def _fetch_from_lyricsdotcom(artist, song):
page = requests.get('http://www.lyrics.com/%s-lyrics-%s.html' % (song, artist))
soup = BeautifulSoup(page.text, 'lxml')
lyrics = str(soup.findAll('div', {'id' : 'lyrics'}))
lyrics = mlstripper.strip_tags(lyrics)
lyrics = lyrics.replace('\\n', '\n') # Re-encode new lines.
return lyrics
def parse(self):
'''
Parses this Billboard 200 page and returns scraped tuples of form:
(album, artist, date, position)
'''
soup = BeautifulSoup(self.read_page(), "lxml")
#print ("Extracting ranks...")
r_raw = soup.findAll("span", {"class" : "chart-row__current-week"})
ranks = [int(r.contents[0]) for r in r_raw] # tags -> int
#print ("Extracting albums...")
a_raw = soup.findAll("h2", {"class" : "chart-row__song"})
albums = [self.clean(str(a.contents[0])) for a in a_raw]
#print ("Extracting artists...")
a_raw = soup.findAll("h3", {"class" : "chart-row__artist"})
artists = [self.clean(mlstripper.strip_tags(str(a))) for a in a_raw]
return [(self._date, z[0], z[1], z[2]) for z in zip(ranks, albums, artists)]
