Download math books from springer

gistfile1.txt

from urllib2 import urlopen
from re import findall, search

base_url = "http://link.springer.com"

links = []

for i in xrange(1, 13):
	index = base_url + '/search/page/%d?facet-series="136"&facet-content-type="Book"&showAll=false' % i
	links.extend(findall('<a class="title" href="(.*?)"', urlopen(index).read()))

for link in links:
    page = urlopen(base_url + link).read()
    name = search('<h1 id="title">(.*?)<', page).group(1)
    pdf = re.search('<a id="toc-download-book-pdf.*?href="(.*?)"', page).group(1)
    print 'Downloading', name
	with open(name+'.pdf', 'w') as book:
		book.write(urlopen(base_url + pdf).read())
	print 'Done'