{"data":{"id":"10.7801/429","type":"dois","attributes":{"doi":"10.7801/429","prefix":"10.7801","suffix":"429","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Brinkmann, Alexander","nameType":"Personal","givenName":"Alexander","familyName":"Brinkmann","affiliation":[],"nameIdentifiers":[]},{"name":"Bizer, Christian","nameType":"Personal","givenName":"Christian","familyName":"Bizer","affiliation":[],"nameIdentifiers":[]}],"titles":[{"lang":"de","title":"Web Data Commons - RDFa, Microdata, Embedded JSON-LD, and Microformats Data Sets - October 2023"},{"lang":"de","title":"RDFa, Microdata, Embedded JSON-LD, and Microformats Data Sets extracted from the October 2023 Common Crawl","titleType":"AlternativeTitle"}],"publisher":"Mannheim University Library","container":{},"publicationYear":2024,"subjects":[{"lang":"de","subject":"Information Extraction, Semantic Annotations, Schema.org, Web Science","subjectScheme":""}],"contributors":[],"dates":[{"date":"2024","dateType":"Issued"}],"language":null,"types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[{"relationType":"IsDocumentedBy","relatedIdentifier":"https://madoc.bib.uni-mannheim.de/id/eprint/64408","resourceTypeGeneral":"Text","relatedIdentifierType":"URL"}],"relatedItems":[],"sizes":[],"formats":[],"version":"1","rightsList":[],"descriptions":[{"lang":"de","description":"The Web Data Commons RDFa, Microdata and Microformats data sets has been extracted from the September/October 2023 release of the Common Crawl. In summary, we found structured data within 1.7 billion HTML pages out of the 3.4 billion pages contained in the crawl (50.60%). These pages originate from 15 million different pay-level-domains out of the 34 million pay-level-domains covered by the crawl (42.89%). Altogether, the extracted data sets consist of 86 billion RDF quads.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"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","url":"https://madata.bib.uni-mannheim.de/429","contentUrl":null,"metadataVersion":3,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2024-02-12T08:01:03.000Z","registered":"2024-02-12T08:01:03.000Z","published":"2024","updated":"2024-06-21T23:14:00.000Z"},"relationships":{"client":{"data":{"id":"gesis.ubma","type":"clients"}},"provider":{"data":{"id":"jjuz","type":"providers"}},"media":{"data":{"id":"10.7801/429","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[]}}}}