source: trollforge/proxy/proxysuite/xroxy.sh @ 773 Tweet

#!/bin/sh
#

base_url="http://www.xroxy.com/proxylist.php?type=All_socks"
n=0
m=-1


wget -U Opera -q -O x.htm "${base_url}" 2>/dev/null ||\
 { echo "failed, ignoring"; }
n="`expr \`sed -n '/proxies selected/s/^.*b>\(.*\)<\/b> proxies.*$/\1/gp' x.htm\` / 10 + 1`"

echo '\c' > ips 2>/dev/null
while [[ $m -lt $n ]]
do
  m=`expr -- ${m} + 1`
  echo "downloading ${base_url}&pnum=${m}... \c"
  wget -U Opera -q -O x.htm "${base_url}&pnum=${m}" 2>/dev/null ||\
   { echo "failed, ignoring"; }
  echo "done"

  echo "  downloading proxies... \c"
  o=0

  sed -n '/with port number/s/^.*>\([0-9]*\)<.a>.*$/\1/gp' x.htm > ports
  for whois_url in `sed -n '/href=..*whois[0-9]*\.htm/s/^.*href=..\(whois[0-9]*\.htm\).*$/\1/gp' x.htm`
  do
    o=`expr $o + 1` ; echo "${o} \c"
    wget -U Opera -q -O u.htm "http://www.xroxy.com/${whois_url}" 2>/dev/null ||\
     { echo "failed."; rm -f ips ports x.htm u.htm; exit 1; }
    ip="`sed -n '/following IP address: /s/^.*details.><b>\(.*\)<.b.*$/\1/pg' u.htm`"
    p=0
    for line in `cat ports`
    do
      p=`expr $p + 1`
      if [[ $p == $o ]]; then
        echo $ip:$line >> ips ; break
      fi
    done
    
    rm -f u.htm 2>/dev/null
  done
  echo " done"
 
  rm -f x.htm 2>/dev/null
  sleep 1
done


mv ips socks_XR.txt
echo "`wc -l socks_XR.txt | awk '{print $1}'` total, \c"
#egrep -v '^$|:23|:8[018]|:108[018]|:3128|:808[018]|:8888' socks_XR.txt |\
cat socks_XR.txt |\
 sort -k1 -u | cat > socks_XR.tmp ; mv -f socks_XR.tmp socks_XR.txt
echo "`wc -l socks_XR.txt | awk '{print $1}'` after clean-up"