A script to download the archives of Girl Genius, Buck Godot and BattlePug locally. Designed so you can add your own comics to it. PLEASE SUPPORT THE ARTISTS!

fetchComic.py

#!/usr/local/bin/python

from bs4 import BeautifulSoup
from urllib2 import urlopen
from urllib import urlretrieve
import argparse

class getComic:
	"""Base class for comics
	"""
	
	# override these
	comicName=None
	host=None
	firstComic=None
	
	def getImage( self, pgsoup ):
		"""override this
		"""
		return None
		
	def getNext(  self, pgsoup ):
		"""override this
		"""
		return None

        # Don't override these

	def grabPage( self, url ):
		pg = urlopen( url )
		pgsoup = BeautifulSoup( pg )
		imageurl = self.getImage( pgsoup )
		nexturl =  self.getNext(  pgsoup )
		return imageurl,nexturl
	
	def getImages( self ):
		
		savename = self.comicName + "_%05d.jpg"
		count = 0
		nexturl = self.host % self.firstComic

		while nexturl:
			comic,nexturl = self.grabPage( nexturl )
			print "Grabbing " + savename % count
			urlretrieve( comic, savename % count )
			count+=1


class BattlePug( getComic ):
	
	comicName = "BattlePug"
	host = "http://battlepug.com/%s"
	firstComic = "/comic/first"
	
	def getImage( self, pgsoup ):
                pgcomic=pgsoup.body.find('div',id='comic')
                pgpage=pgcomic.find('div','page')
                imageurl = pgpage.img['data-image']
                return imageurl
                
        def getNext(  self, pgsoup ):
                pgtrans=pgsoup.body.find('div',id='transport')
                pgnext=pgtrans.find_all('a')[3]  #next
                if pgnext.has_attr('href'):
                        nexturl=pgnext['href']
                else:
                        nexturl=None
                return self.host % nexturl


class BuckGodot( getComic ):

        comicName = "Buck Godot"
        host = "http://www.airshipentertainment.com/%s"
        firstComic = "buckcomic.php?date=20070111"

        def getImage( self, pgsoup ):
                i = pgsoup.find('img',alt='Comic')
                return i['src']

        def getNext(  self, pgsoup ):
                n = pgsoup.find('img',alt='The Next Comic')
                return n.parent['href']
        
class GirlGenius( getComic ):

        comicName = "Girl Genius"
        host = "http://www.girlgeniusonline.com/%s"
        firstComic = "comic.php?date=20021104"

        def getImage( self, pgsoup ):
                i = pgsoup.find('img',alt='Comic')
                return i['src']

        def getNext(  self, pgsoup ):
                n = pgsoup.find('a',title='The Next Comic')
                return n['href']
        

if __name__ == '__main__':

        parser = argparse.ArgumentParser()
        parser.add_argument( 'comicName', type = str, help = "the comic to download")
        args = parser.parse_args()
        
	sparkles = BattlePug()
        winslow  = BuckGodot()
        agatha   = GirlGenius()

        for bla in [ sparkles, winslow, agatha ]:
                if ( args.comicName == bla.comicName ):
                        bla.getImages()