Downloads all the files on a Tokyo Toshokan search page.

Tokyo Toshokan Batch Downloader

#!/usr/bin/env python

#Instructions:
#Download and install python if you have not already.  It comes default on most if not all *nix systems and OS X.
#Click "raw" in the upper right part of this box.  Save it as ttdownload.py in any folder that you want.
#Download http://www.crummy.com/software/BeautifulSoup/download/3.x/BeautifulSoup-3.0.8/BeautifulSoup.py and save it in the same folder as the previous script.
#Open up a terminal in the folder that you have downloaded everything from. 
#Type "python ttdownload.py".
#Search for the files that you want on Tokyo Toshokan.
#Paste the url of the Tokyo Toshokan search page when asked.
#Type the folder name that you want all of the .torrent files saved to (if left blank, it will default to the date and time)
#Now all of the .torrent files are saved in the folder specified.
#Watch some animu.


import re
import os
import sys
import urlparse
import urllib

from datetime import datetime
from BeautifulSoup import BeautifulSoup

#
#  Make some colors for a better experiance in *nix
#
class bcolors:
    HEADER = '\033[95m'
    OKBLUE = '\033[94m'
    OKGREEN = '\033[92m'
    WARNING = '\033[93m'
    FAIL = '\033[91m'
    ENDC = '\033[0m'

    def disable(self):
        self.HEADER = ''
        self.OKBLUE = ''
        self.OKGREEN = ''
        self.WARNING = ''
        self.FAIL = ''
        self.ENDC = ''

#
#  Given a tokyo toshokan page, this function will get all the links,
#  and pass the urls to getDownload(url) which will determine if they are valid
#  then it reurns all valid links in their .torrent form
#
def getTorrents(url):
   print  "reading page..." 
   try:
      gatherer = urllib.urlopen(url)
      html = gatherer.read()
      gatherer.close()
      soup = BeautifulSoup("".join(html))
      
      links = soup.findAll(name="a",attrs={"rel":"nofollow","type":"application/x-bittorrent"})
      torrents = {}
      
      for link in links:
         name = link.string.encode("ascii","ignore")
         try:
            url = getDownload(link["href"])
            torrents[url] = name
         except:
            print bcolors.WARNING + "could not find a .torrent file for " + name + bcolors.ENDC
            pass
      return torrents
   except:
      sys.exit(bcolors.FAIL+"Malformed URL, quitting"+bcolors.ENDC)
         
#
#  Given a link (offsite from tokyotosho) this function will 
#  try to locate the .torrent file
#  
def getDownload(url):
   url = url.strip()
   
   #linking directly to the .torrent file
   if re.search(".torrent",url):
      return url
   #nyaatorrents
   elif re.search("nyaa",url) or re.search("nyaatorrents",url):
      if re.search("page=download",url):
         return url
      else:
         return url.replace("torrentinfo","download")
   #idiots that redirect
   else:
      torrent=urllib.urlopen(url)
      mimeType =  torrent.info().gettype()
      #check the mimetype of the redirected link
      if re.search("application/x-bittorrent",mimeType):
         return url
   
#
#  Given a .torrent file, this function downloads it to the right folder
#
def download(link,name,folder="torrents_from_py"):
   if not os.path.exists(folder):
      os.makedirs(folder)
   
   u = urllib.urlopen(link)
   data = u.read()
   u.close()
   f = open(folder+"/"+name+".torrent","wb+")
   f.write(data)
   f.close()


#
#  The body of our program
#
page = ""
folder = ""
if __name__ == '__main__':
   # ask the user for the page that they want
   page = raw_input("What url: \n")
   print "Starting query..."
   
   # get the list of torrents
   torrents = getTorrents(page)
   print bcolors.OKGREEN + str(len(torrents))+" torrents found" + bcolors.ENDC
   if len(torrents)>0:
      print "torrents found for the following items"
      print "="*50
      #print the valid list
      for name in torrents.itervalues():
         print bcolors.HEADER + name +bcolors.ENDC
      print "="*50
      
      # get the folder that they want to save it in
      now = datetime.now()
      pre = str(now.year) + "_" + str(now.month) + "_" + str(now.day) + "_" + str(now.hour) + "_" + str(now.minute) + "_" + str(now.second)
      folder = raw_input("Folder name: (leave blank to use "+pre+")\n")
      if folder.strip() == "":
         folder = pre
      #download all the files
      print "="*50
      for key,value in torrents.iteritems():
         print bcolors.OKGREEN + "downloading:",value
         try:
            download(key,value,folder)
         except:
            print bcolors.WARNING + "Failed downloading " +value + bcolors.ENDC
   print bcolors.ENDC