Browse Source

fix robots.txt conditions

main
ghost 2 years ago
parent
commit
eb3e70a7b7
  1. 2
      crontab/cleaner.php
  2. 2
      crontab/crawler.php

2
crontab/cleaner.php

@ -57,7 +57,7 @@ foreach ($db->getCleanerQueue(CLEAN_HOST_LIMIT, time() - CLEAN_HOST_SECONDS_OFFS @@ -57,7 +57,7 @@ foreach ($db->getCleanerQueue(CLEAN_HOST_LIMIT, time() - CLEAN_HOST_SECONDS_OFFS
}
// Apply new robots.txt rules
$robots = new Robots((!$hostRobots ? (string) $hostRobots : (string) CRAWL_ROBOTS_DEFAULT_RULES) . PHP_EOL . ($host->robotsPostfix ? (string) $host->robotsPostfix : (string) CRAWL_ROBOTS_POSTFIX_RULES));
$robots = new Robots(($hostRobots ? (string) $hostRobots : (string) CRAWL_ROBOTS_DEFAULT_RULES) . PHP_EOL . ($host->robotsPostfix ? (string) $host->robotsPostfix : (string) CRAWL_ROBOTS_POSTFIX_RULES));
foreach ($db->getHostPages($host->hostId) as $hostPage) {

2
crontab/crawler.php

@ -218,7 +218,7 @@ foreach ($db->getCrawlQueue(CRAWL_PAGE_LIMIT, time() - CRAWL_PAGE_SECONDS_OFFSET @@ -218,7 +218,7 @@ foreach ($db->getCrawlQueue(CRAWL_PAGE_LIMIT, time() - CRAWL_PAGE_SECONDS_OFFSET
}
// Init robots parser
$robots = new Robots((!$hostRobots ? (string) $hostRobots : (string) CRAWL_ROBOTS_DEFAULT_RULES) . PHP_EOL . (string) $hostRobotsPostfix);
$robots = new Robots(($hostRobots ? (string) $hostRobots : (string) CRAWL_ROBOTS_DEFAULT_RULES) . PHP_EOL . ($hostRobotsPostfix ? (string) $hostRobotsPostfix : (string) CRAWL_ROBOTS_POSTFIX_RULES));
// Save page info
if ($hostStatus && // host enabled

Loading…
Cancel
Save