rendered paste body#! /usr/bin/env python
import os,sys,urllib,re
DEBUG = 0
albumFile = multiArtistFile = artistOverviewFile = artistDiscogFile = None
domain = 'http://www.allmusic.com'
artistRequest = '/cg/amg.dll?P=amg&SQL=%s&OPT1=1'
def prepRequest(s):
s = s.lower()
if s.startswith('the '):
s = s.replace('the ','')
s = s.replace(' ','|')
return s
def makeRequest(s):
global albumFile,multiArtistFile,artistOverviewFile,artistDiscogFile
albumPage = re.compile(r'<div id="albumpage">.*')
multiArtist = re.compile(r'<div id="artistsearchresults">.*')
artistPage = re.compile(r'<div id="artistpage">.*')
artistOverview = re.compile(r'<div id="artistpage">.*')
artistDiscog = re.compile(r'(<a HREF=")(/cg/amg.dll[?]p=.*?T2)(">Discography</a></td>)')
file = urllib.urlopen(domain+s).read()
if albumPage.search(file) != None:
if DEBUG:
print 'found albumpage'
albumFile = file
parseAlbumOverview(file)
elif multiArtist.search(file) != None:
if DEBUG:
print 'found multiartists'
multiArtistFile = file
parseMultiArtists(file)
elif artistPage.search(file) != None:
if DEBUG:
print 'found artistpage'
artistOverview=file
try:
discogURL = artistDiscog.search(file).group(2)
except:
print '\r%s\n%s' % (('no album list found for %s' % (artist)).center(60),('falling back to manual entry mode').center(60))
manualMode()
return
if DEBUG:
print 'found artist discog'
artistDiscogFile = urllib.urlopen(domain+discogURL).read()
parseArtistDiscog(artistDiscogFile)
else: print '\r no match'
def parseMultiArtists(file):
global artist
avList = []
items = ['url','artist','genre','active']
item = {}
table = re.compile(r'(<!--Begin Search Results-->)(.*?)(<!--Begin Right SideBar-->)')
reg1 = re.compile(r'(<a href=")(/cg/amg.dll[?]p=amg&sql=(1|4)1:.*?)(">)(.*?)(</a>.*?">)(.*?)(</T.*?">)(.*?)(</td>)')
reg2 = re.compile(r'([0-9s,\ -]+)')
string = table.search(file).group(2)
vals = reg1.findall(string)
# for i in vals:
# print i
for i in vals:
if reg2.match(i[8]) == None:
act = 'N/A'
else:
act = i[8].strip()
if i[6].startswith(' '):
gen = 'N/A'
else:
gen = i[6].strip()
avList.append(dict(zip(items,(i[1].strip(),i[4].strip(),gen,act))))
choice = -1
curItm = 0
page = 1
while choice == -1:
end = 0
os.system('clear')
print '\r%s\n pg.%d%s %-12.12s %s' % (('multiple artists found!').center(60),page,('artist').center(28),'genre',('active years').center(10))
line()
page += 1
for i in range(25):
if curItm >= len(avList)-1:
page = 1
end = 1
print '\r %2d: %-28.28s %-12.10s %s' % (curItm+1,avList[curItm]['artist'],avList[curItm]['genre'],avList[curItm]['active'].center(10))
print '\r%s' % (('RETURN for top, 0 for manual entry').center(60))
curItm = 0
break
print '\r %2d: %-28.28s %-12.10s %s' % (curItm+1,avList[curItm]['artist'],avList[curItm]['genre'],avList[curItm]['active'].center(10))
curItm += 1
if not end:
print '\r%s' % (('RETURN for more, 0 for manual entry').center(60))
print 'choose: ',
try:
choice = int(sys.stdin.readline()) -1
except:
continue
print choice
if choice == -1:
manualInfo()
return
elif choice < -1 or choice > len(avList)-1:
choice = -1
curItm = 0
continue
else:
artist = avList[choice]['artist']
url = avList[choice]['url']
s = url.split('amp;')
url=s[0]+s[1]
makeRequest(url)
def parseArtistOverview(file):
url = None
urlreg = re.compile(r'(<a HREF=")(/cg/amg.dll[?]p=amg&uid=.*?)(">Discography</a)')
url = urlreg.search(file).group(2)
makeRequest(url)
def parseArtistDiscog(file):
global album,year
choice = -2
albList = []
items = ['year','url','title','label']
table = re.compile(r'<!--Begin Album List-->(.*?)<!--End Album List-->')
reg = re.compile(r'<td class="sorted-cell">(.*?)</td>.*?<a href="(/cg/amg.dll[?]p=amg&sql=10:.*?)">(.*?)</a>.*?<td class="cell" style="width:150px;word-wrap:break-word;">(.*?)</td>')
string = table.search(file).group(1)
vals = reg.findall(string)
for i in vals:
albList.append(dict(zip(items,(i[0],i[1],i[2],i[3]))))
for i in albList:
if i['title'].lower() == album.lower():
album = i['title']
year = i['year']
makeRequest(i['url'])
return
os.system('clear')
print '\r %-35.35s %-4.4s %-25.25s' % ('title', 'year', 'label')
line()
if len(albList) < 1:
print '\r%s' % (('no albums found').center(60))
return
for i in range(len(albList)):
print '\r %2d: %-35.35s %-4.4s %-25.25s' % (i+1,albList[i]['title'],albList[i]['year'],albList[i]['label'])
print '\r%s' % (('0 for manual entry').center(60))
while (choice == -2):
print '\rchoose: ',
try:
choice = int(sys.stdin.readline()) -1
except:
continue
if choice < -1 or choice > i:
choice = -2
album = albList[choice]['title']
year = albList[choice]['year']
url = albList[choice]['url']
s=url.split('amp;')
url=s[0]+s[1]
makeRequest(url)
def parseAlbumOverview(file):
reg4 = re.compile(r'(<TD class="cell">)([0-9]*)(</TD>)') #(?<!"/>)?
reg5 = re.compile(r'(<a href="/cg/amg.dll[?]p=amg&sql=33:.*?">)(.*?)(</a>)')
num = reg4.findall(file)
tit = reg5.findall(file)
# print file
# print tit
os.system('clear')
print '\r%s' %(('found...collected the following data').center(60))
line()
print '\r artist: %s\n album: %s\n year: %s' % (artist.title(),album.title(),year)
line()
if len(num) == len(tit) != 0:
for i in range(len(num)):
print '\r %02d: %s' % (int(num[i][1]),tit[i][1].title())
else:
print '\r%s\n%s' % (('no tracklist found for %s - %s' % (artist,album)).center(60),('falling back to manual entry mode').center(60))
manualMode()
def manualMode():
print '\rinput info manually'
def line():
print '\r ------------------------------------------------------------'
year = 0
string = 'STRING'
print string.title()
print '\r artist: ',
artist = sys.stdin.readline().strip()
album =''
# print '\r album: ',
# album = sys.stdin.readline().strip()
makeRequest(artistRequest%(prepRequest(artist)))