def _process_lyrics_table(self, lang_row, lyrics):
for lang, td in zip(('Korean', 'English'),
lang_row.find_all('td')[1:]):
td_str = str(td)
td_str = td_str[:4] + '<p>' + td_str[4:]
fixed_td = soupify(re.sub('(?<!</p>|<td>)<p>', '</p><p>', td_str))
log.log(5, 'Fixed td:\n{}\n\n'.format(fixed_td))
for p in fixed_td.find_all('p'):
lines = [
l
for l in p.get_text().replace('<br/>', '\n').splitlines()
if l
]
for j, line in enumerate(lines):
if line.startswith('<span'):
lines[j] = soupify(line).find('span').get_text()
log.log(
9,
'{}: found stanza with {} lines'.format(lang, len(lines)))
lines.append('<br/>')
lyrics[lang].extend(lines)
def get_english_translation(self, song):
html = soupify(self.get_page(song), 'lxml')
artist_ele = html.find('li', class_='song-node-info-artist')
artist = artist_ele.text.replace('Artist:', '').strip()
title = html.find('h2', class_='title-h2').text
full_title = '{} - {}'.format(artist, title)
content = html.find('div', class_='ltf')
lines = []
for par in content.find_all('div', class_='par'):
stanza = par.get_text().splitlines()
log.log(
19, '{}: found stanza with {} lines'.format(
'English', len(stanza)))
lines.extend(stanza)
lines.append('<br/>')
return lines, full_title
def get_lyrics(self,
song,
title=None,
*,
kor_endpoint=None,
eng_endpoint=None):
lyrics = {'Korean': [], 'English': [], 'title': title}
html = soupify(self.get_page(song), 'lxml')
content = html.find('div', class_='td-post-content')
for h2 in content.find_all('h2'):
if h2.text.endswith('Hangul'):
lang = 'Korean'
if title is None:
lyrics['title'] = re.match('^(.*?)\s+Hangul$',
h2.text).group(1)
elif h2.text.endswith('English Translation'):
lang = 'English'
else:
continue
log.debug('Found {} section'.format(lang))
ele = h2.next_sibling
while ele.name in (None, 'p'):
log.log(
9,
'Processing element: <{0}>{1}</{0}>'.format(ele.name, ele))
if ele.name == 'p':
lines = [
l
for l in ele.text.replace('<br/>', '\n').splitlines()
if l
]
log.log(
19, '{}: found stanza with {} lines'.format(
lang, len(lines)))
lines.append('<br/>')
lyrics[lang].extend(lines)
ele = ele.next_sibling
return lyrics
def get_index_results(self, query):
album_soup = self.get_index(query)
results = []
for a in album_soup.find_all('a', href=re.compile('/album/.*')):
year = a.parent.next_sibling.get_text()
album = '[{}] {}'.format(year, a.get_text())
link = a.get('href')
album_page = soupify(self.get_page(link))
for track_a in album_page.find_all(
'a', href=re.compile('/lyrics/.*(?<!/edit)$')):
track_link = track_a.get('href')
track_name = track_a.find(
'h2', class_=re.compile('.*title$')).get_text()
results.append({
'Album': album,
'Song': track_name,
'Link': track_link
})
# print(album, link)
return results
def get_lyrics(self,
song,
title=None,
*,
kor_endpoint=None,
eng_endpoint=None) -> Dict[str, Union[str, List[str]]]:
log.debug(f'Getting lyrics for {song=!r}')
html = soupify(self.get_page(song), 'lxml')
lyrics = {
'Korean': [],
'English': [],
'title': title or html.find('h1', class_='entry-title').get_text(),
}
try:
lang_row = html.find(
'th', text='Romanization').parent.next_sibling.next_sibling
except AttributeError:
self._process_lyrics_nontable(html, lyrics)
else:
self._process_lyrics_table(lang_row, lyrics)
return lyrics
def get_lyrics(self,
song,
title=None,
*,
kor_endpoint=None,
eng_endpoint=None) -> Dict[str, Union[str, List[str]]]:
html = soupify(self.get_page(self._normalize_title(song)), 'lxml')
title_header = html.find('div', class_='mxm-track-title')
track_title = list(title_header.find('h1').children)[-1]
track_artist = title_header.find('h2').get_text()
lyrics = {
'Korean': [],
'English': [],
'title': title or '{} - {}'.format(track_artist, track_title)
}
lang_names = {0: 'Korean', 1: 'English'}
container = html.find('div', class_='mxm-track-lyrics-container')
for row in container.find_all('div',
class_='mxm-translatable-line-readonly'):
# log.debug(f'Found {row=}')
last_i = -1
for i, div in enumerate(row.find_all(lyric_part_match)):
# TODO: Need to add newlines between stanzas
lang = lang_names[i]
text = div.get_text() or '<br/>'
# log.debug(f'Found {lang=} {text=}')
lyrics[lang].append(text)
last_i = i
if (last_i == 0) and (len(lyrics['Korean']) != len(
lyrics['English'])):
lyrics['English'].append('<br/>')
return lyrics
def get_index(self, *args, **kwargs):
return soupify(self._index(*args, **kwargs))
def search(self, *args, **kwargs):
return soupify(self._search(*args, **kwargs))