!/bin/bash

Web slurping script

for srcurl in "$@"
do

Title content extraction

title=`echo $srcurl | wget -i - -q -O - | nkf --utf8 | grep "<title>.*</title>\|<TITLE>.*</TITLE>" | sed -e "s/\(.*<title>\|.*<TITLE>\)\(.*\)\(<\/title>.*\|<\/TITLE>.*\)/\2/g"`

Headline generation

headline=`echo "[$title]($srcurl)"`

Body content extraction

body=`w3m $srcurl`

Output

echo "*"$'\t'"$headline"$'\n'$'\n'$'\n'"$body"$'\n'$'\n'
done
　
よーしこれで記事収集の手間が減らせる。