def _find_keyword_in_url(self, links, domain):
# Get all url and normalize it
normalized_links = self._normalize_elems(links)
# Filter url that doesn't contain keyword
candidate_links = \
filter(lambda x:
self._is_contain_keyword(x.replace(Utility.find_domain_name(domain), '')), normalized_links)
return candidate_links
def sort_email(self, emails, domain):
# If this is not governor's domain, do not get any email candidate with .go.id domain name
if '.go.id' not in domain:
emails = [email for email in emails if '.go.id' not in emails]
domain_name = Utility.find_domain_name(domain)
emails = map(lambda email: (email, domain_name), emails)
# Sort based on score descending
emails.sort(cmp=lambda a, b: -1
if self.email_scoring(a) > self.email_scoring(b) else 0)
emails = [x for x, y in emails]
return emails[:cfg.max_email]
