{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:44:30Z","timestamp":1742913870045,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319387901"},{"type":"electronic","value":"9783319387918"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-38791-8_7","type":"book-chapter","created":{"date-parts":[[2016,5,24]],"date-time":"2016-05-24T22:07:33Z","timestamp":1464127653000},"page":"114-131","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Revisiting Web Data Extraction Using In-Browser Structural Analysis and Visual Cues in Modern Web Designs"],"prefix":"10.1007","author":[{"given":"Alfonso","family":"Murolo","sequence":"first","affiliation":[]},{"given":"Moira C.","family":"Norrie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,5,25]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Zheng, S., Song, R., Wen, J., Giles, C.L.: Efficient record-level wrapper induction. In: Proceedings of the 18th ACM Conference on Information and Knowledge Management. ACM (2009)","DOI":"10.1145\/1645953.1645962"},{"key":"7_CR2","unstructured":"Liu, W., Meng, X., Meng, W.: Vision-based web data records extraction. In: Proceedings 9th International Workshop on the Web and Databases (2006)"},{"issue":"12","key":"7_CR3","doi-asserted-by":"publisher","first-page":"1606","DOI":"10.14778\/2824032.2824058","volume":"8","author":"T Manabe","year":"2015","unstructured":"Manabe, T., Tajima, K.: Extracting logical hierarchical structure of HTML documents based on headings. Proc. VLDB Endowment 8(12), 1606\u20131617 (2015)","journal-title":"Proc. VLDB Endowment"},{"key":"7_CR4","unstructured":"Pembe, F., Canan, F., G\u00fcng\u00f6r, T.: A tree learning approach to web document sectional hierarchy extraction. In: Proceedings of the 2nd International Conference on Agents and Artificial Intelligence (2010)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Geel, M., Church, T., Norrie, M.C.: Sift: an end-user tool for gathering web content on the go. In: Proceedings of the 2012 ACM Symposium on Document Engineering, pp. 181\u2013190. ACM (2012)","DOI":"10.1145\/2361354.2361395"},{"key":"7_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-319-19890-3_6","volume-title":"Engineering the Web in the Big Data Era","author":"A Murolo","year":"2015","unstructured":"Murolo, A., Norrie, M.C.: Deriving custom post types from digital mockups. In: Cimiano, P., Frasincar, F., Houben, G.-J., Schwabe, D. (eds.) ICWE 2015. LNCS, vol. 9114, pp. 71\u201380. Springer, Heidelberg (2015)"},{"issue":"10","key":"7_CR7","doi-asserted-by":"publisher","first-page":"1411","DOI":"10.1109\/TKDE.2006.152","volume":"18","author":"C Chang","year":"2006","unstructured":"Chang, C., Kayed, M., Girgis, M.R., Shaalan, K.F.: A survey of web information extraction systems. IEEE Trans. Knowl. Data Eng. 18(10), 1411\u20131428 (2006)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Adelberg, B.: NoDoSE a tool for semi-automatically extracting structured and semistructured data from text documents. In: Proceedings of the 9th ACM SIGMOD International Conference on Management of Data (SIGMOD). ACM (1998)","DOI":"10.1145\/276304.276330"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: Roadrunner: towards automatic data extraction from large web sites. In: Proceedings of the 27th International Conference on Very Large Data Bases (VLDB). Morgan Kaufmann (2001)","DOI":"10.1145\/564691.564778"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Chang, C., Lui, S.: IEPAD: information extraction based on pattern discovery. In: Proceedings of the 10th International Conference on World Wide Web (WWW). ACM (2001)","DOI":"10.1145\/371920.372182"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Wang, J., Lochovsky, F.H.: Data extraction and label assignment for web databases. In: Proceedings of the 12th International Conference on World Wide Web (WWW). ACM (2003)","DOI":"10.1145\/775152.775179"},{"issue":"12","key":"7_CR12","doi-asserted-by":"publisher","first-page":"1614","DOI":"10.1109\/TKDE.2006.197","volume":"18","author":"Y Zhai","year":"2006","unstructured":"Zhai, Y., Liu, B.: Structured data extraction from the web based on partial tree alignment. IEEE Trans. Knowl. Data Eng. 18(12), 1614\u20131628 (2006)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"3","key":"7_CR13","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1109\/TKDE.2011.175","volume":"25","author":"Y Lu","year":"2013","unstructured":"Lu, Y., He, H., Zhao, H., Meng, W., Yu, C.: Annotating search results from web databases. IEEE Trans. Knowl. Data Eng. 25(3), 514\u2013527 (2013)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Zhao, H., Meng, W., Wu, Z., Raghavan, V., Yu, C.: Fully automatic wrapper generation for search engines. In: Proceedings of the 14th International Conference on World Wide Web. ACM (2005)","DOI":"10.1145\/1060745.1060760"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Hong, J.L., Siew, E., Egerton, S.: ViWER-Data extraction for search engine results pages using visual cue and dom tree. In: Proceedings of the 1st International Conference on Information Retrieval & Knowledge Management (CAMP). IEEE (2010)","DOI":"10.1109\/INFRKM.2010.5466924"},{"issue":"3","key":"7_CR16","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1109\/TKDE.2009.109","volume":"22","author":"W Liu","year":"2010","unstructured":"Liu, W., Meng, X., Meng, W.: Vide: a vision-based approach for deep web data extraction. IEEE Trans. Knowl. Data Eng. 22(3), 447\u2013460 (2010)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"2","key":"7_CR17","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/S0169-023X(01)00047-7","volume":"40","author":"AH Laender","year":"2002","unstructured":"Laender, A.H., Ribeiro-Neto, B., da Silva, A.S.: DEByE - data extraction by example. Data Knowl. Eng. 40(2), 121\u2013154 (2002)","journal-title":"Data Knowl. Eng."},{"issue":"6","key":"7_CR18","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/MIS.2004.71","volume":"19","author":"C Chang","year":"2004","unstructured":"Chang, C., Kuo, S.: OLERA: semisupervised web-data extraction with visual support. IEEE Intell. Syst. 19(6), 56\u201364 (2004)","journal-title":"IEEE Intell. Syst."},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Hogue, A., Karger, D.: Thresher: automating the unwrapping of semantic content from the world wide web. In: Proceedings of the 14th International Conference on World Wide Web. ACM (2005)","DOI":"10.1145\/1060745.1060762"},{"key":"7_CR20","first-page":"707","volume":"10","author":"V Levenshtein","year":"1966","unstructured":"Levenshtein, V.: Binary codes capable of correcting deletions, insertions, and reversals. Sov. Phys. Dokl. 10, 707\u2013710 (1966)","journal-title":"Sov. Phys. Dokl."},{"key":"7_CR21","unstructured":"Augsten, N., B\u00f6hlen, M., Gamper, J.: Approximate matching of hierarchical data using Pq-Grams. In: Proceedings of the 31st International Conference on Very Large Data Bases (VLDB), VLDB Endowment (2005)"},{"issue":"2","key":"7_CR22","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1016\/S0166-218X(02)00205-6","volume":"126","author":"S Sakai","year":"2003","unstructured":"Sakai, S., Togasaki, M., Yamazaki, K.: A note on greedy algorithms for the maximum weighted independent set problem. Discrete Appl. Math. 126(2), 313\u2013322 (2003)","journal-title":"Discrete Appl. Math."},{"issue":"1","key":"7_CR23","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1023\/A:1008765214400","volume":"14","author":"M Demange","year":"1999","unstructured":"Demange, M.: A note on the approximation of a minimum-weight maximal independent set. Comput. Optim. Appl. 14(1), 157\u2013169 (1999)","journal-title":"Comput. Optim. Appl."}],"container-title":["Lecture Notes in Computer Science","Web Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-38791-8_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:04:59Z","timestamp":1622937899000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-38791-8_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319387901","9783319387918"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-38791-8_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"25 May 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}