Final cleanups to get the download working.

[dead/lwn-epub.git] / src / LWN / HTTP.hs

diff --git a/src/LWN/HTTP.hs b/src/LWN/HTTP.hs
index c74248ba9dca05bdcc54c2417758906ecd021212..71058dc67040b69da700e2744fe1daa796ae3607 100644 (file)
--- a/src/LWN/HTTP.hs
+++ b/src/LWN/HTTP.hs
@@ -1,7 +1,10 @@
+{-# LANGUAGE DoAndIfThenElse #-}
+
 module LWN.HTTP
 where
 
 import qualified Data.ByteString as B (hPut)
+
 import Network.Curl (
   CurlCode(..),
   CurlOption(..),
@@ -11,12 +14,12 @@ import Network.Curl (
   initialize,
   respBody,
   respCurlCode,
-  withCurlDo               
+  withCurlDo
   )
 import Network.Curl.Download (openURI)
-import System.Directory (getTemporaryDirectory)
-import System.IO (hPutStrLn, stderr)
-import System.IO.Temp (openBinaryTempFile)
+import System.Directory (doesFileExist, getTemporaryDirectory)
+import System.IO (hClose, hPutStrLn, stderr)
+import System.IO.Temp (openBinaryTempFile, openTempFile)
 
 import LWN.URI (filename)
 
@@ -41,16 +44,23 @@ default_curl_opts =
     -- And we don't want to use a DNS cache anyway.
     CurlDNSCacheTimeout 0,
 
-    -- Give it a little time...
-    CurlTimeout 45,
+    -- Follow redirects.
+    CurlFollowLocation True,
 
-    -- And let us know when things go wrong.
-    CurlVerbose True ]
+    -- Give it a little time...
+    CurlTimeout 45 ]
 
 
+make_cookie_jar :: IO FilePath
+make_cookie_jar = do
+  temp_dir <- getTemporaryDirectory
+  let file_name_template = "lwn-epub-cookies.txt"
+  (out_path, out_handle) <- openTempFile temp_dir file_name_template
+  hClose out_handle -- We just want to create it for now.
+  return out_path
 
-get_page :: Maybe FilePath -> URLString -> IO (Maybe String)
-get_page cookie_jar url =
+get_page :: Maybe FilePath -> URLString -> IO (Either String String)
+get_page cookie_file url =
   withCurlDo $ do
     -- Create a curl instance.
     curl <- initialize
@@ -58,29 +68,30 @@ get_page cookie_jar url =
     -- 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).
-    resp <- do_curl_ curl login_url curl_opts :: IO CurlResponse
+    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_jar of
+      case cookie_file of
         Nothing -> []
-        Just cookies -> [ CurlCookieJar cookies ]
+        Just cookies -> [ CurlCookieFile cookies ]
 
     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
     -- Create a curl instance.
@@ -94,14 +105,13 @@ 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"
@@ -113,7 +123,7 @@ log_in cookie_jar username password =
     post_password = password_field ++ "=" ++ password
 
     post_data :: [String]
-    post_data = [post_username, post_password]
+    post_data = [post_username, post_password, post_submit]
 
     post_opts :: [CurlOption]
     post_opts =
@@ -135,17 +145,22 @@ log_in cookie_jar username password =
 --   knows that type (jpg, png, etc.) it is.
 save_image :: URLString -> IO (Maybe FilePath)
 save_image url = do
-  let fn = filename url
-  case fn of
-    Nothing -> return Nothing
-    Just file -> do
-      temp_dir <- getTemporaryDirectory
-      (out_path, out_handle) <- openBinaryTempFile temp_dir file
-      result <- openURI url
-      case result of
-        Left err -> do
-          hPutStrLn stderr ("HTTP Error: " ++ err)
-          return Nothing
-        Right bs -> do
-          B.hPut out_handle bs
-          return $ Just out_path
+  it_exists <- doesFileExist url
+  if it_exists then do
+    -- It's local, just use it.
+    return $ Just url
+  else do
+    let fn = filename url
+    case fn of
+      Nothing -> return Nothing
+      Just file -> do
+        temp_dir <- getTemporaryDirectory
+        (out_path, out_handle) <- openBinaryTempFile temp_dir file
+        result <- openURI url
+        case result of
+          Left err -> do
+            hPutStrLn stderr ("HTTP Error: " ++ err)
+            return Nothing
+          Right bs -> do
+            B.hPut out_handle bs
+            return $ Just out_path