Host: " . $this->host; |
||
981 | } |
||
982 | } |
||
983 | if (!empty($this->accept)) { |
||
984 | $headers[] = "Accept: " . $this->accept; |
||
985 | } |
||
986 | if (!empty($this->referer)) { |
||
987 | $headers[] = "Referer: " . $this->referer; |
||
988 | } |
||
989 | if (!empty($this->cookies)) { |
||
990 | if (!is_array($this->cookies)) { |
||
991 | $this->cookies = (array) $this->cookies; |
||
992 | } |
||
993 | |||
994 | reset($this->cookies); |
||
995 | if (count($this->cookies) > 0) { |
||
996 | $cookie_str = 'Cookie: '; |
||
997 | foreach ($this->cookies as $cookieKey => $cookieVal) { |
||
998 | $cookie_str .= $cookieKey . "=" . urlencode($cookieVal) . "; "; |
||
999 | } |
||
1000 | $headers[] = substr($cookie_str, 0, -2); |
||
1001 | } |
||
1002 | } |
||
1003 | if (!empty($this->rawheaders)) { |
||
1004 | if (!is_array($this->rawheaders)) { |
||
1005 | $this->rawheaders = (array) $this->rawheaders; |
||
1006 | } |
||
1007 | while (list($headerKey, $headerVal) = each($this->rawheaders)) { |
||
1008 | $headers[] = $headerKey . ": " . $headerVal; |
||
1009 | } |
||
1010 | } |
||
1011 | if (!empty($content_type)) { |
||
1012 | if ($content_type == "multipart/form-data") { |
||
1013 | $headers[] = "Content-type: $content_type; boundary=" . $this->_mime_boundary; |
||
1014 | } else { |
||
1015 | $headers[] = "Content-type: $content_type"; |
||
1016 | } |
||
1017 | } |
||
1018 | if (!empty($body)) { |
||
1019 | $headers[] = "Content-length: " . strlen($body); |
||
1020 | } |
||
1021 | if (!empty($this->user) || !empty($this->pass)) { |
||
1022 | $headers[] = "Authorization: BASIC " . base64_encode($this->user . ":" . $this->pass); |
||
1023 | } |
||
1024 | |||
1025 | for ($curr_header = 0; $curr_header < count($headers); $curr_header++) { |
||
1026 | $safer_header = strtr($headers[$curr_header], "\"", " "); |
||
1027 | $cmdline_params .= " -H \"" . $safer_header . "\""; |
||
1028 | } |
||
1029 | |||
1030 | if (!empty($body)) { |
||
1031 | $cmdline_params .= " -d \"$body\""; |
||
1032 | } |
||
1033 | |||
1034 | if ($this->read_timeout > 0) { |
||
1035 | $cmdline_params .= " -m " . $this->read_timeout; |
||
1036 | } |
||
1037 | |||
1038 | $headerfile = tempnam($temp_dir, "sno"); |
||
1039 | |||
1040 | exec($this->curl_path . " -k -D \"$headerfile\"" . $cmdline_params . " " . escapeshellarg($URI), $results, $return); |
||
1041 | |||
1042 | if ($return) { |
||
1043 | $this->error = "Error: cURL could not retrieve the document, error $return."; |
||
1044 | return false; |
||
1045 | } |
||
1046 | |||
1047 | |||
1048 | $results = implode("\r\n", $results); |
||
1049 | |||
1050 | $result_headers = file((string)$headerfile); |
||
1051 | |||
1052 | $this->_redirectaddr = false; |
||
1053 | unset($this->headers); |
||
1054 | |||
1055 | for ($currentHeader = 0; $currentHeader < count($result_headers); $currentHeader++) { |
||
1056 | |||
1057 | // if a header begins with Location: or URI:, set the redirect |
||
1058 | if (preg_match("/^(Location: |URI: )/i", $result_headers[$currentHeader])) { |
||
1059 | // get URL portion of the redirect |
||
1060 | preg_match("/^(Location: |URI:)\s+(.*)/", chop($result_headers[$currentHeader]), $matches); |
||
1061 | // look for :// in the Location header to see if hostname is included |
||
1062 | if (!preg_match("|\:\/\/|", $matches[2])) { |
||
1063 | // no host in the path, so prepend |
||
1064 | $this->_redirectaddr = $URI_PARTS["scheme"] . "://" . $this->host . ":" . $this->port; |
||
1065 | // eliminate double slash |
||
1066 | if (!preg_match("|^/|", $matches[2])) { |
||
1067 | $this->_redirectaddr .= "/" . $matches[2]; |
||
1068 | } else { |
||
1069 | $this->_redirectaddr .= $matches[2]; |
||
1070 | } |
||
1071 | } else { |
||
1072 | $this->_redirectaddr = $matches[2]; |
||
1073 | } |
||
1074 | } |
||
1075 | |||
1076 | if (preg_match("|^HTTP/|", $result_headers[$currentHeader])) { |
||
1077 | $this->response_code = $result_headers[$currentHeader]; |
||
1078 | if (preg_match("|^HTTP/[^\s]*\s(.*?)\s|", $this->response_code, $match)) { |
||
1079 | $this->status = $match[1]; |
||
1080 | } |
||
1081 | } |
||
1082 | |||
1083 | $this->headers[] = $result_headers[$currentHeader]; |
||
1084 | } |
||
1085 | |||
1086 | // check if there is a a redirect meta tag |
||
1087 | |||
1088 | if (preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i", $results, $match)) { |
||
1089 | $this->_redirectaddr = $this->_expandlinks($match[1], $URI); |
||
1090 | } |
||
1091 | |||
1092 | // have we hit our frame depth and is there frame src to fetch? |
||
1093 | if (($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i", $results, $match)) { |
||
1094 | $this->results[] = $results; |
||
1095 | for ($x = 0; $x < count($match[1]); $x++) { |
||
1096 | $this->_frameurls[] = $this->_expandlinks($match[1][$x], $URI_PARTS["scheme"] . "://" . $this->host); |
||
1097 | } |
||
1098 | } // have we already fetched framed content? |
||
1099 | elseif (is_array($this->results)) { |
||
1100 | $this->results[] = $results; |
||
1101 | } |
||
1102 | // no framed content |
||
1103 | else { |
||
1104 | $this->results = $results; |
||
1105 | } |
||
1106 | |||
1107 | unlink((string)$headerfile); |
||
1108 | |||
1109 | return true; |
||
1110 | } |
||
1111 | |||
1112 | /*======================================================================*\ |
||
1113 | Function: setcookies() |
||
1114 | Purpose: set cookies for a redirection |
||
1115 | \*======================================================================*/ |
||
1116 | |||
1117 | public function setcookies() |
||
1118 | { |
||
1119 | for ($x = 0; $x < count($this->headers); $x++) { |
||
1120 | if (preg_match('/^set-cookie:[\s]+([^=]+)=([^;]+)/i', $this->headers[$x], $match)) { |
||
1121 | $this->cookies[$match[1]] = urldecode($match[2]); |
||
1122 | } |
||
1123 | } |
||
1124 | } |
||
1125 | |||
1126 | |||
1127 | /*======================================================================*\ |
||
1128 | Function: _check_timeout |
||
1129 | Purpose: checks whether timeout has occurred |
||
1130 | Input: $fp file pointer |
||
1131 | \*======================================================================*/ |
||
1132 | |||
1133 | public function _check_timeout($fp) |
||
1143 | } |
||
1144 | |||
1145 | /*======================================================================*\ |
||
1146 | Function: _connect |
||
1147 | Purpose: make a socket connection |
||
1148 | Input: $fp file pointer |
||
1149 | \*======================================================================*/ |
||
1150 | |||
1151 | public function _connect(&$fp) |
||
1193 | } |
||
1194 | } |
||
1195 | |||
1196 | /*======================================================================*\ |
||
1197 | Function: _disconnect |
||
1198 | Purpose: disconnect a socket connection |
||
1199 | Input: $fp file pointer |
||
1200 | \*======================================================================*/ |
||
1201 | |||
1202 | public function _disconnect($fp) |
||
1205 | } |
||
1206 | |||
1207 | |||
1208 | /*======================================================================*\ |
||
1209 | Function: _prepare_post_body |
||
1210 | Purpose: Prepare post body according to encoding type |
||
1211 | Input: $formvars - form variables |
||
1212 | $formfiles - form upload files |
||
1213 | Output: post body |
||
1214 | \*======================================================================*/ |
||
1215 | |||
1216 | public function _prepare_post_body($formvars, $formfiles) |
||
1283 |
The
break
statement is not necessary if it is preceded for example by areturn
statement:If you would like to keep this construct to be consistent with other
case
statements, you can safely mark this issue as a false-positive.