def parse_songlyrics_songs_by_lyrics(searchString):
'''
Uses songlyrics.com for searching songs by a line of it's lyrics.
Returns list of songs.
'''
log.debug(
"Searching for a song that contains the line '%s' on songlyrics.com..."
% searchString)
url = "http://www.songlyrics.com/index.php?section=search&searchW=%s&submit=Search&searchIn4=lyrics" % urllib2.quote(
searchString.encode("utf8"))
log.debug('Fetching %s...' % url)
obj = urllib2.urlopen(url, timeout=config.metadata_timeout)
response = obj.read()
obj.close()
remove_strings = [
'(remix)', '(Remix)', '(live)', '(Live)', '(single)', '(Single)'
]
chars_to_trim = ['\n', '\r', ' ', ',', "'", '.', '?', '!']
searchString = searchString.lower()
track = ""
soup = BeautifulSoup(response)
for div in soup.find_all('div', class_='serpresult'):
if 'cover)' in div.text.lower() or 'cover]' in div.text.lower():
continue
if not div.a:
continue
artist = div.a.img['alt']
title = div.a['title']
for s in remove_strings:
title.replace(s, '')
title = title.strip()
gen = LyricsGrabber.parse(title, artist)
if gen:
lyrics = gen.next()
if lyrics:
lyrics = lyrics.lyrics.lower()
for c in chars_to_trim:
lyrics = lyrics.replace(c, '')
matching_blocks = SequenceMatcher(
None, lyrics,
searchString.replace(' ', '')).get_matching_blocks()
biggest_match_block_size = sorted(matching_blocks,
key=lambda x: x.size,
reverse=True)[0].size
if 1.0 * biggest_match_block_size / len(searchString) > 0.70:
track = "%s - %s" % (artist, title)
break
return track
def parse_songlyrics_songs_by_lyrics(searchString):
"""
Uses songlyrics.com for searching songs by a line of it's lyrics.
Returns list of songs.
"""
log.debug("Searching for a song that contains the line '%s' on songlyrics.com..." % searchString)
url = (
"http://www.songlyrics.com/index.php?section=search&searchW=%s&submit=Search&searchIn4=lyrics"
% urllib2.quote(searchString.encode("utf8"))
)
log.debug("Fetching %s..." % url)
obj = urllib2.urlopen(url, timeout=config.metadata_timeout)
response = obj.read()
obj.close()
remove_strings = ["(remix)", "(Remix)", "(live)", "(Live)", "(single)", "(Single)"]
chars_to_trim = ["\n", "\r", " ", ",", "'", ".", "?", "!"]
searchString = searchString.lower()
track = ""
soup = BeautifulSoup(response)
for div in soup.find_all("div", class_="serpresult"):
if "cover)" in div.text.lower() or "cover]" in div.text.lower():
continue
if not div.a:
continue
artist = div.a.img["alt"]
title = div.a["title"]
for s in remove_strings:
title.replace(s, "")
title = title.strip()
gen = LyricsGrabber.parse(title, artist)
if gen:
lyrics = gen.next()
if lyrics:
lyrics = lyrics.lyrics.lower()
for c in chars_to_trim:
lyrics = lyrics.replace(c, "")
matching_blocks = SequenceMatcher(None, lyrics, searchString.replace(" ", "")).get_matching_blocks()
biggest_match_block_size = sorted(matching_blocks, key=lambda x: x.size, reverse=True)[0].size
if 1.0 * biggest_match_block_size / len(searchString) > 0.70:
track = "%s - %s" % (artist, title)
break
return track
def parse_songlyrics_songs_by_lyrics(searchString):
'''
Uses songlyrics.com for searching songs by a line of it's lyrics.
Returns list of songs.
'''
log.debug("Searching for a song that contains the line '%s' on songlyrics.com..." % searchString)
url = "http://www.songlyrics.com/index.php?section=search&searchW=%s&submit=Search&searchIn4=lyrics" % urllib2.quote(searchString.encode("utf8"))
log.debug('Fetching %s...' % url)
obj = urllib2.urlopen(url, timeout=config.metadata_timeout)
response = obj.read()
obj.close()
remove_strings = ['(remix)', '(Remix)', '(live)', '(Live)', '(single)', '(Single)']
chars_to_trim = ['\n', '\r', ' ', ',', "'", '.', '?', '!']
searchString = searchString.lower()
track = ""
soup = BeautifulSoup(response)
for div in soup.find_all('div', class_='serpresult'):
if 'cover)' in div.text.lower() or 'cover]' in div.text.lower():
continue
if not div.a:
continue
artist = div.a.img['alt']
title = div.a['title']
for s in remove_strings:
title.replace(s, '')
title = title.strip()
gen = LyricsGrabber.parse(title, artist)
if gen:
lyrics = gen.next()
if lyrics:
lyrics = lyrics.lyrics.lower()
for c in chars_to_trim:
lyrics = lyrics.replace(c, '')
matching_blocks = SequenceMatcher(None, lyrics, searchString.replace(' ','')).get_matching_blocks()
biggest_match_block_size = sorted(matching_blocks, key=lambda x:x.size, reverse=True)[0].size
if 1.0*biggest_match_block_size/len(searchString) > 0.70:
track = "%s - %s" % (artist, title)
break
return track
def parse_shironet_songs_by_lyrics(searchString):
'''
Uses shironet.co.il for searching songs by a line of it's lyrics.
Returns list of songs.
'''
log.debug(
"Searching for a song that contains the line '%s' in shironet.co.il..."
% searchString)
url = "http://shironet.mako.co.il/searchSongs?q=%s&type=lyrics" % urllib2.quote(
searchString.encode("utf8"))
log.debug('Fetching %s...' % url)
obj = urllib2.urlopen(url, timeout=config.metadata_timeout)
response = obj.read()
obj.close()
chars_to_trim = ['\n', '\r', ' ', ',', "'", '.', '?', '!']
searchString = searchString.lower()
track = ""
soup = BeautifulSoup(response)
for link in soup.find_all('a',
class_="search_link_name_big",
href=re.compile('wrkid=')):
title = link.text.strip()
artist = link.find_next_sibling('a').text.strip()
gen = LyricsGrabber.parse(title, artist)
if gen:
lyrics = gen.next()
if lyrics:
lyrics = lyrics.lyrics.lower()
for c in chars_to_trim:
lyrics = lyrics.replace(c, '')
matching_blocks = SequenceMatcher(
None, lyrics,
searchString.replace(' ', '')).get_matching_blocks()
biggest_match_block_size = sorted(matching_blocks,
key=lambda x: x.size,
reverse=True)[0].size
if 1.0 * biggest_match_block_size / len(searchString) > 0.70:
track = "%s - %s" % (artist, title)
break
return track
def parse_shironet_songs_by_lyrics(searchString):
"""
Uses shironet.co.il for searching songs by a line of it's lyrics.
Returns list of songs.
"""
log.debug("Searching for a song that contains the line '%s' in shironet.co.il..." % searchString)
url = "http://shironet.mako.co.il/searchSongs?q=%s&type=lyrics" % urllib2.quote(searchString.encode("utf8"))
log.debug("Fetching %s..." % url)
obj = urllib2.urlopen(url, timeout=config.metadata_timeout)
response = obj.read()
obj.close()
chars_to_trim = ["\n", "\r", " ", ",", "'", ".", "?", "!"]
searchString = searchString.lower()
track = ""
soup = BeautifulSoup(response)
for link in soup.find_all("a", class_="search_link_name_big", href=re.compile("wrkid=")):
title = link.text.strip()
artist = link.find_next_sibling("a").text.strip()
gen = LyricsGrabber.parse(title, artist)
if gen:
lyrics = gen.next()
if lyrics:
lyrics = lyrics.lyrics.lower()
for c in chars_to_trim:
lyrics = lyrics.replace(c, "")
matching_blocks = SequenceMatcher(None, lyrics, searchString.replace(" ", "")).get_matching_blocks()
biggest_match_block_size = sorted(matching_blocks, key=lambda x: x.size, reverse=True)[0].size
if 1.0 * biggest_match_block_size / len(searchString) > 0.70:
track = "%s - %s" % (artist, title)
break
return track
