def parse_url(url):
"""Try to get the amazon product ID (ASIN) out of the url.
Returns (domain, asin) where domain is .co.uk/.com/.de etc"""
regexps = [
r'amazon\.(?P<domain>[a-z.]+)/(?:gp|exec|o)/.*/?(?:ASIN|-|product)/(?P<asin>[^?/]+)',
r'amazon.(?P<domain>[a-z.]+)/[^/]+/(gp|dp)/(?P<asin>[0-9X]+)',
r'amazon.(?P<domain>[a-z.]+)/([^/]+/)?dp/(?P<asin>[^/]+)'
]
for r in regexps:
m = re.search(r, url, re.I)
if m:
return m.group('domain', 'asin')
# Start trying to find odd cases now.
m = re.search(r'amazon.([a-z.]+)/', url)
if not m:
# I can't even see which amazon domain it's from. Time to give up.
raise BadUrl(url)
domain = m.group(1)
# Maybe there's something that
# looks like an ISBN sandwiched between two path separators
for part in url.split("/"):
v = isbn.verify(part)
if v:
return (domain, v)
# Hunt through the URL looking for any sequence of characters
# which look like an ISBN
candidates = list(isbn.hunt(url))
if len(candidates) == 1:
return (domain, candidates[0])
# Nope. I give up.
raise BadUrl(url)
def parse_url(url):
"""Try to get the amazon product ID (ASIN) out of the url.
Returns (domain, asin) where domain is .co.uk/.com/.de etc"""
regexps = [r'amazon\.(?P<domain>[a-z.]+)/(?:gp|exec|o)/.*/?(?:ASIN|-|product)/(?P<asin>[^?/]+)',
r'amazon.(?P<domain>[a-z.]+)/[^/]+/(gp|dp)/(?P<asin>[0-9X]+)',
r'amazon.(?P<domain>[a-z.]+)/([^/]+/)?dp/(?P<asin>[^/]+)'
]
for r in regexps:
m = re.search(r, url, re.I)
if m:
return m.group('domain', 'asin')
# Start trying to find odd cases now.
m = re.search(r'amazon.([a-z.]+)/', url)
if not m:
# I can't even see which amazon domain it's from. Time to give up.
raise BadUrl(url)
domain = m.group(1)
# Maybe there's something that
# looks like an ISBN sandwiched between two path separators
for part in url.split("/"):
v = isbn.verify(part)
if v:
return (domain, v)
# Hunt through the URL looking for any sequence of characters
# which look like an ISBN
candidates = list(isbn.hunt(url))
if len(candidates)==1:
return (domain, candidates[0])
# Nope. I give up.
raise BadUrl(url)
def test_valid_empty_isbn(self):
self.assertIs(verify(''), False)
def test_invalid_check_digit_X_used_for_0(self):
self.assertIs(verify('3-598-21515-X'), False)
def test_invalid_too_long_isbn(self):
self.assertIs(verify('3-598-21507-XX'), False)
def test_invalid_isbn_without_check_digit(self):
self.assertIs(verify('3-598-21507'), False)
def test_invalid_too_long_isbn_with_no_dashes(self):
self.assertIs(verify('3598215078X'), False)
def test_invalid_isbn_without_check_digit_and_dashes(self):
self.assertIs(verify('359821507'), False)
def test_valid_isbn_without_separating_dashes(self):
self.assertIs(verify('3598215088'), True)
def test_invalid_X_other_than_check_digit(self):
self.assertIs(verify('3-598-2X507-9'), False)
def test_invalid_character_in_isbn(self):
self.assertIs(verify('3-598-P1581-X'), False)
def test_invalid_check_digit_other_than_X(self):
self.assertIs(verify('3-598-21507-A'), False)
def test_valid_with_X_check_digit(self):
self.assertIs(verify('3-598-21507-X'), True)
def test_invalid_check_digit(self):
self.assertIs(verify('3-598-21508-9'), False)
def test_input_is_nine_characters(self):
self.assertIs(verify('134456729'), False)
def test_valid_isbn_number(self):
self.assertIs(verify('3-598-21508-8'), True)
def test_valid_isbn_without_separating_dashes_with_X_check_digit(self):
self.assertIs(verify('359821507X'), True)