{"id":"https://openalex.org/W2081989159","doi":"https://doi.org/10.1145/1963192.1963352","title":"The OXPath to success in the deep web","display_name":"The OXPath to success in the deep web","publication_year":2011,"publication_date":"2011-03-28","ids":{"openalex":"https://openalex.org/W2081989159","doi":"https://doi.org/10.1145/1963192.1963352","mag":"2081989159"},"language":"en","primary_location":{"id":"doi:10.1145/1963192.1963352","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1963192.1963352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international conference companion on World wide web","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001911595","display_name":"Andrew Sellers","orcid":"https://orcid.org/0000-0002-5845-3390"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Andrew Jon Sellers","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001911595"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.17802596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"409","last_page":"414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.909493088722229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8808337450027466},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6694433689117432},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5863364338874817},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.555863082408905},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4624837040901184},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.46198660135269165},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3732728064060211},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.3318420946598053},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24576041102409363},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11948877573013306},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.08950534462928772}],"concepts":[{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.909493088722229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8808337450027466},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6694433689117432},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5863364338874817},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.555863082408905},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4624837040901184},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.46198660135269165},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3732728064060211},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.3318420946598053},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24576041102409363},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11948877573013306},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.08950534462928772},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1963192.1963352","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1963192.1963352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international conference companion on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.205.8439","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.205.8439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2011india.com/proceeding/companion/p409.pdf","raw_type":"text"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:2706d997-30dc-4bf5-9f69-223d85fecc5a","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:2706d997-30dc-4bf5-9f69-223d85fecc5a","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Computer Science","raw_type":"Conference item"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1570215497","https://openalex.org/W1772092677","https://openalex.org/W2000243724","https://openalex.org/W2005646337","https://openalex.org/W2042616792","https://openalex.org/W2070632872","https://openalex.org/W2092201404","https://openalex.org/W2102218101","https://openalex.org/W2103060841","https://openalex.org/W2107132276","https://openalex.org/W2133059197","https://openalex.org/W2134150392","https://openalex.org/W2148210463","https://openalex.org/W2167944335","https://openalex.org/W2294034341"],"related_works":["https://openalex.org/W1542110834","https://openalex.org/W2611888112","https://openalex.org/W2121120069","https://openalex.org/W562932586","https://openalex.org/W2124793519","https://openalex.org/W2398280235","https://openalex.org/W1554870463","https://openalex.org/W2111274946","https://openalex.org/W1555764847","https://openalex.org/W151996191"],"abstract_inverted_index":{"The":[0],"world":[1],"wide":[2],"web":[3,37],"provides":[4,108],"access":[5],"to":[6,115,147],"a":[7,66,98,109,152],"wealth":[8],"of":[9,17,53,69,101,145],"data.":[10],"Collecting":[11],"and":[12,56,83,92,117,128],"maintaining":[13],"such":[14],"large":[15],"amounts":[16],"data":[18,73],"necessitates":[19],"automated":[20],"processing":[21],"for":[22,44,103],"extraction,":[23],"since":[24],"appropriate":[25],"automation":[26],"can":[27],"perform":[28],"extraction":[29,74],"tasks":[30],"that":[31,71],"would":[32],"be":[33],"otherwise":[34],"infeasible.":[35],"Modern":[36],"interfaces,":[38],"however,":[39],"are":[40],"generally":[41],"designed":[42],"primarily":[43],"human":[45],"users,":[46],"delivering":[47],"sophisticated":[48],"interactions":[49],"through":[50],"the":[51,76,122],"use":[52,116],"client-side":[54],"scripting":[55],"asynchronous":[57],"server":[58],"communication.":[59],"To":[60],"this":[61],"end,":[62],"we":[63],"introduce":[64],"OXPath,":[65,86,141],"careful":[67],"extension":[68],"XPath":[70],"facilitates":[72],"from":[75],"deep":[77],"web.":[78],"OXPath":[79,107,149],"exploits":[80],"XPath's":[81],"familiarity":[82],"theoretical":[84,124],"foundations.":[85],"then,":[87],"achieves":[88],"favourable":[89],"evaluation":[90],"complexity":[91],"optimal":[93],"page":[94],"buffering,":[95],"storing":[96],"only":[97],"constant":[99],"number":[100],"pages":[102],"non-recursive":[104],"queries.":[105],"Further,":[106],"lightweight":[110],"interface,":[111],"which":[112],"is":[113],"easy":[114],"embed.":[118],"This":[119],"paper":[120],"outlines":[121],"motivation,":[123],"framework,":[125],"current":[126],"implementation,":[127],"preliminary":[129],"results":[130],"obtained":[131],"so":[132],"far.":[133],"We":[134],"conclude":[135],"with":[136],"proposed":[137],"future":[138],"work":[139],"on":[140],"including":[142],"an":[143],"investigation":[144],"how":[146],"deploy":[148],"efficiently":[150],"in":[151],"highly":[153],"elastic":[154],"computing":[155],"framework":[156],"(cloud).":[157]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}