def get_goodreads_details(url):
"""Given a goodreads URL, get title, creator, etc.
"""
# Look for something like http://www.goodreads.com/book/show/40694.Ray_Bradbury_s_Fahrenheit_451
details = {}
#TODO: we should do some validation/error handling here
url = url + '.xml'
url_params = {'key' : GOODREADS['KEY']}
data = urllib.urlencode(url_params)
url = url + '?' + data
req = urllib2.Request(url)
response = urllib2.urlopen(req)
raw_response = response.read()
root = objectify.fromstring(raw_response)
details['format'] = 'book'
if hasattr(root.book, 'title'):
details['title'] = root.book.title
if hasattr(root.book.authors.author, 'name'):
details['creator'] = root.book.authors.author.name
if hasattr(root.book.work, 'original_publication_year'):
details['pub_date'] = get_year_from_raw_date(root.book.work.original_publication_year)
if hasattr(root.book, 'isbn'):
details['isbn'] = root.book.isbn
if hasattr(root.book, 'num_pages') and len(root.book.num_pages.text) > 0:
details['measurement_page_numeric'] = root.book.num_pages
return details
def get_goodreads_details(url):
"""Given a goodreads URL, get title, creator, etc.
"""
# Look for something like http://www.goodreads.com/book/show/40694.Ray_Bradbury_s_Fahrenheit_451
details = {}
#TODO: we should do some validation/error handling here
url = url + '.xml'
url_params = {'key': GOODREADS['KEY']}
data = urllib.urlencode(url_params)
url = url + '?' + data
req = urllib2.Request(url)
response = urllib2.urlopen(req)
raw_response = response.read()
root = objectify.fromstring(raw_response)
details['format'] = 'book'
if hasattr(root.book, 'title'):
details['title'] = root.book.title
if hasattr(root.book.authors.author, 'name'):
details['creator'] = root.book.authors.author.name
if hasattr(root.book.work, 'original_publication_year'):
details['pub_date'] = get_year_from_raw_date(
root.book.work.original_publication_year)
if hasattr(root.book, 'isbn'):
details['isbn'] = root.book.isbn
if hasattr(root.book, 'num_pages') and len(root.book.num_pages.text) > 0:
details['measurement_page_numeric'] = root.book.num_pages
return details
def get_amazon_details(url):
"""Given an Amazon URL, get title, creator, etc. from imdapi.com
"""
matches = re.search(r'\/([A-Z0-9]{10})($|\/)', url)
asin = matches.group(1)
aws_key = AMZ['KEY']
aws_secret_key = AMZ['SECRET_KEY']
aws_associate_tag = AMZ['ASSOCIATE_TAG']
details = {}
amazon = bottlenose.Amazon(aws_key, aws_secret_key, aws_associate_tag)
response = amazon.ItemLookup(ItemId=asin,
ResponseGroup="Large",
IdType="ASIN")
root = objectify.fromstring(response)
if hasattr(root.Items.Item.ItemAttributes, 'Author'):
details['creator'] = root.Items.Item.ItemAttributes.Author
elif hasattr(root.Items.Item.ItemAttributes, 'Artist'):
details['creator'] = root.Items.Item.ItemAttributes.Artist
elif hasattr(root.Items.Item.ItemAttributes, 'Director'):
details['creator'] = root.Items.Item.ItemAttributes.Director
if hasattr(root.Items.Item.ItemAttributes, 'Title'):
details['title'] = root.Items.Item.ItemAttributes.Title
if hasattr(root.Items.Item.ItemAttributes, 'ISBN'):
details['isbn'] = root.Items.Item.ItemAttributes.ISBN.text
if hasattr(root.Items.Item.ItemAttributes, 'NumberOfPages'):
details[
'measurement_page_numeric'] = root.Items.Item.ItemAttributes.NumberOfPages
if hasattr(root.Items.Item.ItemAttributes,
'PackageDimensions') and hasattr(
root.Items.Item.ItemAttributes.PackageDimensions, 'Length'):
amz_length = int(
root.Items.Item.ItemAttributes.PackageDimensions['Length'])
height_in_inches = '{0:.2g}'.format((amz_length / 100.0) * 2.54)
details['measurement_height_numeric'] = height_in_inches
if hasattr(root.Items.Item.ItemAttributes, 'ProductGroup'):
if root.Items.Item.ItemAttributes.ProductGroup.text == 'Music':
details['format'] = 'Sound Recording'
elif root.Items.Item.ItemAttributes.ProductGroup.text == 'DVD':
details['format'] = 'Video/Film'
else:
details['format'] = 'book'
if hasattr(root.Items.Item.ItemAttributes, 'PublicationDate'):
details['pub_date'] = get_year_from_raw_date(
root.Items.Item.ItemAttributes.PublicationDate.text)
return details
def get_amazon_details(url):
"""Given an Amazon URL, get title, creator, etc. from imdapi.com
"""
matches = re.search(r'\/([A-Z0-9]{10})($|\/)', url)
asin = matches.group(1)
aws_key = AMZ['KEY']
aws_secret_key = AMZ['SECRET_KEY']
aws_associate_tag = AMZ['ASSOCIATE_TAG']
details = {}
amazon = bottlenose.Amazon(aws_key, aws_secret_key, aws_associate_tag)
response = amazon.ItemLookup(ItemId=asin, ResponseGroup="Large", IdType="ASIN")
root = objectify.fromstring(response)
if hasattr(root.Items.Item.ItemAttributes, 'Author'):
details['creator'] = root.Items.Item.ItemAttributes.Author
elif hasattr(root.Items.Item.ItemAttributes, 'Artist'):
details['creator'] = root.Items.Item.ItemAttributes.Artist
elif hasattr(root.Items.Item.ItemAttributes, 'Director'):
details['creator'] = root.Items.Item.ItemAttributes.Director
if hasattr(root.Items.Item.ItemAttributes, 'Title'):
details['title'] = root.Items.Item.ItemAttributes.Title
if hasattr(root.Items.Item.ItemAttributes, 'ISBN'):
details['isbn'] = root.Items.Item.ItemAttributes.ISBN.text
if hasattr(root.Items.Item.ItemAttributes, 'NumberOfPages'):
details['measurement_page_numeric'] = root.Items.Item.ItemAttributes.NumberOfPages
if hasattr(root.Items.Item.ItemAttributes, 'PackageDimensions') and hasattr(root.Items.Item.ItemAttributes.PackageDimensions, 'Length'):
amz_length = int(root.Items.Item.ItemAttributes.PackageDimensions['Length'])
height_in_inches = '{0:.2g}'.format((amz_length / 100.0) * 2.54)
details['measurement_height_numeric'] = height_in_inches
if hasattr(root.Items.Item.ItemAttributes, 'ProductGroup'):
if root.Items.Item.ItemAttributes.ProductGroup.text == 'Music':
details['format'] = 'Sound Recording'
elif root.Items.Item.ItemAttributes.ProductGroup.text == 'DVD':
details['format'] = 'Video/Film'
else:
details['format'] = 'book'
if hasattr(root.Items.Item.ItemAttributes, 'PublicationDate'):
details['pub_date'] = get_year_from_raw_date(root.Items.Item.ItemAttributes.PublicationDate.text)
return details
def get_musicbrainz_details(url):
"""Given an musicbrainz URL, get title, creator, etc.
"""
# Look for something like http://musicbrainz.org/release-group/20e845b1-c6b5-44f7-ab7e-cbc0e33767b5
# or http://musicbrainz.org/release/b21c3cb7-a82d-4d9d-aef7-56569ca734be
# See http://musicbrainz.org/doc/XML_Web_Service/Version_2#Lookups
matches = re.search(r'musicbrainz\.org/([a-zA-Z\-]+)/([0\w\-]+)', url)
mb_resource = matches.group(1)
mb_id = matches.group(2)
details = {}
url = 'http://musicbrainz.org/ws/2/' + mb_resource + '/' + mb_id
url_params = {'inc': 'artists'}
data = urllib.urlencode(url_params)
url = url + '?' + data
req = urllib2.Request(url)
response = urllib2.urlopen(req)
raw_response = response.read()
tree = ElementTree(fromstring(raw_response))
namespace = "{http://musicbrainz.org/ns/mmd-2.0#}"
title_element = tree.find('*/{0}title'.format(namespace))
name_element = tree.find(
'*/{0}artist-credit/{0}name-credit/{0}artist/{0}name'.format(
namespace))
date_element = tree.find('*/{0}date'.format(namespace))
# If we don't find the date (date element only occurs in the release type), try
# the first-release-date.
# TODO: There's probably a clever xpath way to do this
if date_element is None:
date_element = tree.find('*/{0}first-release-date'.format(namespace))
details['title'] = title_element.text
details['format'] = 'Sound Recording'
details['creator'] = name_element.text
details['pub_date'] = get_year_from_raw_date(date_element.text)
return details
def get_musicbrainz_details(url):
"""Given an musicbrainz URL, get title, creator, etc.
"""
# Look for something like http://musicbrainz.org/release-group/20e845b1-c6b5-44f7-ab7e-cbc0e33767b5
# or http://musicbrainz.org/release/b21c3cb7-a82d-4d9d-aef7-56569ca734be
# See http://musicbrainz.org/doc/XML_Web_Service/Version_2#Lookups
matches = re.search(r'musicbrainz\.org/([a-zA-Z\-]+)/([0\w\-]+)', url)
mb_resource = matches.group(1)
mb_id = matches.group(2)
details = {}
url = 'http://musicbrainz.org/ws/2/' + mb_resource + '/' + mb_id
url_params = {'inc' : 'artists'}
data = urllib.urlencode(url_params)
url = url + '?' + data
req = urllib2.Request(url)
response = urllib2.urlopen(req)
raw_response = response.read()
tree = ElementTree(fromstring(raw_response))
namespace = "{http://musicbrainz.org/ns/mmd-2.0#}"
title_element = tree.find('*/{0}title'.format(namespace))
name_element = tree.find('*/{0}artist-credit/{0}name-credit/{0}artist/{0}name'.format(namespace))
date_element = tree.find('*/{0}date'.format(namespace))
# If we don't find the date (date element only occurs in the release type), try
# the first-release-date.
# TODO: There's probably a clever xpath way to do this
if date_element is None:
date_element = tree.find('*/{0}first-release-date'.format(namespace))
details['title'] = title_element.text
details['format'] = 'Sound Recording'
details['creator'] = name_element.text
details['pub_date'] = get_year_from_raw_date(date_element.text)
return details