On Fri, Sep 9, 2011 at 4:17 AM, Daniel Patterson
<lists.haskell@dbp.mm.st> wrote:
It looks to me that the link is generated by javascript, so unless you can script an actual browser into the loop, it may not be a viable approach.
On Sep 8, 2011, at 3:57 PM, mukesh tiwari wrote:
> I tried to use the PDF-generation facilities . I wrote a script which
> generates the rendering url . When i am pasting rendering url in
> browser its generating the download file but when i am trying to get
> the tags , its empty. Could some one please tell me what is wrong with
> code.
> Thank You
> Mukesh Tiwari
>
> import Network.HTTP
> import Text.HTML.TagSoup
> import Data.Maybe
>
> parseHelp :: Tag String -> Maybe String
> parseHelp ( TagOpen _ y ) = if ( filter ( \( a , b ) -> b == "Download
> a PDF version of this wiki page" ) y ) /= []
> then Just $ "http://en.wikipedia.org" ++ ( snd $
> y !! 0 )
> else Nothing
>
>
> parse :: [ Tag String ] -> Maybe String
> parse [] = Nothing
> parse ( x : xs )
> | isTagOpen x = case parseHelp x of
> Just s -> Just s
> Nothing -> parse xs
> | otherwise = parse xs
>
>
> main = do
> x <- getLine
> tags_1 <- fmap parseTags $ getResponseBody =<< simpleHTTP
> ( getRequest x ) --open url
> let lst = head . sections ( ~== "<div class=portal id=p-coll-
> print_export>" ) $ tags_1
> url = fromJust . parse $ lst --rendering url
> putStrLn url
> tags_2 <- fmap parseTags $ getResponseBody =<< simpleHTTP
> ( getRequest url )
> print tags_2