GH Downloader

gistfile1.py

# I am totally aware BeautifulSoup is slow.
# Please do not inform me, this is just for fun.

import urllib2
import BeautifulSoup
import re
import os
import sys
from threading import Thread

def slash():
  if os.name == "nt":
    return "\\"
  else:
    return "/"

def replace_all(text, dic):
  for i, j in dic.iteritems():
    text = text.replace(i, j)
  return text

class download(Thread):
  def __init__(self,url):
    Thread.__init__(self)
    self.url = url
  def run(self):
    req = urllib2.urlopen(self.url)
    CHUNK = 16 * 1024
    with open(os.getcwd() + slash() + SOUNDTRACK_NAME + slash() + self.url.split('/')[-1], 'wb') as fp:
      while True:
        chunk = req.read(CHUNK)
        if not chunk: break
        fp.write(chunk)
      print self.url.split('/')[-1],'complete.'


BASE_URL = "http://gh.ffshrine.org/"
SOUNDTRACK_ID = int(raw_input('Soundtrack ID (e.g. http://gh.ffshrine.org/soundtracks/NUMBER/): '))

html_dict = {'%3A':':','%2F':'/','%27':"'",'%22':'"','%3B':';','%28':'(','%29':')'}

page_data = urllib2.urlopen(BASE_URL + "soundtracks/" + str(SOUNDTRACK_ID)).read()
soup = BeautifulSoup.BeautifulSoup(page_data)

SOUNDTRACK_NAME = str(soup.findAll('h1')[0])[4:-19]

url_list = []

print 'Found soundtrack:',SOUNDTRACK_NAME
print 'Parsing all pages for download links. This may take a while.'

for a in soup.findAll('a',attrs={'href':re.compile("^/song/")}):
  song_url = a['href']
  download_page_data = urllib2.urlopen(BASE_URL + song_url[1:]).read()
  temp_soup = BeautifulSoup.BeautifulSoup(download_page_data)
  for script in temp_soup.findAll('script'):
    if 'var data' in str(script):
      # Actual stuff we want always is between chars 42 and len(script) - 38
      java = replace_all(str(script)[42:-38],html_dict)
      url_list.append(java[0:java.index('";')])

print "List built, starting download."

# Maybe it exists, fuck you?
try:
  os.mkdir(SOUNDTRACK_NAME)
except:
  pass

threadlist = []

for i in range(0,len(url_list)):
  cur_thread = download(url_list[i])
  threadlist.append(cur_thread)
  cur_thread.start()
  print 'Started thread for:',url_list[i].split('/')[-1]