2009-03-11 01:40:20 -04:00
|
|
|
#!/usr/bin/python
|
|
|
|
|
|
|
|
from xml.dom import minidom, Node
|
|
|
|
import urllib
|
|
|
|
import time
|
2009-09-08 17:04:44 -04:00
|
|
|
import datetime
|
|
|
|
import hashlib
|
|
|
|
import base64
|
|
|
|
import hmac
|
2009-03-11 01:40:20 -04:00
|
|
|
|
|
|
|
class PyMazonError(Exception):
|
2009-09-08 17:04:44 -04:00
|
|
|
"""Holds information about an error that occured during a pymazon request"""
|
|
|
|
def __init__(self, messages):
|
|
|
|
self.__message = '\n'.join(messages)
|
2009-03-11 01:40:20 -04:00
|
|
|
|
2009-09-08 17:04:44 -04:00
|
|
|
def __get_message(self):
|
|
|
|
return self.__message
|
2009-03-11 01:40:20 -04:00
|
|
|
|
2009-09-08 17:04:44 -04:00
|
|
|
def __str__(self):
|
|
|
|
return repr(self.__message)
|
2009-03-11 01:40:20 -04:00
|
|
|
|
2009-09-08 17:04:44 -04:00
|
|
|
message = property(fget=__get_message)
|
2009-03-11 01:40:20 -04:00
|
|
|
|
|
|
|
|
|
|
|
class PyMazonBook:
|
2009-09-08 17:04:44 -04:00
|
|
|
"""Stores information about a book retrieved via PyMazon."""
|
|
|
|
def __init__(self, title, authors, publisher, year, isbn10, isbn13, edition):
|
|
|
|
self.__title = title
|
|
|
|
self.__authors = authors
|
|
|
|
self.__publisher = publisher
|
|
|
|
self.__year = year
|
|
|
|
self.__isbn10 = isbn10
|
|
|
|
self.__isbn13 = isbn13
|
|
|
|
self.__edition = edition
|
|
|
|
|
|
|
|
def __str__(self):
|
|
|
|
return 'Title: ' + self.title + '\n' + \
|
|
|
|
'Author(s): ' + ', '.join(self.authors) + '\n' \
|
|
|
|
'Publisher: ' + self.publisher + '\n' + \
|
|
|
|
'Year: ' + self.year + '\n' + \
|
|
|
|
'ISBN-10: ' + self.isbn10 + '\n' + \
|
|
|
|
'ISBN-13: ' + self.isbn13 + '\n' + \
|
|
|
|
'Edition: ' + self.edition
|
|
|
|
|
|
|
|
def __get_title(self):
|
|
|
|
return self.__title
|
|
|
|
|
|
|
|
def __get_authors(self):
|
|
|
|
return self.__authors
|
|
|
|
|
|
|
|
def __get_publisher(self):
|
|
|
|
return self.__publisher
|
|
|
|
|
|
|
|
def __get_year(self):
|
|
|
|
return self.__year
|
|
|
|
|
|
|
|
def __get_isbn10(self):
|
|
|
|
return self.__isbn10
|
|
|
|
|
|
|
|
def __get_isbn13(self):
|
|
|
|
return self.__isbn13
|
|
|
|
|
|
|
|
def __get_edition(self):
|
|
|
|
return self.__edition
|
|
|
|
|
|
|
|
title = property(fget=__get_title)
|
|
|
|
authors = property(fget=__get_authors)
|
|
|
|
publisher = property(fget=__get_publisher)
|
|
|
|
year = property(fget=__get_year)
|
|
|
|
isbn10 = property(fget=__get_isbn10)
|
|
|
|
isbn13 = property(fget=__get_isbn13)
|
|
|
|
edition = property(fget=__get_edition)
|
2009-03-11 01:40:20 -04:00
|
|
|
|
|
|
|
|
|
|
|
class PyMazon:
|
2009-09-08 17:04:44 -04:00
|
|
|
"""A method of looking up book information on Amazon."""
|
|
|
|
def __init__(self, accesskey, secretkey):
|
|
|
|
self.__key = accesskey
|
|
|
|
self.__secret = secretkey
|
|
|
|
self.__last_query_time = 0
|
|
|
|
|
|
|
|
def __form_request(self, isbn):
|
|
|
|
content = {}
|
|
|
|
dstamp = datetime.datetime.utcfromtimestamp(time.time())
|
|
|
|
content['Timestamp'] = dstamp.strftime('%Y-%m-%dT%H:%M:%S.000Z')
|
|
|
|
content['Service'] = 'AWSECommerceService'
|
|
|
|
content['Version'] = '2008-08-19'
|
|
|
|
content['Operation'] = 'ItemLookup'
|
|
|
|
content['ResponseGroup'] = 'ItemAttributes'
|
|
|
|
content['IdType'] = 'ISBN'
|
|
|
|
content['SearchIndex'] = 'Books'
|
|
|
|
content['ItemId'] = isbn
|
|
|
|
content['AWSAccessKeyId'] = self.__key
|
|
|
|
|
|
|
|
URI_String = []
|
|
|
|
|
|
|
|
for key, value in sorted(content.items()):
|
|
|
|
URI_String.append('%s=%s' % (key, urllib.quote(value)))
|
|
|
|
|
|
|
|
req = '&'.join(URI_String)
|
|
|
|
to_sign_req = 'GET\necs.amazonaws.com\n/onca/xml\n' + req
|
|
|
|
|
|
|
|
h = hmac.new(self.__secret, to_sign_req, hashlib.sha256)
|
|
|
|
sig = base64.b64encode(h.digest())
|
|
|
|
req += '&Signature=%s' % urllib.quote(sig)
|
|
|
|
|
|
|
|
return 'http://ecs.amazonaws.com/onca/xml?' + req
|
|
|
|
|
|
|
|
def __elements_text(self, element, name):
|
|
|
|
result = []
|
|
|
|
matching = element.getElementsByTagName(name)
|
|
|
|
for match in matching:
|
|
|
|
if len(match.childNodes) != 1:
|
|
|
|
continue
|
|
|
|
child = match.firstChild
|
|
|
|
if child.nodeType != Node.TEXT_NODE:
|
|
|
|
continue
|
|
|
|
result.append(child.nodeValue.strip())
|
|
|
|
return result
|
|
|
|
|
|
|
|
def __format_errors(self, errors):
|
|
|
|
error_list = []
|
|
|
|
for error in errors:
|
|
|
|
error_list.extend(self.__elements_text(error, 'Message'))
|
|
|
|
return error_list
|
|
|
|
|
|
|
|
def __extract_single(self, element, name):
|
|
|
|
matches = self.__elements_text(element, name)
|
|
|
|
if len(matches) == 0:
|
|
|
|
return ''
|
|
|
|
return matches[0]
|
|
|
|
|
|
|
|
def lookup(self, isbn):
|
|
|
|
file = urllib.urlretrieve(self.__form_request(isbn))[0]
|
|
|
|
xmldoc = minidom.parse(file)
|
|
|
|
|
|
|
|
cur_time = time.time()
|
|
|
|
while cur_time - self.__last_query_time < 1.0:
|
|
|
|
sleep(cur_time - self.__last_query_time)
|
|
|
|
cur_time = time.time()
|
|
|
|
self.__last_query_time = cur_time
|
|
|
|
|
|
|
|
errors = xmldoc.getElementsByTagName('Errors')
|
|
|
|
if len(errors) != 0:
|
|
|
|
raise PyMazonError, self.__format_errors(errors)
|
|
|
|
|
|
|
|
title = self.__extract_single(xmldoc, 'Title')
|
|
|
|
authors = self.__elements_text(xmldoc, 'Author')
|
|
|
|
publisher = self.__extract_single(xmldoc, 'Publisher')
|
|
|
|
year = self.__extract_single(xmldoc, 'PublicationDate')[0:4]
|
|
|
|
isbn10 = self.__extract_single(xmldoc, 'ISBN')
|
|
|
|
isbn13 = self.__extract_single(xmldoc, 'EAN')
|
|
|
|
edition = self.__extract_single(xmldoc, 'Edition')
|
|
|
|
|
|
|
|
return PyMazonBook(title, authors, publisher, year, isbn10, isbn13, edition)
|