Update README.md

README.md

-# halCrawler
+# HAL API Crawler
 
 ## API documentation
-https://api.archives-ouvertes.fr/docs
\ No newline at end of file
+
+## Base website
+https://api.archives-ouvertes.fr/docs
+
+## Usage
+### Entry function
+The basic entry point of this crawler is the function `HAL.` `getMetadataWith`.
+
+This function take a `Text` representing the query you want to run on hal
+and a `Maybe Int` representing the maximum number of result you want to get.
+### Return Type
+The return type is a bit more tricky, it's **either** a `ClientError` or a `HAL.Client` `Response Corpus`.
+In the usage it's exactly working as the other crawler `Documents` type, but it facilitate on the implementation side.
+
+`Response x` represent a collection of `x` and the number of `x` returned.
+
+` HAL.Doc.Corpus.` `Corpus` is a simple type that contain every informations we need (id,title,abstract,publicationDate,sources).
+
+### Exemple
+Here is a basic main using the entry point of the crawler and printing the 5 first results.
+```hs
+{-# LANGUAGE OverloadedStrings #-}
+
+module Main where
+
+import Network.HTTP.Client (newManager)
+import Network.HTTP.Client.TLS (tlsManagerSettings)
+import Servant.Client
+
+import HAL (getMetadataWith)
+import HAL.Client
+import HAL.Doc
+import Tree
+
+main :: IO ()
+main = do
+  res <- getMetadataWith "artificial intelligence" (Just 10)
+  case res of
+    (Left  err) -> print err
+    (Right val) -> print $ take 5 $ _docs val
+
+
+```
+