# XList
# An automated HTML arXiv publication list generator
# by Peter Rohde
# University of Queensland, Australia
# e-mail: rohde@physics.uq.edu.au

# INSTRUCTIONS
# Before using the program, two files must be created in the same directory.
# Create a file named 'proxy_settings.txt'. This file contains a single line with your proxy server settings. The string is of the form 'http://username:password@proxy.wherever.com:port'.
# Create a file named 'author_list.txt'. This file contains the list of authors which should be included in the publication list. Each line of the file contains a single author name. The author name should be the arXiv author name.
# Now you're ready to run the program. Simply type 'python XList.py' from the command line.

# DISCLAIMER
# This software may be freely used, modified and distributed, provided that the original author is acknowledged.

import urllib2
import re
import string

ack_str = '<i>This publication list was created automatically by <a href=\"http://www.physics.uq.edu.au/people/rohde/\">Peter Rohde\'s</a> <a href=\"http://www.physics.uq.edu.au/people/rohde/blog/?page_id=20\">XList</a></i>.'

search_string = ''
author_count  = 0

author_file  = open('author_list.txt')

for line in author_file.readlines():
	if author_count == 0:
		search_string += '+' + string.split(line, '\n')[0]
	else:
		search_string = '+OR' + search_string + '+' + string.split(line, '\n')[0]
		
	author_count += 1
	
arxiv_address = 'http://arxiv.org/find/quant-ph/1/au:' + search_string + '/0/1/0/all/0/1?per_page=1000'

proxy_file = open('proxy_settings.txt')
proxy_str = proxy_file.readlines()[0]
proxy_file.close()

proxies = proxies={'http': proxy_str}

proxy_support = urllib2.ProxyHandler(proxies)
opener = urllib2.build_opener(proxy_support)
urllib2.install_opener(opener)

input_file = urllib2.urlopen(arxiv_address)

no_mode			= 0
author_mode		= 1
journal_ref_mode	= 2
title_mode		= 3

output_file = open('publication_list.html','w')

mode = no_mode
author_list = ''
journal_ref = ''
arxiv_ref   = ''
arxiv_year  = ''

bf_sub = re.compile('{\\\\bf ( [^}]* ) }', re.VERBOSE)
em_sub = re.compile('{\\\\em ( [^}]* ) }', re.VERBOSE)

for line in input_file.readlines():
	if re.search('</DD>', line):
		output_file.write(entry_href)
		output_file.write(entry_title + '</a>, ')
		output_file.write(author_list)
		
		if journal_ref != '':
			output_file.write(', ' + journal_ref)
		else:
			arxiv_year = string.split(arxiv_ref,'/')[1][0:2]
			
			if arxiv_year[0] == '0':
				output_file.write(', ' + arxiv_ref + ' (20' + arxiv_year + ')')
			else:
				output_file.write(', ' + arxiv_ref + ' (19' + arxiv_year + ')')
			
		output_file.write('</p>\n')
		
		mode = no_mode
		author_list    = ''
		journal_ref    = ''
		arxiv_ref      = ''
		arxiv_year_str = ''

	if re.search('<A NAME=', line):
		arxiv_ref  = string.split(line, '"')[1]
		entry_href = '<p><a href="http://www.arxiv.org/abs/' + string.split(line, '"')[1] + '">'
		
	if mode == title_mode:
		entry_title += string.split(line, '<')[0]
	
	if re.search('Title:', line):
		entry_title = string.split(string.split(line, '>')[2], '<')[0]
		
		if re.search('<BR />', line):
			mode = no_mode
		else:
			mode = title_mode
		
	if re.search('Authors:', line):
		mode = author_mode
		
	if re.search('<a href="', line) and mode == author_mode:
		current_author = string.split(string.split(line, '>')[1], '<')[0]
		if author_list == '':
			author_list = current_author
		else:
			author_list += ', ' + current_author
		
	if re.search('Journal-ref:', line):
		mode = journal_ref_mode
		journal_ref = string.split(string.split(line, '>')[2], '<')[0]
		journal_ref = bf_sub.sub(r'<b>\1</b>', journal_ref)
		journal_ref = em_sub.sub(r'<i>\1</i>', journal_ref)
		
output_file.write(ack_str)
		
input_file.close()
author_file.close()
output_file.flush()
output_file.close()