|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace Openbuildings\Spiderling; |
|
4
|
|
|
|
|
5
|
|
|
/** |
|
6
|
|
|
* Use phantomjs to load urls. |
|
7
|
|
|
* Has Javascript |
|
8
|
|
|
* |
|
9
|
|
|
* @package Openbuildings\Spiderling |
|
10
|
|
|
* @author Ivan Kerin |
|
11
|
|
|
* @copyright (c) 2013 OpenBuildings Ltd. |
|
12
|
|
|
* @license http://spdx.org/licenses/BSD-3-Clause |
|
13
|
|
|
*/ |
|
14
|
|
|
class Driver_Phantomjs extends Driver { |
|
15
|
|
|
|
|
16
|
|
|
/** |
|
17
|
|
|
* Driver name |
|
18
|
|
|
* @var string |
|
19
|
|
|
*/ |
|
20
|
|
|
public $name = 'phantomjs'; |
|
21
|
|
|
|
|
22
|
|
|
/** |
|
23
|
|
|
* Array containing parameters to be added on the next request |
|
24
|
|
|
* @var array |
|
25
|
|
|
*/ |
|
26
|
|
|
public $_next_query = array(); |
|
27
|
|
|
|
|
28
|
|
|
/** |
|
29
|
|
|
* User agent string cache |
|
30
|
|
|
* @var string |
|
31
|
|
|
*/ |
|
32
|
|
|
protected $_user_agent; |
|
33
|
|
|
|
|
34
|
|
|
/** |
|
35
|
|
|
* Variable holding the current Driver_Phantomjs_Connection |
|
36
|
|
|
* @var Driver_Phantomjs_Connection |
|
37
|
|
|
*/ |
|
38
|
|
|
protected $_connection; |
|
39
|
|
|
|
|
40
|
|
|
/** |
|
41
|
|
|
* The base URL, to be prefixed on each request |
|
42
|
|
|
* @var string |
|
43
|
|
|
*/ |
|
44
|
|
|
protected $_base_url = ''; |
|
45
|
|
|
|
|
46
|
|
|
/** |
|
47
|
|
|
* Getter / Setter of the base_url, that will be prefixed on each request |
|
48
|
|
|
* @param string $base_url |
|
49
|
|
|
* @return string|Driver_PHantomjs |
|
50
|
|
|
*/ |
|
51
|
3 |
|
public function base_url($base_url = NULL) |
|
52
|
|
|
{ |
|
53
|
3 |
|
if ($base_url !== NULL) |
|
54
|
|
|
{ |
|
55
|
1 |
|
$this->_base_url = (string) $base_url; |
|
56
|
1 |
|
return $this; |
|
57
|
|
|
} |
|
58
|
3 |
|
return $this->_base_url; |
|
59
|
|
|
} |
|
60
|
|
|
|
|
61
|
|
|
/** |
|
62
|
|
|
* Getter / Setter of the Driver_Phantomjs_Connection object. |
|
63
|
|
|
* Use this to customize the connection, otherwise a default one on a random port will be used |
|
64
|
|
|
* |
|
65
|
|
|
* @param Driver_Phantomjs_Connection $connection |
|
66
|
|
|
* @return Driver_Phantomjs_Connection|Driver_Phantomjs |
|
67
|
|
|
*/ |
|
68
|
13 |
|
public function connection(Driver_Phantomjs_Connection $connection = NULL) |
|
69
|
|
|
{ |
|
70
|
13 |
|
if ($connection !== NULL) |
|
71
|
|
|
{ |
|
72
|
1 |
|
$this->_connection = $connection; |
|
73
|
1 |
|
return $this; |
|
74
|
|
|
} |
|
75
|
|
|
|
|
76
|
13 |
|
if ( ! $this->_connection) |
|
77
|
|
|
{ |
|
78
|
1 |
|
$this->_connection = new Driver_Phantomjs_Connection(); |
|
79
|
1 |
|
$this->_connection->start(); |
|
80
|
|
|
} |
|
81
|
|
|
|
|
82
|
13 |
|
return $this->_connection; |
|
83
|
|
|
} |
|
84
|
|
|
|
|
85
|
|
|
/** |
|
86
|
|
|
* If a connection has been started, stop it |
|
87
|
|
|
*/ |
|
88
|
2 |
|
public function __destruct() |
|
89
|
|
|
{ |
|
90
|
2 |
|
if ($this->_connection AND $this->_connection->is_started()) |
|
91
|
|
|
{ |
|
92
|
1 |
|
$this->_connection->stop(); |
|
93
|
|
|
} |
|
94
|
2 |
|
} |
|
95
|
|
|
|
|
96
|
|
|
/** |
|
97
|
|
|
* Clear the connection by deleting all cookies |
|
98
|
|
|
*/ |
|
99
|
1 |
|
public function clear() |
|
100
|
|
|
{ |
|
101
|
1 |
|
$this->connection()->delete('cookies'); |
|
|
|
|
|
|
102
|
1 |
|
} |
|
103
|
|
|
|
|
104
|
|
|
/** |
|
105
|
|
|
* Getter of the raw content html, this driver does not allow "setting" |
|
106
|
|
|
* |
|
107
|
|
|
* @param string $content |
|
108
|
|
|
* @return string |
|
109
|
|
|
*/ |
|
110
|
1 |
|
public function content($content = NULL) |
|
111
|
|
|
{ |
|
112
|
1 |
|
return $this->connection()->get('source'); |
|
|
|
|
|
|
113
|
|
|
} |
|
114
|
|
|
|
|
115
|
|
|
/** |
|
116
|
|
|
* NODE GETTERS |
|
117
|
|
|
* ===================================== |
|
118
|
|
|
*/ |
|
119
|
|
|
|
|
120
|
|
|
/** |
|
121
|
|
|
* Get the tag name of a Node with id. e.g. DIV, SPAN ... |
|
122
|
|
|
* @param string $id |
|
123
|
|
|
* @return string |
|
124
|
|
|
*/ |
|
125
|
2 |
|
public function tag_name($id) |
|
126
|
|
|
{ |
|
127
|
2 |
|
return $this->connection()->get("element/$id/name"); |
|
|
|
|
|
|
128
|
|
|
} |
|
129
|
|
|
|
|
130
|
|
|
/** |
|
131
|
|
|
* Get the attribute of a Node with id. If the attribute does not exist, returns NULL |
|
132
|
|
|
* @param string $id |
|
133
|
|
|
* @param string $name |
|
134
|
|
|
* @return string |
|
135
|
|
|
*/ |
|
136
|
2 |
|
public function attribute($id, $name) |
|
137
|
|
|
{ |
|
138
|
2 |
|
return $this->connection()->get("element/$id/attribute/$name"); |
|
|
|
|
|
|
139
|
|
|
} |
|
140
|
|
|
|
|
141
|
|
|
/** |
|
142
|
|
|
* Return the raw html of a Node with id, along with all of its children. |
|
143
|
|
|
* @param string $id |
|
144
|
|
|
* @return string |
|
145
|
|
|
*/ |
|
146
|
1 |
|
public function html($id) |
|
147
|
|
|
{ |
|
148
|
1 |
|
if ($id === NULL) |
|
149
|
|
|
return $this->content(); |
|
150
|
|
|
|
|
151
|
1 |
|
return $this->connection()->get("element/$id/html"); |
|
|
|
|
|
|
152
|
|
|
} |
|
153
|
|
|
|
|
154
|
|
|
/** |
|
155
|
|
|
* Return the text of a Node with id, with all the spaces collapsed, similar to browser rendering. |
|
156
|
|
|
* @param string $id |
|
157
|
|
|
* @return string |
|
158
|
|
|
*/ |
|
159
|
2 |
|
public function text($id) |
|
160
|
|
|
{ |
|
161
|
2 |
|
$text = $this->connection()->get("element/$id/text"); |
|
|
|
|
|
|
162
|
2 |
|
$text = preg_replace('/[ \s\f\n\r\t\v ]+/u', ' ', $text); |
|
163
|
2 |
|
return trim($text); |
|
164
|
|
|
} |
|
165
|
|
|
|
|
166
|
|
|
/** |
|
167
|
|
|
* Return the value of a Node of a form element, e.g. INPUT, TEXTAREA or SELECT |
|
168
|
|
|
* @param string $id |
|
169
|
|
|
* @return string |
|
170
|
|
|
*/ |
|
171
|
2 |
|
public function value($id) |
|
172
|
|
|
{ |
|
173
|
2 |
|
return $this->connection()->get("element/$id/value"); |
|
|
|
|
|
|
174
|
|
|
} |
|
175
|
|
|
|
|
176
|
|
|
/** |
|
177
|
|
|
* Check if a Node with id is visible. |
|
178
|
|
|
* @param string $id |
|
179
|
|
|
* @return boolean |
|
180
|
|
|
*/ |
|
181
|
1 |
|
public function is_visible($id) |
|
182
|
|
|
{ |
|
183
|
1 |
|
return $this->connection()->get("element/$id/visible"); |
|
|
|
|
|
|
184
|
|
|
} |
|
185
|
|
|
|
|
186
|
|
|
/** |
|
187
|
|
|
* Check if a Node with id of an option element is selected |
|
188
|
|
|
* @param string $id |
|
189
|
|
|
* @return boolean |
|
190
|
|
|
*/ |
|
191
|
2 |
|
public function is_selected($id) |
|
192
|
|
|
{ |
|
193
|
2 |
|
return $this->connection()->get("element/$id/selected"); |
|
|
|
|
|
|
194
|
|
|
} |
|
195
|
|
|
|
|
196
|
|
|
/** |
|
197
|
|
|
* Check if a Node with id of an input element (radio or checkbox) is checked |
|
198
|
|
|
* @param string $id |
|
199
|
|
|
* @return boolean |
|
200
|
|
|
*/ |
|
201
|
1 |
|
public function is_checked($id) |
|
202
|
|
|
{ |
|
203
|
1 |
|
return $this->connection()->get("element/$id/checked"); |
|
|
|
|
|
|
204
|
|
|
} |
|
205
|
|
|
|
|
206
|
|
|
/** |
|
207
|
|
|
* Set the value of a Node with id of a form element |
|
208
|
|
|
* @param string $id |
|
209
|
|
|
* @param string $value |
|
210
|
|
|
*/ |
|
211
|
1 |
|
public function set($id, $value) |
|
212
|
|
|
{ |
|
213
|
1 |
|
$tag_name = $this->tag_name($id); |
|
214
|
|
|
|
|
215
|
1 |
|
if ($tag_name == 'textarea') |
|
216
|
|
|
{ |
|
217
|
1 |
|
$this->connection()->post("element/$id/value", array('value' => $value)); |
|
|
|
|
|
|
218
|
|
|
} |
|
219
|
1 |
|
elseif ($tag_name == 'input') |
|
220
|
|
|
{ |
|
221
|
1 |
|
$type = $this->attribute($id, 'type'); |
|
222
|
1 |
|
if ($type == 'checkbox' OR $type == 'radio') |
|
223
|
|
|
{ |
|
224
|
1 |
|
$this->connection()->post("element/$id/click", array()); |
|
225
|
|
|
} |
|
226
|
1 |
|
elseif ($type == 'file') |
|
227
|
|
|
{ |
|
228
|
1 |
|
$this->connection()->post("element/$id/upload", array('value' => $value)); |
|
229
|
|
|
} |
|
230
|
|
|
else |
|
231
|
|
|
{ |
|
232
|
1 |
|
$this->connection()->post("element/$id/value", array('value' => $value)); |
|
233
|
|
|
} |
|
234
|
|
|
} |
|
235
|
1 |
|
elseif ($tag_name == 'option') |
|
236
|
|
|
{ |
|
237
|
1 |
|
$this->connection()->post("element/$id/selected", array('value' => $value)); |
|
238
|
|
|
} |
|
239
|
1 |
|
} |
|
240
|
|
|
|
|
241
|
|
|
/** |
|
242
|
|
|
* Set the option value that is selected of a Node of a select element |
|
243
|
|
|
* @param string $id |
|
244
|
|
|
* @param string $value |
|
245
|
|
|
*/ |
|
246
|
1 |
|
public function select_option($id, $value) |
|
247
|
|
|
{ |
|
248
|
1 |
|
$this->connection()->post("element/$id/selected", array('value' => $value)); |
|
|
|
|
|
|
249
|
1 |
|
} |
|
250
|
|
|
|
|
251
|
|
|
/** |
|
252
|
|
|
* Click on a Node with id, triggering a link or form submit |
|
253
|
|
|
* @param string $id |
|
254
|
|
|
* @throws Exception_Driver If not a clickable element |
|
255
|
|
|
*/ |
|
256
|
1 |
|
public function click($id) |
|
257
|
|
|
{ |
|
258
|
1 |
|
$this->connection()->post("element/$id/click", array()); |
|
|
|
|
|
|
259
|
1 |
|
} |
|
260
|
|
|
|
|
261
|
|
|
/** |
|
262
|
|
|
* Go to a given url address, use next_query along with the provided query array |
|
263
|
|
|
* @param string $uri |
|
264
|
|
|
* @param array $query |
|
265
|
|
|
*/ |
|
266
|
2 |
|
public function visit($uri, array $query = array()) |
|
267
|
|
|
{ |
|
268
|
2 |
|
$query = array_merge((array) $this->_next_query, (array) $query); |
|
269
|
|
|
|
|
270
|
2 |
|
$this->_next_query = NULL; |
|
|
|
|
|
|
271
|
|
|
|
|
272
|
|
|
// Check for implicit query string |
|
273
|
2 |
|
if (strpos($uri, '?') !== FALSE) |
|
274
|
|
|
{ |
|
275
|
|
|
$query = array_merge(self::extract_query_from_uri($uri), $query); |
|
276
|
|
|
$uri = substr($uri, 0, strpos($uri, '?')); |
|
277
|
|
|
} |
|
278
|
|
|
|
|
279
|
2 |
|
$url = $this->base_url().$uri.($query ? '?'.http_build_query($query) : ''); |
|
280
|
|
|
|
|
281
|
2 |
|
$this->connection()->post('url', array('value' => $url)); |
|
|
|
|
|
|
282
|
2 |
|
} |
|
283
|
|
|
|
|
284
|
|
|
/** |
|
285
|
|
|
* Get the current path (without host and protocol) |
|
286
|
|
|
* @return string |
|
287
|
|
|
*/ |
|
288
|
1 |
|
public function current_path() |
|
289
|
|
|
{ |
|
290
|
1 |
|
$url = parse_url($this->connection()->get('url')); |
|
|
|
|
|
|
291
|
|
|
|
|
292
|
1 |
|
return $url['path'].(isset($url['query']) ? '?'.$url['query'] : ''); |
|
293
|
|
|
} |
|
294
|
|
|
|
|
295
|
|
|
/** |
|
296
|
|
|
* Get the current url |
|
297
|
|
|
* @return string |
|
298
|
|
|
*/ |
|
299
|
2 |
|
public function current_url() |
|
300
|
|
|
{ |
|
301
|
2 |
|
return urldecode($this->connection()->get('url')); |
|
|
|
|
|
|
302
|
|
|
} |
|
303
|
|
|
|
|
304
|
|
|
/** |
|
305
|
|
|
* Find all ids of a given XPath |
|
306
|
|
|
* @param string $xpath |
|
307
|
|
|
* @param string $parent id of the parent node |
|
308
|
|
|
* @return array |
|
309
|
|
|
*/ |
|
310
|
7 |
|
public function all($xpath, $parent = NULL) |
|
311
|
|
|
{ |
|
312
|
7 |
|
return $this->connection()->post(($parent === NULL ? '' : 'element/'.$parent.'/').'elements', array('value' => '.'.$xpath)); |
|
|
|
|
|
|
313
|
|
|
} |
|
314
|
|
|
|
|
315
|
|
|
/** |
|
316
|
|
|
* Setter for the next_query variable, to be added to the next visit's query |
|
317
|
|
|
* @param array $query |
|
318
|
|
|
*/ |
|
319
|
1 |
|
public function next_query(array $query) |
|
320
|
|
|
{ |
|
321
|
1 |
|
$this->_next_query = $query; |
|
322
|
1 |
|
} |
|
323
|
|
|
|
|
324
|
|
|
/** |
|
325
|
|
|
* Check if a connection is active |
|
326
|
|
|
* @return boolean |
|
327
|
|
|
*/ |
|
328
|
1 |
|
public function is_page_active() |
|
329
|
|
|
{ |
|
330
|
1 |
|
return (bool) $this->_connection; |
|
331
|
|
|
} |
|
332
|
|
|
|
|
333
|
|
|
/** |
|
334
|
|
|
* Return all javascript errors for the current page |
|
335
|
|
|
* @return array |
|
336
|
|
|
*/ |
|
337
|
1 |
|
public function javascript_errors() |
|
338
|
|
|
{ |
|
339
|
1 |
|
return $this->connection()->get('errors', array()); |
|
|
|
|
|
|
340
|
|
|
} |
|
341
|
|
|
|
|
342
|
|
|
/** |
|
343
|
|
|
* Return all console messages for the current page |
|
344
|
|
|
* @return array |
|
345
|
|
|
*/ |
|
346
|
1 |
|
public function javascript_messages() |
|
347
|
|
|
{ |
|
348
|
1 |
|
return $this->connection()->get('messages', array()); |
|
|
|
|
|
|
349
|
|
|
} |
|
350
|
|
|
|
|
351
|
|
|
/** |
|
352
|
|
|
* Do a screenshot of the current page into a file |
|
353
|
|
|
* @param string $file |
|
354
|
|
|
*/ |
|
355
|
1 |
|
public function screenshot($file) |
|
356
|
|
|
{ |
|
357
|
1 |
|
$this->connection()->post('screenshot', array('value' => $file)); |
|
|
|
|
|
|
358
|
1 |
|
} |
|
359
|
|
|
|
|
360
|
|
|
/** |
|
361
|
|
|
* Get the current user agent |
|
362
|
|
|
* @return string |
|
363
|
|
|
*/ |
|
364
|
1 |
|
public function user_agent() |
|
365
|
|
|
{ |
|
366
|
1 |
|
if ( ! $this->_user_agent) |
|
367
|
|
|
{ |
|
368
|
1 |
|
$settings = $this->connection()->get('settings'); |
|
|
|
|
|
|
369
|
1 |
|
$this->_user_agent = isset($settings['userAgent']) ? $settings['userAgent'] : NULL; |
|
370
|
|
|
} |
|
371
|
|
|
|
|
372
|
1 |
|
return $this->_user_agent; |
|
373
|
|
|
} |
|
374
|
|
|
|
|
375
|
|
|
/** |
|
376
|
|
|
* Execute raw javascript. it will be executed in the context of a given node ('this' will point to the node) and the return of the script will be the return of this method |
|
377
|
|
|
* @param string $id |
|
378
|
|
|
* @param string $script |
|
379
|
|
|
* @return mixed |
|
380
|
|
|
*/ |
|
381
|
2 |
|
public function execute($id, $script) |
|
382
|
|
|
{ |
|
383
|
2 |
|
return $this->connection()->post('execute', array( |
|
|
|
|
|
|
384
|
2 |
|
'value' => $script, |
|
385
|
2 |
|
'id' => $id, |
|
386
|
|
|
)); |
|
387
|
|
|
} |
|
388
|
|
|
|
|
389
|
|
|
/** |
|
390
|
|
|
* Return all the current cookies |
|
391
|
|
|
* @return array |
|
392
|
|
|
*/ |
|
393
|
1 |
|
public function cookies() |
|
394
|
|
|
{ |
|
395
|
1 |
|
return $this->connection()->get('cookies'); |
|
|
|
|
|
|
396
|
|
|
} |
|
397
|
|
|
|
|
398
|
|
|
/** |
|
399
|
|
|
* Set a cookie. Use parameters to set "expires", "path", "domain", "secure" and "httponly" |
|
400
|
|
|
* @param string $name |
|
401
|
|
|
* @param mixed $value |
|
402
|
|
|
* @param array $parameters |
|
403
|
|
|
*/ |
|
404
|
1 |
|
public function cookie($name, $value, array $parameters = array()) |
|
405
|
|
|
{ |
|
406
|
1 |
|
$this->connection()->post('cookie', array( |
|
|
|
|
|
|
407
|
1 |
|
'name' => $name, |
|
408
|
1 |
|
'value' => $value, |
|
409
|
1 |
|
'expires' => isset($parameters['expires']) ? $parameters['expires'] : time() + 86400, |
|
410
|
1 |
|
'path' => isset($parameters['path']) ? $parameters['path'] : '/', |
|
411
|
1 |
|
'domain' => isset($parameters['domain']) ? $parameters['domain'] : NULL, |
|
412
|
1 |
|
'secure' => isset($parameters['secure']) ? $parameters['secure'] : FALSE, |
|
413
|
1 |
|
'httponly' => isset($parameters['httponly']) ? $parameters['httponly'] : FALSE, |
|
414
|
|
|
)); |
|
415
|
1 |
|
} |
|
416
|
|
|
} |
|
417
|
|
|
|
It seems like the method you are trying to call exists only in some of the possible types.
Let’s take a look at an example:
Available Fixes
Add an additional type-check:
Only allow a single type to be passed if the variable comes from a parameter: