Punjab Digital Library Image Downloader

pdl.py

'''
Punjab Digital Library Img Fetcher
By Sarabveer Singh (me@sarabveer.me)
'''
import os
import urllib.request as urllib

print('Punjab Digital Library Img Fetcher')
print('----------')

# ID of Manuscript
# Example: http://www.panjabdigilib.org/webuser/searches/displayPage.jsp?ID=8790&page=1&CategoryID=1&Searched=
# The ID here would be: 8790
id = input('Enter PDL Book ID Number: ')

# First Page Number
# Usually 1
firstPage = input('Enter First Page Number: ')

# Last Page Number
lastPage = input('Enter Last Page Number: ')

# Create Directory
dir = 'PDL-' + id
if not os.path.exists(dir):
    os.makedirs(dir)
    
# Start Download
errors = ''
print('Start downloading:', dir, '...')
for page in range(int(firstPage), int(lastPage)+1):
    try:
        urllib.urlretrieve("http://www.panjabdigilib.org/images?ID=" + id + "&page=" + str(page) + "&CategoryID=1&pagetype=1&Searched=W3GX", dir + "/" + str(page) + ".jpg")
        print('Downloaded Page:', page)
    except:
        print('Error Downloading Page:', page)
        errors += str(page) + ' '

    
print('Finished downloading:', dir)

if errors != '':
    print('Unable to download following pages:', errors)

input("Press enter to exit...")