| Total Complexity | 55 |
| Total Lines | 328 |
| Duplicated Lines | 0 % |
| Changes | 2 | ||
| Bugs | 1 | Features | 1 |
Complex classes like CrawlerConfig 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 CrawlerConfig, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 10 | class CrawlerConfig |
||
| 11 | { |
||
| 12 | /** |
||
| 13 | * @var string contain the user agent used during the crawl |
||
| 14 | */ |
||
| 15 | protected $userAgent; |
||
| 16 | |||
| 17 | /** |
||
| 18 | * @var string crawl id |
||
| 19 | */ |
||
| 20 | protected $id; |
||
| 21 | |||
| 22 | /** |
||
| 23 | * @var string page to ignore during the crawl |
||
| 24 | */ |
||
| 25 | protected $ignore; |
||
| 26 | |||
| 27 | /** |
||
| 28 | * @var int depth max where to crawl |
||
| 29 | */ |
||
| 30 | protected $limit; |
||
| 31 | |||
| 32 | /** |
||
| 33 | * @var string contain https://domain.tdl from start url |
||
| 34 | */ |
||
| 35 | protected $base; |
||
| 36 | |||
| 37 | /** |
||
| 38 | * @var int |
||
| 39 | */ |
||
| 40 | protected $wait; |
||
| 41 | |||
| 42 | /** |
||
| 43 | * @var int |
||
| 44 | */ |
||
| 45 | protected $cacheMethod; |
||
| 46 | |||
| 47 | /** |
||
| 48 | * @var string |
||
| 49 | */ |
||
| 50 | protected $dataDirectory; |
||
| 51 | |||
| 52 | /** |
||
| 53 | * @var string |
||
| 54 | */ |
||
| 55 | protected $startUrl; |
||
| 56 | |||
| 57 | protected $request; |
||
| 58 | protected $robotsTxt; |
||
| 59 | |||
| 60 | /** @var Recorder */ |
||
| 61 | protected $recorder; |
||
| 62 | |||
| 63 | public function __construct( |
||
| 81 | } |
||
| 82 | |||
| 83 | /** |
||
| 84 | * @return string id |
||
| 85 | */ |
||
| 86 | public static function getLastCrawl(string $dataDirectory): string |
||
| 87 | { |
||
| 88 | $dir = scandir($dataDirectory); |
||
| 89 | $lastCrawl = null; |
||
| 90 | $lastRunAt = null; |
||
| 91 | |||
| 92 | foreach ($dir as $file) { |
||
| 93 | if ('.' != $file && '..' != $file |
||
| 94 | && is_dir($dataDirectory.'/'.$file) |
||
| 95 | && filemtime($dataDirectory.'/'.$file) > $lastRunAt) { |
||
| 96 | $lastCrawl = $file; |
||
| 97 | $lastRunAt = filemtime($dataDirectory.'/'.$file); |
||
| 98 | } |
||
| 99 | } |
||
| 100 | |||
| 101 | if (null === $lastCrawl) { |
||
| 102 | throw new \Exception('No crawl previously runned'); |
||
| 103 | } |
||
| 104 | |||
| 105 | return $lastCrawl; |
||
| 106 | } |
||
| 107 | |||
| 108 | public static function loadFrom(string $crawlId, ?string $dataDirectory = null): self |
||
| 109 | { |
||
| 110 | if ('last' === $crawlId) { |
||
| 111 | $crawlId = self::getLastCrawl(rtrim(self::getDataFolderFrom('', $dataDirectory), '/')); |
||
| 112 | } |
||
| 113 | |||
| 114 | $configFilePath = self::getDataFolderFrom($crawlId, $dataDirectory).'/config.json'; |
||
| 115 | if (! file_exists($configFilePath)) { |
||
| 116 | throw new \Exception('Crawl `'.$crawlId.'` not found.'); |
||
| 117 | } |
||
| 118 | $config = json_decode(file_get_contents($configFilePath), true); |
||
| 119 | |||
| 120 | return (new self( |
||
| 121 | $config['base'].$config['startUrl'], |
||
| 122 | $config['ignore'], |
||
| 123 | intval($config['limit']), |
||
| 124 | (string) $config['userAgent'], |
||
| 125 | intval($config['cacheMethod']), |
||
| 126 | intval($config['wait']), |
||
| 127 | $dataDirectory |
||
| 128 | ))->setId($crawlId); |
||
| 129 | } |
||
| 130 | |||
| 131 | public function recordConfig() |
||
| 132 | { |
||
| 133 | $this->getRecorder(); // permit to create folder |
||
| 134 | file_put_contents($this->getDataFolder().'/config.json', json_encode([ |
||
| 135 | 'startUrl' => $this->startUrl, |
||
| 136 | 'base' => $this->base, |
||
| 137 | 'ignore' => $this->ignore, |
||
| 138 | 'limit' => $this->limit, |
||
| 139 | 'userAgent' => $this->userAgent, |
||
| 140 | 'cacheMethod' => $this->cacheMethod, |
||
| 141 | 'wait' => $this->wait, |
||
| 142 | ])); |
||
| 143 | } |
||
| 144 | |||
| 145 | protected function setBaseAndStartUrl(string $url) |
||
| 146 | { |
||
| 147 | if (! filter_var($url, FILTER_VALIDATE_URL)) { |
||
| 148 | throw new \Exception('start is not a valid URL `'.$url.'`'); |
||
| 149 | } |
||
| 150 | |||
| 151 | $this->base = preg_match('@^(http://|https://)?[^/\?#]+@', $url, $match) ? $match[0] : $url; |
||
| 152 | |||
| 153 | $url = substr($url, strlen($this->base)); |
||
| 154 | |||
| 155 | $this->startUrl = (! isset($url[0]) || '/' != $url[0] ? '/' : '').$url; |
||
| 156 | } |
||
| 157 | |||
| 158 | public static function getDataFolderFrom(string $id, ?string $path) |
||
| 159 | { |
||
| 160 | return ($path ?? __DIR__.'/../data').'/'.$id; |
||
| 161 | } |
||
| 162 | |||
| 163 | public function getDataFolder() |
||
| 164 | { |
||
| 165 | return $this->dataDirectory.'/'.$this->id; |
||
| 166 | } |
||
| 167 | |||
| 168 | public function getId() |
||
| 169 | { |
||
| 170 | return $this->id; |
||
| 171 | } |
||
| 172 | |||
| 173 | public function getBase() |
||
| 174 | { |
||
| 175 | return $this->base; |
||
| 176 | } |
||
| 177 | |||
| 178 | public function getStartUrl() |
||
| 181 | } |
||
| 182 | |||
| 183 | public function getWait() |
||
| 184 | { |
||
| 185 | return $this->wait; |
||
| 186 | } |
||
| 187 | |||
| 188 | public function getUserAgent() |
||
| 189 | { |
||
| 190 | return $this->userAgent; |
||
| 191 | } |
||
| 192 | |||
| 193 | public function getLimit() |
||
| 194 | { |
||
| 195 | return $this->limit; |
||
| 196 | } |
||
| 197 | |||
| 198 | public function getCacheMethod() |
||
| 199 | { |
||
| 200 | return $this->cacheMethod; |
||
| 201 | } |
||
| 202 | |||
| 203 | public function getDataDirectory() |
||
| 204 | { |
||
| 205 | $this->dataDirectory; |
||
| 206 | } |
||
| 207 | |||
| 208 | /** @var RobotsTxt */ |
||
| 209 | protected $virtualRobots; |
||
| 210 | |||
| 211 | public function getVirtualRobots() |
||
| 218 | } |
||
| 219 | |||
| 220 | public function setId(string $id): self |
||
| 221 | { |
||
| 225 | } |
||
| 226 | |||
| 227 | public function getDataFromPreviousCrawl() |
||
| 228 | { |
||
| 229 | $dataFilePath = $this->getDataFolder().'/data.csv'; |
||
| 230 | if (! file_exists($dataFilePath)) { |
||
| 231 | throw new \Exception('Previous crawl\'s data not found (index.csv)'); |
||
| 232 | } |
||
| 233 | |||
| 234 | $urls = []; |
||
| 235 | $counter = 0; |
||
| 236 | |||
| 237 | $csv = Reader::createFromPath($dataFilePath, 'r'); |
||
| 238 | $csv->setHeaderOffset(0); |
||
| 239 | |||
| 240 | $records = $csv->getRecords(); |
||
| 241 | foreach ($records as $r) { |
||
| 242 | $urls[$r['uri']] = new Url($this->base.$r['uri'], 0); |
||
| 243 | if (isset($r['can_be_crawled']) && ! empty($r['can_be_crawled']) |
||
| 244 | && Indexable::NOT_INDEXABLE_NETWORK_ERROR != $r['indexable'] // we will retry network errror |
||
| 245 | ) { |
||
| 246 | foreach ($r as $k => $v) { |
||
| 247 | $kFunction = 'set'.self::camelize($k); |
||
| 248 | $urls[$r['uri']]->$kFunction($v); |
||
| 249 | } |
||
| 250 | ++$counter; |
||
| 251 | } |
||
| 252 | } |
||
| 253 | |||
| 254 | $currentClick = $r['click'] ?? 0; |
||
| 255 | |||
| 256 | return [ |
||
| 257 | 'urls' => $urls, |
||
| 258 | 'counter' => $counter, |
||
| 259 | 'currentClick' => $currentClick, |
||
| 260 | ]; |
||
| 261 | } |
||
| 262 | |||
| 263 | protected static function camelize($input) |
||
| 264 | { |
||
| 265 | return ucfirst(str_replace('_', '', ucwords($input, '_'))); |
||
| 266 | } |
||
| 267 | |||
| 268 | // could be add in an other class.. |
||
| 269 | protected $index; |
||
| 270 | |||
| 271 | protected function getIndexFromPreviousCrawl() |
||
| 272 | { |
||
| 273 | if (null !== $this->index) { |
||
| 274 | return $this->index; |
||
| 275 | } |
||
| 276 | |||
| 277 | $this->index = []; |
||
| 278 | |||
| 279 | $indexFilePath = $this->getDataFolder().'/index.csv'; |
||
| 280 | if (! file_exists($indexFilePath)) { |
||
| 281 | throw new \Exception('Previous crawl\'s data not found (index.csv)'); |
||
| 282 | } |
||
| 283 | |||
| 284 | $csv = Reader::createFromPath($indexFilePath, 'r'); |
||
| 285 | $csv->setHeaderOffset(0); |
||
| 286 | |||
| 287 | $records = $csv->getRecords(); |
||
| 288 | foreach ($records as $r) { |
||
| 289 | $this->index[$r['id']] = new Url($this->base.$r['uri'], 0); |
||
| 290 | $this->index[$r['id']]->id = $r['id']; |
||
| 291 | } |
||
| 292 | |||
| 293 | return $this->index; |
||
| 294 | } |
||
| 295 | |||
| 296 | public function getUrlFromId($id, $base = true) |
||
| 301 | } |
||
| 302 | |||
| 303 | public function cacheRequest($harvest) |
||
| 310 | } |
||
| 311 | |||
| 312 | public function getRequestCached() |
||
| 315 | } |
||
| 316 | |||
| 317 | public function cacheRobotsTxt($harvest) |
||
| 318 | { |
||
| 319 | if (null === $this->robotsTxt && $harvest instanceof Harvest) { |
||
| 320 | $this->robotsTxt = $harvest->getRobotsTxt(); |
||
| 321 | } |
||
| 322 | |||
| 323 | return $this; |
||
| 324 | } |
||
| 325 | |||
| 326 | public function getRobotsTxtCached() |
||
| 329 | } |
||
| 330 | |||
| 331 | public function getRecorder() |
||
| 340 |