-- Hoogle documentation, generated by Haddock
-- See Hoogle, http://www.haskell.org/hoogle/


-- | A Haskell library to scrape and crawl web-pages
--   
--   A Haskell library to scrape and crawl web-pages
@package hScraper
@version 0.1.0.0


-- | Module for tidying Malformed html using libtidy(see README).
module HScraper.Tidy

-- | Takes Malformed html and reuturns correct html if it can be corrected.
--   Output is empty if it cannot be corrected.
tidy :: Text -> IO Text


-- | Module for fetching different requests over network(Wrapper around
--   http-conduit).
module HScraper.Network

-- | A Simple wrapper around simpleHttp so that it goes along with with
--   other functions.
fetchResponse :: String -> IO Text

-- | Parses a list of (key,value) pairs to pass with GET and POST requests.
parseParams :: [(String, String)] -> String

-- | takes a Request and a Manager and returns the response. Useful when
--   querying with a modified request.
fetchRequestWith :: Request -> Manager -> IO Text

-- | Minimal GET request, modify it to add proxy,cookies,user-agent etc.
--   Then fetch using @fetchRequestWith.
defaultGETRequest :: String -> [(String, String)] -> IO Request

-- | Fetches request using @defaultGETRequest.
fetchGETRequest :: String -> [(String, String)] -> IO Text

-- | Minimal POST request, modify it to add proxy,cookies,user-agent etc.
--   Then fetch using @fetchRequestWith.
defaultPOSTRequest :: String -> [(String, String)] -> IO Request

-- | Fetches request using @defaultPOSTRequest.
fetchPOSTRequest :: String -> [(String, String)] -> IO Text

module HScraper.Types
data NodeType
Text :: Text -> NodeType
Element :: Text -> AttrList -> NodeType
data NTree a
NTree :: a -> [NTree a] -> NTree a
NullTree :: NTree a
type AttrList = [(Text, Text)]
type HTMLTree = NTree NodeType
toLeaf :: Text -> HTMLTree
toTree :: Text -> AttrList -> [HTMLTree] -> HTMLTree
type Name = Text
type Class = Maybe Text
type ID = Maybe Text
data NodeQuery
NodeQuery :: Name -> Class -> ID -> NodeQuery
type Query = [NodeQuery]
instance GHC.Read.Read HScraper.Types.NodeQuery
instance GHC.Show.Show HScraper.Types.NodeQuery
instance GHC.Show.Show HScraper.Types.NodeType
instance GHC.Show.Show a => GHC.Show.Show (HScraper.Types.NTree a)
instance GHC.Classes.Eq HScraper.Types.NodeType
instance GHC.Classes.Eq a => GHC.Classes.Eq (HScraper.Types.NTree a)


-- | A simple <a>Query</a> format to query the <a>HTMLTree</a>.
--   
--   The Syntax is as follows : <tt>
--   "nodeName[Class(optional)]{ID(optional)} &gt;
--   nodeName[Class(optional)]{ID(optional)}" </tt>
--   
--   eg : <tt>"div{id1} &gt; span[class][id_h1] &gt; a"</tt>
module HScraper.Query
parseQuery :: String -> Either ParseError Query

-- | Compares <a>NodeQuery</a> with a <a>NodeType</a>.
(~=~) :: NodeQuery -> NodeType -> Bool

-- | Applies <a>&gt;=&gt;</a> considering each node as root and combines
--   the result.
(|>>) :: HTMLTree -> Query -> [HTMLTree]

-- | Returns the list of nodes matching the query with root matching the
--   first NodeQuery, and subsequent Children satisfying subsequent
--   <tt>NodeQueries</tt> continously.
(>=>) :: HTMLTree -> Query -> [HTMLTree]

-- | Get Combined Text of immediate children of current node.
getText :: HTMLTree -> Text

-- | Get Entire text contained in the subtree.
getEntireText :: HTMLTree -> Text

-- | Get the value of an attribute of a node.
getAttribute :: String -> HTMLTree -> Maybe String


-- | Module for parsing html.
module HScraper.HTMLparser
parseHtml :: Text -> Either ParseError HTMLTree

module HScraper.Show

-- | takes a <tt>HTMLtree</tt> and prints it in a neat manner.
--   
--   expected output
--   
--   <pre>
--   |html
--          |head
--          |body
--                 YOLO
--   
--   </pre>
showTree :: IO HTMLTree -> IO ()


-- | Module for various convenience functions and error-free wrappers of
--   parsers so that they can be used for batches of urls.
module HScraper.Main

-- | Tries to parse html from file. returns <a>NullTree</a> if parsing
--   fails.
getFromFile :: FilePath -> IO HTMLTree

-- | like <a>parseHtml</a> but returns <a>NullTree</a> if parsing fails.
getParsedHTML :: Text -> HTMLTree

-- | Takes a <a>String</a> and tries to parse as <a>Query</a> returns empty
--   query if parsing fails.
getParsedQuery :: String -> Query

-- | takes url and returns parsed <a>HTMLTree</a>.
parseSite :: String -> IO HTMLTree


-- | A library to parse, crawl and scrape webpages.
--   
--   An example :
--   
--   <pre>
--   import HScraper
--   
--   main :: IO ()
--   main = do
--     html &lt;- parseSite "<a>https://kat.cr/leopard-raws-taimadou-gakuen-35-shiken-shoutai-05-raw-sun-1280x720-x264-aac-mp4-t11528616.html/"</a>
--     let q1 = getParsedQuery "a[movieCover]"
--     print $ html |&gt;&gt; q1
--     let q2 = getParsedQuery "a"
--     let ans = html |&gt;&gt; q2
--     mapM_ (print . getAttribute "href" ) ans -- get all hyperlinks.
--   </pre>
module HScraper