script to download mp3 files from contenidos.comteco.com.bo

example usage

bash$ python mp3box.py http://contenidos.comteco.com.bo/component/content/article/15-mp3-box/6434-top-40-usa.html
Downloading adele-rolling_in_the_deep.mp3 to /home/rolando/adele-rolling_in_the_deep.mp3
Downloading blake_shelton-honey_bee.mp3 to /home/rolando/blake_shelton-honey_bee.mp3
Downloading bruno_mars-grenade.mp3 to /home/rolando/bruno_mars-grenade.mp3
Downloading bruno_mars-just_the_way_you_are.mp3 to /home/rolando/bruno_mars-just_the_way_you_are.mp3
...

mp3box.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import re
import optparse
import os

from urllib2 import urlopen
from urlparse import urljoin, urlparse

__author__ = "Rolando Espinoza La fuente <[email protected]>"
__license__ = "Beerware License (free as in 'free beer')"

DESC = """
Fetchs all available mp3 files from the Comteco's mp3player's pages.
See http://contenidos.comteco.com.bo/. Example url:
http://contenidos.comteco.com.bo/component/content/article/15-mp3-box/6434-top-40-usa.html
"""

PLAYLIST_RE = re.compile(r"file:'(.+?)'")
LOCATION_RE = re.compile(r"<location>(.+?)</location>")
CHUNK_SIZE = 256*1024


def main():
    parser = optparse.OptionParser("%prog [-o dir] <url>",
                                   description=DESC)
    parser.add_option('-o', '--output',
                      help="output dir. default current directory")
    opts, args = parser.parse_args()

    if not args:
        parser.error("url required")

    url = args[0]

    if not url.startswith('http://contenidos.comteco.com.bo/'):
        parser.error("unknown url")

    if opts.output:
        outdir = os.path.realpath(opts.output)
    else:
        outdir = os.getcwd()

    if not os.access(outdir, os.W_OK):
        parser.error("Output dir not writable: {0}".format(outdir))

    # download playlist xml to get mp3 locations
    response = urlopen(url)
    match = PLAYLIST_RE.search(response.read())
    if not match:
        parser.error("Playlist not found")

    playlist = match.group(1)
    response = urlopen(playlist)

    # iterate and download each mp3 file
    for location in LOCATION_RE.findall(response.read()):
        mp3url = urljoin(url, location)
        filename = os.path.basename(urlparse(mp3url).path)
        dest = os.path.join(outdir, filename)
        print("Downloading {0} to {1}".format(filename, dest))

        response = urlopen(mp3url)
        with open(dest, "wb") as fp:
            chunk = response.read(CHUNK_SIZE)
            while chunk:
                fp.write(chunk)
                chunk = response.read(CHUNK_SIZE)


if __name__ == '__main__':
    main()