marathon-pic-saver-2015.py

import urllib2
import lxml.html as lh
import re

USERAGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.86 Safari/537.36'
url = 'http://www.marathonfoto.com/Proofs?PIN=XXXX&LastName=XXXX'
BASE_URL = 'http://www.marathonfoto.com/Ajax/Zoom/?frameid={}'

# URL:
# http://www.marathonfoto.com/Proofs?PIN=XXXX&LastName=XXXX
# Frame URL:
# http://www.marathonfoto.com/Ajax/Zoom/?frameid=12345
# Image
# http://render.marathonfoto.com/Render/Z.ashx?O=123456&R=1234&F=0005&K=123234123

doc = lh.parse(urllib2.urlopen(url))
counter = 1
for frame in doc.iter('a'):
	if frame.text_content().strip().startswith("Enlarge"):
		frameid = frame.attrib['data-frameid']
		print BASE_URL.format(frameid)
		req = urllib2.Request(BASE_URL.format(frameid))
		req.add_header('Referer', url)
		req.add_header('User-Agent', USERAGENT)
		frame_content = urllib2.urlopen(req).read()

		p = re.compile(ur'\/\/(render\.marathonfoto\.com\/.*)\'\)')
		matches = re.search(p, frame_content)
		with open('/tmp/marathon-' + str(counter) + '.jpg', 'wb') as f:
			image_url = "http://" + matches.group(1)
			image_url = image_url.replace("&", "&")
			req = urllib2.Request(image_url)
			print image_url

			req.add_header('Referer', BASE_URL.format(frameid))
			req.add_header('User-Agent', USERAGENT)
			data = urllib2.urlopen(req)
			f.write(data.read())
			counter += 1