#!/usr/bin/python

# This script is (c) 2009 Michael Wojciechowski.
# 
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
#
 
# Find out if any new movie torrents with high leecher count are
# present on the pirate bay. 
# 
# Requirements: python 2.5.x, sqlite3.
# 
# Run this script from cron every half hour or so.

import sgmllib
import re
import urllib
import os

from pysqlite2 import dbapi2 as sqlite3

SITEROOT="http://thepiratebay.org"

class urlList:
    "List of URLs and their age."

    def __init__(self, filename):
        self.filename   = filename
        self.conn       = sqlite3.connect(filename)
        self.curr       = self.conn.cursor()
        self.printDebug = False

    def initDb(self):
        dbPresent = False
        try:
            self.curr.execute('select * from tpbg')
            dbPresent = True
        except sqlite3.OperationalError:
            dbPresent = False

        if (dbPresent == False):
            self.curr.execute('''create table tpbg (url text, descr text, age integer)''')
            if (self.printDebug):
                print "Created db."
        else:
            if (self.printDebug):
                print "Using existing db."

    def add(self, value, descr_link):
        #print "Adding "+str(value)

        t = (value, descr_link)
        self.curr.execute('select * from tpbg where url=? AND descr=?', t)

        row = self.curr.fetchone()
        if (row == None):
            # Add.
            t=(value, descr_link)
            self.curr.execute('insert into tpbg values (?,?,0)', t)
            if (self.printDebug):
                print "adding a new url."
        else:
            # reset age.
            newage=0
            t=(value, descr_link)
            self.curr.execute('update tpbg set age = 1 where url=? AND descr=?', t)
            if (self.printDebug):
                print "updating url age."

    def getNew(self):
        count=1
        self.curr.execute('select * from tpbg where age=0')
        for row in self.curr:
            print "Found new torrent #" + str(count) + "."
            print "URL        : " + str(row[0])
            print "Description: " + SITEROOT + str(row[1])
            print ""
            count += 1

    def incAge(self):
        self.curr.execute('update tpbg set age = age + 1')

    def removeOld(self):
        self.curr.execute('delete from tpbg where age > 100')

    def close(self):
        """
        Close database connection and write cached data to disk.
        """
        self.conn.commit()
        self.curr.close()

class MyParser(sgmllib.SGMLParser):
    "HTML parser class."

    def __init__(self, dbFile, verbose=0):
        "Initialise an object, passing 'verbose' to the superclass."
        self.ul         = urlList(dbFile)
        self.printDebug = False
        self.lastLink   = ""

        self.ul.initDb()

        sgmllib.SGMLParser.__init__(self, verbose)
        # Only want URLs which are torrent files.
        self.urlwantregex = re.compile("^http://.*\.torrent$")
        # This regex is used to remove torrent files in languages which I am not interrested in.
        self.langregex = re.compile("italian|italia|spanish|hindi", re.IGNORECASE)

    def parse(self, s):
        "Parse the given string 's'."
        self.feed(s)
        self.close()

    def start_a(self, attributes):
        "Process a hyperlink and its 'attributes'."

        for name, value in attributes:
            if name == "href":
                self.add_hyperlink(value)
                self.lastLink = value

    def add_hyperlink(self, value):
        match = self.langregex.search(value)
        if (match):
            return

        match = self.urlwantregex.search(value)
        if (match):
            self.ul.add(value, self.lastLink)

            if (self.printDebug):
                print "adding " + value
                print "adding (2) " + self.lastLink

            self.lastLink = ""

    def getNewLinks(self):
        self.ul.getNew()

    def save(self):
        self.ul.incAge()
        self.ul.close()

if __name__ == "__main__":

    dbFile   = os.environ['HOME']+"/.tpdbv2"
    myparser = MyParser(dbFile)

    for i in range(5):
        url = SITEROOT + "/browse/201/"+str(i)+"/9"
        # print "Parsing URL: " + url
        f = urllib.urlopen(url)
        s = f.read()
        myparser.parse(s)

    myparser.getNewLinks()
    myparser.save()