def get_urls(post): candidates = get_url_candidates(post) urls = set() for u in candidates: if 'facebook' not in u: if is_short_url(u): u = unshorten_url(u) urls.add(prepare_url(u)) return list(urls)
def parse_url(url): """ unshorten and/or normalize url. """ if is_short_url(url): long_url = unshorten_url(url) if long_url: return prepare_url(long_url) else: return url else: return prepare_url(url)