def test_extraction():
'''Test simple link extraction'''
url, domain, baseurl = 'https://www.sitemaps.org/sitemap.xml', 'sitemaps.org', 'https://www.sitemaps.org'
# fixing partial URLs
assert fix_relative_urls('https://example.org', 'https://example.org/test.html') == 'https://example.org/test.html'
assert fix_relative_urls('https://example.org', '/test.html') == 'https://example.org/test.html'
assert fix_relative_urls('https://example.org', 'test.html') == 'https://example.org/test.html'
assert fix_relative_urls('https://example.org', '../../test.html') == 'https://example.org/test.html'
# link handling
assert sitemaps.handle_link(url, url, domain, baseurl, None) == (url, '0')
assert sitemaps.handle_link('https://mydomain.wordpress.com/1', 'https://example.org/sitemap.xml', 'example.org', 'https://example.org', None) == ('https://mydomain.wordpress.com/1', 'link')
# safety belts
assert sitemaps.check_sitemap('http://example.org/sitemap.xml.gz', b'\x1f\x8bABC') is None
assert sitemaps.check_sitemap('http://example.org/sitemap.xml', 'ABC') is None
# parsing a file
filepath = os.path.join(RESOURCES_DIR, 'sitemap.xml')
with open(filepath) as f:
teststring = f.read()
contents = sitemaps.check_sitemap('http://example.org/sitemap.xml', teststring)
sitemapurls, linklist = sitemaps.extract_sitemap_links(contents, url, domain, baseurl, None)
assert len(sitemapurls) == 0 and len(linklist) == 84
# hreflang
assert sitemaps.extract_sitemap_langlinks(teststring, url, domain, baseurl, None) == ([], [])
# nested sitemaps
url, domain, baseurl = 'http://www.example.com/sitemap.xml', 'example.com', 'http://www.example.com'
filepath = os.path.join(RESOURCES_DIR, 'sitemap2.xml')
with open(filepath) as f:
teststring = f.read()
sitemapurls, linklist = sitemaps.extract_sitemap_links(teststring, url, domain, baseurl, None)
assert sitemapurls == ['http://www.example.com/sitemap1.xml.gz', 'http://www.example.com/sitemap2.xml.gz'] and linklist == []
# invalid
assert sitemaps.extract_sitemap_links('<html>\n</html>', url, domain, baseurl, None) == ([], [])
# hreflang
filepath = os.path.join(RESOURCES_DIR, 'sitemap-hreflang.xml')
with open(filepath) as f:
teststring = f.read()
sitemapsurls, linklist = sitemaps.extract_sitemap_langlinks(teststring, url, domain, baseurl, target_lang='de')
assert sitemapsurls == ['http://www.example.com/sitemap-de.xml.gz']
assert len(linklist) > 0
# GZ-compressed sitemaps
url, domain, baseurl = 'https://www.sitemaps.org/sitemap.xml', 'sitemaps.org', 'https://www.sitemaps.org'
filepath = os.path.join(RESOURCES_DIR, 'sitemap.xml.gz')
with open(filepath, 'rb') as f:
teststring = f.read()
teststring = decode_response(teststring)
contents = sitemaps.check_sitemap('http://example.org/sitemap.xml.gz', teststring)
sitemapurls, linklist = sitemaps.extract_sitemap_links(contents, url, domain, baseurl, None)
assert len(sitemapurls) == 0 and len(linklist) == 84
# check contents
assert sitemaps.check_sitemap('http://example.org/sitemap.xml.gz?value=1', teststring) is not None
# TXT links
assert sitemaps.process_sitemap('https://test.org/sitemap', 'test.org', 'https://test.org/', 'Tralala\nhttps://test.org/1\nhttps://test.org/2') == ([], ['https://test.org/1', 'https://test.org/2'])
# unique and sorted URLs
urlfilter = 'category'
myurls = ['/category/xyz', '/category/abc', '/cat/test', '/category/abc']
assert filter_urls(myurls, urlfilter) == ['/category/abc', '/category/xyz']
def test_extraction():
'''Test simple link extraction'''
url, domain = 'https://www.sitemaps.org/sitemap.xml', 'sitemaps.org'
# fixing partial URLs
assert sitemaps.fix_relative_urls(
'example.org',
'https://example.org/test.html') == 'https://example.org/test.html'
assert sitemaps.fix_relative_urls(
'example.org', '/test.html') == 'http://example.org/test.html'
# link handling
# assert sitemaps.handle_link(url, domain, url) == (url, '0')
# parsing a file
filepath = os.path.join(RESOURCES_DIR, 'sitemap.xml')
with open(filepath) as f:
teststring = f.read()
sitemapurls, linklist = sitemaps.extract_sitemap_links(
teststring, url, domain)
assert len(sitemapurls) == 0 and len(linklist) == 84
# hreflang
assert sitemaps.extract_sitemap_langlinks(teststring, url,
domain) == ([], [])
# nested sitemaps
filepath = os.path.join(RESOURCES_DIR, 'sitemap2.xml')
with open(filepath) as f:
teststring = f.read()
sitemapurls, linklist = sitemaps.extract_sitemap_links(
teststring, url, domain)
assert len(sitemapurls) == 2 and linklist == []
# invalid
assert sitemaps.extract_sitemap_links('<html>\n</html>', url,
domain) == ([], [])
# hreflang
filepath = os.path.join(RESOURCES_DIR, 'sitemap-hreflang.xml')
with open(filepath) as f:
teststring = f.read()
_, linklist = sitemaps.extract_sitemap_langlinks(teststring,
url,
domain,
target_lang='de')
assert len(linklist) > 0
def test_extraction():
'''Test simple link extraction'''
url, domain, baseurl = 'https://www.sitemaps.org/sitemap.xml', 'sitemaps.org', 'https://www.sitemaps.org'
# fixing partial URLs
assert fix_relative_urls(
'https://example.org',
'https://example.org/test.html') == 'https://example.org/test.html'
assert fix_relative_urls('https://example.org',
'/test.html') == 'https://example.org/test.html'
assert fix_relative_urls('https://example.org',
'test.html') == 'https://example.org/test.html'
# link handling
assert sitemaps.handle_link(url, url, domain, baseurl) == (url, '0')
# safety belts
assert sitemaps.check_sitemap('http://example.org/sitemap.xml.gz',
b'\x1f\x8bABC') is None
assert sitemaps.check_sitemap('http://example.org/sitemap.xml',
'ABC') is None
# parsing a file
filepath = os.path.join(RESOURCES_DIR, 'sitemap.xml')
with open(filepath) as f:
teststring = f.read()
contents = sitemaps.check_sitemap('http://example.org/sitemap.xml',
teststring)
sitemapurls, linklist = sitemaps.extract_sitemap_links(
contents, url, domain, baseurl)
assert len(sitemapurls) == 0 and len(linklist) == 84
# hreflang
assert sitemaps.extract_sitemap_langlinks(teststring, url, domain,
baseurl) == ([], [])
# nested sitemaps
filepath = os.path.join(RESOURCES_DIR, 'sitemap2.xml')
with open(filepath) as f:
teststring = f.read()
sitemapurls, linklist = sitemaps.extract_sitemap_links(
teststring, url, domain, baseurl)
assert len(sitemapurls) == 2 and linklist == []
# invalid
assert sitemaps.extract_sitemap_links('<html>\n</html>', url, domain,
baseurl) == ([], [])
# hreflang
filepath = os.path.join(RESOURCES_DIR, 'sitemap-hreflang.xml')
with open(filepath) as f:
teststring = f.read()
_, linklist = sitemaps.extract_sitemap_langlinks(teststring,
url,
domain,
baseurl,
target_lang='de')
assert len(linklist) > 0
# GZ-compressed sitemaps
filepath = os.path.join(RESOURCES_DIR, 'sitemap.xml.gz')
with open(filepath, 'rb') as f:
teststring = f.read()
contents = sitemaps.check_sitemap('http://example.org/sitemap.xml.gz',
teststring)
sitemapurls, linklist = sitemaps.extract_sitemap_links(
contents, url, domain, baseurl)
assert len(sitemapurls) == 0 and len(linklist) == 84
# check contents
assert sitemaps.check_sitemap('http://example.org/sitemap.xml.gz?value=1',
teststring) is not None