|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace Openbuildings\Spiderling; |
|
4
|
|
|
|
|
5
|
|
|
use Openbuildings\EnvironmentBackup\Environment; |
|
6
|
|
|
use Openbuildings\EnvironmentBackup\Environment_Group_Globals; |
|
7
|
|
|
use Openbuildings\EnvironmentBackup\Environment_Group_Server; |
|
8
|
|
|
use Openbuildings\EnvironmentBackup\Environment_Group_Static; |
|
9
|
|
|
|
|
10
|
|
|
/** |
|
11
|
|
|
* Use Curl to load urls. |
|
12
|
|
|
* In memory. |
|
13
|
|
|
* No Javascript |
|
14
|
|
|
* |
|
15
|
|
|
* @package Openbuildings\Spiderling |
|
16
|
|
|
* @author Ivan Kerin |
|
17
|
|
|
* @copyright (c) 2013 OpenBuildings Ltd. |
|
18
|
|
|
* @license http://spdx.org/licenses/BSD-3-Clause |
|
19
|
|
|
*/ |
|
20
|
|
|
class Driver_Simple extends Driver { |
|
21
|
|
|
|
|
22
|
|
|
/** |
|
23
|
|
|
* The name of the driver |
|
24
|
|
|
* @var string |
|
25
|
|
|
*/ |
|
26
|
|
|
public $name = 'simple'; |
|
27
|
|
|
|
|
28
|
|
|
/** |
|
29
|
|
|
* Wait time is meaningless in simple driver as it does not support javascript |
|
30
|
|
|
* @var integer |
|
31
|
|
|
*/ |
|
32
|
|
|
public $default_wait_time = 10; |
|
33
|
|
|
|
|
34
|
|
|
/** |
|
35
|
|
|
* The raw html content of the page |
|
36
|
|
|
* @var string |
|
37
|
|
|
*/ |
|
38
|
|
|
protected $_content; |
|
39
|
|
|
|
|
40
|
|
|
/** |
|
41
|
|
|
* The DOMDocument of the current page |
|
42
|
|
|
* @var DOMDocument |
|
43
|
|
|
*/ |
|
44
|
|
|
protected $_dom; |
|
45
|
|
|
|
|
46
|
|
|
/** |
|
47
|
|
|
* The DOMXpath object for finding elements on the page |
|
48
|
|
|
* @var DOMXpath |
|
49
|
|
|
*/ |
|
50
|
|
|
protected $_xpath; |
|
51
|
|
|
|
|
52
|
|
|
/** |
|
53
|
|
|
* Object for handling forms on the page |
|
54
|
|
|
* @var Driver_Simple_Forms |
|
55
|
|
|
*/ |
|
56
|
|
|
protected $_forms; |
|
57
|
|
|
|
|
58
|
|
|
/** |
|
59
|
|
|
* Environment object for handling backups of environment state |
|
60
|
|
|
* @var Environment |
|
61
|
|
|
*/ |
|
62
|
|
|
protected $_environment; |
|
63
|
|
|
|
|
64
|
|
|
/** |
|
65
|
|
|
* Driver_Simple_RequestFactory object for opening new pages |
|
66
|
|
|
* @var Driver_Simple_RequestFactory |
|
67
|
|
|
*/ |
|
68
|
|
|
protected $_request_factory; |
|
69
|
|
|
|
|
70
|
57 |
|
function __construct() |
|
|
|
|
|
|
71
|
|
|
{ |
|
72
|
57 |
|
$this->_dom = new \DOMDocument('1.0', 'utf-8'); |
|
|
|
|
|
|
73
|
57 |
|
$this->_environment = new Environment(array( |
|
74
|
57 |
|
'globals' => new Environment_Group_Globals(), |
|
75
|
57 |
|
'server' => new Environment_Group_Server(), |
|
76
|
57 |
|
'static' => new Environment_Group_Static(), |
|
77
|
|
|
)); |
|
78
|
|
|
|
|
79
|
57 |
|
$this->_request_factory = new Driver_Simple_RequestFactory_HTTP(); |
|
80
|
57 |
|
} |
|
81
|
|
|
|
|
82
|
|
|
/** |
|
83
|
|
|
* Getter / Setter for the request factory object for the driver |
|
84
|
|
|
* @param Driver_Simple_RequestFactory $request_factory |
|
85
|
|
|
* @return Driver_Simple_RequestFactory|Driver_Simple |
|
86
|
|
|
*/ |
|
87
|
18 |
|
public function request_factory(Driver_Simple_RequestFactory $request_factory = NULL) |
|
88
|
|
|
{ |
|
89
|
18 |
|
if ($request_factory !== NULL) |
|
90
|
|
|
{ |
|
91
|
14 |
|
$this->_request_factory = $request_factory; |
|
92
|
14 |
|
return $this; |
|
93
|
|
|
} |
|
94
|
|
|
|
|
95
|
9 |
|
return $this->_request_factory; |
|
96
|
|
|
} |
|
97
|
|
|
|
|
98
|
|
|
/** |
|
99
|
|
|
* Getter for the current environment |
|
100
|
|
|
* @return Environment |
|
101
|
|
|
*/ |
|
102
|
7 |
|
public function environment() |
|
103
|
|
|
{ |
|
104
|
7 |
|
return $this->_environment; |
|
105
|
|
|
} |
|
106
|
|
|
|
|
107
|
|
|
/** |
|
108
|
|
|
* Restore the environment |
|
109
|
|
|
* @return Driver_Simple $this |
|
110
|
|
|
*/ |
|
111
|
1 |
|
public function clear() |
|
112
|
|
|
{ |
|
113
|
1 |
|
$this->environment()->restore(); |
|
114
|
|
|
|
|
115
|
1 |
|
return $this; |
|
116
|
|
|
} |
|
117
|
|
|
|
|
118
|
|
|
/** |
|
119
|
|
|
* Getter / Setter of the raw content html |
|
120
|
|
|
* @param string $content |
|
121
|
|
|
* @return string|Driver_Simple |
|
122
|
|
|
*/ |
|
123
|
48 |
|
public function content($content = NULL) |
|
124
|
|
|
{ |
|
125
|
48 |
|
if ($content !== NULL) |
|
126
|
|
|
{ |
|
127
|
48 |
|
$this->_content = (string) $content; |
|
128
|
48 |
|
$this->initialize(); |
|
129
|
|
|
|
|
130
|
48 |
|
return $this; |
|
131
|
|
|
} |
|
132
|
48 |
|
return $this->_content; |
|
133
|
|
|
} |
|
134
|
|
|
|
|
135
|
|
|
/** |
|
136
|
|
|
* Initialze the dom, xpath and forms objects, based on the content string |
|
137
|
|
|
*/ |
|
138
|
48 |
|
public function initialize() |
|
139
|
|
|
{ |
|
140
|
48 |
|
@ $this->_dom->loadHTML($this->content()); |
|
|
|
|
|
|
141
|
48 |
|
$this->_dom->encoding = 'utf-8'; |
|
142
|
48 |
|
$this->_xpath = new Driver_Simple_Xpath($this->_dom); |
|
|
|
|
|
|
143
|
48 |
|
$this->_forms = new Driver_Simple_Forms($this->_xpath); |
|
144
|
48 |
|
} |
|
145
|
|
|
|
|
146
|
|
|
/** |
|
147
|
|
|
* Getter the current forms object |
|
148
|
|
|
* @return Driver_Simple_Forms |
|
149
|
|
|
*/ |
|
150
|
7 |
|
public function forms() |
|
151
|
|
|
{ |
|
152
|
7 |
|
return $this->_forms; |
|
153
|
|
|
} |
|
154
|
|
|
|
|
155
|
|
|
/** |
|
156
|
|
|
* Getter for the current xpath object for the page |
|
157
|
|
|
* @return DOMXpath |
|
158
|
|
|
*/ |
|
159
|
20 |
|
public function xpath() |
|
160
|
|
|
{ |
|
161
|
20 |
|
return $this->_xpath; |
|
162
|
|
|
} |
|
163
|
|
|
|
|
164
|
|
|
/** |
|
165
|
|
|
* Get the DOMElement for the current id, or root if no id is given |
|
166
|
|
|
* @param string $id |
|
167
|
|
|
* @return DOMElement |
|
168
|
|
|
*/ |
|
169
|
15 |
|
public function dom($id = NULL) |
|
170
|
|
|
{ |
|
171
|
15 |
|
return $id ? $this->xpath()->find($id) : $this->_dom; |
|
172
|
|
|
} |
|
173
|
|
|
|
|
174
|
|
|
/** |
|
175
|
|
|
* Initiate a get request to a given uri |
|
176
|
|
|
* @param string $uri |
|
177
|
|
|
* @param array $query an array for the http query |
|
178
|
|
|
* @return Driver_Simple $this |
|
179
|
|
|
*/ |
|
180
|
5 |
|
public function get($uri, array $query = array()) |
|
181
|
|
|
{ |
|
182
|
5 |
|
return $this->request('GET', $uri, $query); |
|
183
|
|
|
} |
|
184
|
|
|
|
|
185
|
|
|
/** |
|
186
|
|
|
* Initiate a post request to a given uri |
|
187
|
|
|
* @param string $uri |
|
188
|
|
|
* @param array $query |
|
189
|
|
|
* @param array $post |
|
190
|
|
|
* @param array $files set the $_FILES array appropriately |
|
191
|
|
|
* @return Driver_Simple $this |
|
192
|
|
|
*/ |
|
193
|
1 |
|
public function post($uri, array $query = array(), array $post = array(), array $files = array()) |
|
194
|
|
|
{ |
|
195
|
1 |
|
return $this->request('POST', $uri, $query, $post, $files); |
|
196
|
|
|
} |
|
197
|
|
|
|
|
198
|
|
|
/** |
|
199
|
|
|
* Initiate a request with a custom method |
|
200
|
|
|
* @param string $method |
|
201
|
|
|
* @param string $uri |
|
202
|
|
|
* @param array $query |
|
203
|
|
|
* @param array $post |
|
204
|
|
|
* @param array $files set the $_FILES array |
|
205
|
|
|
* @return Driver_Simple $this |
|
206
|
|
|
*/ |
|
207
|
5 |
|
public function request($method, $uri, array $query = array(), array $post = array(), array $files = array()) |
|
208
|
|
|
{ |
|
209
|
5 |
|
$uri_params = parse_url($uri, PHP_URL_QUERY); |
|
210
|
|
|
|
|
211
|
5 |
|
if ($uri_params) |
|
|
|
|
|
|
212
|
|
|
{ |
|
213
|
1 |
|
parse_str($uri_params, $params); |
|
214
|
1 |
|
$query = array_merge($params, $query); |
|
215
|
1 |
|
$uri = str_replace('?'.$uri_params, '', $uri); |
|
216
|
|
|
} |
|
217
|
|
|
|
|
218
|
5 |
|
$url = $uri.($query ? '?'.http_build_query($query) : ''); |
|
219
|
|
|
|
|
220
|
5 |
|
$this->environment()->backup_and_set(array( |
|
221
|
5 |
|
'_GET' => $query, |
|
222
|
5 |
|
'_POST' => $post, |
|
223
|
5 |
|
'_FILES' => $files, |
|
224
|
4 |
|
'_SESSION' => isset($_SESSION) ? $_SESSION : array(), |
|
225
|
|
|
)); |
|
226
|
|
|
|
|
227
|
5 |
|
$response = $this->request_factory()->execute($method, $url, $post); |
|
|
|
|
|
|
228
|
|
|
|
|
229
|
4 |
|
$this->content($response); |
|
230
|
|
|
|
|
231
|
4 |
|
return $this; |
|
232
|
|
|
} |
|
233
|
|
|
|
|
234
|
|
|
/** |
|
235
|
|
|
* NODE GETTERS |
|
236
|
|
|
* ===================================== |
|
237
|
|
|
*/ |
|
238
|
|
|
|
|
239
|
|
|
/** |
|
240
|
|
|
* Get the tag name of a Node with id. e.g. DIV, SPAN ... |
|
241
|
|
|
* @param string $id |
|
242
|
|
|
* @return string |
|
243
|
|
|
*/ |
|
244
|
3 |
|
public function tag_name($id) |
|
245
|
|
|
{ |
|
246
|
3 |
|
return $this->dom($id)->tagName; |
|
247
|
|
|
} |
|
248
|
|
|
|
|
249
|
|
|
/** |
|
250
|
|
|
* Get the attribute of a Node with id. If the attribute does not exist, returns NULL |
|
251
|
|
|
* @param string $id |
|
252
|
|
|
* @param string $name |
|
253
|
|
|
* @return string |
|
254
|
|
|
*/ |
|
255
|
4 |
|
public function attribute($id, $name) |
|
256
|
|
|
{ |
|
257
|
4 |
|
$node = $this->dom($id); |
|
258
|
|
|
|
|
259
|
4 |
|
return $node->hasAttribute($name) ? $node->getAttribute($name) : NULL; |
|
260
|
|
|
} |
|
261
|
|
|
|
|
262
|
|
|
/** |
|
263
|
|
|
* Return the raw html of a Node with id, along with all of its children. |
|
264
|
|
|
* @param string $id |
|
265
|
|
|
* @return string |
|
266
|
|
|
*/ |
|
267
|
3 |
|
public function html($id) |
|
268
|
|
|
{ |
|
269
|
3 |
|
if ($id === NULL) |
|
270
|
|
|
return $this->dom()->saveHTML(); |
|
271
|
|
|
|
|
272
|
3 |
|
$node = $this->dom($id); |
|
273
|
|
|
|
|
274
|
3 |
|
return $node->ownerDocument->saveXml($node); |
|
275
|
|
|
} |
|
276
|
|
|
|
|
277
|
|
|
/** |
|
278
|
|
|
* Return the text of a Node with id, with all the spaces collapsed, similar to browser rendering. |
|
279
|
|
|
* @param string $id |
|
280
|
|
|
* @return string |
|
281
|
|
|
*/ |
|
282
|
3 |
|
public function text($id) |
|
283
|
|
|
{ |
|
284
|
3 |
|
$text = $this->dom($id)->textContent; |
|
285
|
3 |
|
$text = preg_replace('/[ \s\f\n\r\t\v ]+/u', ' ', $text); |
|
286
|
|
|
|
|
287
|
3 |
|
return trim($text); |
|
288
|
|
|
} |
|
289
|
|
|
|
|
290
|
|
|
/** |
|
291
|
|
|
* Return the value of a Node of a form element, e.g. INPUT, TEXTAREA or SELECT |
|
292
|
|
|
* @param string $id |
|
293
|
|
|
* @return string |
|
294
|
|
|
*/ |
|
295
|
5 |
|
public function value($id) |
|
296
|
|
|
{ |
|
297
|
5 |
|
return $this->forms()->get_value($id); |
|
298
|
|
|
} |
|
299
|
|
|
|
|
300
|
|
|
/** |
|
301
|
|
|
* Check if a Node with id is visible. |
|
302
|
|
|
* A Node is considered hidden if it has a "display:none" inline style or its a script or head tag. |
|
303
|
|
|
* @param string $id |
|
304
|
|
|
* @return boolean |
|
305
|
|
|
*/ |
|
306
|
2 |
|
public function is_visible($id) |
|
307
|
|
|
{ |
|
308
|
2 |
|
$node = $this->dom($id); |
|
309
|
|
|
|
|
310
|
2 |
|
$hidden_nodes = $this->xpath()->query("./ancestor-or-self::*[contains(@style, 'display:none') or contains(@style, 'display: none') or name()='script' or name()='head']", $node); |
|
311
|
2 |
|
return $hidden_nodes->length == 0; |
|
312
|
|
|
} |
|
313
|
|
|
|
|
314
|
|
|
/** |
|
315
|
|
|
* Check if a Node with id of an option element is selected |
|
316
|
|
|
* @param string $id |
|
317
|
|
|
* @return boolean |
|
318
|
|
|
*/ |
|
319
|
2 |
|
public function is_selected($id) |
|
320
|
|
|
{ |
|
321
|
2 |
|
return (bool) $this->dom($id)->getAttribute('selected'); |
|
322
|
|
|
} |
|
323
|
|
|
|
|
324
|
|
|
/** |
|
325
|
|
|
* Check if a Node with id of an input element (radio or checkbox) is checked |
|
326
|
|
|
* @param string $id |
|
327
|
|
|
* @return boolean |
|
328
|
|
|
*/ |
|
329
|
2 |
|
public function is_checked($id) |
|
330
|
|
|
{ |
|
331
|
2 |
|
return (bool) $this->dom($id)->getAttribute('checked'); |
|
332
|
|
|
} |
|
333
|
|
|
|
|
334
|
|
|
/** |
|
335
|
|
|
* Set the value of a Node with id of a form element |
|
336
|
|
|
* @param string $id |
|
337
|
|
|
* @param string $value |
|
338
|
|
|
*/ |
|
339
|
4 |
|
public function set($id, $value) |
|
340
|
|
|
{ |
|
341
|
4 |
|
$this->forms()->set_value($id, $value); |
|
342
|
4 |
|
} |
|
343
|
|
|
|
|
344
|
|
|
/** |
|
345
|
|
|
* Set the option value that is selected of a Node of a select element |
|
346
|
|
|
* @param string $id |
|
347
|
|
|
* @param string $value |
|
348
|
|
|
*/ |
|
349
|
4 |
|
public function select_option($id, $value) |
|
350
|
|
|
{ |
|
351
|
4 |
|
$this->forms()->set_value($id, $value); |
|
352
|
4 |
|
} |
|
353
|
|
|
|
|
354
|
|
|
/** |
|
355
|
|
|
* Return the serialized representation of the input values of a form. |
|
356
|
|
|
* Do not include files or disabled inputs, as well as submit inputs and buttons |
|
357
|
|
|
* @param string $id |
|
358
|
|
|
* @return string |
|
359
|
|
|
*/ |
|
360
|
1 |
|
public function serialize_form($id) |
|
361
|
|
|
{ |
|
362
|
1 |
|
return $this->forms()->serialize_form($id); |
|
363
|
|
|
} |
|
364
|
|
|
|
|
365
|
|
|
/** |
|
366
|
|
|
* Click on a Node with id, triggering a link or form submit |
|
367
|
|
|
* @param string $id |
|
368
|
|
|
* @throws Exception_Driver If not a clickable element |
|
369
|
|
|
*/ |
|
370
|
3 |
|
public function click($id) |
|
371
|
|
|
{ |
|
372
|
3 |
|
$node = $this->dom($id); |
|
373
|
|
|
|
|
374
|
3 |
|
if ($node->hasAttribute('href')) |
|
375
|
|
|
{ |
|
376
|
3 |
|
$this->get($node->getAttribute('href')); |
|
377
|
|
|
} |
|
378
|
2 |
|
elseif (($node->tagName == 'input' AND $node->getAttribute('type') == 'submit') OR $node->tagName == 'button') |
|
379
|
|
|
{ |
|
380
|
2 |
|
$form = $this->xpath()->find('./ancestor::form', $node); |
|
381
|
|
|
|
|
382
|
2 |
|
$action = $form->hasAttribute('action') ? $form->getAttribute('action') : $this->request->uri(); |
|
|
|
|
|
|
383
|
|
|
|
|
384
|
2 |
|
$method = $form->hasAttribute('method') ? strtoupper($form->getAttribute('method')) : 'GET'; |
|
385
|
|
|
|
|
386
|
2 |
|
$post = $this->forms()->serialize_form($form); |
|
387
|
|
|
|
|
388
|
2 |
|
$files = $this->forms()->serialize_files($form); |
|
389
|
|
|
|
|
390
|
2 |
|
if (in_array($node->tagName, array('button', 'input')) AND $node->hasAttribute('name')) |
|
391
|
|
|
{ |
|
392
|
2 |
|
$post = $post.'&'.$node->getAttribute('name').'='.$node->getAttribute('value'); |
|
393
|
|
|
} |
|
394
|
2 |
|
parse_str($post, $post); |
|
395
|
2 |
|
parse_str($files, $files); |
|
396
|
|
|
|
|
397
|
2 |
|
if ($method == 'GET') |
|
398
|
|
|
{ |
|
399
|
1 |
|
$this->get($action, $post); |
|
|
|
|
|
|
400
|
|
|
} |
|
401
|
|
|
else |
|
402
|
|
|
{ |
|
403
|
2 |
|
$this->post($action, array(), $post, $files); |
|
|
|
|
|
|
404
|
|
|
} |
|
405
|
|
|
} |
|
406
|
|
|
else |
|
407
|
|
|
{ |
|
408
|
1 |
|
throw new Exception_Driver('The html tag :tag cannot be clicked', array(':tag' => $node->tagName)); |
|
409
|
|
|
} |
|
410
|
3 |
|
} |
|
411
|
|
|
|
|
412
|
|
|
/** |
|
413
|
|
|
* Go to a given url address |
|
414
|
|
|
* @param string $uri |
|
415
|
|
|
* @param array $query |
|
416
|
|
|
* @return Driver_Simple $this |
|
417
|
|
|
*/ |
|
418
|
1 |
|
public function visit($uri, array $query = array()) |
|
419
|
|
|
{ |
|
420
|
1 |
|
return $this->get($uri, $query); |
|
421
|
|
|
} |
|
422
|
|
|
|
|
423
|
|
|
/** |
|
424
|
|
|
* Get the current path (without host and protocol) |
|
425
|
|
|
* @return string |
|
426
|
|
|
*/ |
|
427
|
2 |
|
public function current_path() |
|
428
|
|
|
{ |
|
429
|
2 |
|
return $this->request_factory()->current_path(); |
|
430
|
|
|
} |
|
431
|
|
|
|
|
432
|
|
|
/** |
|
433
|
|
|
* Get the current url |
|
434
|
|
|
* @return string |
|
435
|
|
|
*/ |
|
436
|
2 |
|
public function current_url() |
|
437
|
|
|
{ |
|
438
|
2 |
|
return $this->request_factory()->current_url(); |
|
439
|
|
|
} |
|
440
|
|
|
|
|
441
|
|
|
/** |
|
442
|
|
|
* Find all ids of a given XPath |
|
443
|
|
|
* @param string $xpath |
|
444
|
|
|
* @param string $parent id of the parent node |
|
445
|
|
|
* @return array |
|
446
|
|
|
*/ |
|
447
|
15 |
|
public function all($xpath, $parent = NULL) |
|
448
|
|
|
{ |
|
449
|
15 |
|
$xpath = $parent.$xpath; |
|
450
|
15 |
|
$ids = array(); |
|
451
|
15 |
|
foreach ($this->xpath()->query($xpath) as $index => $elmenets) |
|
452
|
|
|
{ |
|
453
|
15 |
|
$ids[] = "($xpath)[".($index+1)."]"; |
|
454
|
|
|
} |
|
455
|
15 |
|
return $ids; |
|
456
|
|
|
} |
|
457
|
|
|
|
|
458
|
|
|
/** |
|
459
|
|
|
* Check if anything has been loaded |
|
460
|
|
|
* @return boolean |
|
461
|
|
|
*/ |
|
462
|
1 |
|
public function is_page_active() |
|
463
|
|
|
{ |
|
464
|
1 |
|
return (bool) $this->content(); |
|
465
|
|
|
} |
|
466
|
|
|
|
|
467
|
|
|
/** |
|
468
|
|
|
* Return the current user agent |
|
469
|
|
|
* @return string |
|
470
|
|
|
*/ |
|
471
|
2 |
|
public function user_agent() |
|
472
|
|
|
{ |
|
473
|
2 |
|
return $this->request_factory()->user_agent(); |
|
474
|
|
|
} |
|
475
|
|
|
|
|
476
|
|
|
/** |
|
477
|
|
|
* Set the cookie (by setting the $_COOKIE array directly) |
|
478
|
|
|
* @param string $name |
|
479
|
|
|
* @param mixed $value |
|
480
|
|
|
* @param array $parameters - not utalized by this driver |
|
481
|
|
|
*/ |
|
482
|
1 |
|
public function cookie($name, $value, array $parameters = array()) |
|
483
|
|
|
{ |
|
484
|
1 |
|
$_COOKIE[$name] = $value; |
|
485
|
1 |
|
} |
|
486
|
|
|
|
|
487
|
|
|
} |
|
488
|
|
|
|
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.