{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T15:58:08Z","timestamp":1774195088131,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,10,10]],"date-time":"2012-10-10T00:00:00Z","timestamp":1349827200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2013,2]]},"DOI":"10.1007\/s00778-012-0286-6","type":"journal-article","created":{"date-parts":[[2012,10,9]],"date-time":"2012-10-09T10:01:03Z","timestamp":1349776863000},"page":"47-72","source":"Crossref","is-referenced-by-count":52,"title":["OXPath: A language for scalable data extraction, automation, and crawling on the deep web"],"prefix":"10.1007","volume":"22","author":[{"given":"Tim","family":"Furche","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Gottlob","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Grasso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Schallhart","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Sellers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,10,10]]},"reference":[{"key":"286_CR1","unstructured":"http:\/\/www.iopus.com\/iMacros"},{"key":"286_CR2","unstructured":"http:\/\/www.newprosoft.com\/web-content-extractor.htm"},{"key":"286_CR3","unstructured":"http:\/\/www.visualwebripper.com"},{"key":"286_CR4","unstructured":"http:\/\/www.web-harvest.sourceforge.net"},{"key":"286_CR5","unstructured":"http:\/\/www.w3.org\/TR\/CSS2\/selector.html"},{"key":"286_CR6","doi-asserted-by":"crossref","unstructured":"Alba, A., Bhagwan, V., Grandison, T.: Accessing the deep web: when good ideas go bad. In: OOPSLA (2008)","DOI":"10.1145\/1449814.1449871"},{"key":"286_CR7","unstructured":"Anton, T.: XPath\u2014wrapper induction by generalizing tree traversal patterns. In: LWA (2005)"},{"key":"286_CR8","doi-asserted-by":"crossref","unstructured":"Anupam, V., Freire, J., Kumar, B., Lieuwen, D.: Automating web navigation with the webvcr. In: WWW (2000)","DOI":"10.1016\/S1389-1286(00)00073-6"},{"key":"286_CR9","doi-asserted-by":"crossref","unstructured":"Arocena, G.O., Mendelzon, A.O.: Weboql: Restructuring documents, databases, and webs. In: ICDE (1998)","DOI":"10.1002\/(SICI)1096-9942(1999)5:3<127::AID-TAPO2>3.0.CO;2-X"},{"issue":"8","key":"286_CR10","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1007\/s00500-006-0118-y","volume":"11","author":"C Badica","year":"2007","unstructured":"Badica, C., Badica, A., Popescu, E., Abraham, A.: L-wrappers: concepts, properties and construction: A declarative approach to data extraction from web sources. Soft Comput. 11(8), 753\u2013772 (2007)","journal-title":"Soft Comput."},{"key":"286_CR11","unstructured":"Banko, M., Cafarella, M.J., Soderland, S., Broadhead, M., Etzioni, O.: Open information extraction from the Web. In: IJCAI (2007)"},{"key":"286_CR12","unstructured":"Baumgartner, R., Flesca, S., Gottlob, G.: Visual web information extraction with Lixto. In: VLDB (2001)"},{"key":"286_CR13","doi-asserted-by":"crossref","first-page":"3:1","DOI":"10.1145\/1456650.1456653","volume":"41","author":"M Benedikt","year":"2009","unstructured":"Benedikt, M., Koch, C.: Xpath leashed. CSUR 41, 3:1\u20133:54 (2009)","journal-title":"CSUR"},{"issue":"1","key":"286_CR14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3998\/3336451.0007.104","volume":"7","author":"MK Bergman","year":"2001","unstructured":"Bergman, M.K.: The deep web: Surfacing hidden value. J. Electron. Publ. 7(1), 1\u201317 (2001)","journal-title":"J. Electron. Publ."},{"key":"286_CR15","doi-asserted-by":"crossref","unstructured":"Bigham, J.P., Cavender, A.C., Kaminsky, R.S., Prince, C.M., Obison T.S.: Transcendence: enabling a personal view of the deep web. In: IUI (2008)","DOI":"10.1145\/1378773.1378796"},{"key":"286_CR16","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1002\/spe.587","volume":"34","author":"P Boldi","year":"2004","unstructured":"Boldi, P., Codenotti, B., Santini, M., Vigna, S.: Ubicrawler: a scalable fully distributed web crawler. Softw. Practice Experience 34, 711\u2013726 (2004)","journal-title":"Softw. Practice Experience"},{"key":"286_CR17","doi-asserted-by":"crossref","unstructured":"Bolin, M., Webber, M., Rha, P., Wilson, T., Miller, R.C.:. Automation and customization of rendered web pages. In: UIST (2005)","DOI":"10.1145\/1095034.1095062"},{"key":"286_CR18","doi-asserted-by":"crossref","unstructured":"Brin, S., Page, L.: The anatomy of a large-scale hypertextual web search engine. Comput. Netw. ISDN Syst. 30(1\u20137), 107\u2013117 (1998)","DOI":"10.1016\/S0169-7552(98)00110-X"},{"issue":"1","key":"286_CR19","first-page":"538","volume":"1","author":"MJ Cafarella","year":"2008","unstructured":"Cafarella, M.J., Halevy, A.Y., Wang, D.Z., Wy, E., Zhang, Y.: WebTables: exploring the power of tables on the web. PVLDB 1(1), 538\u2013549 (2008)","journal-title":"PVLDB"},{"key":"286_CR20","unstructured":"Centeno, V.L., Kloos, C.D., Fern\u00e1ndez, L.S.: Garc\u00eda, N.F.: Intelligent automated navigation through the deep web. In: Advances in Web Intelligence (2004)"},{"issue":"10","key":"286_CR21","first-page":"1411","volume":"18","author":"C-H Chang","year":"2006","unstructured":"Chang, C.-H., Kayed, M., Girgis, M.R., Shaalan, K.F.: A survey of web information extraction systems. TKDE 18(10), 1411\u20131428 (2006)","journal-title":"TKDE"},{"key":"286_CR22","doi-asserted-by":"crossref","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: Roadrunner: automatic data extraction from data-intensive web sites. In: SIGMOD (2002)","DOI":"10.1145\/564691.564778"},{"issue":"1","key":"286_CR23","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.artint.2005.03.001","volume":"165","author":"MJ Cafarella","year":"2005","unstructured":"Cafarella, M.J., Downey, D., Popescu, A.-M., Shaked, T., Soderland, S., Weld, D.S., Yates, A.: Unsupervised named-entity extraction from the Web: an experimental study. Artif. Intell. 165(1), 91\u2013134 (2005)","journal-title":"Artif. Intell."},{"key":"286_CR24","doi-asserted-by":"crossref","unstructured":"Furche, T., Gottlob, G., Grasso, G., Gunes, O., Guo, X., Kravchenko, A., Orsi, G., Schallhart, C., Sellers, A., Wang, C.: DIADEM: Domain-centric, intelligent, automated data extraction methodology. In: WWW (2012)","DOI":"10.1145\/2187980.2188025"},{"key":"286_CR25","doi-asserted-by":"crossref","unstructured":"Furche, T., Gottlob, G., Grasso, G., Schallhart, C., Sellers, A.: Oxpath: A language for scalable, memory-efficient data extraction from web applications. PVLDB 4(11), 1016\u20131027 (2011)","DOI":"10.14778\/3402707.3402738"},{"key":"286_CR26","doi-asserted-by":"crossref","unstructured":"Gottlob, G., Koch, C., Pichler, R.: Efficient algorithms for processing XPath queries. In: TODS (2005)","DOI":"10.1145\/1071610.1071614"},{"key":"286_CR27","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1147\/sj.431.0064","volume":"43","author":"D Gruhl","year":"2004","unstructured":"Gruhl, D., Chavet, L., Gibson, D., Meyer, J., Pattanayak, P., Tomkins, A., Zien, J.: How to build a webfountain: an architecture for very large-scale text analytics. IBM Syst. J. 43, 64\u201377 (2004)","journal-title":"IBM Syst. J."},{"issue":"5","key":"286_CR28","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1145\/1230819.1241670","volume":"50","author":"B He","year":"2007","unstructured":"He, B., Patel, M., Zhang, Z., Chang, K.C.-C.: Accessing the deep web. Commun. ACM 50(5), 94\u2013101 (2007)","journal-title":"Commun. ACM"},{"issue":"4","key":"286_CR29","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1023\/A:1019213109274","volume":"2","author":"A Heydon","year":"1999","unstructured":"Heydon, A., Najork, M.: Mercator: a scalable, extensible web crawler. World Wide Web 2(4), 219\u2013229 (1999)","journal-title":"World Wide Web"},{"key":"286_CR30","doi-asserted-by":"crossref","unstructured":"Kranzdorf, J., Sellers, A., Grasso, G., Schallhart, C., Furche, T: Spotting the tracks on the oxpath. In: WWW (2012)","DOI":"10.1145\/1963192.1963304"},{"key":"286_CR31","doi-asserted-by":"crossref","unstructured":"Leshed, G., Haber, E.M., Matthews, T., Lau, T.: Coscripter: automating& sharing how-to knowledge in the enterprise. In: CHI (2008)","DOI":"10.1145\/1357054.1357323"},{"key":"286_CR32","doi-asserted-by":"crossref","unstructured":"Lin, J., Wong, J., Nichols, J., Cypher, A., Lau, T.A.: End-user programming of mashups with vegemite. In: IUI (2009)","DOI":"10.1145\/1502650.1502667"},{"key":"286_CR33","unstructured":"Liu, L., Pu, C., Han, W.: Xwrap: an xml-enabled wrapper construction system for web information sources. In: ICDE (2000)"},{"key":"286_CR34","unstructured":"Liu, M., Ling, T.W.: A rule-based query language for html. In: DASFAA (2001)"},{"issue":"4","key":"286_CR35","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1145\/1114244.1114247","volume":"30","author":"M Marx","year":"2005","unstructured":"Marx, M.: Conditional XPath. ACM Trans. Database Syst. 30(4), 929\u2013959 (2005)","journal-title":"ACM Trans. Database Syst."},{"key":"286_CR36","doi-asserted-by":"crossref","unstructured":"Marx, M., de Rijke, M.: Semantic characterizations of navigational XPath. ACM SIGMOD Rec. 34(2), 41\u201346 (2005)","DOI":"10.1145\/1083784.1083792"},{"issue":"1","key":"286_CR37","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1007\/s007990050004","volume":"1","author":"AO Mendelzon","year":"1997","unstructured":"Mendelzon, A.O., Mihaila, G.A., Milo, T.: Querying the world wide web. Int. J. Digit. Libr. 1(1), 54\u201367 (1997)","journal-title":"Int. J. Digit. Libr."},{"key":"286_CR38","doi-asserted-by":"crossref","unstructured":"Mir, S., Staab, S., Rojas, I.: Web-prospector\u2014an automatic, site-wide wrapper induction approach for scientific deep-web databases. In: BTW (2009)","DOI":"10.1007\/978-3-642-02879-3_9"},{"key":"286_CR39","doi-asserted-by":"crossref","unstructured":"Montoto, P., Pan, A., Raposo, J., Bellas, F., L\u00f3pez, J: Automating navigation sequences in ajax websites. In: ICWE (2009)","DOI":"10.1007\/978-3-642-02818-2_12"},{"issue":"5","key":"286_CR40","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1016\/S1389-1286(02)00214-1","volume":"39","author":"J Myllymaki","year":"2002","unstructured":"Myllymaki, J.: Effective web data extraction with standard xml technologies. Comput. Netw. 39(5), 635\u2013644 (2002)","journal-title":"Comput. Netw."},{"key":"286_CR41","doi-asserted-by":"crossref","unstructured":"Olteanu, D., Meuss, H., Furche, T., Bry, F.: XPath: looking Forward. In: EDBT-XML-Based Data Management, LNCS 2490 (2002)","DOI":"10.1007\/3-540-36128-6_7"},{"key":"286_CR42","unstructured":"Raposo, J., Pan, A., \u00c1lvarez, M., Hidalgo, J., Vi\u00f1a., A.: The wargo system: semi-automatic wrapper generation in presence of complex data access modes. In: DEXA (2002)"},{"key":"286_CR43","doi-asserted-by":"crossref","unstructured":"Safonov, A.: Web macros by example: users managing the www of applications. In: CHI, pp. 71\u201372. ACM (1999)","DOI":"10.1145\/632751.632761"},{"key":"286_CR44","unstructured":"Sahuguet, A., Azavant, F.: Building light-weight wrappers for legacy web data-sources using w4f. In: VLDB, pp. 738\u2013741 (1999)"},{"key":"286_CR45","doi-asserted-by":"crossref","unstructured":"Sawa, N., Morishima, A., Sugimoto, S., Kitagawa, H.: Wraplet: Wrapping your web contents with a lightweight language. In: SITIS, pp. 387\u2013394 (2007)","DOI":"10.1109\/SITIS.2007.135"},{"key":"286_CR46","doi-asserted-by":"crossref","unstructured":"Shen, W., Doan, A., Naughton, J.F., Ramakrishnan, R: Declarative information extraction using datalog with embedded extraction predicates. In: VLDB (2007)","DOI":"10.1145\/1376616.1376718"},{"issue":"2","key":"286_CR47","first-page":"189","volume":"18","author":"J-Y Su","year":"2010","unstructured":"Su, J.-Y., Sun, D.-J., Wu, I.-C., Chen, L.-P.: On design of browser-oriented data extraction system and plug-ins. J. Mar. Sci. Technol. 18(2), 189\u2013200 (2010)","journal-title":"J. Mar. Sci. Technol."},{"key":"286_CR48","first-page":"281","volume":"9","author":"Y Wang","year":"2008","unstructured":"Wang, Y., Hornung, T.: Deep web navigation by example. Scalable Comput. Practice Experience 9, 281\u2013292 (2008)","journal-title":"Scalable Comput. Practice Experience"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-012-0286-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-012-0286-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-012-0286-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,14]],"date-time":"2020-07-14T16:21:38Z","timestamp":1594743698000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-012-0286-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,10,10]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,2]]}},"alternative-id":["286"],"URL":"https:\/\/doi.org\/10.1007\/s00778-012-0286-6","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,10,10]]}}}