Downloads every track from "History of Electronic / Electroacoustic Music, 1937-2000"

electronic_music.py

import urllib2
import os
import re
from sgmllib import SGMLParser


print '-' * 80
print '           History of Electronic / Electroacoustic Music, 1937-2000         '
print '-' * 80
print 
print 'This small script will download every track from "History of Electronic / Electroacoustic Music, 1937-2000"'


link = 'http://norbertschiegl.tumblr.com/post/5870608201/history-of-electronic-electroacoustic-music-1937-2001'

page = urllib2.urlopen(link)


if not os.path.exists('electronic_music'):
    os.mkdir('electronic_music')
    existing_files = set([])
else:
    existing_files = set(os.listdir('electronic_music'))


class URLLister(SGMLParser):
    def reset(self):
        SGMLParser.reset(self)
        self.urls = []

    def start_a(self, attrs):
        href = [v for k, v in attrs if k=='href']
        if href:
            self.urls.extend(href)

parser = URLLister()
parser.feed(page.read())

pieces = [link for link in parser.urls if '.mp3' in link]

total = len(pieces)

for i, piece in enumerate(pieces):
    #link = piece['href']
    link = piece
    filename = link.split('/')[-1]
    if filename not in existing_files:
        a = open('electronic_music/_%s' % filename, 'wb')
        try:
            f = urllib2.urlopen(link)
        except urllib2.HTTPError:
            f = None
        if f:
            a.write(f.read())
            a.close()
            os.rename('electronic_music/_%s' % filename, 'electronic_music/%s' % filename)
        else:
            print '%s / %s was not available - 404 error.  Sheesh.' % (i + 1, total)
    print 'finished %s / %s (%s)' % (i+1, total, filename)
        

I updated this with another url and to a single command line

wget --accept mp3,MP3 --convert-links --random-wait -r -p -E --no-directories -e robots=off https://ubu.com/sound/electronic.html