rolling

#automated nzb downloader based on imdb ratings
#this script is designed to download nzb files from nzbs.org (requires registration)
#original script created by popcorn, modified by binhex
#ver 1.0

import urllib
import xml.dom.minidom
import re
import time
import os
import traceback
import logging
import socket

#put your own folder names below as specified in sabnzbd+
#double slashes for windows users essential
watch_dir="J:\\downloads\\nzb"
nzb_dir="J:\\downloads\\nzbbackup"
completed_dir="E:\\Warez"

#put your own folder names below to specify the location of your movie collection
movies_dir1="E:\\Warez\\Movies"

#put your own folder and filenames below to specify location of log files
mainlog="J:\\sabnzbd+\\Logs\\Scriptlogs\\autodl_hd_main.log"
tracelog="J:\\sabnzbd+\\Logs\\Scriptlogs\\autodl_hd_traceback.log"

#put your own notification message process below for error logging or use the default
notifylog="cmd /c msg console /TIME:43200 Script Error, Check Logs"

#send failure messages to log file
main_logger = logging.getLogger('myapp1')
main_handler = logging.FileHandler(mainlog)
main_formatter = logging.Formatter('%(asctime)s %(levelname)s %(message)s')
main_handler.setFormatter(main_formatter)
main_logger.addHandler(main_handler)
main_logger.setLevel(logging.INFO)

#sets timeout period for urlretrieve (in seconds)
socket.setdefaulttimeout(240)

#un-comment for x264 movies
#movie_category="catid=4"

#un-comment for dvdrips only
#movie_format="&q=dvdrip.xvid"

#un-comment for XviD movies
movie_category="catid=2"

#put your userid for nzbs.org website below (register and then go to http://www.nzbs.org/index.php?action=rss)
userid="&i=11111&h=e1111111111111111111111111111111"

#un-comment for 720p resolution only
#movie_format="&q=720p"

#un-comment for 1080p resolution only
#movie_format="&q=1080p"

#un-comment for all formats in selected category
movie_format=""

#rss feed for nzbs.org
nzbs_org_feed="http://www.nzbs.org/rss.php?" + movie_category + userid + "&dl=1" + movie_format

##############
# os filters #
##############

try:
        def isInWatched(check_watched_folder):

                #this is set to download only if the nzb file doesn't exist in the watch folder (watch_dir)
                if os.path.exists(watch_dir + "\\" + check_watched_folder + ".nzb"):

                        return 0
                else:
                        return 1

        def isInNZB(check_nzb_folder):

                #this is set to download only if the nzb file doesn't exist in the nzb folder (nzb_dir)
                if os.path.exists(nzb_dir + "\\" + check_nzb_folder + ".nzb.gz"):

                        return 0
                else:
                        return 1

        def isCompleted(check_completed_folder):

                #this is set to download only if the movie doesn't exist in the completed folder (completed_dir)
                if os.path.exists(completed_dir + "\\" + check_completed_folder):

                        return 0
                else:
                        return 1

        def isDownloaded(check_downloaded_folder):

                #this is set to download only movies which don't exist in the movies folders (movies_dir1/2)
                if os.path.exists(movies_dir1 + "\\" + check_downloaded_folder):

                        return 0
                else:
                        return 1

except:
        print("Error: OS Filter Error")
        main_logger.error("OS Filter Error")
        traceback.print_exc(file=open(tracelog,"a"))
        os.system(notifylog)

################
# imdb filters #
################

try:
        def isGoodRatings(imdb_html):

                #this is set to download only movies with a rating of 6.5 or more
                if re.compile("<b>6\.[5-9]/10</b>|<b>[7-9]\.[0-9]/10</b>").search(imdb_html):

                        return 1
                else:
                        return 0

        def isGoodVotes(imdb_html):

                #this is set to download only movies with 5,000 votes or more
                if re.compile(">[0-9][0-9]+,[0-9]+ votes<|>[5-9],[0-9]+ votes<", re.IGNORECASE).search(imdb_html):

                        return 1
                else:
                        return 0

        def isGoodLang(imdb_html):

                #this is set to download movies that contain language "English" (movie may contain other languages)
                if re.compile("Languages/English", re.IGNORECASE).search(imdb_html):

                        return 1
                else:
                        return 0

        def isGoodCountry(imdb_html):

                #this is set to download movies from countries that have english as their native language
                if re.compile("Countries/UK|Countries/USA|Countries/Canada|Countries/Australia|Countries/Ireland|Countries/SouthAfrica|Countries/NewZealand", re.IGNORECASE).search(imdb_html):

                        return 1
                else:
                        return 0

        def isBadDate(imdb_html):

                #this is set to download only movies with a release date of 1970 and newer
                movie_year = re.compile("<title>.+</title>").search(imdb_html)

                if movie_year is not None:

                        if re.search("19[0-6][0-9]", movie_year.group()):

                                return 0
                        else:
                                return 1

        def isBadGenre(imdb_html):

                #this is set to download only movies that DO NOT match certain genre's
                if re.compile(">Documentary<|>Musical<|>Music<", re.IGNORECASE).search(imdb_html):

                        return 0
                else:
                        return 1

except:
        print("Error: IMDB Filter Error")
        main_logger.error("IMDB Filter Error")
        traceback.print_exc(file=open(tracelog,"a"))
        os.system(notifylog)

#######################
# nzb release filters #
#######################

try:
        def isGoodSize(check_movie_size):

                #this is set to download movies with file sizes from 700 MB to 2.59 GB (xvid format)
                if re.compile("[7-9][0-9][0-9].[0-9][0-9] MB|1.[0-9][0-9] GB|2.[0-5][0-9] GB", re.IGNORECASE).search(check_movie_size):

                        return 1
                else:
                        return 0

        def isBadGroup(check_group):

                #this is set to skip movies with the following release group names (currently disabled)
                if re.compile("-BadGroup", re.IGNORECASE).search(check_group):

                        return 0
                else:
                        return 1

        def isGoodMovie(check_movie):

                #this is set to ignore filters for certain movie titles
                if re.compile("good movie", re.IGNORECASE).search(check_movie):

                        return 1
                else:
                        return 0

except:
        print("Error: NZB Filter Error")
        main_logger.error("NZB Filter Error")
        traceback.print_exc(file=open(tracelog,"a"))
        os.system(notifylog)

try:
        def download(report_id):

                #this downloads the nzb from the link in the rss feed.
                print("")
                print("Status: Downloading Movie.....")
                print("IMDB Movie Title: " + imdb_movie_title + " (" + imdb_link + ")")
                print("Release Movie Title: " + movie_title)
                urllib.urlretrieve(msgid, watch_dir + "\\" + imdb_movie_title + ".nzb")

except:
        print("Error: Download Of NZB Failed")
        main_logger.error("Download Of Movie " + imdb_movie_title + " Failed")
        traceback.print_exc(file=open(tracelog,"a"))
        os.system(notifylog)

        removeRetryCount = 0
        while removeRetryCount < 3:
                time.sleep(10)

                #sleep and retry to delete partial download 3 times
                try:
                        os.remove(watch_dir + "\\" + imdb_movie_title + ".nzb")
                        break
                except:
                        removeRetryCount += 1
        else:
                print("Error: Deletion Of Partial NZB Failed")
                main_logger.error("Deletion Of NZB " + imdb_movie_title + " Failed")
                traceback.print_exc(file=open(tracelog,"a"))
                os.system(notifylog)

#this reads the content of the rss feed from nzbs.org
try:
        dom=xml.dom.minidom.parse(urllib.urlopen(nzbs_org_feed))
except:
        print("Error: RSS Feed Error")
        main_logger.error("RSS Feed Error")
        traceback.print_exc(file=open(tracelog,"a"))
        os.system(notifylog)

#this breaks down the rss feed page into tag sections
for node in dom.getElementsByTagName("item"):

        movie_title = node.getElementsByTagName("title")[0].childNodes[0].data
        report_description = node.getElementsByTagName("description")[0].childNodes[0].data
        movie_desc = re.search("IMDB:.+\/\"\>", report_description)

        if movie_desc:

                try:
                        movie_link = re.search("http.+\/",movie_desc.group())
                        imdb_link=movie_link.group()
                        sock = urllib.urlopen(imdb_link)
                        htmlSource = sock.read()
                        sock.close()
                except:
                        print("Error: RSS Feed Tag Error")
                        main_logger.error("RSS Feed Tag Error")
                        traceback.print_exc(file=open(tracelog,"a"))
                        os.system(notify)

                        ######################
                        # IMDB Title Filters #
                        ######################
                try:
                        #search imdb page for movie title
                        imdb_movie_title_search = re.compile("<title>.+</title>").search(htmlSource)

                        if imdb_movie_title_search is not None:

                                imdb_movie_title = imdb_movie_title_search.group()

                                #removes title tags from movie title
                                imdb_movie_title = re.sub("</?title>?","" ,imdb_movie_title)

                                #removes year from movie title
                                imdb_movie_title = re.sub(" \(.*\)","" ,imdb_movie_title)

                                #removes colons from movie title - e.g. "the movie: big movie" converts to "the movie big movie"
                                imdb_movie_title = re.sub("\:","" ,imdb_movie_title)

                                #removes question marks from movie title - e.g. "the movie?" converts to "the movie"
                                imdb_movie_title = re.sub("\?","" ,imdb_movie_title)

                                #removes end period from movie title - e.g. "the movie b.m." converts to "the movie b.m"
                                imdb_movie_title = re.sub("\.$","" ,imdb_movie_title)

                                #removes apostrophe from movie title - e.g. "the movie big movie's" converts to "the movie big movies"
                                imdb_movie_title = re.sub("'","" ,imdb_movie_title)

                                #replace xml & with "and" - e.g. "the movie & big movie" converts to "the movie and big movie"
                                imdb_movie_title = re.sub("\&amp\;|\&\#38\;","and" ,imdb_movie_title)

                                #replace roman numerals to numerics - e.g. "the movie V" converts to "the movie 5"
                                imdb_movie_title = re.sub("V(?![a-zA-Z0-9_])","5", imdb_movie_title, re.I)

                                #replace roman numerals to numerics - e.g. "the movie IV" converts to "the movie 4"
                                imdb_movie_title = re.sub("IV(?![a-zA-Z0-9_])","4", imdb_movie_title, re.I)

                                #replace roman numerals to numerics - e.g. "the movie III" converts to "the movie 3"
                                imdb_movie_title = re.sub("III(?![a-zA-Z0-9_])","3" ,imdb_movie_title, re.I)

                                #replace roman numerals to numerics - e.g. "the movie II" converts to "the movie 2"
                                imdb_movie_title = re.sub("II(?![a-zA-Z0-9_])","2" ,imdb_movie_title, re.I)

                                #converts first letter of each word in the movie title to caps e.g. "the movie" converts to "The Movie"
                                imdb_movie_title = imdb_movie_title.title()

                except:
                        print("Error: Title Modification Error")
                        main_logger.error("Title Modification Error")
                        traceback.print_exc(file=open(tracelog,"a"))
                        os.system(notifylog)

                try:
                        #######################
                        # check filter values #
                        #######################

                        if (isGoodRatings(htmlSource) == 1):

                                VisGoodRatings = 1
                        else:
                                VisGoodRatings = 0

                        if (isGoodVotes(htmlSource) == 1):

                                VisGoodVotes = 1
                        else:
                                VisGoodVotes = 0

                        if (isDownloaded(imdb_movie_title) == 1):

                                VisDownloaded = 1
                        else:
                                VisDownloaded = 0

                        if (isInNZB(imdb_movie_title) == 1):

                                VisInNZB = 1
                        else:
                                VisInNZB = 0

                        if (isInWatched(imdb_movie_title) == 1):

                                VisInWatched = 1
                        else:
                                VisInWatched = 0

                        if (isCompleted(imdb_movie_title) == 1):

                                VisCompleted = 1
                        else:
                                VisCompleted = 0

                        if (isBadDate(htmlSource) == 1):

                                VisBadDate = 1
                        else:
                                VisBadDate = 0

                        if (isBadGenre(htmlSource) == 1):

                                VisBadGenre = 1
                        else:
                                VisBadGenre = 0

                        if (isBadGroup(movie_title) == 1):

                                VisBadGroup = 1
                        else:
                                VisBadGroup = 0

                        if (isGoodLang(htmlSource) == 1):

                                VisGoodLang = 1
                        else:
                                VisGoodLang = 0

                        if (isGoodCountry(htmlSource) == 1):

                                VisGoodCountry = 1
                        else:
                                VisGoodCountry = 0

                        if (isGoodSize(report_description) == 1):

                                VisGoodSize = 1
                        else:
                                VisGoodSize = 0

                        if (isGoodMovie(imdb_movie_title) == 1):

                                VisGoodMovie = 1
                        else:
                                VisGoodMovie = 0

                        if ((VisDownloaded == 1) and (VisInNZB == 1) and (VisInWatched == 1) and (VisCompleted == 1)) and (((VisGoodRatings == 1) and (VisGoodVotes == 1) and (VisBadDate == 1) and (VisBadGenre == 1) and (VisBadGroup == 1) and (VisGoodLang == 1) and (VisGoodCountry == 1) and (VisGoodSize == 1)) or (VisGoodMovie == 1)):
                                msgid=node.getElementsByTagName("link")[0].childNodes[0].data
                                download(msgid)

                        else:
                                print("")
                                print("Status: Skipping Movie.....")
                                print("IMDB Movie Title: " + imdb_movie_title + " (" + imdb_link + ")")
                                print("Release Movie Title: " + movie_title)
                except:
                        print("Error: Filter Value Check Error")
                        main_logger.error("Filter Value Check Error")
                        traceback.print_exc(file=open(tracelog,"a"))
                        os.system(notifylog)

                #############
                # Debugging #
                #############

                if (VisGoodMovie == 1):
                        print("Debug: Movie In Ignore Filters List")

                if (VisGoodRatings == 0):
                        print("Debug: Rating < 6.5")

                if (VisGoodVotes == 0):
                        print("Debug: Votes < 5,000")

                if (VisDownloaded == 0):
                        print("Debug: Movie Exists In Downloaded Folder")

                if (VisInNZB == 0):
                        print("Debug: NZB Exists In NZB Folder")

                if (VisInWatched == 0):
                        print("Debug: NZB Exists In Watch Folder")

                if (VisCompleted == 0):
                        print("Debug: Movie Exists In Completed Folder")

                if (VisBadDate == 0):
                        print("Debug: Release Date Is Before 1970")

                if (VisBadGenre == 0):
                        print("Debug: Genre Is Unsuitable")

                if (VisBadGroup == 0):
                        print("Debug: Bad Release Group")

                if (VisGoodLang == 0):
                        print("Debug: Language Of Movie Is NOT English")

                if (VisGoodCountry == 0):
                        print("Debug: Language Of Country Is NOT English")

                if (VisGoodSize == 0):
                        print("Debug: Size Is Too Small/Large")