def parse_Mp3skull(song, maxpages=1):
"Function connects to mp3skull.com and returns the .mp3 links in it"
if utils.isHebrew(song): # Dilandau doesn't have hebrew
log.warning("[Mp3skull] source has no hebrew songs. Skipping...")
return
song = urllib2.quote(song.encode("utf8"))
for i in range(maxpages):
# http://mp3skull.com/mp3/how_i_met_your_mother.html
url = 'http://mp3skull.com/mp3/%s.html' % (song.replace('-','').replace(' ','_').replace('__','_').lower())
log.debug("[Mp3skull] Parsing %s... " % url)
obj = urllib2.urlopen(url)
response = obj.read()
links = []
soup = BeautifulSoup(response)
for link in soup.find_all('a', href=re.compile(r'\.mp3$')):
links.append(link['href'])
log.debug("[Mp3skull] found %d links" % len(links))
if not links:
break
for link in links:
yield utils.cls.MetaUrl(link, 'Mp3skull')
def parse_Mp3skull(song, maxpages=1):
"Function connects to mp3skull.com and returns the .mp3 links in it"
if utils.isHebrew(song): # Dilandau doesn't have hebrew
log.warning("[Mp3skull] source has no hebrew songs. Skipping...")
return
song = urllib2.quote(song.encode("utf8"))
for i in range(maxpages):
# http://mp3skull.com/mp3/how_i_met_your_mother.html
url = 'http://mp3skull.com/mp3/%s.html' % (song.replace(
'-', '').replace(' ', '_').replace('__', '_').lower())
log.debug("[Mp3skull] Parsing %s... " % url)
obj = urllib2.urlopen(url)
response = obj.read()
links = []
soup = BeautifulSoup(response)
for link in soup.find_all('a', href=re.compile(r'\.mp3$')):
links.append(link['href'])
log.debug("[Mp3skull] found %d links" % len(links))
if not links:
break
for link in links:
yield utils.cls.MetaUrl(link, 'Mp3skull')
def slot_apply(self):
self.ID3TagsToEdit = {}
log.debug("Saving ID3 Data in cache...")
self.ID3TagsToEdit['TIT2'] = TIT2(encoding=3, text=unicode(self.title.displayText()))
self.ID3TagsToEdit['TPE1'] = TPE1(encoding=3, text=unicode(self.artist.displayText()))
self.ID3TagsToEdit['TALB'] = TALB(encoding=3, text=unicode(self.album.displayText()))
self.ID3TagsToEdit['TDRC'] = TDRC(encoding=3, text=unicode(self.date.displayText()))
self.ID3TagsToEdit['COMM'] = COMM(encoding=3, text=unicode(config.id3tags_whitemark), desc='')
lyrics = unicode(self.lyrics.toPlainText()).replace('\r\n','\n').replace('\n','\r\n')
if lyrics:
if utils.isHebrew(lyrics):
self.ID3TagsToEdit['USLT'] = USLT(encoding=3, lang=u'heb', desc=u'', text=lyrics)
else:
self.ID3TagsToEdit['USLT'] = USLT(encoding=3, lang=u'eng', desc=u'', text=lyrics)
else:
self.ID3TagsToEdit['USLT'] = ''
if self.albumArt_task == 'add' and self.pix_path:
with open(self.pix_path, 'rb') as f:
data = f.read()
self.ID3TagsToEdit['APIC'] = APIC(encoding=0, mime=utils.guess_image_mime_type(self.pix_path),
type=0, desc="", data=data)
elif self.albumArt_task == 'delete':
self.ID3TagsToEdit['APIC'] = '' # empty value doesn't add a new APIC tag. All other APIC tags are removed piror to insertion.
self.close()
def run(self): # Called by Qt once the thread environment has been set up. if utils.isHebrew(self.lyric): track = Main.WebParser.MetadataGrabber.parse_shironet_songs_by_lyrics(self.lyric) else: track = Main.WebParser.MetadataGrabber.parse_songlyrics_songs_by_lyrics(self.lyric) if not track: track = Main.WebParser.MetadataGrabber.parse_animelyrics_songs_by_lyrics(self.lyric) self.output.emit(track)
def run(self): # Called by Qt once the thread environment has been set up. if utils.isHebrew(self.lyric): track = Main.WebParser.MetadataGrabber.parse_shironet_songs_by_lyrics(self.lyric) else: track = Main.WebParser.MetadataGrabber.parse_songlyrics_songs_by_lyrics(self.lyric) if not track: track = Main.WebParser.MetadataGrabber.parse_animelyrics_songs_by_lyrics(self.lyric) self.output.emit(track)
def old_spell_fix(s):
"Uses google API to fix spelling"
data = u"""
<spellrequest textalreadyclipped="0" ignoredups="1" ignoredigits="1" ignoreallcaps="0">
<text>%s</text>
</spellrequest>
"""
data = data % s
data_octets = data.encode('utf-8')
new_s = s
if log:
log.debug("Checking spell suggestions for '%s'..." % s)
if utils.isHebrew(s):
log.debug("Search string is hebrew. Skipping on spell checking...")
return s
con = httplib.HTTPConnection("www.google.com",
timeout=config.webservices_timeout)
con.request("POST", "/tbproxy/spell?lang=en", data_octets,
{'content-type': 'text/xml; charset=utf-8'})
response = con.getresponse().read()
if log:
log.debug("Response: %s" % response)
try:
dom = xml.dom.minidom.parseString(response)
dom_data = dom.getElementsByTagName('spellresult')[0]
except ExpatError:
log.warning('spell_fix failed: ExpatError.')
return s
for node in dom_data.childNodes:
att_o = int(node.attributes.item(
2).value) # The offset from the start of the text of the word
att_l = int(node.attributes.item(1).value) # Length of misspelled word
att_s = int(
node.attributes.item(0).value) # Confidence of the suggestion
if not node.firstChild: # no suggestions
return s
text = node.firstChild.data.split("\t")[0]
# print "%s --> %s (s: %d)" % (s[att_o:att_o+att_l], text, att_s)
if att_s: # if suggestion is confident
new_s = new_s.replace(s[att_o:att_o + att_l], text)
if log:
if s == new_s:
log.debug("No suggestions were accepted.")
else:
log.debug("Suggestions were accepted: %s --> %s." % (s, new_s))
return new_s
def run(self): # Called by Qt once the thread environment has been set up.
if utils.isHebrew(self.artist):
f = Main.WebParser.MetadataGrabber.shironet_artist_search
else:
f = Main.WebParser.MetadataGrabber.musicbrainz_artist_search
artists = f(self.artist)
if not artists:
self.error.emit(tr("No data was found."))
return
self.output.emit(artists)
def run(self): # Called by Qt once the thread environment has been set up.
if utils.isHebrew(self.artist):
f = Main.WebParser.MetadataGrabber.shironet_artist_search
else:
f = Main.WebParser.MetadataGrabber.musicbrainz_artist_search
artists = f(self.artist)
if not artists:
self.error.emit(tr("No data was found."))
return
self.output.emit(artists)
def old_spell_fix(s):
"Uses google API to fix spelling"
data = u"""
<spellrequest textalreadyclipped="0" ignoredups="1" ignoredigits="1" ignoreallcaps="0">
<text>%s</text>
</spellrequest>
"""
data = data % s
data_octets = data.encode('utf-8')
new_s = s
if log:
log.debug("Checking spell suggestions for '%s'..." % s)
if utils.isHebrew(s):
log.debug("Search string is hebrew. Skipping on spell checking...")
return s
con = httplib.HTTPConnection("www.google.com", timeout=config.webservices_timeout)
con.request("POST", "/tbproxy/spell?lang=en", data_octets, {'content-type': 'text/xml; charset=utf-8'})
response = con.getresponse().read()
if log:
log.debug("Response: %s" % response)
try:
dom = xml.dom.minidom.parseString(response)
dom_data = dom.getElementsByTagName('spellresult')[0]
except ExpatError:
log.warning('spell_fix failed: ExpatError.')
return s
for node in dom_data.childNodes:
att_o = int(node.attributes.item(2).value) # The offset from the start of the text of the word
att_l = int(node.attributes.item(1).value) # Length of misspelled word
att_s = int(node.attributes.item(0).value) # Confidence of the suggestion
if not node.firstChild: # no suggestions
return s
text = node.firstChild.data.split("\t")[0]
# print "%s --> %s (s: %d)" % (s[att_o:att_o+att_l], text, att_s)
if att_s: # if suggestion is confident
new_s = new_s.replace(s[att_o:att_o+att_l], text)
if log:
if s == new_s:
log.debug("No suggestions were accepted.")
else:
log.debug("Suggestions were accepted: %s --> %s." % (s, new_s))
return new_s
def slot_apply(self):
self.ID3TagsToEdit = {}
log.debug("Saving ID3 Data in cache...")
self.ID3TagsToEdit['TIT2'] = TIT2(encoding=3,
text=unicode(
self.title.displayText()))
self.ID3TagsToEdit['TPE1'] = TPE1(encoding=3,
text=unicode(
self.artist.displayText()))
self.ID3TagsToEdit['TALB'] = TALB(encoding=3,
text=unicode(
self.album.displayText()))
self.ID3TagsToEdit['TDRC'] = TDRC(encoding=3,
text=unicode(
self.date.displayText()))
self.ID3TagsToEdit['COMM'] = COMM(encoding=3,
text=unicode(
config.id3tags_whitemark),
desc='')
lyrics = unicode(self.lyrics.toPlainText()).replace('\r\n',
'\n').replace(
'\n', '\r\n')
if lyrics:
if utils.isHebrew(lyrics):
self.ID3TagsToEdit['USLT'] = USLT(encoding=3,
lang=u'heb',
desc=u'',
text=lyrics)
else:
self.ID3TagsToEdit['USLT'] = USLT(encoding=3,
lang=u'eng',
desc=u'',
text=lyrics)
else:
self.ID3TagsToEdit['USLT'] = ''
if self.albumArt_task == 'add' and self.pix_path:
with open(self.pix_path, 'rb') as f:
data = f.read()
self.ID3TagsToEdit['APIC'] = APIC(encoding=0,
mime=utils.guess_image_mime_type(
self.pix_path),
type=0,
desc="",
data=data)
elif self.albumArt_task == 'delete':
self.ID3TagsToEdit[
'APIC'] = '' # empty value doesn't add a new APIC tag. All other APIC tags are removed piror to insertion.
self.close()
def parse_MusicAddict(song, maxpages=10):
"Function connects to MusicAddict.com and returns the .mp3 links in it"
if utils.isHebrew(song): # Dilandau doesn't have hebrew
log.warning("[MusicAddict] source has no hebrew songs. Skipping...")
return
song = urllib2.quote(song.encode("utf8"))
for i in range(maxpages):
# http://www.musicaddict.com/mp3/naruto-shippuden/page-1.html
url = 'http://www.musicaddict.com/mp3/%s/page-%d.html' % (song.replace(
'-', '').replace('_', '').replace(' ', '-').lower(), i + 1)
log.debug("[MusicAddict] Parsing %s... " % url)
obj = urllib2.urlopen(url)
response = obj.read()
DOMAIN = 'http://www.musicaddict.com/'
t_links = []
links = []
soup = BeautifulSoup(response)
for span in soup.find_all('span', class_='dl_link'):
if not span.a['href'].startswith('http'):
url = DOMAIN + span.a['href']
t_links.append(url)
for link in t_links:
obj = urllib2.urlopen(link)
response = obj.read()
soup = BeautifulSoup(response)
js = soup.find('script', src=re.compile(r"js3/\d+.js"))
jsUrl = DOMAIN + js['src']
obj = urllib2.urlopen(jsUrl)
response = obj.read()
url = re.search('src="(.+?)"', response).group(1)
links.append(url)
yield utils.cls.MetaUrl(url, 'MusicAddict')
if not links:
break
def parse(song, artist):
"Function searches the web for song lyrics. returns a generator."
s = '%s - %s' % (artist.strip(), song.strip())
if utils.isHebrew(song) or utils.isHebrew(artist):
log.debug("Grabbing lyrics for %s from shironet.co.il..." % s)
gen = parse_shironet(s)
for lyrics in gen:
yield lyrics
else: # if english
log.debug("Grabbing lyrics for %s from LyricsMode..." % song)
gen = parse_LyricsMode(song, artist)
for lyrics in gen:
yield lyrics
# lets try trim the ()'s or []'s
_song = song
_artist = artist
song = utils.trim_between(_song)
song = utils.trim_between(song, '[', ']')
if song != _song:
log.debug("Trimming %s --> %s" % (_song, song))
artist = utils.trim_between(_artist)
artist = utils.trim_between(artist, '[', ']')
if artist != _artist:
log.debug("Trimming %s --> %s" % (_artist, artist))
'''
The following situation may happen:
>>> song = "Train - 50 Ways To Say Goodbye"
>>> artist = "Train"
'''
x, y = utils.parse_title_from_filename(song)
if artist:
if artist.lower() == x.lower():
log.debug("Trimming %s --> %s" % (song, y))
song = y
if artist.lower() == y.lower():
log.debug("Trimming %s --> %s" % (song, x))
song = x
else:
log.debug("Setting artist name from nothing to %s" % y)
song, artist = x, y
if artist != _artist or song != _song:
s = '%s - %s' % (artist.strip(), song.strip())
log.debug("Grabbing lyrics for %s from LyricsMode..." % song)
gen = parse_LyricsMode(song, artist)
for lyrics in gen:
yield lyrics
log.debug("Grabbing lyrics for %s from OnlyLyrics..." % song)
try:
gen = parse_onlylyrics(song, artist)
except socket.error:
return
for lyrics in gen:
yield lyrics
if len(artist.split()) == 2:
flipped_artist = " ".join(artist.split(' ')[::-1])
log.debug("Grabbing lyrics for %s from OnlyLyrics (flipping last and first name)..." % song)
try:
gen = parse_onlylyrics(song, flipped_artist)
except socket.error:
return
for lyrics in gen:
yield lyrics
log.debug("Grabbing lyrics for %s from ChartLyrics..." % song)
try:
gen = parse_ChartLyrics(song, artist)
except socket.error:
return
for lyrics in gen:
yield lyrics
return
def parse(song, artist):
"Function searches the web for song lyrics. returns a generator."
s = '%s - %s' % (artist.strip(), song.strip())
if utils.isHebrew(song) or utils.isHebrew(artist):
log.debug("Grabbing lyrics for %s from shironet.co.il..." % s)
gen = parse_shironet(s)
for lyrics in gen:
yield lyrics
else: # if english
log.debug("Grabbing lyrics for %s from LyricsMode..." % song)
gen = parse_LyricsMode(song, artist)
for lyrics in gen:
yield lyrics
# lets try trim the ()'s or []'s
_song = song
_artist = artist
song = utils.trim_between(_song)
song = utils.trim_between(song, '[', ']')
if song != _song:
log.debug("Trimming %s --> %s" % (_song, song))
artist = utils.trim_between(_artist)
artist = utils.trim_between(artist, '[', ']')
if artist != _artist:
log.debug("Trimming %s --> %s" % (_artist, artist))
'''
The following situation may happen:
>>> song = "Train - 50 Ways To Say Goodbye"
>>> artist = "Train"
'''
x, y = utils.parse_title_from_filename(song)
if artist:
if artist.lower() == x.lower():
log.debug("Trimming %s --> %s" % (song, y))
song = y
if artist.lower() == y.lower():
log.debug("Trimming %s --> %s" % (song, x))
song = x
else:
log.debug("Setting artist name from nothing to %s" % y)
song, artist = x, y
if artist != _artist or song != _song:
s = '%s - %s' % (artist.strip(), song.strip())
log.debug("Grabbing lyrics for %s from LyricsMode..." % song)
gen = parse_LyricsMode(song, artist)
for lyrics in gen:
yield lyrics
log.debug("Grabbing lyrics for %s from OnlyLyrics..." % song)
try:
gen = parse_onlylyrics(song, artist)
except socket.error:
return
for lyrics in gen:
yield lyrics
if len(artist.split()) == 2:
flipped_artist = " ".join(artist.split(' ')[::-1])
log.debug(
"Grabbing lyrics for %s from OnlyLyrics (flipping last and first name)..."
% song)
try:
gen = parse_onlylyrics(song, flipped_artist)
except socket.error:
return
for lyrics in gen:
yield lyrics
log.debug("Grabbing lyrics for %s from ChartLyrics..." % song)
try:
gen = parse_ChartLyrics(song, artist)
except socket.error:
return
for lyrics in gen:
yield lyrics
return
