bio_amg.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 re_parse(dt, rx):
    match = re.search(rx, dt)
    if match: return match.group(1)

def go(artist, album):
    src = '/cg/amg.dll?p=amg&sql=%s&P=amg&opt1=2' % (urllib.quote(album))
    rx_src = re.compile('(<tr class=\"visible\".*?<td class=\"cell\" style.*?>)(.*?)(<.*?;"><a href=\")(.*?)(\">)', re.M|re.S)
    req = MyOpener().open(str(url + src)).read().decode('latin-1').encode('utf-8')
    for match in rx_src.finditer(str(req)):
        if strip_white(artist) == strip_white(match.group(2)) or levenshtein(strip_white(artist), strip_white(match.group(2))) <= 3:
            global rel, link
            link = match.group(4).replace('amp;','')
            req = MyOpener().open(url + link).read().decode('latin-1').encode('utf-8')
            rel = re.search('<!--Begin Content-->(.*?)<!--ADBANNER-->', req, re.S|re.M)
            break

def get_review():
    revw = re_parse(rel.group(1), '<td align=\"left\" class=\"title\">.*?\"author\">by\s.*?</td>.*?<p>(.*?)</p>')
    if revw:
        amg_review = re.sub('<.*?>', '', revw)
        if amg_review.find('Read More...') > 0:
            rx_more = re.compile('<td align="left" class="title">.*?"author">by\s.*?</td>.*?<p>(.*?)</p>', re.M|re.S)
            more = re_parse(rel.group(1), '\.\.\. <a href="(.*?)\">Read More\.\.\.</a>')
            more_review = MyOpener().open(url + more).read().decode('latin-1').encode('utf-8')
            amg_review = re.sub('<.*?>', '', rx_more.search(more_review).group(1))
        amg = amg_review + '\r\nAMG Review by ' + re_parse(rel.group(1), '<td align=\"left\" class=\"title\">.*?"author\">by\s.(.*?)<')
        print amg

url = 'http://www.allmusic.com'
rel = None;

try:
    go(sys.argv[1], sys.argv[2])
    if not rel == None: get_review()
except Exception, e:
    print e