def validate(self):
links = self.get_links()
page_domain, domain_url = get_domain_from_url(self.review.page_url)
rel_nofollow = []
for link in links:
href = link.get('href')
if not is_valid(href):
continue
link_domain, link_domain_url = get_domain_from_url(href)
if link.get('rel') == 'nofollow' and page_domain == link_domain:
rel_nofollow.append(href)
if rel_nofollow:
self.add_violation(
key='invalid.links.nofollow',
value=rel_nofollow,
points=10 * len(rel_nofollow)
)
def normalize_url(self, url):
parse = is_valid(url)
if parse:
if not self.is_absolute(url):
url = self.rebase(url)
return self.url_ends_with_slash(url)
return None
def normalize_url(self, url):
parse = is_valid(url)
if parse:
if not self.is_absolute(url):
url = self.rebase(url)
return url
return None
def validate(self):
url = self.reviewer.page_url
parsed_url = is_valid(url)
path = parsed_url.path
if '_' in path:
self.add_violation(key='invalid.url_word_separator',
value=url,
points=10)
def validate(self):
url = self.reviewer.page_url
parsed_url = is_valid(url)
path = parsed_url.path
if '_' in path:
self.add_violation(
key='invalid.url_word_separator',
value=url,
points=10
)
def get_canonical_urls(self):
url = self.reviewer.page_url
parsed_url = is_valid(url)
scheme_url = parsed_url.scheme
domain_url = parsed_url.netloc
if domain_url.startswith('www.'):
www_url = url.rstrip('/')
no_www_url = '{}://{}'.format(scheme_url, domain_url[4:])
else:
no_www_url = url.rstrip('/')
www_url = '{}://www.{}'.format(scheme_url, domain_url)
return {'www_url': www_url, 'no_www_url': no_www_url}
def validate(self):
if not self.config.FORCE_CANONICAL:
# Only pages with query string parameters
if self.page_url:
if not is_valid(self.page_url):
return
if not urlparse(self.page_url).query:
return
head = self.get_head()
if head:
canonical = [item for item in head if item.get('rel') == 'canonical']
if not canonical:
self.add_violation(
key='absent.meta.canonical',
value=None,
points=30
)
def validate(self):
blacklist_domains = self.get_violation_pref('blacklist.domains')
domains = []
links = self.get_links()
for link in links:
href = link.get('href')
if not is_valid(href):
continue
link_domain, link_domain_url = get_domain_from_url(href)
if link_domain in blacklist_domains:
domains.append(href)
if domains:
self.add_violation(key='blacklist.domains',
value=domains,
points=100 * len(domains))
def validate(self):
force_canonical = self.get_violation_pref('absent.meta.canonical')
if not force_canonical:
# Only pages with query string parameters
if self.page_url:
if not is_valid(self.page_url):
return
if not urlparse(self.page_url).query:
return
head = self.get_head()
if head:
canonical = [
item for item in head if item.get('rel') == 'canonical'
]
if not canonical:
self.add_violation(key='absent.meta.canonical',
value=None,
points=30)
def validate(self):
blacklist_domains = self.get_violation_pref('blacklist.domains')
domains = []
links = self.get_links()
for link in links:
href = link.get('href')
if not is_valid(href):
continue
link_domain, link_domain_url = get_domain_from_url(href)
if link_domain in blacklist_domains:
domains.append(href)
if domains:
self.add_violation(
key='blacklist.domains',
value=domains,
points=100 * len(domains)
)
def validate(self):
links = self.get_links()
page_domain, domain_url = get_domain_from_url(self.review.page_url)
rel_nofollow = []
for link in links:
href = link.get('href')
if not is_valid(href):
continue
link_domain, link_domain_url = get_domain_from_url(href)
if link.get('rel') == 'nofollow' and page_domain == link_domain:
rel_nofollow.append(href)
if rel_nofollow:
self.add_violation(key='invalid.links.nofollow',
value=rel_nofollow,
points=10 * len(rel_nofollow))
