-- Query to find the longest pages in Wikipedia MAINSPACE ONLY

-- This query sorts pages by length in mainspace (namespace 0) and shows the full URL

-- Run this on the 'enwiki_p' database in Quarry

SELECT

  CONCAT('https://en.wikipedia.org/wiki/', 

    REPLACE(page_title, ' ', '_')

  ) AS Full_URL,

  page_len AS Length_in_Bytes

FROM page

WHERE page_namespace = 0      -- ONLY mainspace articles

  AND page_is_redirect = 0    -- Exclude redirects

  AND page_len > 0            -- Only pages with content

ORDER BY page_len DESC        -- Sort by descending length

LIMIT 100;                    -- Show top 100 results