Fork of Potentially extraneous homepage links (dewiki <= M) by HaeB
This query is marked as a draft This query has been published by HaeB.

SQL

AخA
 
USE dewiki_p; SET @language = 'de';
WITH externallinksforhumans AS (
  SELECT 
    el_from,
    # https://quarry.wmcloud.org/query/77235 :
    REGEXP_REPLACE(el_to_domain_index,
       '^(.*?://)(?:([^.]+)\\.)([^.]+\\.)?([^.]+\\.)?([^.]+\\.)?([^.]+\\.)?([^.]+\\.)?([^.]+\\.)?([^.]+\\.)$',
                             '\\1\\9\\8\\7\\6\\5\\4\\3\\2/') AS rooturl,
    el_to_path
  FROM externallinks)
SELECT 
  CONCAT('https://', @language , '.wikipedia.org/wiki/' ,page_title, '?action=edit&veswitched=1#:~:text=', rooturl) AS page_edit_link, 
  # try to highlight homepage URL in source wikitext
  rooturl,
  url,
  SUM(IF( url=rooturl, 1, 0) ) AS rootlinks,
  SUM(1) AS alllinks
FROM (
  SELECT
    page_title,
    CONCAT(rooturl,SUBSTRING(el_to_path,1)) AS url,
    rooturl
  FROM externallinksforhumans, page
  WHERE el_from = page_id
  AND page_namespace = 0
  # restrict query to a subset of articles for performance reasons:
  AND LEFT(page_title, 1) = 'N'
  )  AS pagelinks
GROUP BY page_title, rooturl
LIMIT 200
By running queries you agree to the Cloud Services Terms of Use and you irrevocably agree to release your SQL under CC0 License.
All SQL code is licensed under CC0 License.

Checking query status...