{"id":"https://openalex.org/W2156072898","doi":"https://doi.org/10.1145/2611040.2611067","title":"BlogForever Crawler","display_name":"BlogForever Crawler","publication_year":2014,"publication_date":"2014-05-27","ids":{"openalex":"https://openalex.org/W2156072898","doi":"https://doi.org/10.1145/2611040.2611067","mag":"2156072898"},"language":"en","primary_location":{"id":"doi:10.1145/2611040.2611067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2611040.2611067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Web Intelligence, Mining and Semantics (WIMS14)","raw_type":"proceedings-article"},"type":"article","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/A5014926250","display_name":"Olivier Blanvillain","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Olivier Blanvillain","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), 1015 Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), 1015 Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083270440","display_name":"Nikos Kasioumis","orcid":null},"institutions":[{"id":"https://openalex.org/I67311998","display_name":"European Organization for Nuclear Research","ror":"https://ror.org/01ggx4157","country_code":"CH","type":"facility","lineage":["https://openalex.org/I67311998"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nikos Kasioumis","raw_affiliation_strings":["European Organization for Nuclear Research (CERN), 1211 Geneva 23, Switzerland"],"affiliations":[{"raw_affiliation_string":"European Organization for Nuclear Research (CERN), 1211 Geneva 23, Switzerland","institution_ids":["https://openalex.org/I67311998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054863295","display_name":"Vangelis Banos","orcid":null},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vangelis Banos","raw_affiliation_strings":["Department of Informatics, Aristotle University of Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014926250"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":2.3667,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91393777,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9524000287055969,"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/T13976","display_name":"Web visibility and informetrics","score":0.9365000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8280030488967896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7876245975494385},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6335638761520386},{"id":"https://openalex.org/keywords/javascript","display_name":"JavaScript","score":0.6131654977798462},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5197384357452393},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5009148120880127},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5008740425109863},{"id":"https://openalex.org/keywords/hypertext","display_name":"Hypertext","score":0.48963600397109985},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.45645543932914734},{"id":"https://openalex.org/keywords/dynamic-web-page","display_name":"Dynamic web page","score":0.43113598227500916},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.3790319859981537},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33192479610443115},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.29783958196640015},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13344904780387878},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07333171367645264}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8280030488967896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876245975494385},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6335638761520386},{"id":"https://openalex.org/C544833334","wikidata":"https://www.wikidata.org/wiki/Q2005","display_name":"JavaScript","level":2,"score":0.6131654977798462},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5197384357452393},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5009148120880127},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5008740425109863},{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.48963600397109985},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.45645543932914734},{"id":"https://openalex.org/C100158260","wikidata":"https://www.wikidata.org/wiki/Q1650567","display_name":"Dynamic web page","level":3,"score":0.43113598227500916},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3790319859981537},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33192479610443115},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29783958196640015},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13344904780387878},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07333171367645264},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2611040.2611067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2611040.2611067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Web Intelligence, Mining and Semantics (WIMS14)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320279","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1582702620","https://openalex.org/W1598718436","https://openalex.org/W1613836731","https://openalex.org/W1616576116","https://openalex.org/W1647671624","https://openalex.org/W1972993442","https://openalex.org/W1987869189","https://openalex.org/W2000273502","https://openalex.org/W2064466058","https://openalex.org/W2106115215","https://openalex.org/W2120101509","https://openalex.org/W2129595335","https://openalex.org/W2130695501","https://openalex.org/W2157140910","https://openalex.org/W2164542999","https://openalex.org/W2165718336","https://openalex.org/W2184180660","https://openalex.org/W2319012534","https://openalex.org/W2548007011","https://openalex.org/W2809042564","https://openalex.org/W4233570883","https://openalex.org/W6700017563","https://openalex.org/W6724331316","https://openalex.org/W6752615178"],"related_works":["https://openalex.org/W2418196546","https://openalex.org/W1569598199","https://openalex.org/W2475047236","https://openalex.org/W2914791830","https://openalex.org/W2474398508","https://openalex.org/W4252479898","https://openalex.org/W2610795643","https://openalex.org/W4785472","https://openalex.org/W2214197538","https://openalex.org/W2364333047"],"abstract_inverted_index":{"Blogs":[0],"are":[1],"a":[2,33,70,97,109],"dynamic":[3],"communication":[4],"medium":[5],"which":[6],"has":[7,17],"been":[8],"widely":[9],"established":[10],"on":[11,48,80],"the":[12,37,40,84,113],"web.":[13],"The":[14],"BlogForever":[15,38],"project":[16],"developed":[18],"an":[19],"innovative":[20],"system":[21],"to":[22,50,75,96,119],"harvest,":[23],"preserve,":[24],"manage":[25],"and":[26,59,72],"reuse":[27],"blog":[28,62,91,99],"content.":[29,128],"This":[30,93],"paper":[31],"presents":[32],"key":[34],"component":[35],"of":[36],"platform,":[39],"web":[41,86,110,114],"crawler.":[42],"More":[43],"precisely,":[44],"our":[45],"work":[46],"concentrates":[47],"techniques":[49],"automatically":[51],"extract":[52],"content":[53],"such":[54],"as":[55],"articles,":[56],"authors,":[57],"dates":[58],"comments":[60],"from":[61,123],"posts.":[63],"To":[64],"achieve":[65],"this":[66],"goal,":[67],"we":[68,104,107],"introduce":[69],"simple":[71],"robust":[73],"algorithm":[74],"generate":[76],"extraction":[77,101,122],"rules":[78],"based":[79],"string":[81],"matching":[82],"using":[83],"blog's":[85],"feed":[87],"in":[88,117],"conjunction":[89],"with":[90,125],"hypertext.":[92],"approach":[94],"leads":[95],"scalable":[98],"data":[100,121],"process.":[102],"Furthermore,":[103],"show":[105],"how":[106],"integrate":[108],"browser":[111],"into":[112],"harvesting":[115],"process":[116],"order":[118],"support":[120],"blogs":[124],"JavaScript":[126],"generated":[127]},"counts_by_year":[{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
