Download math books from springer

gistfile1.txt

import urllib2, re

pmax = 13
links = []
for i in xrange(1, pmax):
  index = 'http://link.springer.com/search/page/%d?facet-series="136"&facet-content-type="Book"&showAll=false' % i
  page = urllib2.urlopen(index).read()
  links.extend(re.findall('<a class="title" href="(.*?)"', page))

for link in links:
  url = 'http://link.springer.com' + link
  page = urllib2.urlopen(url).read()
  name = re.search('<h1 id="title">(.*?)<', page).group(1)
  pdf = re.search('<a id="toc-download-book-pdf.*?href="(.*?)"', page).group(1)
  print "wget http://link.springer.com" + pdf
  print 'mv %s "%s.pdf"' % (
    re.search("([^/]*)$", pdf).group(1),
    name)