Skip to content

Instantly share code, notes, and snippets.

@takaki

takaki/gist:3891747

Created October 15, 2012 09:48
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save takaki/3891747 to your computer and use it in GitHub Desktop.
Save takaki/3891747 to your computer and use it in GitHub Desktop.
Download ZIP
HXT, XPath
Raw
gistfile1.hs
import Codec.Binary.UTF8.String
import Codec.Text.IConv
import Data.List
import Text.XML.HXT.Core
import qualified Data.ByteString.Lazy as BSL
import Text.XML.HXT.XPath.Arrows
-- 日本語
main = do
cs <- BSL.readFile "4731398C.html"
let u8s = convert "CP932" "UTF-8" cs
let html = decode (BSL.unpack u8s)
let doc = readString [withParseHTML yes, withWarnings no] html
nodes <- runX $ doc
>>>
getXPathTrees "//*[@id=\"main\"]/form/div[4]/table/tr/td[1]/table[1]/tr[1]/td/div/p"
//> getText
mapM_ ( putStrLn . id) nodes
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment