name:          wp-archivebot
version:       0.1
license:       BSD3
license-file:  LICENSE
author:        Gwern
maintainer:    gwern0@gmail.com
stability:     Experimental
tested-with:   GHC==6.10.2
category:      Network
synopsis:      Subscribe to a wiki's RSS feed and archive external links
description:   A MediaWiki's RecentChanges or NewPages links to every new edit or article; this bot will
               poll the corresponding RSS feeds (easier and more reliable than parsing the HTML), follow
               the links to the new edit/article, and then use TagSoup to filter out every off-wiki link
               (eg. to http://cnn.com).
               .
               With this list of external links, the bot will then fire off requests to http://webcitation.org/,
               which will make a backup (similar to the Internet Archive, but on-demand).
               .
               Example: to archive links from every article in the English Wikipedia's RecentChanges:
               .
               > wp-archivebot gwern0@gmail.com 'http://en.wikipedia.org/w/index.php?title=Special:RecentChanges&feed=rss'
               .
cabal-version: >= 1.2
build-type:    Simple

executable wp-archivebot
    main-is:       Main.hs

    build-depends: feed,
                   tagsoup,
                   network,
                   HTTP
    build-depends: base >= 3 && < 4, parallel
    ghc-options:   -Wall