小说站-维护-清理无效小说存储 1.清理指定id的小说所有内容DROP PROCEDURE IF EXISTS clear_invalid_novel; CREATE PROCEDURE clear_invalid_novel() BEGIN DECLARE bookid varchar(255) DEFAULT '1431094810327994368'; DELETE FROM book_content WHERE index_id in (SELECT id FROM book_index WHERE book_id=bookid); DELETE FROM book_content0 WHERE index_id in (SELECT id FROM book_index WHERE book_id=bookid); DELETE FROM book_content1 WHERE index_id in (SELECT id FROM book_index WHERE book_id=bookid); DELETE FROM book_content2 WHERE index_id in (SELECT id FROM book_index WHERE book_id=bookid); DELETE FROM book_content3 WHERE index_id in (SELECT id FROM book_index WHERE book_id=bookid); DELETE FROM book_content4 WHERE index_id in (SELECT id FROM book_index WHERE book_id=bookid); DELETE FROM book_content5 WHERE index_id in (SELECT id FROM book_index WHERE book_id=bookid); DELETE FROM book_content6 WHERE index_id in (SELECT id FROM book_index WHERE book_id=bookid); DELETE FROM book_content7 WHERE index_id in (SELECT id FROM book_index WHERE book_id=bookid); DELETE FROM book_content8 WHERE index_id in (SELECT id FROM book_index WHERE book_id=bookid); DELETE FROM book_content9 WHERE index_id in (SELECT id FROM book_index WHERE book_id=bookid); DELETE FROM book_index WHERE book_id=bookid; DELETE FROM book WHERE id=bookid; END; call clear_invalid_novel();2.删除无效的小说文本delete from book_content where index_id not in(SELECT id from book_index); delete from book_content0 where index_id not in(SELECT id from book_index); delete from book_content1 where index_id not in(SELECT id from book_index); delete from book_content2 where index_id not in(SELECT id from book_index); delete from book_content3 where index_id not in(SELECT id from book_index); delete from book_content4 where index_id not in(SELECT id from book_index); delete from book_content5 where index_id not in(SELECT id from book_index); delete from book_content6 where index_id not in(SELECT id from book_index); delete from book_content7 where index_id not in(SELECT id from book_index); delete from book_content8 where index_id not in(SELECT id from book_index); delete from book_content9 where index_id not in(SELECT id from book_index);3.整合表内容create table book_content_test as SELECT id, index_id,content from ( SELECT * FROM book_content0 B0 WHERE B0.index_id in (SELECT id FROM book_index WHERE book_id='1431142380391714816') union all SELECT * FROM book_content1 B1 WHERE B1.index_id in (SELECT id FROM book_index WHERE book_id='1431142380391714816') union all SELECT * FROM book_content2 B2 WHERE B2.index_id in (SELECT id FROM book_index WHERE book_id='1431142380391714816') union all SELECT * FROM book_content3 B3 WHERE B3.index_id in (SELECT id FROM book_index WHERE book_id='1431142380391714816') union all SELECT * FROM book_content4 B4 WHERE B4.index_id in (SELECT id FROM book_index WHERE book_id='1431142380391714816') union all SELECT * FROM book_content5 B5 WHERE B5.index_id in (SELECT id FROM book_index WHERE book_id='1431142380391714816') union all SELECT * FROM book_content6 B6 WHERE B6.index_id in (SELECT id FROM book_index WHERE book_id='1431142380391714816') union all SELECT * FROM book_content7 B7 WHERE B7.index_id in (SELECT id FROM book_index WHERE book_id='1431142380391714816') union all SELECT * FROM book_content8 B8 WHERE B8.index_id in (SELECT id FROM book_index WHERE book_id='1431142380391714816') union all SELECT * FROM book_content9 B9 WHERE B9.index_id in (SELECT id FROM book_index WHERE book_id='1431142380391714816') ) as T1;

小说站 笔趣阁U INSERT INTO `crawl_source` ( `id`, `source_name`, `crawl_rule`, `source_status`, `create_time`, `update_time` ) VALUES ( 11, '笔趣阁U', '{\n \"bookListUrl\": \"http://m.biqugeu.com/book/lhb/{catId}/{page}.html\",\n \"catIdRule\": {\n \"catId1\": \"1\",\n \"catId2\": \"2\",\n \"catId3\": \"3\",\n \"catId4\": \"4\",\n \"catId5\": \"5\",\n \"catId6\": \"6\",\n \"catId7\": \"7\"\n },\n \"bookIdPatten\": \"href=\\\"/book/(\\\\d+)/\\\"\",\n \"pagePatten\": \"value=\\\"(\\\\d+)/\\\\d+\\\"\",\n \"totalPagePatten\": \"value=\\\"\\\\d+/(\\\\d+)\\\"\",\n \"bookDetailUrl\": \"http://m.biqugeu.com/book/{bookId}/\",\n \"bookNamePatten\": \"<span\\\\s+class=\\\"title\\\"\\\\s+id=\\\"sw\\\">([^/]+)</span>\",\n \"authorNamePatten\": \"<li\\\\s+class=\\\"author\\\">作者：([^/]+)</li>\",\n \"picUrlPatten\": \"<img src=\\\"([^>]+)\\\"\\\\s+onerror=\\\"this.src=\",\n \"statusPatten\": \"状态：([^/]+)</li>\",\n \"bookStatusRule\": {\n \"连载\": 0,\n \"完成\": 1\n },\n \"scorePatten\": \"<em>(\\\\d+\\\\.\\\\d+)</em>\",\n \"descStart\": \"<p class=\\\"review\\\">\",\n \"descEnd\": \"</p>\",\n \"upadateTimePatten\": \"更新：(\\\\d+-\\\\d+-\\\\d+\\\\s+\\\\d+:\\\\d+:\\\\d+)</a>\",\n \"upadateTimeFormatPatten\": \"yyyy-MM-dd HH:mm:ss\",\n \"bookIndexUrl\": \"http://m.biqugeu.com/book/{bookId}/all.html\",\n \"indexIdPatten\": \"<a\\\\s+style=\\\"\\\"\\\\s+href=\\\"/book/\\\\d+/(\\\\d+)\\\\.html\\\">[^/]+</a>\",\n \"indexNamePatten\": \"<a\\\\s+style=\\\"\\\"\\\\s+href=\\\"/book/\\\\d+/\\\\d+\\\\.html\\\">([^/]+)</a>\",\n \"bookContentUrl\": \"http://www.biqugeu.com/{cal_1_1_3}_{bookId}/{indexId}.html\",\n \"contentStart\": \"id=\\\"content\\\">\",\n \"contentEnd\": \"<script>\"\n}', 0, '2020-12-10 18:04:33', '2020-12-10 18:04:33' );顶点小说网INSERT INTO `crawl_source` ( `id`, `source_name`, `crawl_rule`, `source_status`, `create_time`, `update_time` ) VALUES ( 14, '顶点小说网', '{\"bookListUrl\":\"http://m.xdingdiann.com/sort/{catId}/{page}.html\",\"catIdRule\":{\"catId1\":\"1\",\"catId2\":\"2\",\"catId3\":\"3\",\"catId4\":\"4\",\"catId5\":\"5\",\"catId6\":\"6\",\"catId7\":\"7\"},\"bookIdPatten\":\"href=\\\"/ddk(\\\\d+)/\\\"\",\"pagePatten\":\"value=\\\"(\\\\d+)/\\\\d+\\\"\",\"totalPagePatten\":\"value=\\\"\\\\d+/(\\\\d+)\\\"\",\"bookDetailUrl\":\"http://m.xdingdiann.com/ddk{bookId}/\",\"bookNamePatten\":\"<span class=\\\"title\\\">([^/]+)</span>\",\"authorNamePatten\":\"作者：([^/]+)<\",\"picUrlPatten\":\"<img src=\\\"([^>]+)\\\"\\\\s+onerror=\\\"this.src=\",\"statusPatten\":\"状态：([^/]+)</li>\",\"bookStatusRule\":{\"连载\":0,\"完成\":1},\"scorePatten\":\"<em>(\\\\d+\\\\.\\\\d+)</em>\",\"descStart\":\"<p class=\\\"review\\\">\",\"descEnd\":\"</p>\",\"bookIndexUrl\":\"http://m.xdingdiann.com/ddk{bookId}/all.html\",\"indexIdPatten\":\"<a\\\\s+style=\\\"\\\"\\\\s+href=\\\"/ddk\\\\d+/(\\\\d+)\\\\.html\\\">[^/]+</a>\",\"indexNamePatten\":\"<a\\\\s+style=\\\"\\\"\\\\s+href=\\\"/ddk\\\\d+/\\\\d+\\\\.html\\\">([^/]+)</a>\",\"bookContentUrl\":\"http://www.xdingdiann.com/ddk{bookId}/{indexId}.html\",\"contentStart\":\"id=\\\"content\\\">\",\"contentEnd\":\"<script>\"}', 1, '2021-01-03 19:39:29', '2021-01-03 19:39:29' );