def iter_lyrics(self, criteria):
for link in self.parser.select(self.document.getroot(),
'div.box-content td.song-name a'):
href = link.attrib.get('href', '')
if criteria == 'artist':
if len(href.split('/')) != 4:
continue
else:
self.browser.location('%s' % href)
assert self.browser.is_on_page(
ArtistSongsPage) or self.browser.is_on_page(
SonglyricsPage)
for lyr in self.browser.page.iter_lyrics():
yield lyr
else:
if len(href.split('/')) != 5:
continue
else:
artist = unicode(
self.parser.select(
link.getparent().getparent().getparent(),
'td.song-artist > p', 1).text.strip())
title = unicode(link.text)
id = unicode(
link.attrib.get('href',
'').replace('http://www.paroles.net/',
''))
lyr = SongLyrics(id, title)
lyr.artist = artist
yield lyr
def iter_lyrics(self):
artist = unicode(self.parser.select(self.document.getroot(), 'span[itemprop=name]', 1).text)
for link in self.parser.select(self.document.getroot(), 'td.song-name > p[itemprop=name] > a[itemprop=url]'):
href = unicode(link.attrib.get('href', ''))
title = unicode(link.text)
id = href.replace('http://www.paroles.net/', '')
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def get_lyrics(self, id):
artist = NotAvailable
title = NotAvailable
content = unicode(self.parser.select(self.document.getroot(), 'div.song-text', 1).text_content().strip())
artist = unicode(self.parser.select(self.document.getroot(), 'span[property$=artist]', 1).text)
title = unicode(self.parser.select(self.document.getroot(), 'span[property$=name]', 1).text)
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = content
return songlyrics
def iter_lyrics(self, artist):
for link in self.parser.select(self.document.getroot(), 'div.cont_catA div.art_scroll a'):
href = link.attrib.get('href', '')
if href.startswith('./paroles'):
title = unicode(link.text)
id = href.replace('./paroles-', '')
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def iter_lyrics(self):
artist = unicode(self.parser.select(self.document.getroot(), 'span[itemprop=name]', 1).text)
for link in self.parser.select(self.document.getroot(), 'td.song-name > p[itemprop=name] > a[itemprop=url]'):
href = unicode(link.attrib.get('href', ''))
title = unicode(link.text)
id = href.replace('http://www.paroles.net/', '')
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def get_lyrics(self, id):
artist = NotAvailable
title = NotAvailable
content = unicode(self.parser.select(self.document.getroot(), 'div.song-text', 1).text_content().strip())
artist = unicode(self.parser.select(self.document.getroot(), 'span[property$=artist]', 1).text)
title = unicode(self.parser.select(self.document.getroot(), 'span[property$=name]', 1).text)
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = content
return songlyrics
def iter_lyrics(self, artist):
for link in self.parser.select(self.document.getroot(),
'div.cont_catA div.art_scroll a'):
href = link.attrib.get('href', '')
if href.startswith('./paroles'):
title = unicode(link.text)
id = href.replace('./paroles-', '')
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def get_lyrics(self, id):
artist = NotAvailable
title = NotAvailable
content = unicode(self.parser.select(self.document.getroot(), 'div#lyr_scroll', 1).text_content().strip())
infos = self.parser.select(self.document.getroot(), 'h2.lyrics > font')
artist = unicode(infos[0].text)
title = unicode(infos[1].text)
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = content
return songlyrics
def iter_lyrics(self, artist):
for th in self.parser.select(self.document.getroot(), 'th.text'):
txt = th.text_content()
if txt.startswith('Top') and txt.endswith('Lyrics'):
for link in self.parser.select(th.getparent().getparent(), 'a.tlink'):
title = unicode(link.attrib.get('title', '').replace(' Lyrics', ''))
id = link.attrib.get('href', '').replace('/lyrics/', '').replace('.html', '')
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def iter_lyrics(self, artist):
for th in self.parser.select(self.document.getroot(), 'th.text'):
txt = th.text_content()
if txt.startswith('Top') and txt.endswith('Lyrics'):
for link in self.parser.select(th.getparent().getparent(), 'a.tlink'):
title = unicode(link.attrib.get('title', '').replace(' Lyrics', ''))
id = link.attrib.get('href', '').replace('/lyrics/', '').replace('.html', '')
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def iter_lyrics(self):
for link in self.parser.select(self.document.getroot(), 'div.elenco div.col-left li a'):
artist = NotAvailable
title = unicode(link.text.split(' - ')[0])
href = link.attrib.get('href', '')
if href.startswith('/paroles') and not href.endswith('alpha.html'):
ids = href.replace('/', '').replace('.html', '').split('paroles_')
id = '%s|%s' % (ids[1], ids[2])
artist = unicode(link.text.split(' - ')[1])
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def get_lyrics(self, id):
artist = NotAvailable
title = NotAvailable
l_artitle = self.parser.select(self.document.getroot(), 'table.text td > b > h2')
if len(l_artitle) > 0:
artitle = l_artitle[0].text.split(' Lyrics by ')
artist = unicode(artitle[1])
title = unicode(artitle[0])
content = unicode(self.parser.select(self.document.getroot(), 'div#songlyrics', 1).text_content().strip())
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = content
return songlyrics
def iter_lyrics(self):
for link in self.parser.select(self.document.getroot(), 'div#albums a'):
artist = NotAvailable
title = unicode(link.text.split(' - ')[0])
href = link.attrib.get('href', '')
if href.startswith('/paroles') and not href.endswith('alpha.html'):
ids = href.replace('/', '').replace('.html', '').split('paroles_')
id = '%s|%s' % (ids[1], ids[2])
artist = unicode(link.text.split(' - ')[1])
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def get_lyrics(self, id):
artist = NotAvailable
title = NotAvailable
l_artitle = self.parser.select(self.document.getroot(), 'table.text td > b > h2')
if len(l_artitle) > 0:
artitle = l_artitle[0].text.split(' Lyrics by ')
artist = unicode(artitle[1])
title = unicode(artitle[0])
content = unicode(self.parser.select(self.document.getroot(), 'div#songlyrics', 1).text_content().strip())
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = content
return songlyrics
def get_lyrics(self, id):
artist = NotAvailable
title = NotAvailable
content = unicode(
self.parser.select(self.document.getroot(), 'div#lyr_scroll',
1).text_content().strip())
infos = self.parser.select(self.document.getroot(), 'h2.lyrics > font')
artist = unicode(infos[0].text)
title = unicode(infos[1].text)
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = content
return songlyrics
def get_lyrics(self, id):
content = NotAvailable
artist = NotAvailable
title = NotAvailable
lyrdiv = self.parser.select(self.document.getroot(), 'div.lyrics-body')
if len(lyrdiv) > 0:
content = unicode(lyrdiv[0].text_content().strip())
infos = self.parser.select(self.document.getroot(), 'head > title', 1).text
artist = unicode(infos.split(' - ')[1])
title = unicode(infos.split(' - ')[0].replace('Paroles ', ''))
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = content
return songlyrics
def iter_lyrics(self, artist=None):
if artist is None:
artist = self.parser.select(self.document.getroot(), 'head > title', 1).text.replace('Paroles ', '')
for link in self.parser.select(self.document.getroot(), 'div#albums a'):
href = link.attrib.get('href', '')
titleattrib = link.attrib.get('title', '')
if href.startswith('/paroles') and not href.endswith('alpha.html') and titleattrib.startswith('Paroles '):
title = unicode(link.text)
ids = href.replace('/', '').replace('.html', '').split('paroles_')
id = '%s|%s' % (ids[1], ids[2])
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def get_lyrics(self, id):
content = NotAvailable
artist = NotAvailable
title = NotAvailable
lyrdiv = self.parser.select(self.document.getroot(), 'div#songlyrics_h')
if len(lyrdiv) > 0:
content = unicode(lyrdiv[0].text_content().strip())
infos = self.parser.select(self.document.getroot(), 'head > title', 1).text
artist = unicode(infos.split(' - ')[1])
title = unicode(infos.split(' - ')[0].replace('Paroles ', ''))
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = content
return songlyrics
def iter_lyrics(self, artist=None):
if artist is None:
artist = self.parser.select(self.document.getroot(), 'head > title', 1).text.replace('Paroles ', '')
for link in self.parser.select(self.document.getroot(), 'div#albums a'):
href = link.attrib.get('href', '')
titleattrib = link.attrib.get('title', '')
if href.startswith('/paroles') and not href.endswith('alpha.html') and titleattrib.startswith('Paroles '):
title = unicode(link.text)
ids = href.replace('/', '').replace('.html', '').split('paroles_')
id = '%s|%s' % (ids[1], ids[2])
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def iter_lyrics(self):
first = True
for tr in self.parser.select(self.document.getroot(), 'div.cont_cat table tr'):
if first:
first = False
continue
artist = NotAvailable
links = self.parser.select(tr, 'a.std')
title = unicode(links[0].text)
id = links[0].attrib.get('href', '').replace('/paroles-', '')
artist = unicode(links[1].text)
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def iter_lyrics(self):
first = True
for tr in self.parser.select(self.document.getroot(),
'div.cont_cat table tr'):
if first:
first = False
continue
artist = NotAvailable
links = self.parser.select(tr, 'a.std')
title = unicode(links[0].text)
id = links[0].attrib.get('href', '').replace('/paroles-', '')
artist = unicode(links[1].text)
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def iter_lyrics(self):
first = True
for tr in self.parser.select(self.document.getroot(), 'table[title~=Results] tr'):
if first:
first = False
continue
artist = NotAvailable
tds = self.parser.select(tr, 'td')
assert len(tds) > 2
title = unicode(tds[1].text_content())
link = self.parser.select(tds[1], 'a', 1)
id = link.attrib.get('href', '').replace('/lyrics/', '').replace('.html', '')
aartist = self.parser.select(tr, 'a')[-1]
artist = unicode(aartist.text)
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def iter_lyrics(self):
first = True
for tr in self.parser.select(self.document.getroot(), 'table[title~=Results] tr'):
if first:
first = False
continue
artist = NotAvailable
tds = self.parser.select(tr, 'td')
assert len(tds) > 2
title = unicode(tds[1].text_content())
link = self.parser.select(tds[1], 'a', 1)
id = link.attrib.get('href', '').replace('/lyrics/', '').replace('.html', '')
aartist = self.parser.select(tr, 'a')[-1]
artist = unicode(aartist.text)
songlyrics = SongLyrics(id, title)
songlyrics.artist = artist
songlyrics.content = NotLoaded
yield songlyrics
def iter_lyrics(self, criteria):
for link in self.parser.select(self.document.getroot(), 'div.box-content td.song-name a'):
href = link.attrib.get('href','')
if criteria == 'artist':
if len(href.split('/')) != 4:
continue
else:
self.browser.location('%s' % href)
assert self.browser.is_on_page(ArtistSongsPage) or self.browser.is_on_page(SonglyricsPage)
for lyr in self.browser.page.iter_lyrics():
yield lyr
else:
if len(href.split('/')) != 5:
continue
else:
artist = unicode(self.parser.select(link.getparent().getparent().getparent(), 'td.song-artist > p', 1).text.strip())
title = unicode(link.text)
id = unicode(link.attrib.get('href', '').replace('http://www.paroles.net/',''))
lyr = SongLyrics(id, title)
lyr.artist = artist
yield lyr