backup.sh

#!/bin/bash

#
# Backs up my entire website, in case Tumblr or CloudApp goes down someday.
# Last time I ran this, it took 18 minutes.
#

wget \
  --mirror             `# turns on recursion and timestamping, basically says we want to "mirror" the whole site` \
  --convert-links      `# after download, convert all links to point to localhost` \
  --page-requisites    `# download images and stylesheets and stuff` \
  --adjust-extension   `# add .html extensions for local viewing` \
  -H                   `# allow crawling to external hosts besides nfarina.com (needed for cl.ly image links)` \
  -Dcl.ly,nfarina.com  `# allowed hosts` \
  -e robots=off        `# cl.ly's robots.txt requests no crawling at all. Makes sense for Google, not for us` \
  -w 2                 `# wait two seconds between HTTP requests` \
  http://nfarina.com