def test_is_page_candidate_fuzzy_match(self):
url = u"http://www.example.com/lazy_madonna_beatles"
urlTitle = u"example.com | lazy madonna lyrics by the beatles"
title = u"Lady Madonna"
artist = u"The Beatles"
# very small diffs (typo) are ok
self.assertEqual(lyrics.is_page_candidate(url, urlTitle, title, artist), True, url)
# reject different title
urlTitle = u"example.com | busy madonna lyrics by the beatles"
self.assertEqual(lyrics.is_page_candidate(url, urlTitle, title, artist), False, url)
# (title, artist) != (artist, title)
urlTitle = u"example.com | the beatles lyrics by Lazy Madonna"
self.assertEqual(lyrics.is_page_candidate(url, urlTitle, title, artist), False, url)
def test_is_page_candidate_fuzzy_match(self):
"""Test matching html page title with song infos -- when song infos are
not present in the title."""
s = self.source
url = s['url'] + s['path']
urlTitle = u'example.com | Beats song by John doe'
# very small diffs (typo) are ok eg 'beats' vs 'beets' with same artist
self.assertEqual(lyrics.is_page_candidate(url, urlTitle, s['title'],
s['artist']), True, url)
# reject different title
urlTitle = u'example.com | seets bong lyrics by John doe'
self.assertEqual(lyrics.is_page_candidate(url, urlTitle, s['title'],
s['artist']), False, url)
def test_is_page_candidate_fuzzy_match(self):
"""Test matching html page title with song infos -- when song infos are
not present in the title."""
s = self.source
url = s['url'] + s['path']
urlTitle = u'example.com | Beats song by John doe'
# very small diffs (typo) are ok eg 'beats' vs 'beets' with same artist
self.assertEqual(lyrics.is_page_candidate(url, urlTitle, s['title'],
s['artist']), True, url)
# reject different title
urlTitle = u'example.com | seets bong lyrics by John doe'
self.assertEqual(lyrics.is_page_candidate(url, urlTitle, s['title'],
s['artist']), False, url)
def test_is_page_candidate_fuzzy_match(self):
url = u'http://www.example.com/lazy_madonna_beatles'
urlTitle = u'example.com | lazy madonna lyrics by the beatles'
title = u'Lady Madonna'
artist = u'The Beatles'
# very small diffs (typo) are ok
self.assertEqual(
lyrics.is_page_candidate(url, urlTitle, title, artist), True, url)
# reject different title
urlTitle = u'example.com | busy madonna lyrics by the beatles'
self.assertEqual(
lyrics.is_page_candidate(url, urlTitle, title, artist), False, url)
# (title, artist) != (artist, title)
urlTitle = u'example.com | the beatles lyrics by Lazy Madonna'
self.assertEqual(
lyrics.is_page_candidate(url, urlTitle, title, artist), False, url)
def test_is_page_candidate_exact_match(self):
from bs4 import SoupStrainer, BeautifulSoup
for s in self.sourcesOk:
url = unicode(s["url"] + s["path"])
html = lyrics.fetch_url(url)
soup = BeautifulSoup(html, "html.parser", parse_only=SoupStrainer("title"))
self.assertEqual(lyrics.is_page_candidate(url, soup.title.string, s["title"], s["artist"]), True, url)
def test_is_page_candidate(self):
for s in self.sourcesOk:
url = unicode(s['url'] + s['path'])
html = lyrics.fetch_url(url)
soup = BeautifulSoup(html)
if not soup.title:
continue
self.assertEqual(
lyrics.is_page_candidate(url, soup.title.string, s['title'],
s['artist']), True, url)
def test_is_page_candidate(self):
for s in self.sourcesOk:
url = unicode(s['url'] + s['path'])
html = lyrics.fetch_url(url)
soup = BeautifulSoup(html)
if not soup.title:
continue
self.assertEqual(lyrics.is_page_candidate(url, soup.title.string,
s['title'], s['artist']),
True, url)
def test_is_page_candidate(self):
from bs4 import SoupStrainer, BeautifulSoup
for s in self.sourcesOk:
url = unicode(s['url'] + s['path'])
html = lyrics.fetch_url(url)
soup = BeautifulSoup(html, "html.parser",
parse_only=SoupStrainer('title'))
self.assertEqual(lyrics.is_page_candidate(url, soup.title.string,
s['title'], s['artist']),
True, url)
def test_is_page_candidate_exact_match(self):
"""Test matching html page title with song infos -- when song infos are
present in the title."""
from bs4 import SoupStrainer, BeautifulSoup
s = self.source
url = unicode(s['url'] + s['path'])
html = lyrics.fetch_url(url)
soup = BeautifulSoup(html, "html.parser",
parse_only=SoupStrainer('title'))
self.assertEqual(lyrics.is_page_candidate(url, soup.title.string,
s['title'], s['artist']),
True, url)
def test_is_page_candidate_exact_match(self):
"""Test matching html page title with song infos -- when song infos are
present in the title."""
from bs4 import SoupStrainer, BeautifulSoup
s = self.source
url = unicode(s['url'] + s['path'])
html = lyrics.fetch_url(url)
soup = BeautifulSoup(html, "html.parser",
parse_only=SoupStrainer('title'))
self.assertEqual(lyrics.is_page_candidate(url, soup.title.string,
s['title'], s['artist']),
True, url)