def test_oclc_22239204(self):
# Book found, but no data
oclc = 22239204
info = get_by_oclc(oclc)
self.assertIn(('oclc', str(oclc)), info['identifiers'])
self.assertNotIn('authors', info)
self.assertNotIn('title', info)
def getBookData(urlOrNum):
if urlOrNum.isdigit():
oclc = urlOrNum
thisdict = worldcat_api.get_by_oclc(oclc)
if thisdict is None:
error('The OCLC number entered was not found.')
return thisdict
book_url = urlOrNum
#print "url:", book_url, "<br />"
if not re.search('books.google.', book_url, re.I) and not re.search('\?id=', book_url, re.I):
error('Not a Google Books URL.')
return
urlsep = re.search('\?([^#]*)', book_url)
if not urlsep:
error('Bad URL.')
return
book_url_qs = urlsep.group(1)
#print "url_qs:", book_url_qs, "<br />"
book_url_qs_fields = cgi.parse_qs(book_url_qs)
#print "book_url_qs_fields:", book_url_qs_fields, "<br />"
if "id" not in book_url_qs_fields:
error('Bad URL. It has to be for a specific book, not a search result page')
return
book_id = book_url_qs_fields["id"][0]
#print "book_id:", book_id, "<br />"
page = ''
page_string = ''
if 'pg' in book_url_qs_fields:
page_string = book_url_qs_fields['pg'][0]
match = re.search('\D*(\d+)', page_string)
if match:
page = match.group(1) + u"\u2013".encode("utf-8")
new_url = 'http://books.google.com/books?id=' + urllib.quote_plus(book_id)
if page_string:
new_url += '&pg=' + urllib.quote_plus(page_string)
client = gdata.books.service.BookService()
gdata.alt.appengine.run_on_appengine(client)
try:
thisbook = client.get_by_google_id(book_id) # '8cp-Z_G42g4C'
thisdict = thisbook.to_dict()
thisdict['page'] = page
thisdict['new_url'] = new_url
return thisdict
except Exception, err:
print >> sys.stderr, 'ERROR: %s\n' % str(err)
error('No information available for this URL.')
return
def test_oclc(self):
oclc = '550538756'
info = get_by_oclc(oclc)
self.assertEquals(info['title'], "On hobos and homelessness")
self.assertIn('Nels Anderson', info['authors'][0])
self.assertIn('1998', info['date'])
self.assertIn('Chicago Press', info['publishers'][0])
identifiers = info['identifiers']
self.assertIn(('oclc', oclc), identifiers)
self.assertIn(('isbn', '9780226019666'), identifiers)
def test_igma(self):
oclc = '608542024'
info = get_by_oclc(oclc)
self.assertEquals(info['title'], "It probably won't kill you ... : twisted humor for your kitchen")
self.assertEquals('Iyan Igma', info['authors'][0])
self.assertIn('2009', info['date'])
self.assertIn('CreateSpace', info['publishers'][0])
identifiers = info['identifiers']
self.assertIn(('oclc', oclc), identifiers)
self.assertIn(('isbn', '9781441476562'), identifiers)
def test_bad_oclc(self):
#Bad OCLC (actual an ISBN)
oclc = '1441476563'
info = get_by_oclc(oclc)
self.assertIsNone(info)
def test_oclc_2340417(self):
# Returns an HTTP error
oclc = 2340417
info = get_by_oclc(oclc)
self.assertIsNone(info)
def test_oclc_35883297(self):
#'author': 'ed. by Kenneth T. MacKay'
info = get_by_oclc(35883297)
self.assertEquals(info['authors'], ['Kenneth T. MacKay'])
def test_oclc_41271560(self):
#'author': u'[Michael Wielsch, Jens Prahm] ; [trad. Liger Fran\xe7ois, Wolf Pierre M., Springinsfeld Serge].'
info = get_by_oclc(41271560)
self.assertEquals(info['authors'], ['Michael Wielsch', 'Jens Prahm'])
