Integrate projects
Make both projects use the same items.py, the original should be from the littlecrawler project
Both projects should output to a single folder the JSON/CSV files required.
Add filtering of HTML elements in the scraped data.
Both projects should use the same pipelines and settings.
SHOW FULL COLUMNS FROM `jrk_downrecords` [ RunTime:0.000952s ]
SELECT `a`.`aid`,`a`.`title`,`a`.`create_time`,`m`.`username` FROM `jrk_downrecords` `a` INNER JOIN `jrk_member` `m` ON `a`.`uid`=`m`.`id` WHERE `a`.`status` = 1 GROUP BY `a`.`aid` ORDER BY `a`.`create_time` DESC LIMIT 10 [ RunTime:0.072402s ]
SHOW FULL COLUMNS FROM `jrk_tagrecords` [ RunTime:0.000894s ]
SELECT * FROM `jrk_tagrecords` WHERE `status` = 1 ORDER BY `num` DESC LIMIT 20 [ RunTime:0.001167s ]
SHOW FULL COLUMNS FROM `jrk_member` [ RunTime:0.000976s ]
SELECT `id`,`username`,`userhead`,`usertime` FROM `jrk_member` WHERE `status` = 1 ORDER BY `usertime` DESC LIMIT 10 [ RunTime:0.003179s ]
SHOW FULL COLUMNS FROM `jrk_searchrecords` [ RunTime:0.001062s ]
SELECT * FROM `jrk_searchrecords` WHERE `status` = 1 ORDER BY `num` DESC LIMIT 5 [ RunTime:0.003798s ]
SELECT aid,title,count(aid) as c FROM `jrk_downrecords` GROUP BY `aid` ORDER BY `c` DESC LIMIT 10 [ RunTime:0.014620s ]
SHOW FULL COLUMNS FROM `jrk_articles` [ RunTime:0.001219s ]
UPDATE `jrk_articles` SET `hits` = 2 WHERE `id` = 196101 [ RunTime:0.018737s ]
