#!/usr/bin/env python

#
# NOTE - This script requires Python version 2.0 or greater.
#        Replace "python" with "python2" above if necessary!
#

#
# patent.py - Get patent image from USPTO and convert to pdf.
#
#   usage: patent.py patent_number
#

#
# Copyright (c) 2002, 2006  Everett Lipman
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
# 
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
# 
# The GNU General Public License is available at
#
#    http://www.fsf.org/copyleft/gpl.html
#
# Alternatively, you can write to the 
#
#    Free Software Foundation, Inc.
#    59 Temple Place - Suite 330
#    Boston, MA  02111-1307, USA
#

#
# How to use this script:
#
# Change the WORKINGDIR variable below to the name of a
# directory where the script can safely create files of
# the form 'patent_number.P' and 'patent_number.ps'.
# 'patent_number' is the number you specified on the
# command line, and 'P' is a page number.  The final
# output will be in 'patent_number.pdf'
#
# You must have working versions of ps2pdf and tiff2ps
# available.  Specify the locations of these programs
# in the variables PSPDF and TIFFPS below.  ps2pdf comes
# with Ghostscript, and tiff2ps comes with libtiff.
#
# This script is a kludge, and is guaranteed to break
# if the USPTO changes their web interface.  Consider
# yourself lucky if it isn't already broken.
#
# 31 July 2002  Everett Lipman
#
# 04May06  Updated to work with modified USPTO interface
#

###############################################################################

import sys
import os
import urllib
import string

###############################################################################

def usage(message = ''):
   sys.stdout = sys.stderr
   if message != '':
      print message
   print '\nusage: %s patent_number\n' % progname

#  'patent_number' is the patent to get.

   sys.exit(1)

N_ARGUMENTS = (1,)

###############################################################################

WORKINGDIR = os.getenv('HOME') + '/tmp'
PSPDF = '/usr/bin/ps2pdf'
TIFFPS = '/usr/bin/tiff2ps'
TIFFPS_OPTS= '-p1 -w 8.5 -h 11'

###############################################################################

def get_id(patentnum):
   """Get ID and server name as if we were using the web interface.

      returns: a two-element list containing the idkey and server name.
   """

   URL = 'http://patimg1.uspto.gov/.piw?Docid=%d&idkey=NONE' % patentnum
   server = 'patimg1'

   connection = urllib.urlopen(URL)
   page = connection.read()
   idindex = string.find(page, 'IDKey=')
   idkey = page[idindex:idindex+18]
   connection.close()

   print 'idkey: %s' % idkey
   print 'server: %s' % server

   return [idkey, server]

###############################################################################

def get_page(patentnum, pagenum, paramlist):
   """Get patent page.

   get_page(patentnum, pagenum, paramlist)

      patentnum: patent number
        pagenum: page number
      paramlist: [idkey, server]

   returns: a string containing the tiff file for this page,
            or an empty string if the page doesn't exist.
   """
   
   URL = 'http://'
   URL = URL+ paramlist[1]
   URL = URL + '.uspto.gov/.DImg?Docid=US'
   URL = URL + '%09d' % patentnum
   URL = URL + '&PageNum=' + '%d' % pagenum
   URL = URL + '&%s' % paramlist[0]
   URL = URL + '&ImgFormat=tif'

   connection = urllib.urlopen(URL)
   page = connection.read()
   connection.close()

   if string.find(page, '\x48\xb2\x61\x6d\x08\x86\x1a\x0c\x1a\x06') == -1:
      return page
   else:
      return ''

###############################################################################

if __name__ == '__main__':
   nargs = len(sys.argv) - 1
   progname = os.path.basename(sys.argv[0])
   flag = 1
   if nargs != 0 and N_ARGUMENTS[-1] == '*':
      flag = 0
   else:
      for i in N_ARGUMENTS:
         if nargs == i:
            flag = 0
   if flag:
      usage()

   print
   
   print 'Changing to working directory %s...' % WORKINGDIR,
   os.chdir(WORKINGDIR)
   print 'done.'
   print

   patno = int(sys.argv[1])
   print 'Connecting to USPTO...'
   paramlist = get_id(patno)

   pages = []
   pagelist = []

   counter = 1
   while 1:
      pagestring = get_page(patno, counter, paramlist)
      if pagestring == '':
         break
      print 'Got page %d.' % counter
      pages.append(pagestring)
      counter = counter + 1

   for i in range(len(pages)):
      pagefile = '%d.%d' % (patno, i+1)
      pagelist.append(pagefile)
      outfile = open(pagefile, 'w')
      outfile.write(pages[i])
      outfile.flush()
      outfile.close()

   print 'Converting to PostScript...',
   command = '%s %s' % (TIFFPS, TIFFPS_OPTS)
   for i in pagelist:
      command = command + ' %s' % i
   command = command + ' > %d.ps' % patno
   os.popen2(command)
   os.wait()
   print 'done.'

   print 'Creating pdf file...',
   command = '%s %d.ps' % (PSPDF, patno)
   os.popen2(command)
   os.wait()
   print 'done.'

   print 'Cleaning up temporary files...',
   command = 'rm'
   for i in pagelist:
      command = command + ' %s' % i
   command = command + ' %d.ps' % patno
   os.popen2(command)
   os.wait()
   print 'done.'
   print
   print 'Wrote file: %s/%d.pdf' % (WORKINGDIR, patno)
   print