{"id":"https://openalex.org/W1565339651","doi":"https://doi.org/10.1007/11775300_24","title":"CCWrapper: Adaptive Predefined Schema Guided Web Extraction","display_name":"CCWrapper: Adaptive Predefined Schema Guided Web Extraction","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W1565339651","doi":"https://doi.org/10.1007/11775300_24","mag":"1565339651"},"language":"en","primary_location":{"id":"doi:10.1007/11775300_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11775300_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5100776555","display_name":"Jun Gao","orcid":"https://orcid.org/0000-0002-6750-8496"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Gao","raw_affiliation_strings":["Department of Computer Science and Technology, Peking University, Beijing, China","Dept. of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Dept. of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106446263","display_name":"Dongqing Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongqing Yang","raw_affiliation_strings":["Department of Computer Science and Technology, Peking University, Beijing, China","Dept. of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Dept. of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115590373","display_name":"Tengjiao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tengjiao Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Peking University, Beijing, China","Dept. of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Dept. of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100776555"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10951327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"286"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9616000056266785,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12285","display_name":"Surface Chemistry and Catalysis","score":0.95660001039505,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.794323742389679},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7035599946975708},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6382792592048645},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.6193206310272217},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5756953954696655},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5187882781028748},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4628860652446747},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.41297489404678345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29565930366516113},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21232324838638306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794323742389679},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7035599946975708},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6382792592048645},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.6193206310272217},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5756953954696655},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5187882781028748},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4628860652446747},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.41297489404678345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29565930366516113},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21232324838638306},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/11775300_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11775300_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W72943092","https://openalex.org/W188427339","https://openalex.org/W1534024124","https://openalex.org/W1927338256","https://openalex.org/W1969268549","https://openalex.org/W2005646337","https://openalex.org/W2015551056","https://openalex.org/W2104086170","https://openalex.org/W2110686900","https://openalex.org/W2128341918","https://openalex.org/W2128836931","https://openalex.org/W2150721933","https://openalex.org/W4230980612"],"related_works":["https://openalex.org/W1656419755","https://openalex.org/W1539890081","https://openalex.org/W4302086745","https://openalex.org/W2373402338","https://openalex.org/W2114620981","https://openalex.org/W2626998250","https://openalex.org/W2184959150","https://openalex.org/W2039658447","https://openalex.org/W2411679502","https://openalex.org/W2998827288"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
