{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T16:32:19Z","timestamp":1742401939918},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642401725"},{"type":"electronic","value":"9783642401732"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40173-2_10","type":"book-chapter","created":{"date-parts":[[2013,8,17]],"date-time":"2013-08-17T01:38:34Z","timestamp":1376703514000},"page":"81-93","source":"Crossref","is-referenced-by-count":6,"title":["Main Content Extraction from Web Documents Using Text Block Context"],"prefix":"10.1007","author":[{"given":"Myungwon","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngjin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wonmoon","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ara","family":"Khil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"10_CR1","unstructured":"(Februry 2013), \n                    \n                      http:\/\/en.wikipedia.org\/wiki\/Document_Object_Model"},{"key":"10_CR2","unstructured":"Deng, C., Shipeng, Y., Ji-Rong, W., Wei-Ying, M.: VIPS: a Vision-based Page Segmentation Algorithm. Microsoft Technical Report(MSR-TR-2003-79) (2003)"},{"key":"10_CR3","unstructured":"Suhit, G., Gail, E.K., David, N., Peter, G.: DOM-based Content Extraction of HTML Documents. In: 12th International Conference on World Wide Web, pp. 207\u2013214 (2003)"},{"issue":"2","key":"10_CR4","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/s11280-004-4873-3","volume":"8","author":"G. Suhit","year":"2005","unstructured":"Suhit, G., Gail, E.K., Peter, G., Michael, F.C., Justin, S.: Automating Content Extraction of HTML Documents. World Wide Web\u00a08(2), 179\u2013224 (2005)","journal-title":"World Wide Web"},{"key":"10_CR5","unstructured":"Jeff, P., Dan, R.: Extracting Article Text from the Web with Maximum Subsequence Segmentation. In: The 18th International Conference on World Wide Web, pp. 971\u2013980 (2009)"},{"key":"10_CR6","unstructured":"Stefan, E.: A lightweight and efficient tool for cleaning Web pages. In: The 6th International Conference on Language Resources and Evaluation (2008)"},{"key":"10_CR7","unstructured":"Stefan, E.: StupidOS: A high-precision approach to boilerplate removal. In: Building and Exploring Web Corpora: Proceedings of the 3rd Web as Corpus Workshop, pp. 123\u2013133 (2007)"},{"key":"10_CR8","unstructured":"Young, S., Hasan, J., Farshad, F.: Autonomic Wrapper Induction using Minimal Type System from Web Data. In: Artificial Intelligence, pp. 130\u2013135 (2005)"},{"key":"10_CR9","unstructured":"Christian, K., Peter, F., Wolfgang, N.: Boilerplate Detection using Shallow Text Features. In: The Third ACM International Conference on Web Search and Data Mining, pp. 441\u2013450 (2010)"},{"key":"10_CR10","unstructured":"Jian, F., Ping, L., Suk Hwan, L., Sam, L., Parag, J., Jerry, L.: Article Clipper- A System for Web Article Extraction. In: 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 743\u2013746 (2011)"},{"key":"10_CR11","unstructured":"Tim, W., William, H.H., Jiawei, H.: CETR - Content Extraction via Tag Ratios. In: 19th International Conference on World Wide Web, pp. 971\u2013980 (2010)"},{"key":"10_CR12","unstructured":"Tim, W., William, H.H.: Text Extraction from the Web via Text-to-Tag Ratio. In: The 19th International Conference on Database and Expert Systems Application, pp. 23\u201328 (2008)"},{"key":"10_CR13","unstructured":"(July 2012), \n                    \n                      http:\/\/tomazkovacic.com\/"},{"key":"10_CR14","unstructured":"W3C (February 2013), \n                    \n                      http:\/\/www.w3.org\/TR\/html401\/"},{"key":"10_CR15","unstructured":"Jiawei, H., Micheline, K.: Data Mining: Concepts and Techniques. Morgan Kaufmann (2006)"},{"key":"10_CR16","unstructured":"Ian, H.W., Eibe, F.: Data Mining: Practical Machine Learning Tools and Techniques. Elsevier (2005)"},{"key":"10_CR17","unstructured":"Waikato Univ. (February 2013), \n                    \n                      http:\/\/www.cs.waikato.ac.nz\/ml\/weka\/"},{"key":"10_CR18","unstructured":"Andy, C., Marc G.: (February 2012), \n                    \n                      http:\/\/nekohtml.sourceforge.net\/"},{"key":"10_CR19","unstructured":"L3S Research Center (February 2013), \n                    \n                      http:\/\/www.l3s.de\/~kohlschuetter\/boilerplate\/"},{"key":"10_CR20","unstructured":"(February 2013), \n                    \n                      http:\/\/121.78.244.168:8090\/ice\/index.jsp"}],"container-title":["Lecture Notes in Computer Science","Database and Expert Systems Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40173-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T14:12:29Z","timestamp":1558015949000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40173-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642401725","9783642401732"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40173-2_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}