forked from t1gor/Robots.txt-Parser-Class
-
Notifications
You must be signed in to change notification settings - Fork 0
/
robotstxtparser.php
414 lines (363 loc) · 10 KB
/
robotstxtparser.php
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
<?php
/**
* Class for parsing robots.txt files
*
* @author Igor Timoshenkov ([email protected])
*
* Logic schem and signals:
* @link https://docs.google.com/document/d/1_rNjxpnUUeJG13ap6cnXM6Sx9ZQtd1ngADXnW9SHJSE/edit
*
* Some useful links and materials:
* @link https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
* @link http://help.yandex.com/webmaster/?id=1113851
* @link http://socoder.net/index.php?snippet=23824
* @link http://www.the-art-of-web.com/php/parse-robots/#.UP0C1ZGhM6I
*/
class RobotsTxtParser {
// default encoding
const DEFAULT_ENCODING = 'UTF-8';
// states
const STATE_ZERO_POINT = 'zero-point';
const STATE_READ_DIRECTIVE = 'read-directive';
const STATE_SKIP_SPACE = 'skip-space';
const STATE_SKIP_LINE = 'skip-line';
const STATE_READ_VALUE = 'read-value';
// directives
const DIRECTIVE_ALLOW = 'allow';
const DIRECTIVE_DISALLOW = 'disallow';
const DIRECTIVE_HOST = 'host';
const DIRECTIVE_SITEMAP = 'sitemap';
const DIRECTIVE_USERAGENT = 'user-agent';
const DIRECTIVE_CRAWL_DELAY = 'crawl-delay';
// language
const LANG_NO_CONTENT_PASSED = "No content submitted - please check the file that you are using.";
// internal logs
public $log_enabled = true;
// current state
public $state = "";
// robots.txt file content
public $content = "";
// rules set
public $rules = array();
// internally used variables
protected $current_word = "";
protected $current_char = "";
protected $char_index = 0;
protected $current_directive = "";
protected $previous_directive = "";
protected $userAgent = "*";
/**
* @param string $content - file content
* @param string $encoding - encoding
* @throws InvalidArgumentException
* @return RobotsTxtParser
*/
public function __construct($content, $encoding = self::DEFAULT_ENCODING)
{
// checl for empty content
if (strlen($content) == 0) {
throw new InvalidArgumentException(self::LANG_NO_CONTENT_PASSED);
}
// convert encoding
$encoding = !empty($encoding) ? $encoding : mb_detect_encoding($content);
mb_internal_encoding($encoding);
// set content
$this->content = iconv($encoding, 'UTF-8//IGNORE', $content);
// Ensure that there's a newline at the end of the file, otherwise the
// last line is ignored
$this->content .= "\n";
// set default state
$this->state = self::STATE_ZERO_POINT;
// parse rools - default state
$this->prepareRules();
}
// signals
/**
* Comment signal (#)
*/
protected function sharp() {
return ($this->current_char == '#');
}
/**
* Allow directive signal
*/
protected function allow() {
return ($this->current_word == self::DIRECTIVE_ALLOW);
}
/**
* Disallow directive signal
*/
protected function disallow() {
return ($this->current_word == self::DIRECTIVE_DISALLOW);
}
/**
* Host directive signal
*/
protected function host() {
return ($this->current_word == self::DIRECTIVE_HOST);
}
/**
* Sitemap directive signal
*/
protected function sitemap() {
return ($this->current_word == self::DIRECTIVE_SITEMAP);
}
/**
* Key : value pair separator signal
*/
protected function lineSeparator() {
return ($this->current_char == ':');
}
/**
* Move to new line signal
*/
protected function newLine()
{
return ($this->current_char == "\n"
|| $this->current_word == "\r\n"
|| $this->current_word == "\n\r"
);
}
/**
* "Space" signal
*/
protected function space() {
return ($this->current_char == "\s");
}
/**
* User-agent directive signal
*/
protected function userAgent() {
return ($this->current_word == self::DIRECTIVE_USERAGENT);
}
/**
* Crawl-Delay directive signal
*/
protected function crawlDelay() {
return ($this->current_word == self::DIRECTIVE_CRAWL_DELAY);
}
/**
* Change state
*
* @param string $stateTo - state that should be set
* @return void
*/
protected function switchState($stateTo = self::STATE_SKIP_LINE) {
$this->state = $stateTo;
}
/**
* Parse rools
*
* @return void
*/
public function prepareRules()
{
$contentLength = mb_strlen($this->content);
while ($this->char_index <= $contentLength) {
$this->step();
}
}
/**
* Machine step
*
* @return void
*/
protected function step()
{
switch ($this->state)
{
case self::STATE_ZERO_POINT:
if ($this->allow()
|| $this->disallow()
|| $this->host()
|| $this->userAgent()
|| $this->crawlDelay()
|| $this->sitemap()
) {
$this->switchState(self::STATE_READ_DIRECTIVE);
}
elseif ($this->newLine()) {
// unknown directive - skip it
$this->current_word = "";
$this->increment();
}
else {
$this->increment();
}
break;
case self::STATE_READ_DIRECTIVE:
$this->previous_directive = $this->current_directive;
$this->current_directive = mb_strtolower(trim($this->current_word));
$this->current_word = "";
$this->increment();
if ($this->lineSeparator())
{
$this->current_word = "";
$this->switchState(self::STATE_READ_VALUE);
}
else {
if ($this->space()) {
$this->switchState(self::STATE_SKIP_SPACE);
}
}
break;
case self::STATE_SKIP_SPACE:
$this->char_index++;
$this->current_word = mb_substr($this->current_word, -1);
break;
case self::STATE_SKIP_LINE:
$this->char_index++;
$this->switchState(self::STATE_ZERO_POINT);
break;
case self::STATE_READ_VALUE:
if ($this->newLine())
{
if ($this->current_directive == self::DIRECTIVE_USERAGENT)
{
if (empty($this->rules[$this->current_word])) {
$this->rules[$this->current_word] = array();
}
$this->userAgent = $this->current_word;
}
elseif ($this->current_directive == self::DIRECTIVE_CRAWL_DELAY)
{
$this->rules[$this->userAgent][$this->current_directive] = (double) $this->current_word;
}
elseif ($this->current_directive == self::DIRECTIVE_SITEMAP) {
$this->rules[$this->userAgent][$this->current_directive][] = $this->current_word;
}
else {
if (!empty($this->current_word)) {
if ($this->current_directive == self::DIRECTIVE_ALLOW
|| $this->current_directive == self::DIRECTIVE_DISALLOW
) {
$this->current_word = "/".ltrim($this->current_word, '/');
}
$this->rules[$this->userAgent][$this->current_directive][] = self::prepareRegexRule($this->current_word);
}
}
$this->current_word = "";
$this->switchState(self::STATE_ZERO_POINT);
}
else {
$this->increment();
}
break;
}
}
/**
* Convert robots.txt rool to php regex
*
* @param string $value
* @return string
*/
protected static function prepareRegexRule($value)
{
$value = str_replace('*', '.*', str_replace('.', '\.', str_replace('?', '\?', str_replace('$', '\$', $value))));
/**
* @link https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
*/
if (mb_strlen($value) > 2 && mb_substr($value, -2) == '\$') {
$value = substr($value, 0, -2).'$';
}
if (mb_strrpos($value, '/') == (mb_strlen($value)-1) ||
mb_strrpos($value, '=') == (mb_strlen($value)-1) ||
mb_strrpos($value, '?') == (mb_strlen($value)-1)
) {
$value .= '.*';
}
return $value;
}
/**
* Common part for the most of the states - skip line and space
*
* @return void
*/
protected function skip()
{
if ($this->space()) {
$this->switchState(self::STATE_SKIP_SPACE);
}
if ($this->sharp() || $this->newLine()) {
$this->switchState(self::STATE_SKIP_LINE);
}
}
/**
* Move to the following step
*
* @return void
*/
protected function increment()
{
$this->current_char = mb_strtolower(mb_substr($this->content, $this->char_index, 1));
$this->current_word .= $this->current_char;
$this->current_word = trim($this->current_word);
$this->char_index++;
}
/**
* Check url wrapper
*
* @param string $url - url to check
* @param string $userAgent - which robot to check for
* @return bool
*/
public function isAllowed($url, $userAgent = "*")
{
return $this->checkRule(self::DIRECTIVE_ALLOW, $url, $userAgent)
&& !$this->checkRule(self::DIRECTIVE_DISALLOW, $url, $userAgent);
}
/**
* Check url wrapper
*
* @param string $url - url to check
* @param string $userAgent - which robot to check for
* @return bool
*/
public function isDisallowed($url, $userAgent = "*")
{
return $this->checkRule(self::DIRECTIVE_DISALLOW, $url, $userAgent);
}
/**
* Check url rules
*
* @param string $rule - which rule to check
* @param string $value - url to check
* @param string $userAgent - which robot to check for
* @internal param string $url - url to check
* @return bool
*/
public function checkRule($rule, $value = '/', $userAgent = '*')
{
$result = false;
// if there is no rule or a set of rules for user-agent
if (!isset($this->rules[$userAgent]) || !isset($this->rules[$userAgent][$rule]))
{
// check 'For all' category - '*'
return ($userAgent != '*') ? $this->checkRule($rule, $value) : false;
}
foreach ($this->rules[$userAgent][$rule] as $robotRule)
{
if (preg_match('@'.preg_quote($robotRule,'@').'@', $value)) {
return true;
}
}
return $result;
}
/**
* Sitemaps check wrapper
*
* @param string $userAgent - which robot to check for
* @return mixed
*/
public function getSitemaps($userAgent = '*')
{
// if there is not rule or a set of rules for UserAgent
if (!isset($this->rules[$userAgent]) || !isset($this->rules[$userAgent][self::DIRECTIVE_SITEMAP]))
{
// check for all
return ($userAgent != '*') ? $this->getSitemaps() : false;
}
return $this->rules[$userAgent][self::DIRECTIVE_SITEMAP];
}
}
?>