Scraping the darwin awards page

gistfile1.txt

curl 'http://darwinawards.com/darwin/darwin[1993-2013].html' -o '#1.html'

cat *.html | grep -o -E 'href="([^"#]+)"' | cut -d'"' -f2 |  sort | uniq | grep -o -E '^.*darwin.*$' | grep -v '/' | grep '-'
rm *.html
#!/bin/sh
while read line
do
    echo "http://darwinawards.com/darwin/$line">>url2.txt
done < url.txt


wget -i url2.txt