extracturls.hs

-- extracturls.hs
import Text.Pandoc

extractURL :: Inline -> [String]
extractURL (Link _ (u,_)) = [u]
extractURL (Image _ (u,_)) = [u]
extractURL _ = []

extractURLs :: Pandoc -> [String]
extractURLs = queryWith extractURL

readDoc :: String -> Pandoc
readDoc = readMarkdown defaultParserState

main :: IO ()
main = interact (unlines . extractURLs . readDoc)

print_missing_images.sh

cat foo.txt| runhaskell ./extracturls.hs | xargs -0 python -c "import sys,os; fnames=sys.argv[1].split(); foo=[fn for fn in fnames if not os.path.exists(fn)]; print 'missing files: \n%s' % ('\n'.join(foo),)"