#!/usr/bin/python -tt

# amazon-wishlist v0.3
# Copyright (c) 2008-9, John Morrissey <jwm@horde.net>
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
#	* Redistributions of source code must retain the above copyright notice,
#	  this list of conditions and the following disclaimer.
#	* Redistributions in binary form must reproduce the above copyright
#	  notice, this list of conditions and the following disclaimer in the
#	  documentation and/or other materials provided with the distribution.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS
# IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
# THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

AWS_ACCESS_KEY = ''
AWS_SECRET_KEY = ''
WISHLIST_ID = ''
AWS_XML_NS = 'http://webservices.amazon.com/AWSECommerceService/2011-08-01'

# MCLS branches I prefer.
BRANCHES = [
	'Evans Branch West - Irondequoit Library',
	'Henrietta Public Library',
	'McGraw Branch East - Irondequoit Library',
	'Rochester Public Library Central',
]


from base64 import b64encode
from datetime import date
import hashlib
import hmac
import json
import re
import sys
from time import gmtime, strftime
from urllib import quote_plus, urlencode
from urllib2 import Request
from urlparse import parse_qs, urljoin, urlparse
from xml.etree.ElementTree import ElementTree

import html5lib
import mechanize
from BeautifulSoup import Comment as BeautifulSoupComment

cj = mechanize.LWPCookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cj))

class MclsScraper(object):
	endpoint = 'http://classic.libraryweb.org/carlweb/jsp/'

	def _parse_result(self, body):
		parser = html5lib.HTMLParser(tree=html5lib.treebuilders.getTreeBuilder("beautifulsoup"))
		soup = parser.parse(body)

		if soup.find(text=re.compile(r'No status information was found for this title\.')):
			return []
		if soup.find(text=re.compile(r'No se sabe el estado de')):
			return []
		if soup.find(text=re.compile(r'No matches were found')):
			return []

		marcid = soup.find('td', {'class': 'MARCtaglabel'})
		if not marcid:
			return []
		id = (marcid.findParents('tr')[0].
			find(text=re.compile(r'^\s*\d+\s*$')).strip())

		branches_req = Request(
			'%sGetDisplayBranches?databaseID=720&controlNumber=%s' % (
				self.endpoint, id,
			)
		)
		branches_req.add_header('User-Agent', 'amazon-wishlist 0.3')
		data = opener.open(branches_req)
		body = ''.join(data.fp.readlines()).strip()
		if not body:
			return []
		branches = json.loads(body)

		locations = []
		for branch in branches:
			branch_req = Request(
				'%sGetDisplayItems?databaseID=720&controlNumber=%s&branchID=%s' % (
					self.endpoint, id, branch['BRANCHID']
				)
			)
			branch_req.add_header('User-Agent', 'amazon-wishlist 0.3')
			data = opener.open(branch_req)

			branch_item = json.loads(''.join(data.fp.readlines()))
			locations.append({
				'Branch': branch['BRANCHNAME'],
				'Call Number': ', '.join([
					item['CALLNUM']
					for item
					 in branch_item
				]),
				'numAvailable': int(branch['NUMAVAILABLE']),
			})
		return locations

	def get_info(self, type, title, author):
		cj.clear()
		search = Request(
			'%sDoSearch?%s' % (
				self.endpoint,
				urlencode([
					('databaseID', 720),
					('count', 10),
					('index', 'w'),
					('terms', '%s %s' % (title, author)),
					('keywords', type),
				])
			)
		)
		search.add_header('User-Agent', 'amazon-wishlist 0.3')
		data = opener.open(search)

		results = Request('%stitlelist.jsp' % self.endpoint)
		results.add_header('User-Agent', 'amazon-wishlist 0.3')
		data = opener.open(results)

		body = ''.join(data.fp.readlines())
		parser = html5lib.HTMLParser(tree=html5lib.treebuilders.getTreeBuilder("beautifulsoup"))
		soup = parser.parse(body)
		result_uris = []
		for tr in soup.findAll('tr'):
			if 'eBook' in tr:
				continue
			for rec in tr.findAll(href=re.compile('FullRecord')):
				if rec['href'] not in result_uris:
					result_uris.append(rec['href'])
		if len(result_uris) == 0:
			return self._parse_result(body)

		locations = []
		for uri in result_uris:
			auth = Request('%s%s' % (self.endpoint, uri))
			auth.add_header('User-Agent', 'amazon-wishlist 0.3')
			data = opener.open(auth)

			auth = Request('%sfullrecord.jsp' % (self.endpoint))
			auth.add_header('User-Agent', 'amazon-wishlist 0.3')
			locations.extend(self._parse_result(''.join(opener.open(auth).fp.readlines())))
		return locations

class RitScraper(object):
	def _parse_result(self, body):
		parser = html5lib.HTMLParser(tree=html5lib.treebuilders.getTreeBuilder("beautifulsoup"))
		soup = parser.parse(body)

		if soup.find(text=re.compile('NO ENTRIES FOUND')):
			return []

		if soup.find(text=re.compile('Available electronically:')):
			return [{
				'LOCATION': 'ELECTRONIC',
			}]

		try:
			header = soup.find('tr', attrs={'class': 'bibItemsHeader'})
			items = soup.findAll('tr', attrs={'class': 'bibItemsEntry'})
		except:
			return []

		fields = {}
		i = 0
		for col in header.findAll('th'):
			fields[col.find(text=True).strip()] = i
			i += 1

		locations = []
		for location in items:
			locinfo = {}
			cells = location.findAll('td')
			for pretty, td_index in fields.iteritems():
				value = ''.join(cells[td_index].findAll(
					text=lambda text: not isinstance(text, BeautifulSoupComment))).strip()

				if pretty == 'LOCATION':
					value = value.replace(' FLOOR', '')
				elif pretty == 'STATUS':
					if value.split(' ')[0] == 'DUE':
						month, day, year = \
							[int(i) for i in re.sub(r'.*?(\d+-\d+-\d+).*', r'\1', value).split('-')]
						if year >= 0 and year <= date.today().year:
							year += 2000
						else:
							year += 1900
						locinfo['DUE'] = date(year, month, day)
					locinfo['AVAILABLE'] = (value == 'AVAILABLE')

				locinfo[pretty] = value

			locations.append(locinfo)
		return locations

	def get_info(self, type, title, author):
		auth = Request(
			'http://albert.rit.edu/search/X?t:(%s)+and+a:(%s)&searchscope=3&SORT=A' % \
			(quote_plus(title), quote_plus(author)))
		auth.add_header('User-Agent', 'amazon-wishlist 0.3')
		data = mechanize.urlopen(auth)

		body = ''.join(data.fp.readlines())
		parser = html5lib.HTMLParser(tree=html5lib.treebuilders.getTreeBuilder("beautifulsoup"))
		soup = parser.parse(body)

		result_uris = []
		for rec in soup.findAll(attrs={'class': 'briefCitRow'}):
			link = rec.find('a', {'href': re.compile('SUBKEY')})
			if link['href'] not in result_uris:
				result_uris.append(link['href'])
		if len(result_uris) == 0:
			return self._parse_result(body)

		locations = []
		for uri in result_uris:
			item = Request(urljoin(auth.get_full_url(), uri))
			item.add_header('User-Agent', 'amazon-wishlist 0.3')
			locations.extend(self._parse_result(''.join(mechanize.urlopen(item).fp.readlines())))
		return locations

def get_wishlist_body(url):
	if not url.startswith('http'):
		url = 'http://www.amazon.com' + url

	wishlist = Request(url)
	wishlist.add_header('User-Agent', 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.186 Safari/535.1')
	data = mechanize.urlopen(wishlist)
	body = ''.join(data.fp.readlines())

	parser = html5lib.HTMLParser(
		tree=html5lib.treebuilders.getTreeBuilder("beautifulsoup"))
	return parser.parse(body)

def get_asins(body):
	list = body.find(attrs={'class': 'compact-items wlrdZeroTable'})

	asins = []
	for item in list.findAll('tbody'):
		asins.append(re.sub(r'.*\.', r'', item['name']))
	return asins

def ele(ns, item, name):
	if item is None:
		return None

	qname = '{%s}%s' % (ns, ('/{%s}' % (ns)).join(name.split('/')))
	return item.find('.//%s' % qname)

def elet(item, name):
	node = ele(AWS_XML_NS, item, name)
	if node is None:
		return ''
	return node.text

def loadItems(wishlist_id):
	global AWS_ACCESS_KEY, AWS_SECRET_KEY, AWS_XML_NS

	mcls = MclsScraper()
	rit = RitScraper()

	body = get_wishlist_body(
		'http://www.amazon.com/registry/wishlist/%s/ref=cm_wl_sb?reveal=unpurchased&filter=all&sort=date-added&layout=compact' % wishlist_id)
	asins = []
	asins = get_asins(body)

	page_links = body.find(attrs={'class': 'pagDiv'}).findAll('a')
	for link in page_links:
		page_num = link.find(text=re.compile(r'^\d+$'))
		if not page_num:
			continue
		asins.extend(get_asins(get_wishlist_body(link['href'])))

	items = []
	for asin in asins:
		qs_dict = {
			'Service': 'AWSECommerceService',
			'AWSAccessKeyId': AWS_ACCESS_KEY,
			'Operation': 'ItemLookup',
			'IdType': 'ASIN',
			'ItemId': asin,
			'Condition': 'All',
			'ResponseGroup': 'Medium',
			'AssociateTag': '0',
		}
		url = sign_amazon_req(AWS_SECRET_KEY, 'GET',
			'http://webservices.amazon.com/onca/xml', qs_dict)
		auth = Request(url)
		auth.add_header('User-Agent', 'amazon-wishlist 0.3')

		tree = ElementTree(file=mechanize.urlopen(auth))
		item = tree.getroot().find('.//{%s}Item' % (AWS_XML_NS))

		img = ele(AWS_XML_NS, item, 'MediumImage')
		attrs = ele(AWS_XML_NS, item, 'ItemAttributes')
		offers = ele(AWS_XML_NS, item, 'OfferSummary')

		this_item = {
			'title': elet(attrs, 'Title'),
			'url': elet(item, 'DetailPageURL'),
			'sort': [
				elet(attrs, 'ProductGroup'),
				elet(item, 'BrowseNodes/BrowseNode/Ancestors/BrowseNode/Ancestors/BrowseNode/Ancestors/BrowseNode/Name'),
				elet(item, 'BrowseNodes/BrowseNode/Ancestors/BrowseNode/Ancestors/BrowseNode/Name'),
			],
			'img': {
				'url': elet(img, 'URL'),
				'width': elet(img, 'Width'),
				'height': elet(img, 'Height'),
				'caption': elet(attrs, 'Title'),
			},
			'prices': {
				'list': elet(ele(AWS_XML_NS, attrs, 'ListPrice'), 'FormattedPrice'),
				'new': {
					'count': elet(offers, 'TotalNew'),
					'lowest': elet(ele(AWS_XML_NS, offers, 'LowestNewPrice'), 'FormattedPrice'),
				},
				'used': {
					'count': elet(offers, 'TotalUsed'),
					'lowest': elet(ele(AWS_XML_NS, offers, 'LowestUsedPrice'), 'FormattedPrice'),
				},
			},
		}

		author = ele(AWS_XML_NS, attrs, 'Author')
		if author is not None:
			this_item['by'] = author.text
		artist = ele(AWS_XML_NS, attrs, 'Artist')
		if artist is not None:
			this_item['by'] = artist.text

		group = elet(attrs, 'ProductGroup')
		if group == 'Book':
			type = 'Book=qbook'
		elif group == 'Music':
			type = 'Music CD=qmusiccompactdisc'
		else:
			type = ''

		search_title = re.sub(r'[:(].*', '', this_item['title'])
		search_title = ' '.join([
			word
			for word in search_title.split(' ')
			 if word.lower() not in
				['the', 'and', 'a', 'an', 'of', 'in', 'to', 'is', 'with']
		])
		search_author = re.sub(r'\s\w{1,3}\.(\s|$)', r'\1',
			this_item.get('by', ''))

		for attempt in [1, 2, 3, 4, 5]:
			try:
				mcls_info = mcls.get_info(type, search_title, search_author)
				break
			except Exception, e:
				print 'Unable to retrieve MCLS info for %s: %s' % (
					this_item['title'].encode('utf-8'), str(e))
				mcls_info = []

		branches = {}
		for avail in mcls_info:
			if 'Branch' not in avail:
				continue

			if avail['Branch'] not in branches:
				branches[avail['Branch']] = {
					'count': 0,
				}
				if 'Call Number' in avail:
					branches[avail['Branch']]['call'] = avail['Call Number']

			branches[avail['Branch']]['count'] += avail['numAvailable']
		this_item['mcls'] = branches

		try:
			rit_info = rit.get_info(None, search_title, this_item.get('by', ''))
		except Exception, e:
			print 'Unable to retrieve RIT info for %s: %s' % (
				this_item['title'].encode('utf-8'), str(e))
			rit_info = []

		if len(rit_info) > 0:
			this_item['rit'] = {}
			if rit_info[0]['LOCATION'] == 'ELECTRONIC':
				this_item['rit']['call'] = rit_info[0]['LOCATION']
			else:
				this_item['rit']['call'] = \
					'%s %s' % (rit_info[0]['LOCATION'], rit_info[0]['CALL NO.'])
				this_item['rit']['status'] = rit_info[0]['STATUS']

		items.append(this_item)

	return items

def displayItems(items):
	global BRANCHES

	for i in range(len(items)):
		item = items[i]

		if i % 2 == 0:
			print '<li class="left">'
		else:
			print '<li class="right">'

		print '<a href="%s">' % item['url']
		print '<img style="float: left" src="%s" height="%s" width="%s" alt="%s">' % (
			item['img']['url'], item['img']['height'],
			item['img']['width'], item['img']['caption'].encode('utf-8')
		)
		print '</a>'

		print item['title'].encode('utf-8'), '<br>'
		if 'by' in item:
			print item['by'].encode('utf-8'), '<br>'

		print 'List:', item['prices']['list'], '<br>'
		print 'New (%s): %s, Used (%s): %s<br>' % \
			(item['prices']['new']['count'], item['prices']['new']['lowest'],
			 item['prices']['used']['count'], item['prices']['used']['lowest'])

		if 'mcls' in item and len(item['mcls']) > 0:
			print 'MCLS: '
			branches = [
				'%s (%s, %s)' % (branch, avail['count'], avail['call'])
				for branch, avail in item['mcls'].iteritems()
				if branch in BRANCHES
			]
			if len(branches) > 0:
				print ', '.join(branches)
			else:
				print ', '.join([
					'%s (%s, %s)' % (branch, avail['count'], avail['call'])
					for branch, avail in item['mcls'].iteritems()
				])

		if 'rit' in item and 'call' in item['rit']:
			if 'status' in item['rit']:
				print 'RIT: %s, %s' % \
					(item['rit']['status'], item['rit']['call'])
			else:
				print 'RIT: %s' % item['rit']['call']

		print '</li>'

def sign_amazon_req(key, method, url, qs_dict):
	parsed_url = urlparse(url)
	qs = urlencode([
		(k, qs_dict[k])
		for k
		 in sorted(qs_dict.keys())
	] + [('Timestamp', strftime('%Y-%m-%dT%H:%M:%S.000Z', gmtime()))])

	to_sign = '\n'.join([method, parsed_url.netloc, parsed_url.path, qs])
	sig = quote_plus(b64encode(
		hmac.new(
			key=key,
			msg=to_sign,
			digestmod=hashlib.sha256).digest()
	))

	return '%s?%s&Signature=%s' % (url, qs, sig)

print '''
<!DOCTYPE html>
<html>
<head>
	<title>jwm's Amazon Wishlist</title>

	<style type='text/css'>
		li {
			list-style-type: none;
			width: 50%;
		}

		li.left {
			float: left;
			clear: left;
		}
		li.right {
			float: right;
			clear: right;
		}

		img {
			border: 0;
			margin-right: 0.3em;
			margin-bottom: 0.5em;
		}
	</style>
</head>

<body>
<ul>
'''

items = loadItems(WISHLIST_ID)
displayItems(items)

print '''
</ul>
</body>
</html>
'''