Download all Dilbert strips do a directory or display a link

download_dilbert.py

#!/usr/bin/env python
from __future__ import print_function

import urllib
import sys
import os

from datetime import date, timedelta, datetime
from BeautifulSoup import BeautifulSoup

class DilbertDownload(object):
	"""Downloads all Dilbert Strips"""
	def __init__(self, path = '.'):
		self.base_url = "http://www.dilbert.com"
		self.url = "%s/strips/comic/%%s/" % self.base_url
		self.date_format = "%Y-%m-%d"
		self.start_date = datetime.strptime('1989-04-16', self.date_format)
		if os.path.isdir(path):
			self.path = path
		else:
			raise Exception('Directory "%s" does not exist' % path)

	def get_strip(self, url):
		soup = BeautifulSoup(urllib.urlopen(url).read())
		try:
			img = soup.find('img', attrs={'alt': 'The Official Dilbert Website featuring Scott Adams Dilbert strips, animations and more'})
			return self.base_url + img['src']
		except Exception, e:
			print("[ERROR]: %s" % e)
			return None

	def get_strip_url(self, date):
		date_string = date.strftime(self.date_format)
		return self.get_strip(self.url % date_string)

	def download_strip(self, date):
		date_string = date.strftime(self.date_format)
		print(date_string, end="...")
		img_url = self.get_strip(self.url % date_string)
		extention = img_url.split('.')[-1]
		urllib.urlretrieve(img_url, "%s/%s.%s" % (self.path, date_string, extention))
		print("[DONE]")

	def download_all(self):
		end_date = datetime.today()
		while end_date > self.start_date:
			self.download_strip(end_date)
			end_date = end_date-timedelta(days=1)

	def get_todays_url(self):
		today = datetime.today()
		return (self.get_strip_url(today))

if __name__ == "__main__":

	from optparse import OptionParser
	parser = OptionParser()
	parser.add_option("-d", "--directory", dest="directory", help="download directory")
	parser.add_option("-t", "--today", default=True, action="store_false", dest="todayslink", help="Get todays link")
	(opt, args) = parser.parse_args()

	if opt.todayslink:
		if opt.directory:
			dl=DilbertDownload(opt.directory)
		else:
			dl=DilbertDownload()
		dl.download_all()
	else:
		dl=DilbertDownload()
		print(dl.get_todays_url())