# remove the /* */ comments q = re . sub ( r"/\*[^*]*\*+(?:[^*/][^*]*\*+)*/" , "" , sql_str ) # remove whole line -- and # comments lines = [ line for line in q . splitlines ( ) if not re . match ( "^\s*(--|#)" , line ) ] # remove trailing -- and # comments q = " " . join ( [ re . split ( "--|#" , line ) [ 0 ] for line in lines ] ) # split on blanks, parens and semicolons tokens = re . split ( r"[\s)(;]+" , q ) # scan the tokens. if we see a FROM or JOIN, we set the get_next # flag, and grab the next one (unless it's SELECT). result = set ( ) get_next = False for token in tokens : if get_next : if token . lower ( ) not in [ "" , "select" ] : result . add ( token ) get_next = False get_next = token . lower ( ) in [ "from" , "join" ] return result sql2 = "SELECT a.time_updated_server/1000,content,nick,name FROM " \ "table1 a JOIN " \ "table2 b ON a.sender_id = b.user_id JOIN table3 c ON a.channel_id = c.channel_id JOIN table4 d ON c.store_id = d.store_id WHERE sender_id NOT IN(SELECT user_id FROM table5 WHERE store_id IN ('agent_store:1', 'ask:1')) AND to_timestamp(a.time_updated_server/1000)::date >= '2014-05-01' GROUP BY 1,2,3,4 HAVING sum(1) > 500 ORDER BY 1 ASC" print ( extract_table_name_from_sql ( sql2 ) )

本文转自：
https://blog.csdn.net/onwingsofsong/article/details/83546768?utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7EBlogCommendFromMachineLearnPai2%7Edefault-7.control&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7EBlogCommendFromMachineLearnPai2%7Edefault-7.control