Testing - Quarry

SQL

USE euwiki_p;
        -- Extract all (page_id, domain) tuples.
        SELECT
            el_from AS page_id,
            el_to,
            REGEXP_REPLACE(el_to, '^(?:[^:/]+:)?//(\\w+\\.(?:\\w+\\.)\\w+)(?:[/:?].*)?$', '\\1'),
            SUBSTRING_INDEX(SUBSTRING_INDEX(SUBSTRING_INDEX(SUBSTRING_INDEX(SUBSTRING_INDEX(
            CAST(el_to AS CHAR(1000) CHARACTER SET utf8),
            '/', 3), '://', -1), '/', 1), '?', 1), ':', 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:]].*'
      	LIMIT 100;
SQL

Checking query status...
