{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T13:29:24Z","timestamp":1725888564491},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319590714"},{"type":"electronic","value":"9783319590721"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-59072-1_12","type":"book-chapter","created":{"date-parts":[[2017,5,30]],"date-time":"2017-05-30T02:41:58Z","timestamp":1496112118000},"page":"95-103","source":"Crossref","is-referenced-by-count":1,"title":["Web Content Extraction Using Clustering with Web Structure"],"prefix":"10.1007","author":[{"given":"Xiaotao","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liqun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhua","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,5,31]]},"reference":[{"issue":"9","key":"12_CR1","first-page":"2581","volume":"32","author":"L Yang","year":"2015","unstructured":"Yang, L., Li, X., Geng, G.: Study of web pages content extraction based on layout similarity. Appl. Res. Comput. 32(9), 2581\u20132586 (2015)","journal-title":"Appl. Res. Comput."},{"issue":"1","key":"12_CR2","first-page":"80","volume":"25","author":"Z Xiong","year":"2010","unstructured":"Xiong, Z., Zhang, H., Lin, M.: An extraction algorithm of Chinese HTML content based on similarity. J. Southwest Univ. Sci. Technol. 25(1), 80\u201384 (2010)","journal-title":"J. Southwest Univ. Sci. Technol."},{"issue":"24","key":"12_CR3","first-page":"5187","volume":"31","author":"Y Chang","year":"2010","unstructured":"Chang, Y., Zheng, Y., Chen, Y.: Content extraction technique for web pages based on HTML-tags. J. Comput. Eng. Des. 31(24), 5187\u20135191 (2010)","journal-title":"J. Comput. Eng. Des."},{"key":"12_CR4","unstructured":"Cai, D., Yu, S., Wen, J., et al.: VIPS: a vision- based page segmentation algorithm (2003)"},{"key":"12_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1007\/3-540-36901-5_42","volume-title":"Web Technologies and Applications","author":"D Cai","year":"2003","unstructured":"Cai, D., Yu, S., Wen, J.-R., Ma, W.-Y.: Extracting content structure for web pages based on visual representation. In: Zhou, X., Orlowska, M.E., Zhang, Y. (eds.) APWeb 2003. LNCS, vol. 2642, pp. 406\u2013417. Springer, Heidelberg (2003). doi:\n10.1007\/3-540-36901-5_42"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Mehta, R., Mitra, P., Karnick, H.: Extracting semantic structure of web document using content and visual information. In: Proceedings of the 14th Special Interest Tracks and Posters of International Conference on World Wide Web, pp. 928\u2013929, ACM Press, New York (2005)","DOI":"10.1145\/1062745.1062802"},{"key":"12_CR7","unstructured":"Aanshi, B., Veenu, M.: A novel approach for content extraction from web pages. In: Proceedings of 2014 RAECS UIET, pp. 6\u20138. Panjab University, Chandigarh (2014)"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Peng, Q., Wang, Q., Li, Y., Zhang, J., et al.: Content extraction from chinese web pages based on punctuations distribution. In: International Conference on Computer Science and Service System, pp. 1351\u20131355 (2012)","DOI":"10.1109\/CSSS.2012.341"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Guo, Y., Tang, H., Song, L., et al.: ECON: an approach to extract content from web news page. In: International Asia-Pacific Web Conference, pp. 314\u2013320 (2010)","DOI":"10.1109\/APWeb.2010.11"},{"issue":"4","key":"12_CR10","first-page":"42","volume":"5","author":"Q Yang","year":"2015","unstructured":"Yang, Q., Yang, M.: A method of webpage content extraction based on point density. J. Intell. Comput. Appl. 5(4), 42\u201344 (2015)","journal-title":"J. Intell. Comput. Appl."},{"issue":"3","key":"12_CR11","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1109\/TST.2012.6216755","volume":"17","author":"S Lin","year":"2012","unstructured":"Lin, S., Chen, J., Niu, Z.: Combining a segmentation-like approach and a density-based approach in content extraction. Tsinghua Sci. Technol. 17(3), 256\u2013264 (2012)","journal-title":"Tsinghua Sci. Technol."},{"issue":"3","key":"12_CR12","first-page":"256","volume":"17","author":"Z Xiong","year":"2013","unstructured":"Xiong, Z., Lin, X., Zhang, Y., et al.: Content extraction method combining web page structure and text feature. Comput. Eng. 17(3), 256\u2013264 (2013)","journal-title":"Comput. Eng."},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Joshi, S., Agrawal, N., Krishnapuram, R., Negi, S.: A bag of paths model for measuring structural similarity in Web documents. In: Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD), pp. 577\u2013582. ACM Press, Washington (2003)","DOI":"10.1145\/956750.956822"},{"issue":"6","key":"12_CR14","first-page":"1199","volume":"50","author":"H Liao","year":"2012","unstructured":"Liao, H., Yang, Y., Jia, Z., et al.: An improved web structure similarity based on matching algorithm of tree paths. J. Jilin Univ. 50(6), 1199\u20131203 (2012)","journal-title":"J. Jilin Univ."},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Joshi, S., Agrawal, N., Krishnapuram, R., Negi, S.: A bag of paths model for measuring structural similarity in web documents. In: SIGKDD 2003 (2003)","DOI":"10.1145\/956750.956822"},{"key":"12_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1007\/BFb0053296","volume-title":"Electronic Publishing, Artistic Imaging, and Digital Typography","author":"IF Cruz","year":"1998","unstructured":"Cruz, I.F., Borisov, S., Marks, M.A., Webb, T.R.: Measuring structural similarity among web documents: preliminary results. In: Hersch, R.D., Andr\u00e9, J., Brown, H. (eds.) EP\/RIDT-1998. LNCS, vol. 1375, pp. 513\u2013524. Springer, Heidelberg (1998). doi:\n10.1007\/BFb0053296"}],"container-title":["Lecture Notes in Computer Science","Advances in Neural Networks - ISNN 2017"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-59072-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,5,30]],"date-time":"2017-05-30T02:45:18Z","timestamp":1496112318000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-59072-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319590714","9783319590721"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-59072-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}