{"id":"https://openalex.org/W2520326549","doi":"https://doi.org/10.1045/september2016-meschenmoser","title":"Scraping Scientific Web Repositories: Challenges and Solutions for Automated Content Extraction","display_name":"Scraping Scientific Web Repositories: Challenges and Solutions for Automated Content Extraction","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2520326549","doi":"https://doi.org/10.1045/september2016-meschenmoser","mag":"2520326549"},"language":"en","primary_location":{"id":"doi:10.1045/september2016-meschenmoser","is_oa":true,"landing_page_url":"https://doi.org/10.1045/september2016-meschenmoser","pdf_url":null,"source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1045/september2016-meschenmoser","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088492233","display_name":"Philipp Meschenmoser","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Philipp Meschenmoser","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060549879","display_name":"Norman Meuschke","orcid":"https://orcid.org/0000-0003-4648-8198"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Norman Meuschke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032754500","display_name":"Manuel Hotz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuel Hotz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058837356","display_name":"B\u00e9la Gipp","orcid":"https://orcid.org/0000-0001-6522-3019"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bela Gipp","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088492233"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5452,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.9406981,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"22","issue":"9/10","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9681000113487244,"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/T11719","display_name":"Data Quality and Management","score":0.9487000107765198,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5754840970039368},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5713716745376587},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5390969514846802},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5368376970291138},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.5080447196960449},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40579065680503845},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.27715781331062317},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.19548892974853516},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1627439558506012},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11236116290092468}],"concepts":[{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5754840970039368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5713716745376587},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5390969514846802},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5368376970291138},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.5080447196960449},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40579065680503845},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.27715781331062317},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.19548892974853516},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1627439558506012},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11236116290092468},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1045/september2016-meschenmoser","is_oa":true,"landing_page_url":"https://doi.org/10.1045/september2016-meschenmoser","pdf_url":null,"source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/106782","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/106782","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1045/september2016-meschenmoser","is_oa":true,"landing_page_url":"https://doi.org/10.1045/september2016-meschenmoser","pdf_url":null,"source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4250539519","https://openalex.org/W4249299808","https://openalex.org/W2800921325","https://openalex.org/W2207500339","https://openalex.org/W2163230867","https://openalex.org/W4307079979","https://openalex.org/W275430299","https://openalex.org/W1484163267","https://openalex.org/W234092521"],"abstract_inverted_index":{"Aside":[0],"from":[1],"improving":[2],"the":[3,28,68,89,93,97,100,108,115,125,141,168,172,183,196,203],"visibility":[4],"and":[5,18,38,63,70,95,127,202],"accessibility":[6],"of":[7,117,145,185,206],"scientific":[8,11,54,136],"publications,":[9],"many":[10],"Web":[12,55,137],"repositories":[13,56],"also":[14],"assess":[15],"researchers'":[16],"quantitative":[17],"qualitative":[19],"publication":[20],"performance,":[21],"e.g.,":[22],"by":[23,182],"displaying":[24],"metrics":[25,31,62,75],"such":[26,47,133],"as":[27,48,143],"h-index.":[29],"These":[30],"have":[32],"become":[33],"important":[34],"for":[35],"research":[36,154,197],"institutions":[37],"other":[39],"stakeholders":[40],"to":[41,72,113,130,165],"support":[42],"impactful":[43],"decision":[44],"making":[45],"processes":[46],"hiring":[49],"or":[50,85],"funding":[51],"decisions.":[52],"However,":[53],"typically":[57],"offer":[58],"only":[59,175],"simple":[60],"performance":[61,74,155],"limited":[64],"analysis":[65],"options.":[66],"Moreover,":[67],"data":[69,112,134],"algorithms":[71],"compute":[73],"are":[76,104,199],"usually":[77],"not":[78,83],"published.":[79],"Hence,":[80],"it":[81],"is":[82,192,205],"transparent":[84],"verifiable":[86],"which":[87],"publications":[88],"systems":[90,98],"include":[91],"in":[92,106,135,171],"computation":[94],"how":[96],"rank":[99],"results.":[101],"Many":[102],"researchers":[103],"interested":[105],"accessing":[107],"underlying":[109],"scientometric":[110],"raw":[111],"increase":[114],"transparency":[116],"these":[118],"systems.":[119],"In":[120,188],"this":[121],"paper,":[122],"we":[123],"discuss":[124],"challenges":[126],"present":[128],"strategies":[129,142],"programmatically":[131],"access":[132],"repositories.":[138],"We":[139,162],"demonstrate":[140],"part":[144],"an":[146],"open":[147],"source":[148],"tool":[149,173],"(MIT":[150],"license)":[151],"that":[152,167],"allows":[153],"comparisons":[156],"based":[157],"on":[158],"Google":[159],"Scholar":[160],"data.":[161],"would":[163],"like":[164],"emphasize":[166],"scraper":[169],"included":[170],"should":[174],"be":[176],"used":[177],"if":[178,195],"consent":[179,191],"was":[180],"given":[181,194],"operator":[184],"a":[186,207],"repository.":[187],"our":[189],"experience,":[190],"often":[193],"goals":[198],"clearly":[200],"explained":[201],"project":[204],"non-commercial":[208],"nature.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}
