simple scientific american pdf url builder

parseit.py

#!/usr/bin/env python

from HTMLParser import HTMLParser
import urllib2, re

pdfre = re.compile(r"^pdf/1[89][0-9][0-9]-[0-9]{2}-[0-9]{2}\.pdf$")
journalpage = re.compile(r"^/scientificamerican/journal/v([1-9]|[1-9][0-9]|10[01])/")

class SAParser(HTMLParser):
        def __init__(self, linkcallback):
                HTMLParser.__init__(self)
                self.newlink = linkcallback

        def handle_starttag(self, tag, attrs):
                if tag.lower() == "a":
                        for attr in attrs:
                                if attr[0].lower() == "href":
                                        self.newlink(attr[1])


issues = list()

def issuelink(href):
        if journalpage.match(href):
                issues.append(href)

archivepage = urllib2.urlopen("http://www.nature.com/scientificamerican/archive/index_1909.html")

parser = SAParser(issuelink)
parser.feed(archivepage.read())
parser.close()
archivepage.close()

baseurl = ''
def pdflink(href):
        if pdfre.match(href):
                print "http://www.nature.com%s/%s" % (baseurl, href)

for issue in issues:
        baseurl = issue.rpartition('/')[0]

        page = urllib2.urlopen("http://www.nature.com%s" % issue)
        parser = SAParser(pdflink)
        parser.feed(page.read())
        parser.close()
        page.close()