split_web

   1 #!/bin/sh
   2
   3 LANGUAGES=en
   4
   5 for LANG in ${LANGUAGES}; do
   6     rm -f *er?.${LANG}.html
   7     wget -q -O- http://www.debian.org/CD/index.${LANG}.html | awk -v LANG=$LANG '
   8
   9         /^<div id="header">/               {state="header1"}
  10         /^<p id="breadcrumbs">/            {state=""}
  11
  12         /^<\/div> <!-- end header -->/     {state="header2"}
  13         /^<div id="maincol">/              {state=""}
  14
  15         /^<\/div> <!-- end maincol -->/    {state="footer1"}
  16         /^<div id="pageLang">/             {state=""}
  17
  18         /\/MailingLists\/disclaimer/       {state="footer2"}
  19         /^<\/div> <!-- end footermap -->/  {print $0 >> "footer2."LANG".html";state=""}
  20
  21 /.*/ {
  22          gsub("\"\\.\\./","\"http://www.debian.org/")
  23          gsub("\"/\"","\"http://www.debian.org/\"")
  24          gsub("/MailingLists/","http://www.debian.org/MailingLists/")
  25          if (state == "header1") { print $0 >> "header1."LANG".html" }
  26          if (state == "header2") { print $0 >> "header2."LANG".html" }
  27          if (state == "footer1") { print $0 >> "footer1."LANG".html" }
  28          if (state == "footer2") { print $0 >> "footer2."LANG".html" }
  29      }'
  30
  31 done