Testing - Quarry

SQL

USE euwiki_p;
USE euwiki_p;

    -- Extract all (page_id, main_domain) tuples
	SELECT
		page_id,
    	-- Extract main_domain from domain.
    	-- Examples:
    	--   news.bbc.com -> bbc.com
    	--   news.bbc.co.uk -> bbc.co.uk
    	IF(domain REGEXP '^.*[-\\w]{4,}\\.[[:alpha:]]{2,}$',
           SUBSTRING_INDEX(domain, '.', -2),
           IF(domain REGEXP '^.*\\.(ac|edu|org|or|com|co|net|gov|go)\\.[[:alpha:]]{2,}$',
              SUBSTRING_INDEX(domain, '.', -3),
              IF(domain REGEXP '.*\\.[[:alpha:]]{2}\\.(us|ca|za)$',
                 SUBSTRING_INDEX(domain, '.', -3),
                 SUBSTRING_INDEX(domain, '.', -2)
                ))) AS main_domain
    FROM (
        -- Extract all (page_id, domain) tuples.
        SELECT
            el_from AS page_id,
            REGEXP_REPLACE(el_to, '^(?:[^:/]+:)?//((?:[_0-9A-Za-z]+\\.)+[_0-9A-Za-z]+)(?:[/:?].*)?$', '\\1') AS domain
        FROM externallinks
        WHERE
            -- Only links from main namespace articles.
            el_from_namespace = 0
            -- Get only fairly well-formed URLs for http and https (or implicit https?) and exclude IPv4.
            AND el_to REGEXP '^(https?:)?//[[:alnum:]]+\\..*[[:alpha:]].*'
    ) AS q
	LIMIT 100;
SQL

Checking query status...
