Holumbus.Crawler.PdfToText

Documentation

pdfToText :: String -> IO String

Conversion of pdf data into plain text. The conversion is done by calling an external program pdftotext (contained in linux packages xpdf). IO is done via the ByteString API.

pdfToTextBS :: ByteString -> IO String

pdfToTextA :: IOSArrow String String

pdfResource :: MVar (FilePath, FilePath)

requestPdf :: IO (FilePath, FilePath)

releasePdf :: (FilePath, FilePath) -> IO ()