Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- CREATE TABLE IF NOT EXISTS `links` (
- `link_id` int(10) unsigned NOT NULL,
- `domain_id` mediumint(7) unsigned NOT NULL,
- `parent_id` int(11) unsigned DEFAULT NULL,
- `hash` int(10) unsigned NOT NULL,
- `url` text NOT NULL,
- `type` enum('html','pdf') DEFAULT NULL,
- `processed` enum('N','Y') NOT NULL DEFAULT 'N',
- UNIQUE KEY `hash` (`hash`),
- KEY `idx_processed` (`processed`),
- KEY `domain_id` (`domain_id`)
- ) ENGINE=MyISAM DEFAULT CHARSET=utf8 ROW_FORMAT=COMPACT;
- CREATE TABLE IF NOT EXISTS `domains` (
- `domain_id` mediumint(7) unsigned NOT NULL AUTO_INCREMENT,
- `name` varchar(170) NOT NULL,
- `blocked` enum('N','Y') NOT NULL DEFAULT 'N',
- `count` mediumint(6) NOT NULL DEFAULT '0',
- `mcount` mediumint(3) NOT NULL,
- PRIMARY KEY (`domain_id`),
- KEY `name` (`name`),
- KEY `blocked` (`blocked`),
- KEY `mcount` (`mcount`),
- KEY `count` (`count`)
- ) ENGINE=MyISAM DEFAULT CHARSET=utf8 AUTO_INCREMENT=10834389 ;
- (SELECT link_id, url, hash FROM links, domains WHERE links.domain_id = domains.domain_id and mcount > 1 and processed='N' limit 200)
- UNION
- (SELECT link_id, url, hash FROM links where processed='N' and type='html' limit 200)
- | id | select_type | table | type | possible_keys | key | key_len | ref | rows | Extra |
- +----+--------------+------------+-------+-------------------------+--------------- +---------+---------------------------+---------+-------------+
- | 1 | PRIMARY | domains | range | PRIMARY,mcount | mcount | 3 | NULL | 257673 | Using where |
- | 1 | PRIMARY | links | ref | idx_processed,domain_id | domain_id | 3 | crawler.domains.domain_id | 1 | Using where |
- | 2 | UNION | links | ref | idx_processed | idx_processed | 1 | const | 7090017 | Using where |
- | NULL | UNION RESULT | <union1,2> | ALL | NULL | NULL | NULL | NULL | NULL | |
- +----+--------------+------------+-------+-------------------------+---------------+---------+---------------------------+---------+-------------+
- SELECT link_id, url, hash
- FROM links, domains
- WHERE links.domain_id = domains.domain_id
- AND mcount > 1
- AND processed='N'
- AND type='html'
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement