def test_serach_links_join_url(self):
feed_str = get_data_file("chooseopera.html")
links = feedutil.search_links_url(
"http://my.opera.com/chooseopera/blog/", feed_str)
self.assertListEqual(links, [
'http://my.opera.com/chooseopera/xml/rss/blog/',
'http://my.opera.com/chooseopera/xml/atom/blog/'
])
def test_search_links_order(self):
""" Different order for type and href in link sentence.
Format in UTF-8 (Russian)"""
feed_str = get_data_file("mk.ru.html")
links = feedutil.search_links_url("http://www.mk.ru/", feed_str)
self.assertListEqual(links, [
'http://www.mk.ru/rss/news/index.xml',
'http://www.mk.ru/rss/mk/index.xml'
])
def check_homepage_for_feeds(self, dryrun=False):
homepages = [self.homepage, self.rss_homepage]
for homepage in homepages:
if not homepage:
continue
links = search_links_url(url=homepage, depth=3)
for link in links:
print('link:', link)
if not dryrun:
feed = OrganizationFeed.objects.get_or_create(
organization=self,
feed_url=link,
defaults=dict(is_active=False))[0]
self.save()
def test_search_links_mixed(self):
""" Mixed atom and rss sentences """
feed_str = get_data_file("elcomercio.pe.html")
links = feedutil.search_links_url("http://www.elcomercio.pe/",
feed_str)
self.assertListEqual(links, [
'http://www.elcomercio.pe/feed/portada.xml',
'http://www.elcomercio.pe/feed/portada/politica.xml',
'http://www.elcomercio.pe/feed/portada/lima.xml',
'http://www.elcomercio.pe/feed/portada/peru.xml',
'http://www.elcomercio.pe/feed/portada/mundo.xml',
'http://www.elcomercio.pe/feed/portada/economia.xml',
'http://www.elcomercio.pe/feed/portada/tecnologia.xml',
'http://www.elcomercio.pe/feed/portada/deportes.xml',
'http://www.elcomercio.pe/feed/portada/espectaculos.xml',
'http://www.elcomercio.pe/feed/portada/ecologia.xml',
'http://www.elcomercio.pe/feed/portada/opinion.xml'
])
def test_search_alternate_links_double_function(self):
feed_str = get_data_file("smp.no.html")
# Feedparser no longer supports parsing raw HTML documents.
# feed = feedparser.parse(feed_str)
# links = feedutil.search_alternate_links(feed)
# self.assertListEqual(links,
# [u'http://www.smp.no/?service=rss',
# u'http://www.smp.no/?service=rss&t=0',
# u'http://www.smp.no/nyheter/?service=rss',
# u'http://www.smp.no/kultur/?service=rss']
# )
links = feedutil.search_links_url("http://www.smp.no/", feed_str)
self.assertListEqual(links, [
u'http://www.smp.no/?service=rss',
u'http://www.smp.no/?service=rss&t=0',
u'http://www.smp.no/nyheter/?service=rss',
u'http://www.smp.no/kultur/?service=rss'
])
def test_search_link_malformed(self):
""" SGML and others are not able to parse it """
feed_str = get_data_file("foxnews.com.html")
links = feedutil.search_links_url("http://www.foxnews.com/", feed_str)
self.assertListEqual(links,
['http://feeds.feedburner.com/foxnews/latest'])