hhdl.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# House Hunters International episode downloader
# Code referenced from https://github.com/pantuts/asskick and https://stackoverflow.com/questions/12708751/python-writing-on-a-text-file
# Created by Andrew Morgan (2015)

from bs4 import BeautifulSoup
import os
import re
import requests
import subprocess
import sys
import math

torrent_download_dir = os.getcwd() + "/../torrents_watch/"

def check_if_previously_downloaded(torrent_name):
    with open(os.getcwd() + "/" + 'torrent_list.txt','r+') as torrent_list:
        for line in torrent_list:
            if line.strip() == torrent_name:
                print "torrent already downloaded"
                return True
        else:
            torrent_list.write(torrent_name + "\n")
            return False

def download_torrent(url):
    fname = torrent_download_dir + '/' + url.split('title=')[-1] + '.torrent'
    if check_if_previously_downloaded(url.split('title=')[-1] + '.torrent'):
        return

    print ("Downloading " + url.split('title=')[-1])
    # http://stackoverflow.com/a/14114741/1302018
    try:
        r = requests.get(url, stream=True)
        with open(fname, 'wb') as f:
            for chunk in r.iter_content(chunk_size=1024):
                if chunk:
                    f.write(chunk)
                    f.flush()
    except requests.exceptions.RequestException as e:
        print('\n' + str(e))
        sys.exit(1)

    return fname


def retrieve_torrent_listings(url,torrent):
    try:
        cont = requests.get(url)
    except requests.exceptions.RequestException as e:
        raise SystemExit('\n' + str(e))

    # check if no torrents found
    if not re.findall(r'Download torrent file', str(cont.content)):
        print('Torrents found: 0')
        retrieve_torrent_listings()
    else:
        soup = BeautifulSoup(cont.content)

        al = [s.get_text() for s in soup.find_all('td', {'class':'center'})]

        href = [a.get('href') for a in soup.find_all('a', {'title':'Download torrent file'})]
        size = [t.get_text() for t in soup.find_all('td', {'class':'nobr'}) ]
        title = [ti.get_text() for ti in soup.find_all('a', {'class':'cellMainLink'})]
        age = al[2::5]
        seeders = al[3::5]
        leechers = al[4::5]

        # Check if torrent has seeders
        if (int(seeders[torrent-1]) > 0):
            print (seeders[torrent-1] + " seeders found.")
            fname = download_torrent(href[int(torrent)-1])
        else:
            print ("No seeders found")

def download_show(initial_torrent_amount):
    torrent_amount = initial_torrent_amount
    pages = int(math.ceil(torrent_amount/25))
    print ("pages: " + str(pages))
    for i in xrange(1,pages + 1):
        if pages > 1 and i == pages:
            torrent_amount = initial_torrent_amount % 25.0
        else:
            torrent_amount = 25
        for j in xrange(1,int(torrent_amount)+1):
            print ("\nTrying page " + str(i) + " torrent num #" + str(j))
            try:
                retrieve_torrent_listings("http://kickass.to/usearch/house%20hunters%20international%20720%20DOCERE/" + str(i) + "/?field=time_add&sorder=desc",j)
            except IndexError, e:
                print "Reached end of torrent queue"
                return

download_show(300.0)