def test_is_feed(self):
finder = feed_seeker.FeedSeeker(self.base_url,
html=self.regular_feed_page)
assert finder.is_feed()
finder = feed_seeker.FeedSeeker(self.base_url,
html=self.regular_html_template)
assert not finder.is_feed()
def test_generate_feed_urls_not_a_page(self):
feeds, _ = self.generate_responses()
finder = feed_seeker.FeedSeeker(self.base_url + '/what_is_this_even')
found_feeds = list(finder.generate_feed_urls())
assert len(found_feeds) == 0
def test_generate_feed_urls_on_feed(self):
feeds, _ = self.generate_responses()
finder = feed_seeker.FeedSeeker(self.base_url + feeds[0])
found_feeds = list(finder.generate_feed_urls())
assert len(found_feeds) == 1
def test_guess_feed_links(self):
# even empty page has some guesses
finder = feed_seeker.FeedSeeker(self.base_url, html=self.regular_html_template)
guessed_links = list(finder.guess_feed_links())
assert len(guessed_links) > 0
for feed_link in guessed_links:
assert self.base_url in feed_link
def test_html_property(self):
responses.add(responses.GET,
self.base_url,
body=self.regular_html_template,
status=200)
finder = feed_seeker.FeedSeeker(self.base_url)
found_html = finder.html
assert found_html == self.regular_html_template
def test_generate_feed_urls_max_links(self):
feeds, _ = self.generate_responses()
finder = feed_seeker.FeedSeeker(self.base_url)
max_links = 2
found_feeds = list(finder.generate_feed_urls(max_links=max_links))
assert len(found_feeds) > 0
assert len(found_feeds) <= max_links < len(feeds)
def test_find_link_feeds(self):
num_feeds = 4
feed_urls = []
# note that we do NOT eliminate duplicates at this level
for _ in range(num_feeds):
feed_urls.append(self.rss_feed_template.format('http://whatever.com'))
html = self.regular_html_template.format(head='\n'.join(feed_urls), body='')
finder = feed_seeker.FeedSeeker(self.base_url, html=html)
assert len(list(finder.find_link_feeds())) == num_feeds
assert len(list(finder.find_anchor_feeds())) == 0
def test_find_anchor_feeds(self):
num_feeds = 4
feed_urls = []
# we should find these four links
for feed in range(num_feeds):
feed_urls.append('<a href="http://{}.rss"></a>'.format(feed))
# but will not flag this one, since it does not look like a feed
feed_urls.append('<a href="https://not_an_example.com"></a>')
html = self.regular_html_template.format(head='', body='\n'.join(feed_urls))
finder = feed_seeker.FeedSeeker(self.base_url, html=html)
assert len(list(finder.find_link_feeds())) == 0
assert len(set(finder.find_anchor_feeds())) == num_feeds
def test_empty_page(self):
finder = feed_seeker.FeedSeeker(self.base_url,
html=self.regular_html_template)
# Page has no links, so should fail
assert finder.find_feed_url() is None
def test_find_internal_links(self):
self.generate_responses()
finder = feed_seeker.FeedSeeker(self.base_url, html=None)
internal_links = finder.find_internal_links()
assert len(internal_links) == 1 # from `self.generate_responses`