# coding: utf-8
# -------------------------------------------#
# Lyrics grabbing module #
# -------------------------------------------#
# Written up by Alexander Miles #
# Available at http://www.alexander-miles.com#
# Last updated: November 30th, 2009 #
# -------------------------------------------#
import urllib2, sys, re
try:
from translate import *
no_trans_script = 0
except ImportError:
no_trans_script = 1
from urllib import *
decodedict = [ [' ', ' ' ], [' ', ' ' ], [' ', ' ' ], ['!', '!' ], ['"', '"' ],
['#', '#' ], ['$', '$' ], ['%', '%' ], ['&', '&' ], ["'", ''' ],
['(', '(' ], [')', ')' ], ['*', '*' ], ['+', '+' ], [',', ',' ],
['-', '-' ], ['.', '.' ], ['/', '/' ], ['0', '0' ], ['1', '1' ],
['2', '2' ], ['3', '3' ], ['4', '4' ], ['5', '5' ], ['6', '6' ],
['7', '7' ], ['8', '8' ], ['9', '9' ], [':', ':' ], [';', ';' ],
['<', '<' ], ['=', '=' ], ['>', '>' ], ['?', '?' ], ['@', '@' ],
['A', 'A' ], ['B', 'B' ], ['C', 'C' ], ['D', 'D' ], ['E', 'E' ],
['F', 'F' ], ['G', 'G' ], ['H', 'H' ], ['I', 'I' ], ['J', 'J' ],
['K', 'K' ], ['L', 'L' ], ['M', 'M' ], ['N', 'N' ], ['O', 'O' ],
['P', 'P' ], ['Q', 'Q' ], ['R', 'R' ], ['S', 'S' ], ['T', 'T' ],
['U', 'U' ], ['V', 'V' ], ['W', 'W' ], ['X', 'X' ], ['Y', 'Y' ],
['Z', 'Z' ], ['[', '[' ], ['\\', '\'], ['\]',']' ], ['^', '^' ],
['_', '_' ], ["`", '`' ], ['a', 'a' ], ['b', 'b' ], ['c', 'c' ],
['d', 'd'], ['e', 'e'], ['f', 'f'], ['g', 'g'], ['h', 'h'],
['i', 'i'], ['j', 'j'], ['k', 'k'], ['l', 'l'], ['m', 'm'],
['n', 'n'], ['o', 'o'], ['p', 'p'], ['q', 'q'], ['r', 'r'],
['s', 's'], ['t', 't'], ['u', 'u'], ['v', 'v'], ['w', 'w'],
['x', 'x'], ['y', 'y'], ['z', 'z'], ['{', '{'], ['|', '|'],
['}', '}'], ['~', '~'], ["'", '''] ]
umlats = [ ['ä', 'ä'], ['ö', 'ö'], ['ë', 'ë'], ['ä', 'ä'], ['ß', 'ß'],
['Ä', 'Ä'], ['Ö', 'Ö'], ['Ë', 'Ë'], ['ü', 'ü'], ['Ü', 'Ü'],
['æ', 'æ'], ['´', '´'] ]
decodedict = decodedict + umlats
def HTMLDecode(text):
for i in range(len(decodedict)):
text = text.replace(decodedict[i][1], decodedict[i][0])
return text
title_finder = re.compile('.+?(.+)')
hid_finder = re.compile('.+?hid="([/a-zA-Z0-9_=+-]+)"')
# If translate.py isn't present, don't create a function that would call it.
if no_trans_script == 0:
def translate_lyrics(artist, song, langfrom='German', langto='English', verb=0, source=0, output=0):
'''
translate_lyrics(artist, song, langfrom='German', langto='English', verb=0, source=0, output=0)
The artist, song, langfrom and langto are strings determinging
which lyrics to fetch and the language pair to translate between
and display.
* Setting 'Verb' to 1 causes the artist and song strings to be
taken verbatim, rather than being set to standard formatting.
* Setting source to 1 causes the lyrics search to use LeosLyrics
instead of lyrics.wikia.com, can grab the wrong song if an
exact match cannot be found.
* Setting output to 1 causes status statements to print as the
script runs, often good for probing why it isn't working, or
seeing exactly which URL is giving it problems.
'''
lines = lyrics(artist, song, source=source, intent=1)
feed_to_google = '
'.join(lines).replace('
','\r\n')
if output == 1: print "Translating with google translate."
translated_lines = translate(feed_to_google, langfrom, langto).split('\r
')
translated_lines = translated_lines[0].split('<br>')
output = []
output.append(song.capitalize() + " : " + '\033[1;34m'+translate(song.capitalize(), langfrom, langto)+'\033[1;m')
if output == 1: print "Formatting and decoding from HTML. . ."
for i in range(len(lines) ):
if lines[i] != '': lines[i] = lines[i] + " : " + '\033[1;32m'+translated_lines[i]+"\033[1;m"
lines[i] = HTMLDecode(lines[i])
output.append(lines[i])
for line in output: print line
pass
def lyrics(artist, song, source=0, output=0, intent=0):
'''
lyrics(artist, song, source=0, output=0, intent=0)
The artist and song are strings determinging which
lyrics to fetch.
* Setting source to 1 causes the lyrics search to use LeosLyrics
instead of lyrics.wikia.com, can grab the wrong song if an
exact match cannot be found.
* Setting output to 1 causes status statements to print as the
script runs, often good for probing why it isn't working, or
seeing exactly which URL is giving it problems.
* Setting intent to 1 causes the function to return the lyrics
as a list of strings, one for each line of the song.
'''
title = song
i = 0
if (source == 0):
song = '_'.join([ bit.capitalize() for bit in song.split() ])
artist = '_'.join([ bit.capitalize() for bit in artist.split() ])
wikia_url = 'http://lyrics.wikia.com/lyrics/'+artist+':'+song
if output == 1: print "Grabbing URL:"+wikia_url
try:
data = urlopen(wikia_url).read()
except IOError:
print "Cannot connect to lyrics.wikia.com. Likely a network problem."
return
#Attempt using pattern 1
if output == 1: print "Trying to match pattern 1."
before ="
"
after = "