Pdftotext

Usage

import qualified Data.Text.IO as T
import Pdftotext

main :: IO ()
main = do
  Just pdf <- openFile "path/to/file.pdf"
  T.putStrLn $ pdftotext Physical pdf

Types

data Document

data Layout

Layout of text extracted from PDF.

Constructors

Physical

Text emulates layout of PDF, including horizontal spaces, and preserves hyphenation; corresponds to calling pdftotext -layout

Raw

Discards horizontal spaces, preserves hyphenation; corresponds to calling pdftotext -raw

None

Discards horizontal spaces, removes hyphenation; corresponds to calling pdftotext without layout argument

Instances

Eq Layout

Defined in Pdftotext.Internal

Methods

(==) :: Layout -> Layout -> Bool

(/=) :: Layout -> Layout -> Bool

Show Layout

Defined in Pdftotext.Internal

Methods

showsPrec :: Int -> Layout -> ShowS

show :: Layout -> String

showList :: [Layout] -> ShowS

data Page

Instances

Show Page

Defined in Pdftotext.Internal

Methods

showsPrec :: Int -> Page -> ShowS

show :: Page -> String

showList :: [Page] -> ShowS

Loading PDF's

openByteString :: ByteString -> Maybe Document

Open PDF represented as bytestring. If document cannot be parsed as valid PDF, Nothing is returned.

openFile :: FilePath -> IO (Maybe Document)

Open PDF from file. If file does not exist or cannot be parsed as valid PDF, Nothing is returned.

Document functions

page :: Int -> Document -> Maybe Page

Return page number no from PDF document, if the page exists.

pages :: Document -> [Page]

Return all pages from document.

pagesTotal :: Document -> Int

Return number of pages contained in document.

pdftotext :: Layout -> Document -> Text

Extract text from PDF document with given Layout.

Page functions

pageNumber :: Page -> Int

Number of this page in original document.

pageOutOf :: Page -> Int

Total number of pages in original document.

pageText :: Layout -> Page -> Text

Extract text from a page with given Layout.