Untitled query #26249

SQL

USE enwiki_p;
SELECT
              el_from AS page_id,
              REGEXP_REPLACE(LOWER(CONVERT(SUBSTRING(el_to FROM 1 FOR 255) USING utf8)),  '^(?:[^:/]+:)?//((?:[-_0-9a-z]+\\.)+[a-z]+)(?:[/:?].*)?$', '\\1') AS domain
          FROM externallinks
          WHERE
              -- Only links from main namespace articles.
              el_from_namespace = 0
			  -- Only http, https, implicit https (//) and ftp. el_index is already lowercase.
			  AND (el_index LIKE 'http://%' OR el_index LIKE 'https://%' OR el_index LIKE '//%' OR el_index LIKE 'ftp://%')
			  -- Get only fairly well-formed URLs and exclude IPv4.
			  AND SUBSTRING(el_to FROM 1 FOR 40) REGEXP '(?i)^(?:https?:|ftp:)?//(?:[-_0-9A-Za-z]+\\.)+[A-Za-z]+(?:[/:?].*)?$'
LIMIT 100;
SQL

Checking query status...
