sinfest_downloader.py

# NOTE: some of these will be 404s (30th of February, days with no comics, etc.)
# 404s can be removed with `find . -type f -size -1000c -iname "*.gif" -exec rm {} \;`

from urllib import urlretrieve

for y in range(2000, 2013):
    for m in range(1, 13):

        print "starting", y, m

        for d in range(1, 32):

            name = "%d-%02d-%02d.gif" % (y, m, d)
            url = "http://www.sinfest.net/comikaze/comics/" + name
            path = "./" + name

            try:
                urlretrieve(url, path)
            except:
                print url