{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T10:49:59Z","timestamp":1730285399832,"version":"3.28.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1109\/nextcomp.2019.8883665","type":"proceedings-article","created":{"date-parts":[[2019,10,29]],"date-time":"2019-10-29T00:25:08Z","timestamp":1572308708000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Categorising AWS Common Crawl Dataset using MapReduce"],"prefix":"10.1109","author":[{"given":"Aatish","family":"Chiniah","sequence":"first","affiliation":[]},{"given":"Ayaz","family":"Chummun","sequence":"additional","affiliation":[]},{"given":"Zaid","family":"Burkutally","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"19","article-title":"Resource Optimization in Automatic Web Page Classification using Integrated Feature Selection and Machine Learning","volume":"1","author":"mahadevan","year":"2013","journal-title":"International Arab Journal of E-Technology"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45490-X_36"},{"article-title":"Pakistan&#x2019;s Internet Landscape. A Report by Bytes for All, Pakistan","year":"2013","author":"haque","key":"ref12"},{"year":"2017","key":"ref13","article-title":"The Moo Web Directory - Human Edited Website and Business Directory now offering Website Reviews"},{"year":"2019","key":"ref14","article-title":"Web Filter Lookup"},{"year":"2018","key":"ref15","article-title":"Alexa - Top sites"},{"key":"ref4","article-title":"Structure of URL","author":"znurl","year":"2017","journal-title":"Stack Overflow"},{"year":"2017","key":"ref3","article-title":"December 2017 Crawl Archive Now Available &#x2013; Common Crawl"},{"journal-title":"Welcome to Apache Hadoop","year":"2017","key":"ref6"},{"year":"2017","key":"ref5","article-title":"What is a Web Crawler&#x0192; - Definition from Techopedia"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IC3.2014.6897245"},{"journal-title":"IBM","article-title":"What is MapReduce&#x0192;","year":"2017","key":"ref7"},{"year":"2017","key":"ref2","article-title":"Total number of Websites - Internet Live Stats"},{"key":"ref1","first-page":"470","article-title":"Categorising the .mu domain using map-reduce","author":"chiniah","year":"2017","journal-title":"2017 IEEE 2nd International Conference on Signal and Image Processing (ICSIP)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1108\/14684520410531673"}],"event":{"name":"2019 Conference on Next Generation Computing Applications (NextComp)","start":{"date-parts":[[2019,9,19]]},"location":"Mauritius","end":{"date-parts":[[2019,9,21]]}},"container-title":["2019 Conference on Next Generation Computing Applications (NextComp)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8882365\/8883436\/08883665.pdf?arnumber=8883665","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:23:01Z","timestamp":1658262181000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8883665\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/nextcomp.2019.8883665","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}