import urllib
import urllib2
import os

#function to add preceding 0's to pages when necessary
def fix(input):
    desired = 3
    while len(input) < desired:
        input = "0"+input

    return input


# defining what to download
prefix = "http://quod.lib.umich.edu/cache/a/g/e/age2118.0001.001/00000"
suffix = ".tif100.gif"
prefix2 = "http://quod.lib.umich.edu/g/genpub/AGE2118.0001.001/"
suffix2 = "?rgn=full+text;view=image"

for page in range(398):

    #set the specific URLs
    pagestr = fix(str(page+1))

    #try to download the picture, retry if it fails
    try:

        print "trying page"+pagestr

        statinfo = os.stat("page"+pagestr+".gif")

        while statinfo.st_size < 3000:

            #visiting the page before
            response = urllib2.urlopen(prefix2+pagestr+suffix2)
            page_source = response.read()

            #file0 = open("page"+pagestr+".html",'w')
            #file0.write(page_source)

            #print upon completion
            print "read page "+pagestr

            #download the picture in gif
            urllib.urlretrieve (prefix+pagestr+suffix, "page"+pagestr+".gif")

            statinfo = os.stat("page"+pagestr+".gif")

            if statinfo.st_size < 3000:
                specialurl = "http://quod.lib.umich.edu/cache//a/g/e/age2118.0001.001/p0000"+pagestr+".jp2.100.jpg"
                print specialurl

                urllib.urlretrieve (specialurl, "page"+pagestr+".gif")

            #print upon completion
            print "downloaded picture "+pagestr

            statinfo = os.stat("page"+pagestr+".gif")





    except:
        continue