Last active
December 23, 2015 03:09
-
-
Save cdfmr/6571304 to your computer and use it in GitHub Desktop.
用Shell来抓取煎蛋妹子图
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/sh | |
delay=0 | |
timeout=10 | |
retry=2 | |
usage() | |
{ | |
echo "Usage: `basename $0` frompage topage" | |
exit 1 | |
} | |
[ $# -ne 2 ] && usage | |
[ $1 -le 0 ] || [ $2 -le 0 ] || [ $1 -gt $2 ] && usage | |
page=$1 | |
while [ $page -le $2 ] ; do | |
echo "[INFO] Downloading page $page ..." | |
imgs=`wget -q -O - http://jandan.net/ooxx/page-$page | grep -ioE '<img src="http.*\.(jpg|gif)" */>' | sed 's/<[Ii][Mm][Gg].*[Ss][Rr][Cc]\s*=\s*"*//;s/[" ].*//'` | |
[ -z "$imgs" ] && { | |
echo "[WARNING] Failed to get image list of page $page" | |
page=$((page+1)) | |
continue | |
} | |
index=1 | |
for img in $imgs ; do | |
wget -q --tries=$retry --timeout=$timeout -O "$page-$index.${img##*.}" "$img" | |
if [ $? -ne 0 ] ; then | |
rm -f "$page-$index.${img##*.}" | |
echo "[WARNING] Failed to download $img" | |
else | |
index=$((index+1)) | |
fi | |
done | |
page=$((page+1)) | |
[ $page -le $2 ] && sleep $delay | |
done | |
exit 0 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Cool!