{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T05:46:20Z","timestamp":1725515180507},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,11]]},"DOI":"10.1109\/dbta.2010.5659105","type":"proceedings-article","created":{"date-parts":[[2010,12,11]],"date-time":"2010-12-11T08:53:44Z","timestamp":1292057624000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Analysis of Duplicated Web Pages Identification Methods in Search Engine"],"prefix":"10.1109","author":[{"given":"Fei","family":"Duan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"BloomFilter Technical Report","year":"0","key":"ref10"},{"key":"ref11","first-page":"95","article-title":"The study of the strategy of duplicated web pages' removing in large scale web pages based on BloomFilter","author":"ding","year":"2008"},{"journal-title":"Google MapReduce\/GFS\/BigTable","year":"0","key":"ref12"},{"article-title":"Hadoop: the definitive guide","year":"2010","author":"white","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LAWEB.2003.1250280"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/584792.584835"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335429"},{"key":"ref17","first-page":"1579","article-title":"Minor, minor on the web: a study of host pairs with replicated content","author":"krishma","year":"1999","journal-title":"Proceedings of the Eighth International World Wide Web Conference"},{"key":"ref4","article-title":"Method for determining the resemblance of documents","author":"broder","year":"1999","journal-title":"Sci"},{"key":"ref3","article-title":"Hashing comparison in web crawling","author":"lihui","year":"2006","journal-title":"Journal of Chinese Computer Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/226931.226961"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/236452.236525"},{"key":"ref8","first-page":"21","article-title":"SCAM: A copy detection mechanism for digital documents","author":"shivakumar","year":"1995","journal-title":"Processing of 2 International Conference in Theory and Practice of Digital Libraries(DL'95)"},{"key":"ref7","first-page":"51","article-title":"Scalable document fingerprinting","author":"heintze","year":"1996","journal-title":"Proc 2nd Usenix Workshop Electron Commerce"},{"journal-title":"The Introduction of DOM (in Chinese)","year":"0","key":"ref2"},{"journal-title":"Sixteenth Status Report of China Internet Development","year":"2005","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/331697.335176"}],"event":{"name":"2010 2nd International Workshop on Database Technology and Applications (DBTA)","start":{"date-parts":[[2010,11,27]]},"location":"Wuhan, China","end":{"date-parts":[[2010,11,28]]}},"container-title":["2010 2nd International Workshop on Database Technology and Applications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5658186\/5658597\/05659105.pdf?arnumber=5659105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,21]],"date-time":"2017-03-21T06:51:41Z","timestamp":1490079101000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5659105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,11]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/dbta.2010.5659105","relation":{},"subject":[],"published":{"date-parts":[[2010,11]]}}}