X-Git-Url: http://gitweb.michael.orlitzky.com/?p=dead%2Flwn-epub.git;a=blobdiff_plain;f=src%2FLWN%2FHTTP.hs;h=a8a1980f273cfdc352911bb7bcd3b55b58137cdf;hp=ea7174ad1e5b70d8ec9a6a9bc8b9ad3f0411fbba;hb=f3321e2ce7d7645ad562dc8f6620bfd561edc75d;hpb=5b4118c3497d02fc7b533f6b3f5db3b13969f99a diff --git a/src/LWN/HTTP.hs b/src/LWN/HTTP.hs index ea7174a..a8a1980 100644 --- a/src/LWN/HTTP.hs +++ b/src/LWN/HTTP.hs @@ -4,12 +4,11 @@ module LWN.HTTP where import qualified Data.ByteString as B (hPut) - +import qualified Data.Map as Map (Map, empty, insert) import Network.Curl ( CurlCode(..), CurlOption(..), CurlResponse, - URLString, do_curl_, initialize, respBody, @@ -18,12 +17,12 @@ import Network.Curl ( ) import Network.Curl.Download (openURI) import System.Directory (doesFileExist, getTemporaryDirectory) -import System.IO (hClose, hPutStrLn, stderr, stdout) +import System.IO (hClose, hPutStrLn, stderr) import System.IO.Temp (openBinaryTempFile, openTempFile) -import LWN.URI (filename) +import LWN.URI (URL, filename) -login_url :: URLString +login_url :: URL login_url = "https://lwn.net/login" username_field :: String @@ -48,10 +47,7 @@ default_curl_opts = CurlFollowLocation True, -- Give it a little time... - CurlTimeout 45, - - -- For debugging. - CurlVerbose True ] + CurlTimeout 45 ] make_cookie_jar :: IO FilePath @@ -62,33 +58,27 @@ make_cookie_jar = do hClose out_handle -- We just want to create it for now. return out_path -get_page :: Maybe FilePath -> URLString -> IO (Maybe String) +get_page :: Maybe FilePath -> URL -> IO (Either String String) get_page cookie_file url = withCurlDo $ do - hPutStrLn stdout ("Getting page: " ++ url ++ "...") - -- Create a curl instance. curl <- initialize -- Perform the request, and get back a CurlResponse object. -- The cast is needed to specify how we would like our headers -- and body returned (Strings). - putStrLn "Curl options:" - print curl_opts - resp <- do_curl_ curl url curl_opts :: IO CurlResponse -- Pull out the response code as a CurlCode. let code = respCurlCode resp - case code of - CurlOK -> return $ Just (respBody resp) - error_code -> do - hPutStrLn stderr ("HTTP Error: " ++ (show error_code)) + return $ + case code of + CurlOK -> Right (respBody resp) + error_code -> Left ("HTTP Error: " ++ (show error_code)) -- If an error occurred, we want to dump as much information as -- possible. If this becomes a problem, we can use respGetInfo to -- query the response object for more information - return Nothing where get_opts = case cookie_file of @@ -98,11 +88,11 @@ get_page cookie_file url = curl_opts = default_curl_opts ++ get_opts -log_in :: FilePath -> String -> String -> IO Bool +-- | Log in using curl. Store the resulting session cookies in the +-- supplied file. +log_in :: FilePath -> String -> String -> IO (Either String String) log_in cookie_jar username password = withCurlDo $ do - hPutStrLn stdout ("Logging " ++ username ++ " in...") - -- Create a curl instance. curl <- initialize @@ -114,14 +104,13 @@ log_in cookie_jar username password = -- Pull out the response code as a CurlCode. let code = respCurlCode resp - case code of - CurlOK -> return True - error_code -> do - hPutStrLn stderr ("HTTP Error: " ++ (show error_code)) + return $ + case code of + CurlOK -> Right (respBody resp) + error_code -> Left $ "HTTP Error: " ++ (show error_code) -- If an error occurred, we want to dump as much information as -- possible. If this becomes a problem, we can use respGetInfo to -- query the response object for more information - return False where post_submit :: String post_submit = submit_field ++ "=Log+In" @@ -153,7 +142,7 @@ log_in cookie_jar username password = -- We need to be able to parse the filename out of the URL -- so that when we stick our image in the document, the reader -- knows that type (jpg, png, etc.) it is. -save_image :: URLString -> IO (Maybe FilePath) +save_image :: URL -> IO (Maybe FilePath) save_image url = do it_exists <- doesFileExist url if it_exists then do @@ -174,3 +163,22 @@ save_image url = do Right bs -> do B.hPut out_handle bs return $ Just out_path + + + + +-- | Map absolute image URLs to local system file paths where the +-- image referenced by the URL is stored. +type ImageMap = Map.Map URL FilePath + +download_image_urls :: [URL] -> IO ImageMap +download_image_urls image_urls = do + files <- mapM save_image image_urls + let pairs = zip image_urls files + return $ foldl my_insert empty_map pairs + where + empty_map = Map.empty :: ImageMap + + my_insert :: ImageMap -> (URL, Maybe FilePath) -> ImageMap + my_insert dict (_, Nothing) = dict + my_insert dict (k, Just v) = Map.insert k v dict