def test_sources_fail(self):
for s in self.sourcesFail:
url = s['url'] + s['path']
res = lyrics.scrape_lyrics_from_url(url)
# very unlikely these sources pass if the scraping algo is not
# tweaked on purpose for these cases
self.assertFalse(lyrics.is_lyrics(res), "%s => %s" % (url, res))
def test_sources_fail(self):
for s in self.sourcesFail:
url = s['url'] + s['path']
res = lyrics.scrape_lyrics_from_url(url)
# very unlikely these sources pass if the scraping algo is not
# tweaked on purpose for these cases
self.assertFalse(lyrics.is_lyrics(res), "%s => %s" % (url, res))
def test_sources_incomplete(self):
for s in self.sourcesIncomplete:
url = s['url'] + s['path']
res = lyrics.scrape_lyrics_from_url(url)
self.assertTrue(lyrics.is_lyrics(res))
# these sources may pass if the html source evolve or after
# a random improvement in the scraping algo: we want to
# be noticed if it's the case.
if is_lyrics_content_ok(s['title'], res):
log.debug('Source %s actually return valid lyrics!' % s['url'])
def test_sources_incomplete(self):
for s in self.sourcesIncomplete:
url = s['url'] + s['path']
res = lyrics.scrape_lyrics_from_url(url)
self.assertTrue(lyrics.is_lyrics(res))
# these sources may pass if the html source evolve or after
# a random improvement in the scraping algo: we want to
# be noticed if it's the case.
if is_lyrics_content_ok(s['title'], res):
log.debug('Source %s actually return valid lyrics!' % s['url'])
def test_sources_ok(self):
for s in self.sourcesOk:
url = s['url'] + s['path']
res = lyrics.scrape_lyrics_from_url(url)
self.assertTrue(lyrics.is_lyrics(res), url)
self.assertTrue(is_lyrics_content_ok(s['title'], res), url)
def test_sources_ok(self):
for s in self.sourcesOk:
url = s['url'] + s['path']
res = lyrics.scrape_lyrics_from_url(url)
self.assertTrue(lyrics.is_lyrics(res), url)
self.assertTrue(is_lyrics_content_ok(s['title'], res), url)