wnpp-query/wnpp-query.py

#!/usr/bin/python
# -*- coding: utf-8 -*-

# This program is free software. It comes without any warranty, to
# the extent permitted by applicable law. You can redistribute it
# and/or modify it under the terms of the Do What The Fuck You Want
# To Public License, Version 2, as published by Sam Hocevar. See
# http://sam.zoy.org/wtfpl/COPYING for more details.

# Author: Stefan Ritter <xeno@thehappy.de>
# Description: Query Debian WNPP pages

import urllib2, sys, re
from optparse import OptionParser

parser = OptionParser()
parser.add_option('-i', action='store_true', dest='itp', default=False, help='query ITPs')
parser.add_option('-r', action='store_true', dest='rfp', default=False, help='query RFPs')
parser.add_option('-d', action='store_true', dest='description', default=False, help='show description of each package')
parser.add_option('--min', dest='min_days_old', type="int", help='minimum age (in days)')
parser.add_option('--max', dest='max_days_old', type="int", help='maximum age (in days)')
(options, args) = parser.parse_args()

if not options.min_days_old and not options.max_days_old or not options.itp and not options.rfp or options.itp and options.rfp:
	parser.error('You have to give at least one of --min or --max and one of -r or -i options.')
	sys.exit

if not options.min_days_old: options.min_days_old = 0
if not options.max_days_old: options.max_days_old = 9999

if options.itp: url = urllib2.urlopen('http://www.debian.org/devel/wnpp/being_packaged')
else:           url = urllib2.urlopen('http://www.debian.org/devel/wnpp/requested')

reports = []
item = []

line_match        = re.compile('(^(.*)bugs\.debian\.org(.*)$|^requested(.*)$|^in preparation since(.*)$|^(.*)days in preparation\.$)')
line_match_desc   = re.compile('(^\<ul\>(.*),|^ \<li\>\<a href(.*)\</a\>,)')
line_match_age    = re.compile('(^requested(.*)$|^(.*)days in preparation(.*)$|^in preparation since(.*)$)')

req_today         = re.compile('^requested today\.$')
req_yesterday     = re.compile('^requested yesterday\.$')
in_prep_today     = re.compile('^in preparation since today\.$')
in_prep_yesterday = re.compile('^in preparation since yesterday\.$')

for line in url:
	if re.match(line_match, line):
		if re.match(line_match_desc, line):
			line = line.strip()

			link = re.sub('<ul>', '', line)
			link = line[13:42]
			item.append(link)

			name = re.sub('<ul>', '', line)
			name = name[44:]
			name = name.split(':', 1)[0]
			item.append(name)

			if options.description: 
				try:
					description = re.sub('</a>,', '', line)
					description = ' (' + description.split(':')[2].strip() + ')'
				except:
					description = ''
				item.append(description)
			else:
				item.append('')

		if re.match(line_match_age, line):
			if options.itp:
				if re.match(in_prep_yesterday, line): days = '1'
				elif re.match(in_prep_today, line): days = '0'
				else: days = line.split(' ')[0]
			else:
				if re.match(req_yesterday, line): days = '1'
				elif re.match(req_today, line): days = '0'
				else: days = line.split(' ')[1]
			item.append(days)

		if len(item) == 4:
			reports.append(item)
			item = []

reports.sort(key = lambda x: int(x[3]))
for entry in reports:
	if int(entry[3]) <= options.max_days_old \
	and int(entry[3]) >= options.min_days_old:
		print entry[3], 'days ago:', entry[1], entry[0], entry[2]