#!/bin/sh
GET=fetch
#GET=echo
FILETYPES="jpg jpeg png gif"
filename() {
echo $1 | grep -o '[^/]*$'
}
get_img() {
if [ ! -f `filename $1` ]; then
echo getting $1
$GET $1
else
echo $1 already exists.
fi
}
grab_board() {
url=$1
dir=$2
prefix=`echo $url | sed 's/[^/]*$//'`
board=`filename $url`
mkdir $dir
cd $dir
mkdir thumbs
echo board $board
$GET $url
for link in `egrep -o 'a href="[^"]+' $board | egrep -o '[^"=]*res[^" #]+' | uniq`; do
echo $link | grep '^http://'
if [ $? = 0 ]; then
$GET $link
else
$GET $prefix$link
fi
done
for thread in `ls *html`; do
thumbs=`egrep -io 'img src="?[^" #]+' $thread | egrep -o '[^="]+$' | grep thumb`
cd thumbs
for img in $thumbs; do
get_img $img
done
cd ..
for type in $FILETYPES; do
imgs=`egrep -io 'a href="?[^" #]+' $thread | egrep -o '[^="]+$' | grep -i $type\$`
for img in $imgs; do
get_img $img
done
#echo $imgs
done
done
echo '' > index.html
lines=`wc -l ../index.html | awk '{ print $1 }'`
tail -$(($lines - 2)) ../index.html | head -$(($lines - 4)) | sed 's,"\([^"]*\)","../\1",' >> index.html
date >> index.html
echo '
' >> index.html
for type in $FILETYPES; do
for img in `ls *$type`; do
thumb=`echo $img | cut -d . -f 1`s.jpg
echo '
' >> index.html
done
done
echo '' >> index.html
cd ..
}
#n=`wc -l $1 | awk '{ print $1 }'`
#for i in `jot $n 1`; do
# line=`cat $1 | head -$i | tail -1`
# url=`echo $line | awk '{ print $1 }'`
# dir=`echo $line | awk '{ print $2 }'`
# grab_board $url $dir
#done
grab_board $1 $2