def test_atom_extraction():
'''Test link extraction from an Atom feed'''
filepath = os.path.join(RESOURCES_DIR, 'feed1.atom')
with open(filepath) as f:
teststring = f.read()
assert len(feeds.extract_links(teststring)) > 0
assert len(feeds.extract_links('<link type="application/atom+xml" rel="self" href="https://www.dwds.de/api/feed/themenglossar/Corona"/>')) == 0
def test_atom_extraction():
'''Test link extraction from an Atom feed'''
assert len(feeds.extract_links('<html></html>', 'example.org', 'https://example.org', '')) == 0
filepath = os.path.join(RESOURCES_DIR, 'feed1.atom')
with open(filepath) as f:
teststring = f.read()
assert len(feeds.extract_links(teststring, 'example.org', 'https://example.org', '')) > 0
assert len(feeds.extract_links(XMLDECL + '<link type="application/atom+xml" rel="self" href="https://www.dwds.de/api/feed/themenglossar/Corona"/>', 'dwds.de', 'https://www.dwds.de', '')) == 0
assert len(feeds.extract_links(XMLDECL + '<link type="application/atom+xml" rel="self" href="123://api.exe"/>', 'example.org', 'https://example.org', '')) == 0
def test_rss_extraction():
'''Test link extraction from a RSS feed'''
assert len(feeds.extract_links(XMLDECL + '<link>http://example.org/article1/</link>', 'example.org', 'http://example.org/', '')) == 1
assert len(feeds.extract_links(XMLDECL + '<link>http://example.org/</link>', 'example.org', 'http://example.org', 'http://example.org')) == 0
assert len(feeds.extract_links(XMLDECL + '<link rel="self">http://example.org/article1/</link>', 'example.org', 'http://example.org/', '')) == 0
assert feeds.extract_links(XMLDECL + '<link>/api/feed/themenglossar/Corona</link>', 'www.dwds.de', 'https://www.dwds.de', 'https://www.dwds.de') == ['https://www.dwds.de/api/feed/themenglossar/Corona']
filepath = os.path.join(RESOURCES_DIR, 'feed2.rss')
with open(filepath) as f:
teststring = f.read()
assert len(feeds.extract_links(teststring, 'example.com', 'https://example.org', '')) > 0
def test_rss_extraction():
'''Test link extraction from a RSS feed'''
assert len(
feeds.extract_links(
XMLDECL + '<link>http://example.org/article1/</link>',
'example.org', 'http://example.org/', '')) == 1
# CDATA
assert feeds.extract_links(
XMLDECL + '<link><![CDATA[http://example.org/article1/]]></link>',
'example.org', 'http://example.org/',
'') == ['http://example.org/article1/']
# spaces
assert len(
feeds.extract_links(
XMLDECL +
'<link>\r\n https://www.ak-kurier.de/akkurier/www/artikel/108815-sinfonisches-blasorchester-spielt-1500-euro-fuer-kinder-in-drk-krankenhaus-kirchen-ein </link>',
'ak-kurier.de', 'https://www.ak-kurier.de/', '')) == 1
assert len(
feeds.extract_links(XMLDECL + '<link>http://example.org/</link>',
'example.org', 'http://example.org',
'http://example.org')) == 0
assert len(
feeds.extract_links(XMLDECL + '<link>https://example.org</link>',
'example.org', 'http://example.org/', '')) == 0
assert feeds.extract_links(
XMLDECL + '<link>/api/feed/themenglossar/Corona</link>', 'www.dwds.de',
'https://www.dwds.de', 'https://www.dwds.de') == [
'https://www.dwds.de/api/feed/themenglossar/Corona'
]
filepath = os.path.join(RESOURCES_DIR, 'feed2.rss')
with open(filepath) as f:
teststring = f.read()
assert len(
feeds.extract_links(teststring, 'example.com', 'https://example.org',
'')) > 0
def test_json_extraction():
'''Test link extraction from a JSON feed'''
# find link
assert len(
feeds.determine_feed(
'<html><meta><link rel="alternate" type="application/json" title="JSON Feed" href="https://www.jsonfeed.org/feed.json" />></meta><body/></html>',
'jsonfeed.org', 'https://www.jsonfeed.org')) == 1
# extract data
filepath = os.path.join(RESOURCES_DIR, 'feed.json')
with open(filepath) as f:
teststring = f.read()
links = feeds.extract_links(teststring, 'npr.org', 'https://npr.org', '')
assert len(links) == 25
# id as a backup
links = feeds.extract_links(
r'{"version":"https:\/\/jsonfeed.org\/version\/1","items":[{"id":"https://www.example.org/1","title":"Test"}]}',
'example.org', 'https://example.org', '')
assert len(links) == 1
def test_rss_extraction():
'''Test link extraction from a RSS feed'''
filepath = os.path.join(RESOURCES_DIR, 'feed2.rss')
with open(filepath) as f:
teststring = f.read()
assert len(feeds.extract_links(teststring)) > 0
def test_atom_extraction():
'''Test link extraction from an Atom feed'''
filepath = os.path.join(RESOURCES_DIR, 'feed1.atom')
with open(filepath) as f:
teststring = f.read()
assert len(feeds.extract_links(teststring)) > 0
