Code to get MP3 links from newgrounds easily

[Ihaveworms]

So yeah, I wrote this stuff. If you run it, give it a while to load the links because it has to go to 51 web pages and parse through them, so it takes a few seconds.

Copy and paste from comments:
I created this steaming pile to rip mp3 URLs from Newgrounds
because it is a pain in the ASS to download them manually.

Usage:
Pass a url of a "index" page to some music when you run it. For example, http://www.newgrounds.com/audio/list/10/3
This program will then list all the mp3s associated with all the links on that listing. You will need to
then copy and paste those URLs in a text file and then use Internet Download Manager or something else
to batch download all the links.

Code: [Select]

'''
Created on Apr 7, 2009

@author: Justin (Ihaveworms)

version 1

I created this steaming pile to rip mp3 URLs from Newgrounds
because it is a pain in the ASS to download them manually.

usage: Pass a url of a "index" page to some music when you run it. For example, http://www.newgrounds.com/audio/list/10/3
This program will then list all the mp3s associated with all the links on that listing. You will need to
then copy and paste those URLs in a text file and then use Internet Download Manager or something else
to batch download all the links.

Written in Python
'''

import sre, urllib2, sys, BaseHTTPServer



def parseAddress(input):
        if input[:7] != "http://":
                if input.find("://") != -1:
                        print "Error: Cannot retrive URL, address must be HTTP"
                        sys.exit(1)
                else:
                        input = "http://" + input

        return input

def retrieveWebPage(address):
        try:
                web_handle = urllib2.urlopen(address)
        except urllib2.HTTPError, e:
                error_desc = BaseHTTPServer.BaseHTTPRequestHandler.responses[e.code][0]
                #print "Cannot retrieve URL: " + str(e.code) + ": " + error_desc
                print "Cannot retrieve URL: HTTP Error Code", e.code
                sys.exit(1)
        except urllib2.URLError, e:
                print "Cannot retrieve URL: " + e.reason[1]
                sys.exit(1)
        except:
                print "Cannot retrieve URL: unknown error"
                sys.exit(1)
        return web_handle

if len(sys.argv) < 2:
        print "Usage:"
        print "%s url" % (sys.argv[0])
        sys.exit(1)

match_set = set()
mp3match_set = set()

address = parseAddress(sys.argv[1])
website_handle = retrieveWebPage(address)
website_text = website_handle.read()

dir = website_handle.geturl().rsplit('/',1)[0]
if (dir == "http:/"):
        dir = website_handle.geturl()


#matches = sre.findall('filename=(.*?)&', website_text)
matches = sre.findall('<td class="listtitle"><a href="(.*?)"', website_text)

for match in matches:
        if match[:7] != "http://":
                if match[0] == "/":
                        slash = ""
                else:
                        slash = "/"
                match_set.add(dir + slash + match)
        else:
                match_set.add(match)

match_set = list(match_set)
match_set.sort()

#print match_set[1]

for sub_address in match_set:
    website_handle = retrieveWebPage(sub_address)
    website_text = website_handle.read()

    dir = website_handle.geturl().rsplit('/',1)[0]
    if (dir == "http:/"):
        dir = website_handle.geturl()
   
    sub_matches = sre.findall('filename=(.*?)&', website_text)
   
    for mp3match in sub_matches:
        if mp3match[:7] != "http://":
            if mp3match[0] == "/":
                slash = ""
            else:
                slash = "/"
                mp3match_set.add(dir + slash + mp3match)
        else:
                mp3match_set.add(mp3match)

mp3match_set = list(mp3match_set)
mp3match_set.sort()
       
for item in mp3match_set:
        print item


[Bobby's Pipes]

Jibberish!