【python】提取sql语句中的表名

前言

最近刚学python，写一个小工具时需要提取sql语句中表名，查询一番后找到一篇文章挺不错的，mark一下

PS.那篇文章是转载的，且没有标注转载自哪里

正文

import ply.lex as lex, re

def extract_table_name_from_sql(sql_str):

    # 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 = []
    get_next = False
    for token in tokens:
        if get_next:
            if token.lower() not in ["", "select"]:
                result.append(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))