|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace TreeHouse\IoBundle\Entity; |
|
4
|
|
|
|
|
5
|
|
|
use Doctrine\Common\Collections\ArrayCollection; |
|
6
|
|
|
use Doctrine\ORM\Mapping as ORM; |
|
7
|
|
|
use TreeHouse\IoBundle\Model\OriginInterface; |
|
8
|
|
|
use TreeHouse\IoBundle\Model\SourceInterface; |
|
9
|
|
|
|
|
10
|
|
|
/** |
|
11
|
|
|
* @ORM\Entity(repositoryClass="ScraperRepository") |
|
12
|
|
|
* @ORM\Table |
|
13
|
|
|
*/ |
|
14
|
|
|
class Scraper |
|
15
|
|
|
{ |
|
16
|
|
|
/** |
|
17
|
|
|
* @var int |
|
18
|
|
|
* |
|
19
|
|
|
* @ORM\Column(type="integer") |
|
20
|
|
|
* @ORM\Id |
|
21
|
|
|
* @ORM\GeneratedValue(strategy="AUTO") |
|
22
|
|
|
*/ |
|
23
|
|
|
protected $id; |
|
24
|
|
|
|
|
25
|
|
|
/** |
|
26
|
|
|
* The frequency to start the scraper, in hours. |
|
27
|
|
|
* |
|
28
|
|
|
* @var int |
|
29
|
|
|
* |
|
30
|
|
|
* @ORM\Column(type="integer") |
|
31
|
|
|
*/ |
|
32
|
|
|
protected $startFrequency; |
|
33
|
|
|
|
|
34
|
|
|
/** |
|
35
|
|
|
* The frequency to revisit sources, in hours. |
|
36
|
|
|
* |
|
37
|
|
|
* @var int |
|
38
|
|
|
* |
|
39
|
|
|
* @ORM\Column(type="integer") |
|
40
|
|
|
*/ |
|
41
|
|
|
protected $revisitFrequency; |
|
42
|
|
|
|
|
43
|
|
|
/** |
|
44
|
|
|
* One of the configured crawler types. |
|
45
|
|
|
* |
|
46
|
|
|
* @var string |
|
47
|
|
|
* |
|
48
|
|
|
* @ORM\Column(type="string") |
|
49
|
|
|
*/ |
|
50
|
|
|
protected $crawler; |
|
51
|
|
|
|
|
52
|
|
|
/** |
|
53
|
|
|
* Options to be passed to the crawler type. |
|
54
|
|
|
* |
|
55
|
|
|
* @var array |
|
56
|
|
|
* |
|
57
|
|
|
* @ORM\Column(type="json_array", nullable=true) |
|
58
|
|
|
*/ |
|
59
|
|
|
protected $crawlerOptions; |
|
60
|
|
|
|
|
61
|
|
|
/** |
|
62
|
|
|
* One of the configured parser types. |
|
63
|
|
|
* |
|
64
|
|
|
* @var string |
|
65
|
|
|
* |
|
66
|
|
|
* @ORM\Column(type="string") |
|
67
|
|
|
*/ |
|
68
|
|
|
protected $parser; |
|
69
|
|
|
|
|
70
|
|
|
/** |
|
71
|
|
|
* Options to be passed to the parser type. |
|
72
|
|
|
* |
|
73
|
|
|
* @var array |
|
74
|
|
|
* |
|
75
|
|
|
* @ORM\Column(type="json_array", nullable=true) |
|
76
|
|
|
*/ |
|
77
|
|
|
protected $parserOptions; |
|
78
|
|
|
|
|
79
|
|
|
/** |
|
80
|
|
|
* One of the configured handlers. |
|
81
|
|
|
* |
|
82
|
|
|
* @var string |
|
83
|
|
|
* |
|
84
|
|
|
* @ORM\Column(type="string") |
|
85
|
|
|
*/ |
|
86
|
|
|
protected $handler; |
|
87
|
|
|
|
|
88
|
|
|
/** |
|
89
|
|
|
* The root url. |
|
90
|
|
|
* |
|
91
|
|
|
* @var string |
|
92
|
|
|
* |
|
93
|
|
|
* @ORM\Column(type="string") |
|
94
|
|
|
*/ |
|
95
|
|
|
protected $url; |
|
96
|
|
|
|
|
97
|
|
|
/** |
|
98
|
|
|
* Can contain key/value pairs to be used as defaults if the scraped pages doesn't supply them. |
|
99
|
|
|
* |
|
100
|
|
|
* @var array |
|
101
|
|
|
* |
|
102
|
|
|
* @ORM\Column(type="json_array", nullable=true) |
|
103
|
|
|
*/ |
|
104
|
|
|
protected $defaultValues; |
|
105
|
|
|
|
|
106
|
|
|
/** |
|
107
|
|
|
* @var \DateTime |
|
108
|
|
|
* |
|
109
|
|
|
* @ORM\Column(type="datetime", nullable=true) |
|
110
|
|
|
*/ |
|
111
|
|
|
protected $datetimeLastStarted; |
|
112
|
|
|
|
|
113
|
|
|
/** |
|
114
|
|
|
* @var OriginInterface |
|
115
|
|
|
* |
|
116
|
|
|
* @ORM\ManyToOne(targetEntity="TreeHouse\IoBundle\Model\OriginInterface", inversedBy="scrapers", cascade={"persist"}) |
|
117
|
|
|
*/ |
|
118
|
|
|
protected $origin; |
|
119
|
|
|
|
|
120
|
|
|
/** |
|
121
|
|
|
* @var SourceInterface |
|
122
|
|
|
* |
|
123
|
|
|
* @ORM\OneToMany(targetEntity="TreeHouse\IoBundle\Model\SourceInterface", mappedBy="scraper", cascade={"persist", "remove"}) |
|
124
|
|
|
*/ |
|
125
|
|
|
protected $sources; |
|
126
|
|
|
|
|
127
|
|
|
/** |
|
128
|
|
|
* Constructor. |
|
129
|
|
|
*/ |
|
130
|
40 |
|
public function __construct() |
|
131
|
|
|
{ |
|
132
|
40 |
|
$this->sources = new ArrayCollection(); |
|
|
|
|
|
|
133
|
40 |
|
} |
|
134
|
|
|
|
|
135
|
|
|
/** |
|
136
|
|
|
* @return string |
|
137
|
|
|
*/ |
|
138
|
|
|
public function __toString() |
|
139
|
|
|
{ |
|
140
|
|
|
return $this->url; |
|
141
|
|
|
} |
|
142
|
|
|
|
|
143
|
|
|
/** |
|
144
|
|
|
* @return int |
|
145
|
|
|
*/ |
|
146
|
|
|
public function getId() |
|
147
|
|
|
{ |
|
148
|
|
|
return $this->id; |
|
149
|
|
|
} |
|
150
|
|
|
|
|
151
|
|
|
/** |
|
152
|
|
|
* @param int $startFrequency |
|
153
|
|
|
* |
|
154
|
|
|
* @return $this |
|
155
|
|
|
*/ |
|
156
|
|
|
public function setStartFrequency($startFrequency) |
|
157
|
|
|
{ |
|
158
|
|
|
$this->startFrequency = $startFrequency; |
|
159
|
|
|
|
|
160
|
|
|
return $this; |
|
161
|
|
|
} |
|
162
|
|
|
|
|
163
|
|
|
/** |
|
164
|
|
|
* @return int |
|
165
|
|
|
*/ |
|
166
|
|
|
public function getStartFrequency() |
|
167
|
|
|
{ |
|
168
|
|
|
return $this->startFrequency; |
|
169
|
|
|
} |
|
170
|
|
|
|
|
171
|
|
|
/** |
|
172
|
|
|
* @param int $revisitFrequency |
|
173
|
|
|
* |
|
174
|
|
|
* @return $this |
|
175
|
|
|
*/ |
|
176
|
|
|
public function setRevisitFrequency($revisitFrequency) |
|
177
|
|
|
{ |
|
178
|
|
|
$this->revisitFrequency = $revisitFrequency; |
|
179
|
|
|
|
|
180
|
|
|
return $this; |
|
181
|
|
|
} |
|
182
|
|
|
|
|
183
|
|
|
/** |
|
184
|
|
|
* @return int |
|
185
|
|
|
*/ |
|
186
|
|
|
public function getRevisitFrequency() |
|
187
|
|
|
{ |
|
188
|
|
|
return $this->revisitFrequency; |
|
189
|
|
|
} |
|
190
|
|
|
|
|
191
|
|
|
/** |
|
192
|
|
|
* @param string $crawler |
|
193
|
|
|
* |
|
194
|
|
|
* @return $this |
|
195
|
|
|
*/ |
|
196
|
|
|
public function setCrawler($crawler) |
|
197
|
|
|
{ |
|
198
|
|
|
$this->crawler = $crawler; |
|
199
|
|
|
|
|
200
|
|
|
return $this; |
|
201
|
|
|
} |
|
202
|
|
|
|
|
203
|
|
|
/** |
|
204
|
|
|
* @return string |
|
205
|
|
|
*/ |
|
206
|
|
|
public function getCrawler() |
|
207
|
|
|
{ |
|
208
|
|
|
return $this->crawler; |
|
209
|
|
|
} |
|
210
|
|
|
|
|
211
|
|
|
/** |
|
212
|
|
|
* @param array $crawlerOptions |
|
213
|
|
|
* |
|
214
|
|
|
* @return $this |
|
215
|
|
|
*/ |
|
216
|
|
|
public function setCrawlerOptions(array $crawlerOptions) |
|
217
|
|
|
{ |
|
218
|
|
|
$this->crawlerOptions = $crawlerOptions; |
|
219
|
|
|
|
|
220
|
|
|
return $this; |
|
221
|
|
|
} |
|
222
|
|
|
|
|
223
|
|
|
/** |
|
224
|
|
|
* @return array |
|
225
|
|
|
*/ |
|
226
|
|
|
public function getCrawlerOptions() |
|
227
|
|
|
{ |
|
228
|
|
|
return $this->crawlerOptions; |
|
229
|
|
|
} |
|
230
|
|
|
|
|
231
|
|
|
/** |
|
232
|
|
|
* @param string $parser |
|
233
|
|
|
* |
|
234
|
|
|
* @return $this |
|
235
|
|
|
*/ |
|
236
|
|
|
public function setParser($parser) |
|
237
|
|
|
{ |
|
238
|
|
|
$this->parser = $parser; |
|
239
|
|
|
|
|
240
|
|
|
return $this; |
|
241
|
|
|
} |
|
242
|
|
|
|
|
243
|
|
|
/** |
|
244
|
|
|
* @return string |
|
245
|
|
|
*/ |
|
246
|
|
|
public function getParser() |
|
247
|
|
|
{ |
|
248
|
|
|
return $this->parser; |
|
249
|
|
|
} |
|
250
|
|
|
|
|
251
|
|
|
/** |
|
252
|
|
|
* @param array $parserOptions |
|
253
|
|
|
* |
|
254
|
|
|
* @return $this |
|
255
|
|
|
*/ |
|
256
|
|
|
public function setParserOptions(array $parserOptions) |
|
257
|
|
|
{ |
|
258
|
|
|
$this->parserOptions = $parserOptions; |
|
259
|
|
|
|
|
260
|
|
|
return $this; |
|
261
|
|
|
} |
|
262
|
|
|
|
|
263
|
|
|
/** |
|
264
|
|
|
* @return array |
|
265
|
|
|
*/ |
|
266
|
|
|
public function getParserOptions() |
|
267
|
|
|
{ |
|
268
|
|
|
return $this->parserOptions; |
|
269
|
|
|
} |
|
270
|
|
|
|
|
271
|
|
|
/** |
|
272
|
|
|
* @param string $handler |
|
273
|
|
|
* |
|
274
|
|
|
* @return $this |
|
275
|
|
|
*/ |
|
276
|
|
|
public function setHandler($handler) |
|
277
|
|
|
{ |
|
278
|
|
|
$this->handler = $handler; |
|
279
|
|
|
|
|
280
|
|
|
return $this; |
|
281
|
|
|
} |
|
282
|
|
|
|
|
283
|
|
|
/** |
|
284
|
|
|
* @return string |
|
285
|
|
|
*/ |
|
286
|
|
|
public function getHandler() |
|
287
|
|
|
{ |
|
288
|
|
|
return $this->handler; |
|
289
|
|
|
} |
|
290
|
|
|
|
|
291
|
|
|
/** |
|
292
|
|
|
* @param string $url |
|
293
|
|
|
* |
|
294
|
|
|
* @return $this |
|
295
|
|
|
*/ |
|
296
|
|
|
public function setUrl($url) |
|
297
|
|
|
{ |
|
298
|
|
|
$this->url = $url; |
|
299
|
|
|
|
|
300
|
|
|
return $this; |
|
301
|
|
|
} |
|
302
|
|
|
|
|
303
|
|
|
/** |
|
304
|
|
|
* @return string |
|
305
|
|
|
*/ |
|
306
|
|
|
public function getUrl() |
|
307
|
|
|
{ |
|
308
|
|
|
return $this->url; |
|
309
|
|
|
} |
|
310
|
|
|
|
|
311
|
|
|
/** |
|
312
|
|
|
* @param array $defaultValues |
|
313
|
|
|
* |
|
314
|
|
|
* @return $this |
|
315
|
|
|
*/ |
|
316
|
|
|
public function setDefaultValues(array $defaultValues) |
|
317
|
|
|
{ |
|
318
|
|
|
$this->defaultValues = $defaultValues; |
|
319
|
|
|
|
|
320
|
|
|
return $this; |
|
321
|
|
|
} |
|
322
|
|
|
|
|
323
|
|
|
/** |
|
324
|
|
|
* @return array |
|
325
|
|
|
*/ |
|
326
|
|
|
public function getDefaultValues() |
|
327
|
|
|
{ |
|
328
|
|
|
return $this->defaultValues; |
|
329
|
|
|
} |
|
330
|
|
|
|
|
331
|
|
|
/** |
|
332
|
|
|
* @param \DateTime $datetimeLastStarted |
|
333
|
|
|
* |
|
334
|
|
|
* @return $this |
|
335
|
|
|
*/ |
|
336
|
|
|
public function setDatetimeLastStarted(\DateTime $datetimeLastStarted = null) |
|
337
|
|
|
{ |
|
338
|
|
|
$this->datetimeLastStarted = $datetimeLastStarted; |
|
339
|
|
|
|
|
340
|
|
|
return $this; |
|
341
|
|
|
} |
|
342
|
|
|
|
|
343
|
|
|
/** |
|
344
|
|
|
* @return \DateTime |
|
345
|
|
|
*/ |
|
346
|
|
|
public function getDatetimeLastStarted() |
|
347
|
|
|
{ |
|
348
|
|
|
return $this->datetimeLastStarted; |
|
349
|
|
|
} |
|
350
|
|
|
|
|
351
|
|
|
/** |
|
352
|
|
|
* @param OriginInterface $origin |
|
353
|
|
|
* |
|
354
|
|
|
* @return $this |
|
355
|
|
|
*/ |
|
356
|
|
|
public function setOrigin(OriginInterface $origin = null) |
|
357
|
|
|
{ |
|
358
|
|
|
$this->origin = $origin; |
|
359
|
|
|
|
|
360
|
|
|
return $this; |
|
361
|
|
|
} |
|
362
|
|
|
|
|
363
|
|
|
/** |
|
364
|
|
|
* @return OriginInterface |
|
365
|
|
|
*/ |
|
366
|
|
|
public function getOrigin() |
|
367
|
|
|
{ |
|
368
|
|
|
return $this->origin; |
|
369
|
|
|
} |
|
370
|
|
|
|
|
371
|
|
|
/** |
|
372
|
|
|
* @param SourceInterface $source |
|
373
|
|
|
* |
|
374
|
|
|
* @return $this |
|
375
|
|
|
*/ |
|
376
|
|
|
public function addSource(SourceInterface $source) |
|
377
|
|
|
{ |
|
378
|
|
|
$this->sources[] = $source; |
|
379
|
|
|
|
|
380
|
|
|
return $this; |
|
381
|
|
|
} |
|
382
|
|
|
|
|
383
|
|
|
/** |
|
384
|
|
|
* @param SourceInterface $source |
|
385
|
|
|
*/ |
|
386
|
|
|
public function removeSource(SourceInterface $source) |
|
387
|
|
|
{ |
|
388
|
|
|
$this->sources->removeElement($source); |
|
|
|
|
|
|
389
|
|
|
} |
|
390
|
|
|
|
|
391
|
|
|
/** |
|
392
|
|
|
* @return SourceInterface[]|ArrayCollection |
|
393
|
|
|
*/ |
|
394
|
|
|
public function getSources() |
|
395
|
|
|
{ |
|
396
|
|
|
return $this->sources; |
|
397
|
|
|
} |
|
398
|
|
|
} |
|
399
|
|
|
|
Our type inference engine has found an assignment to a property that is incompatible with the declared type of that property.
Either this assignment is in error or the assigned type should be added to the documentation/type hint for that property..