bio_gracenote.py

# -*- coding: utf-8 -*-
import encodings.utf_8
import sys, urllib, re

class MyOpener(urllib.FancyURLopener):
    version = 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3'

def strip_white(stp):
    stp = stp.replace('amp;','')
    stp = re.sub('\W+?','', stp.lower())
    return stp

def levenshtein(s1, s2):
  l1 = len(s1)
  l2 = len(s2)
  matrix = [list(range(l1 + 1))] * (l2 + 1)
  for zz in range(l2 + 1):
    matrix[zz] = list(range(zz,zz + l1 + 1))
  for zz in range(0,l2):
    for sz in range(0,l1):
      if s1[sz] == s2[zz]:
        matrix[zz+1][sz+1] = min(matrix[zz+1][sz] + 1, matrix[zz][sz+1] + 1, matrix[zz][sz])
      else:
        matrix[zz+1][sz+1] = min(matrix[zz+1][sz] + 1, matrix[zz][sz+1] + 1, matrix[zz][sz] + 1)
  return matrix[l2][l1]

def go(artist):
    req = MyOpener().open(url + '/search/?query=%s&search_type=artist' % (urllib.quote(artist))).read()
    rx_src = re.compile('Artist:.*?artist_id=(.*?)">(.*?)</a>', re.M|re.S|re.I)
    for match in rx_src.finditer(req):
        if strip_white(artist) == strip_white(match.group(2)) or levenshtein(strip_white(artist), strip_white(match.group(2))) <= ld:
            link = url + '/artist/artist.php?artist_id=' + match.group(1)
            req = MyOpener().open(link).read()
            bio = re.search('var originalBiography.*?"(.*?)";', req, re.M|re.S|re.I)
            if bio: print re.sub('<.*?>', '', bio.group(1)).replace('\\','')
            break

url = 'http://www.gracenote.com'
ld = 3 # more info: http://en.wikipedia.org/wiki/Levenshtein_distance

try:
    go(sys.argv[1])
except Exception, e:
    print e