Interface ExtractTextOptions

Options for extractText.

interface ExtractTextOptions {
    onWarning?: (message: string) => void;
    onWords?: (words: PageWord[]) => void;
    pageMarkers?: boolean;
    pages?: PageSelection;
}

Properties

onWarning?: (message: string) => void

delivered as each warning happens (also returned, in full, as warnings on the resolved result)

onWords?: (words: PageWord[]) => void

source PDF text runs entering layout, delivered once for the selected final result. Runs retain measured bounds and are not fabricated words.

pageMarkers?: boolean

emit a ### pN marker before each page's content (output formatting only — report.pageStats is always populated regardless)

convert only this page range (1-based, inclusive); defaults to the whole document