{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T20:51:41Z","timestamp":1783803101872,"version":"3.55.0"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[1999,12,1]],"date-time":"1999-12-01T00:00:00Z","timestamp":944006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[1999,12,1]],"date-time":"1999-12-01T00:00:00Z","timestamp":944006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[1999,12]]},"DOI":"10.1023\/a:1019213109274","type":"journal-article","created":{"date-parts":[[2003,2,19]],"date-time":"2003-02-19T19:09:50Z","timestamp":1045681790000},"page":"219-229","source":"Crossref","is-referenced-by-count":286,"title":["Mercator: A scalable, extensible Web crawler"],"prefix":"10.1007","volume":"2","author":[{"given":"Allan","family":"Heydon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Najork","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"330617_CR1","unstructured":"AltaVista, \u201cAltaVista Software Search Intranet Home Page,\u201d altavista.software.digital.com\/search\/intranet."},{"key":"330617_CR2","unstructured":"BIND, \u201cBerkeley Internet Name Domain (BIND),\u201d www.isc.org\/bind.html."},{"key":"330617_CR3","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1145\/362686.362692","volume":"7","author":"B. Bloom","year":"1970","unstructured":"Bloom, B. (1970), \u201cSpace\/Time Trade-Offs in Hash Coding with Allowable Errors,\u201d Communications of the ACM 13, 7, 422\u2013426.","journal-title":"Communications of the ACM 13"},{"key":"330617_CR4","doi-asserted-by":"crossref","unstructured":"Brin, S. and L. Page (1998), \u201cThe Anatomy of a Large-Scale Hypertextual Web Search Engine,\u201d In Proceedings of the Seventh International World Wide Web Conference, pp. 107\u2013117.","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"330617_CR5","doi-asserted-by":"crossref","unstructured":"Broder, A. (1993), \u201cSome Applications of Rabin's Fingerprinting Method,\u201d In Sequences II: Methods in Communications, Security, and Computer Science, R. Capocelli, A. De Santis, and U. Vaccaro, Eds., Springer-Verlag, pp. 143\u2013152.","DOI":"10.1007\/978-1-4613-9323-8_11"},{"key":"330617_CR6","unstructured":"Burner, M. (1977), \u201cCrawling Towards Eternity: Building an Archive of the World Wide Web,\u201d Web Techniques Magazine 2, 5."},{"key":"330617_CR7","doi-asserted-by":"crossref","unstructured":"Cho, J., H. Garcia-Molina, and L. Page (1998), \u201cEfficient Crawling Through URL Ordering,\u201d In Proceedings of the Seventh International World Wide Web Conference, pp. 161\u2013172.","DOI":"10.1016\/S0169-7552(98)00108-1"},{"key":"330617_CR8","unstructured":"DCPI, \u201cDigital Continuous Profiling Infrastructure,\u201d www.research.digital.com\/SRC\/dcpi\/."},{"key":"330617_CR9","doi-asserted-by":"crossref","unstructured":"Eichmann, D. (1994), \u201cThe RBSE Spider - Balancing Effective Search Against Web Load,\u201d In Proceedings of the First International World Wide Web Conference, pp. 113\u2013120.","DOI":"10.1016\/S0169-7552(94)90151-1"},{"key":"330617_CR10","unstructured":"Ghemawat, S., \u201csrcjava home page,\u201d www.research.digital.com\/SRC\/java\/."},{"key":"330617_CR11","unstructured":"Google, \u201cGoogle! Search Engine,\u201d google.stanford.edu\/."},{"key":"330617_CR12","unstructured":"Gray, M., \u201cInternet Growth and Statistics: Credits and Background,\u201d www.mit.edu\/people\/mkgray\/net\/background.html."},{"key":"330617_CR13","doi-asserted-by":"crossref","unstructured":"Henzinger, M., A. Heydon, M. Mitzenmacher, and M.A. Najork (1999), \u201cMeasuring Index Quality Using Random Walks on the Web,\u201d In Proceedings of the Eighth International World Wide Web Conference, pp. 213\u2013225.","DOI":"10.1016\/S1389-1286(99)00016-X"},{"key":"330617_CR14","doi-asserted-by":"crossref","unstructured":"Heydon, A. and M. Najork (1999), \u201cPerformance Limitations of the Java Core Libraries,\u201d In Proceedings of the 1999 ACM Java Grande Conference, pp. 35\u201341.","DOI":"10.1145\/304065.304092"},{"key":"330617_CR15","unstructured":"InternetArchive, \u201cThe Internet Archive,\u201d www.archive.org\/."},{"key":"330617_CR16","unstructured":"Koster, M., \u201cThe Web Robots Pages,\u201d info.webcrawler.com\/mak\/projects\/robots\/robots. html."},{"key":"330617_CR17","doi-asserted-by":"crossref","unstructured":"McBryan, O.A. (1994), \u201cGENVL and WWWW: Tools for Taming the Web,\u201d In Proceedings of the First International World Wide Web Conference, pp. 79\u201390.","DOI":"10.1016\/S0169-7552(94)90149-X"},{"key":"330617_CR18","doi-asserted-by":"crossref","unstructured":"Miller, R.C. and K. Bharat (1998), \u201cSPHINX: A Framework for Creating Personal, Site-Specific Web Crawlers,\u201d In Proceedings of the Seventh International World Wide Web Conference, pp. 119\u2013130.","DOI":"10.1016\/S0169-7552(98)00064-6"},{"key":"330617_CR19","unstructured":"Pinkerton, B. (1994), \u201cFinding What People Want: Experiences with the WebCrawler,\u201d In Proceedings of the Second International World Wide Web Conference."},{"key":"330617_CR20","unstructured":"Rabin, M.O. (1981), \u201cFingerprinting by Random Polynomials,\u201d Technical Report TR\u201315-81, Center for Research in Computing Technology, Harvard University."},{"key":"330617_CR21","unstructured":"RobotsExclusion, \u201cThe Robots Exclusion Protocol,\u201d info.webcrawler.com\/mak\/projects\/robots\/ exclusion.html."},{"key":"330617_CR22","unstructured":"Smith, Z. (1997), \u201cThe Truth About the Web: Crawling Towards Eternity,\u201d Web Techniques Magazine 2, 5."}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1019213109274.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1019213109274\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1019213109274.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T11:55:51Z","timestamp":1755086151000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1019213109274"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,12]]},"references-count":22,"journal-issue":{"issue":"4","published-print":{"date-parts":[[1999,12]]}},"alternative-id":["330617"],"URL":"https:\/\/doi.org\/10.1023\/a:1019213109274","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"value":"1386-145X","type":"print"},{"value":"1573-1413","type":"electronic"}],"subject":[],"published":{"date-parts":[[1999,12]]}}}