ZenPencils Scraper.py

def main():
	from urllib.request import Request, urlopen, urlretrieve
	from os.path import isfile
	import re

	print('** WELCOME **\n\n')
	comic_base_url='http://zenpencils.com/comic/'
	img_base_url='http://1j74duke02o49spu52ub76g1bzq.wpengine.netdna-cdn.com/wp-content/uploads/'

	print('** DOWNLOADING CRUCIAL DATA **')
	root_source = urlopen(Request(comic_base_url, headers={'User-Agent': 'Chrome'})).read()

	print('** GENERATING LIST OF COMICS **\n\n')
	all_comics_url_list=re.search('<option.*/option>',str(root_source)).group(0).split('\\n')

	print('** STARTING COMIC DOWNLOADS  **\n')
	for link in all_comics_url_list:
		comic_id=re.search('(%s)(.*)(/\">)'%comic_base_url,link).group(2)

		if isfile('ZenPencils/%s.png'%comic_id) or isfile('ZenPencils/%s.gif'%comic_id) or isfile('ZenPencils/%s.jpg'%comic_id):
			print('%s already exists  ---  moving on\n'%comic_id)
			continue

		print('%s  ---  begin'%comic_id)

		comic_url=comic_base_url+comic_id
		comic_source = urlopen(Request(comic_url, headers={'User-Agent': 'Chrome'})).read()

		img_url = re.search('(%s)([0-9]+.*)(\.[a-z]+.*)(\" alt=\"\" title=\"\")'%img_base_url, str(comic_source))
		img_id=img_url.group(2)
		img_format=img_url.group(3)
		img_url=img_url.group(1)+img_url.group(2)+img_url.group(3)

		urlretrieve(img_url,'ZenPencils/%s%s'%(comic_id,img_format))

		print('%s  ---  done\n'%comic_id)
	print('\n** ALL DOWNLOADS FINISHED **')

if __name__ == '__main__':
	main()