Python Talks to Questionable Content

Yeah, I know it's late, but I got obsessed and couldn't turn away. Now I have a really slick python script that pulls down the latest Questionable Content strip and adds it to my collection to read later:

#!/usr/bin/env python

import os, sys, re
import pycurl, urllib2

destination = "/path/to/qc/repository"

class QC:

  def __init__(self):

    self.contents = ''
    self.baseurl  = 'http://questionablecontent.net/'


  def callback(self,buf):

    self.contents = self.contents + buf


  def end(self):

    c = pycurl.Curl()
    c.setopt(c.URL, self.baseurl)
    c.setopt(c.WRITEFUNCTION, self.callback)
    c.perform()
    c.close()

    try:
      return int(re.search('.*\/comics\/(\d+)\.png', self.contents).group(1))
    except:
      print ""
      print "  The regular expression no longer works."
      print "  You might want to check into that."
      print ""
      exit()


  def fetch(self,n):

    strip = urllib2.build_opener().open(self.baseurl + 'comics/' + str(n) + ".png").read()

    f = "%s%s%04d%s" % (destination, "/", n, ".png")

    fout = open(f, "wb")
    fout.write(strip)
    fout.close()


# Main -----------------------------------------------------------------------

qc = QC()

for i in range(1, qc.end() + 1):
  f = "%s%s%04d%s" % (destination, "/", i, ".png")
  if not os.path.exists(f):
    print "Fetching strip #" + str(i)
    qc.fetch(i)