Respekt - PDF links extraction

norespekt.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Pulls out links to PDFs from Respekt user section.
# *As the site allows only one logged in user at once,
#  you need to logout in your browser in order to use this script.
# usage:
#     $ ./norespekt.py > respekt_links
#     $ cat respekt_links | xargs -P 10 -r -n 1 wget -nv
#
# there's also js version over here https://gist.github.com/870509 
#
# @author:     starenka
# @email:      'moc]tod[liamg].T.E[0aknerats'[::-1]
# @version:    1.0.3
# @since       Dec 22, 2010

import re,mechanize

file_format, login, passwd = '', None, None

while not login:
    login = raw_input('Login? ')
while not passwd:
    passwd = raw_input('Heslo? ')
while file_format.lower() not in ('pdf','txt'):
    file_format = raw_input('Odkazy na PDF nebo TXT? ')

br = mechanize.Browser()
br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)
br.addheaders = [('User-agent', 'Opera/9.80 (X11; Linux i686; U; en) Presto/2.7.62 Version/11.00')]

br.open('http://service.ihned.cz/respekt/respekt-v-pdf.php?year=2004&number=37')
br.select_form(nr=1)
br.form['username'] = login
br.form['password'] = passwd
br.submit()

page = br.response().read()
br.open('http://respekt.ihned.cz/index.php?p=RRL000&login[logout]=1') #logout

parsed = {}
for tar,regexp in {'years':     r'var ay = new Array\((.*?)\)',
                   'ynrs':      r'var ayn = new Array\((.*?)\)',
                   'nrs':       r'var an = new Array\((.*?)\)',
                   'hashes':    r'var ah = new Array\((.*?)\)'
                   }.items():
    parsed[tar] = re.compile(regexp).search(page).group(1).replace('"','').split(',')

start = 0
for y,max in enumerate(parsed['ynrs'][:-1]):
    for i,hash in enumerate(parsed['hashes'][start:start+int(max)]):
        print 'http://81.95.101.5/download/pdf_respekt/%s/Respekt_%s_%s_%s%s.%s'%(parsed['years'][y],
                                                                                  file_format.upper(),
                                                                                  parsed['years'][y],
                                                                                  parsed['nrs'][start+i],
                                                                                  hash,
                                                                                  file_format
                                                                                )
    start += int(max)