fetching imdb ratings and summary

'''
    Author: Sayyad Shaha Hassan
    Date:   21 August 2016
if (you no like verbos):
    hey there,
    this program fetches the ratings, plot, genres and other stuff of the movies on your disk,
    so you can decide which one to watch first and which ones to show to your little cousins.
    It also lists movies according to their genres so if you would like to watch all the sci-fies first you can check that list and enjoy.
elif (you enjoy reading):
    With the rise of high capacity hard disks, we all love to keep as many movies and serials as we can.
    And this gives rise to a new problem. We soemtimes end up having so many unseen movies in our harddisk that we can't decide which movie to start with.
    I was gifted a hard disk by my beloved cowerkers and I immediately filled it up with everythng I could.
    The when it came to watching movies I was so overwhelmed to see so many movies that I could not decide which ones are worth watching and of those which are worth it where should I begin.

    Then I realised I could use imdb to fetch the genres, rating and plots of the movies and I immediately made an automation to do exactly that.
    Here I present to you a python script* that makes your work easier. You simply run it on a folder which contains your movies.
    Internet needed here. Not much data will be consumed. Even 2G net is enough, a few kb for each folder.
    You only need to keep one movie in one folder and the name of the folder should be renamed to the name of the movie. Now just run the script on the folder.
    Voila!!
    Each movie folder will now be renamed as "Movie name (ReleaseYear) [Rating**,imdbRating,RottenTomatoRating]"
    **Rating as in R, PG etc.
    Along with this, each folder will have a file that will contain the names of the actors, duration of the movie and the plot of the movie (from imdb).

    ----
    *script? But I thought this page is about C programmin you say?
    Well, yes. But I don't get as much time with my job and lazying and catching and training pokemons around at other times. Pokemons? o.O Ahh! It's so I can walk and stay healthy plus the pokemons :P.
    Also scripting is real cool. It helps you write so much in such less time. So well it's only good if you can write code in more than one language.
'''
#=================================================================

#Python code begins:
import os, sys, glob, re, json, urllib
from collections import defaultdict

longmsg = '''
syntax:
    MovieRatings.py RootFolder [-u|-s]
    MovieRatings.py RootFolder -m CustomName

    -m manual override. In case you want to send the movie's name by yourself.
        For eg MovieRatings.py D:\mymovies\someName -m "Different movie name than the folder's"

    -u flag undoes all the stuff. (Deletes summary files and also ratings from folder names)
    -s summarize. Only makes the lists of movies by their genres.

    The movies should be kept as given below.
    One movie per folder.
    The parent folder of movie should contain
            >> [SNo] Movie Name [(Year)]
    SNo:    In case of sequels/prequels this can be a digit or two
    Movie Name: Try to match it with movie title as much as possible. No spelling mistakes
    Year:   Optional. Should be enclosed in round brackets.
    3 Star Wars III
    1 Madagascar (2005) This will work too.
    Madagascar (2005)   This is the best
    Madagascar          This is OK.

    movies
    movies\Madagascar series
    movies\Madagascar series\madagascar (2005)\file.mp4
    movies\Madagascar series\madagascar 2 \file.avi
    movies\Frozen\file.avi

    Output:
    it will rename the folders so they show Name (Year) [Rating, imdbRating, tomatoRating]
    and drop a summary file in the folder. which contains plot and other details of the movie.


    ProTips:
    Use full name only 'Part II' != 'Part 2'
    do not skip words in between. 'hangover part' is still ok, 'the hangover II' is not. (for searching 'the hangover part II')


    Author: Sayyad Shaha Hassan
    Date: 21/Aug/2016
'''

strFileMatch = "sh .*\(.+\) \[.*\]\.txt"
reFileMatch = re.compile(strFileMatch)
strYear = "(.*)(\()(\d{4})(\))(.*)"
reYear = re.compile(strYear)
dictReYearMatch = {"name":1, "bracket1":2, "year":3, "bracket2":4, "remName":5}
strRating = "\[.{1,10},.{1,5},.{1,5}\]"

def fSummarize(dpRoot):
    for root, dirs, files in os.walk(dpRoot):
        for file in files:
            if reFileMatch.search(file):
                with open(os.path.join(root,file)) as fIn:
                    data = fIn.read()
                lines = data.split("\n")
                sTitle = lines[1]
                sGenres = lines[3][lines[3].find(":") + 1:]
                lGenres = sGenres.split(",")
                dctDic = defaultdict(list)
                for sGenre in lGenres:
                    dctDic[sGenre].append(sTitle)
                    tfpGenreList = os.path.join(dpRoot, sGenre)  + ".txt"
                    try:
                        with open(tfpGenreList) as fIn:
                            movieList = fIn.read()
                        movieList = movieList.split("\n")
                        if sTitle in movieList:
                            continue
                    except:
                        pass
                    with open(tfpGenreList, "a") as fOut:
                        fOut.write(sTitle + "\n")
    return

def fMakeFileNRenFolder(jsonResponse, root, PDir):
    if not jsonResponse:
        return None
    #formatting json response
    resTitle = fMakePathSafe(jsonResponse['Title'])
    resYear = fMakePathSafe(jsonResponse["Year"])
    resRated = fMakePathSafe(jsonResponse["Rated"])
    resimdbRate = fMakePathSafe(jsonResponse['imdbRating'])
    resTomatoUserRate = fMakePathSafe(jsonResponse['tomatoUserRating'])
    resGenre  = fMakePathSafe(jsonResponse['Genre'])
    resActors = fMakePathSafe(jsonResponse['Actors'])
    resRuntime = fMakePathSafe(jsonResponse['Runtime'])
    0
    tYear = ""
    if not reYear.search(PDir):
        tYear = ' (' + resYear + ')'

    dnNewPDirName = PDir + tYear + " [" + resRated + "," + resimdbRate + "," + resTomatoUserRate + "]"
    newRoot = root
    if root[2] != "\\":
        newRoot = root[:2] + "\\" + root[2:]

    fnSumFile = root + "\\sh " + fMakePathSafe(resTitle) + " (" + resYear + ") [" + resRated + "," + resimdbRate + "," + resTomatoUserRate + "].txt"
    with open(fnSumFile, "w") as fOut:
        fOut.write("\n" + resTitle + " (" + resYear + ")")
        fOut.write("\nRated: " + resRated)
        fOut.write("\nGenre: " + resGenre)
        fOut.write("\nActors: " + resActors)
        fOut.write("\nRuntime: " + resRuntime)

        fOut.write("\n\n Ratings: ")
        fOut.write("\nMetascore:        " + jsonResponse['Metascore'])
        fOut.write("\nimdbRating:       " + jsonResponse['imdbRating'])
        fOut.write("\ntomatoRating:     " + jsonResponse['tomatoRating'])
        fOut.write("\ntomatoUserRating: " + jsonResponse['tomatoUserRating'])

        fOut.write("\n\nPlot Summary(Full) \n" + jsonResponse['Plot'].encode('ascii','ignore'))
        fOut.write("\n\nSayyad")

    try:
        os.system('ren "' + newRoot + '", "' + dnNewPDirName + '"')
    except:
        print "could not rename(" +newRoot + "," + dnNewPDirName + ')'
        pass
    return

def fUnDoStuff(dpRoot):
    count = 0
    for root, dirs, files in os.walk(dpRoot):
        for file in files:
            if reFileMatch.search(file):
                os.remove(os.path.join(root, file))
                count += 1

                dpPDir = root
                dnPDir = root[root.rfind("\\") + 1:]
                locBrack = dnPDir.rfind("[")
                if locBrack == -1:
                    continue
                dnNewPDir = dnPDir[:locBrack]
                try:
                    os.system('ren "' + dpPDir + '", "' + dnNewPDir + '"')
                except:
                    print "could not rename(" +dpPDir + ", " + dnNewPDir + '). Sorry! '
                    pass
    print str(count) + " files deleted."
    return

def fMakePathSafe(token):
    chars = '/\\:?"*|<>'
    token = token.encode('ascii','ignore')
    for char in chars:
        token = token.replace(char,'')
    return token

def fTryUrl(sTitle, iYear):
    if sTitle == "":
        return None

    print sTitle +" :" + iYear
    urlStubYear = ""
    if iYear:
        urlStubYear = "&y="

    urlFull= "http://www.omdbapi.com/?t={}{}{}&type={}&plot={}&tomatoes={}&r={}".format(urllib.quote(sTitle), urlStubYear, iYear, "movie", "full", "true", "json")
    opener = urllib.FancyURLopener({})
    try:
        handle = opener.open(urlFull)
    except:
        return None
    jsonData = json.load(handle)
    if jsonData['Response'] == 'False':
        return None
    return jsonData

def fGetResponse(PDir):
    match = reYear.search(PDir)
    iYear = ""
    sTitle = PDir

    if match:
        iYear = match.group(dictReYearMatch["year"])
        if int(iYear) < 1900 or int(iYear) > 2050:
            iYear = ""
        else:
            sTitle = match.group(dictReYearMatch["name"]) + match.group(dictReYearMatch["remName"])
    else:
        iYear = ""

    sTitle = sTitle.strip()
    sTitle = sTitle.replace(" ", "+")
    if sTitle == "":
        return None

    #in case of movie series where name is "2. Star Wars"
    firstWord = sTitle[:sTitle.find("+")]
    if not firstWord.isdigit():
        firstWord = sTitle[:sTitle.find(".")]
        if not firstWord.isdigit():
            firstWord = ""

    sAltTitle = ""
    if firstWord:
        sAltTitle = sTitle[len(firstWord)+1:]

    jsonData = fTryUrl(sTitle, iYear)
    if not jsonData:
        jsonData = fTryUrl(sAltTitle, iYear)
        if not jsonData:
            jsonData = fTryUrl(sTitle, "")
            if not jsonData:
                jsonData = fTryUrl(sAltTitle, "")
                if not jsonData:
                    print "failed: not found"
    return jsonData

def fHelp(minArgCount, maxArgCount):
    msgHelp = """
    invalid no of args. other blah blah
    """
    if not minArgCount:
        minArgCount = 1
    if not maxArgCount:
        maxArgCount = minArgCount

    count = len(sys.argv)
    if count < minArgCount or count > maxArgCount:
        print msgHelp
        print longmsg
        exit()
    return
fHelp(2, 5)

dnRoot = sys.argv[1]
#undo
if "-u" in sys.argv:
    fUnDoStuff(dnRoot)
    exit()
elif "-m" in sys.argv:
    #title manual override
    # PathPDir -m manualTitle [manualYear]
    argC = 0
    for arg in sys.argv:
        if "-m" == arg:
            break
        argC += 1

    strManualTitle = sys.argv[argC + 1]
    strManualYear = ""
    try:
        strManualYear = sys.argv[argC + 2]
    except:
        pass
    jsonResponse = fTryUrl(strManualTitle, strManualYear)
    PDir = dnRoot[dnRoot.rfind("\\") + 1:]
    fMakeFileNRenFolder( jsonResponse, dnRoot, PDir)
    exit()
elif "-s" in sys.argv:
    #summerize the movies
    fSummarize(dnRoot)
    exit()
else:
    #normal Execution
    lastRoot = ""
    for root, dirs, files in os.walk(dnRoot):
        if not files:
            continue
        flag = 0
        for file in files:
            if file.startswith("sh "):
                flag = 1
                break
        if flag: continue

        tRoot = root
        if ":" in tRoot:
            si = 2
            if tRoot[2] == "\\":
                si += 1
        else:
            si = 0
        tRoot = tRoot[si:]
        PDir = tRoot[tRoot.rfind("\\")+1:]
        print "working on... ",
        print PDir

        jsonResponse = fGetResponse(PDir)
        if not jsonResponse: continue

        fMakeFileNRenFolder(jsonResponse, root, PDir)
    fSummarize(dnRoot)