Atomise.sh

#!/bin/bash

# atomise.sh - converts the MPlayer website’s news.src.en into an Atom feed.
#
# Copyright 2007 Hagfish
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License,
# version 2, as published by the Free Software Foundation.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.


function outputHead
{
cat <<Here-document
<?xml version="1.0" encoding="UTF-8" ?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <id>http://www.mplayerhq.hu/atomise.xml</id>
  <title>MPlayer - The Movie Player</title>
  <subtitle>MPlayer News</subtitle>
  <link rel="self" type="application/atom+xml" href="http://www.mplayerhq.hu/atomise.xml"/>
  <link href="http://www.mplayerhq.hu/design7/news.html" />
  <author><email>webmaster@mplayerhq.hu</email><name>Webmaster</name></author>
Here-document
}

function outputMetaData
{
        echo "<id>http://www.mplayerhq.hu/atomise.xml/"$isoDate"T00:00:00Z</id>"
        echo "<title>$title</title>"
        echo "<updated>"$isoDate"T00:00:00Z</updated>"
        echo ‘<link rel="alternate" type="text/html" href="http://www.mplayerhq.hu/mplayernews.html#’$anchor‘" />’
        echo "<author><name>$author</name></author>"
}

function gatherMetaData
{
        extractDate $i
        extractTitle $i
        extractAnchor $i
        extractAuthor $i
}

function extractDate
{
        # try removing the text " :: " from the end of the line
        aDatePlus=${line%% :: *}
        #echo $datePlus
        if [ "$aDatePlus" != "$line" ]
        then # the removal has shortened the line, so this line contains the token present on a line with a date
        datePlus=${aDatePlus##*>}
        date=${datePlus%%,*}
        isoDate=${date//./-}
        fi
}

function extractTitle
{
        # try removing the text " :: " from the beginning of the line
        titlePlus=${line##* :: }
        #echo $titlePlus
        if [ "$titlePlus" != "$line" ]
        then # the removal has shortened the line, so this line contains the token present on a line with a title
        title=${titlePlus%%</a>*}
        fi
}

function extractAnchor
{
        # try removing the text " :: " from the end of the line
        aAnchorDate=${line%% :: *}
        #echo $aAnchorDate
        if [ "$aAnchorDate" != "$line" ]
        then # the removal has shortened the line, so this line contains the token present on a line with an anchor
        anchorDate=${aAnchorDate##*<a name=?}
        anchor=${anchorDate%%?>*}
        fi
}

function extractAuthor
{
        # try removing the text "posted by" from the beginning of the line
        authorPlus=${line##*posted by }
        #echo $authorPlus
        if [ "$authorPlus" != "$line" ]
        then # the removal has shortened the line, so this line contains an author
        author=${authorPlus%%</span>}
        fi
}

function encodeEntities
{
        noAmps=${line//&[^a]/&amp;}
        noOpenBracket=${noAmps//</&lt;}
        noCloseBracket=${noOpenBracket//>/&gt;}
        line=$noCloseBracket
}

entryNumber=0
cat news.src.en | while read line
do

if [[ $mode = ‘waiting for content’ ]]
then
        if [[ $line = ‘</h2>’ ]]
        then # $line is the end of a metadata section
                # start the new entry
                if [ $entryNumber -eq 1 ]
                then # before the first entry, there is a head section which contains the date the feed was updated
                outputHead
                echo ‘<updated>’$isoDate‘T00:00:00Z</updated>’
                fi
                echo ‘<entry>’
                outputMetaData
                echo ‘<content type="html">’
                #this <div> is to match the uncaught </div> which in the source document closes the <div class="newsentry">
                echo ‘&lt;div&gt;’
                #Uncomment when the news page uses XHTML: echo ‘<content type="xhtml" xml:lang="en">’
                #Uncomment when the news page uses XHTML: echo ‘<div xmlns="http://www.w3.org/1999/xhtml">’
                mode=‘echoing content’
                continue
        else
                gatherMetaData $line
        fi
fi

if [[ $line = ‘<div class="newsentry">’ ]]
then # $line is the start of a new entry
        entryNumber=$(($entryNumber+1))
                # check whether this is the start of the first entry
                if [ $entryNumber -gt 1 ]
                then # this is not the first entry
                # close the previous entry
                echo ‘</content>’
                echo ‘</entry>’
                fi
        # the next lines are gathering metadata until the content section starts
        mode=‘waiting for content’
fi


if [[ $mode = ‘echoing content’ ]]
then
        # this is one of the content lines to echo
        #Minimal content debug mode: echo -n ${line:0:3}
        #When the page is XHTML and the <img /> tags self-close: echo $line
        encodeEntities $line
        echo $line
fi

done

echo ‘</content>’
echo ‘</entry>’
echo ‘</feed>’