Buch-Metadaten-Extraktor
Laden Sie ein PDF oder EPUB hoch und erhalten Sie die wichtigsten Metadaten normalisiert nach dem ONIX-3-Standard — Titel, Mitwirkende, Verlag, ISBN, BISAC- und Thema-Kategorien sowie Schlagwörter für den Handel.
Kostenloses KI-ToolZiehen Sie Ihr PDF oder EPUB hierher
oder
Dateien durchsuchenIhre Datei wird sicher verarbeitet und unmittelbar nach der Analyse gelöscht. Es werden nur stichprobenartige Auszüge analysiert.
Ihre Datei wird hochgeladen...
Ihre Datei wird vorbereitet...
What the Book Metadata Extractor does
Good metadata is what makes a book findable and sellable — and it is tedious to assemble by hand. Upload a PDF or EPUB and this free metadata extractor reads the file, samples the pages where bibliographic data lives (title page, copyright page, colophon), and returns clean metadata normalized to the ONIX for Books 3 standard: title and subtitle, contributors with role codes, publisher, dates, identifiers, language, BISAC and Thema subjects, and retail keywords.
Where the file already carries embedded metadata, that always wins; the AI fills the gaps and suggests classification and keywords in the language of the book. You get a structured record you can drop straight into a catalog, plus a copy sent to your inbox.
It is free and private, one book at a time. Only sampled excerpts are analyzed, and your file is deleted immediately after.
When to use it
- Building a catalog record from a manuscript or finished file.
- Filling in missing BISAC / Thema subjects and retail keywords.
- Standardizing contributor roles to ONIX List 17 codes.
- Spot-checking the metadata embedded in a file you received.
Do this for your whole catalog in Origami
Metadata, EPUB and accessibility checks, descriptions and more — all in one place, without the one-off limit. Origami is where these tools live for your entire list.
Start in OrigamiFields are normalized to the ONIX for Books 3 standard maintained by EDItEUR. BISAC is a trademark of BISG; Thema is maintained by EDItEUR. Extraction is AI-assisted — always verify against the printed copyright page.