import os,sys,re,urllib



#NZB_ = {'Details':[], 'Genre':[], 'Year':[], 'Tagline':[], 'Plot':[], 'Rating':[], 'Runtime':[], 'Actor':[], 'Alias':[]}


def Title(url):
    IMDb_ = {'Title':[]}
    title = re.compile(r'<title>.*')
    in_title = re.compile(r'<title>(.*?)</title>')
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()

    for i in page:
        if title.match(i) != None:
            try:
                IMDb_['Title'] = in_title.search(i).group(1).strip()
            except:
                IMDb_['Title'].append('None')
    return str(IMDb_['Title'])

def Director(url):
    IMDb_ = {'Director':[]}
    director = re.compile(r'<b class="blackcatheader">Directed by</b><br>')
    in_director = re.compile(r'.*?">(.*?)</.*?')
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()
        
    for i in range(len(page)):
        if director.search(page[i]) != None:
            i+=1
            while in_director.search(page[i]) != None:
                IMDb_['Director'].append(in_director.findall(page[i])) #.group(1))
                i+=1
        else:
            i+=1
    return str(IMDb_['Director'])[2:-2]

def Writer(url):
    IMDb_ = {'Writer':[]}
    IMDb_ = {'Writer1':[]}
    IMDb_ = {'Writer2':[]}
    writer = re.compile(r'<b class="blackcatheader">Writing credits</b>')
    in_writer = re.compile(r'.*?">(.*?)</.*?')
    in_writer1 = re.compile(r'.*?">.*?</a> (.*?)<br>')
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()
        
    for i in range(len(page)):
        if writer.search(page[i]) != None:
            i+=3
            while in_writer.search(page[i]) != None:
                IMDb_['Writer1'] = in_writer.findall(page[i])
                i+=3
            while in_writer1.search(page[i]) != None:
                IMDb_['Writer2'] = in_writer.findall(page[i])
                i+=3
        else:
            i+=3
    if IMDb_['Writer1'][len(IMDb_['Writer1'])-1] == '(more)':
        IMDb_['Writer1'].pop(len(IMDb_['Writer1'])-1)

        #for a,b in zip(IMDb_['Writer1'],IMDb_['Writer2']):
            #Writer = '%s as %s' % (a,b)
            #IMDb_['Writer'].append(Writer)

    return str(IMDb_['Writer1'])[1:-1]

def Genre(url):
    IMDb_ = {'Genre':[]}
    genre = re.compile(r'<b class="ch">Genre:</b>')
    in_genre = re.compile(r'.*?"/Sections/Genres/(.*?)/".*?')
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()
        
    for i in range(len(page)):
        if genre.search(page[i]) != None:
            i+=1
            while in_genre.search(page[i]) != None:
                IMDb_['Genre'] = in_genre.findall(page[i])
                i+=1
        else:
            i+=1
    return str(IMDb_['Genre'])[1:-1]

def Details(url):
    IMDb_ = {'Details':[]}
    details = re.compile(r'<p class="plotpar">.*')
    in_details = re.compile(r'">(.*?)</p>')
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()

    for i in page:
        if details.match(i) != None:
            try:
                IMDb_['Details'].append(in_details.search(i).group(1).strip())
            except:
                IMDb_['Details'].append('None')
    return str(IMDb_['Details'])[2:-2]

def Year(url):
    IMDb_ = {'Year':[]}
    year = re.compile(r'.*<a href="/Sections/Years/.*')
    in_year = re.compile(r'<a href="/Sections/Years/.*">(.*?)</a>')
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()

    for i in page:
        if year.match(i) != None:
            try:
                IMDb_['Year'].append(in_year.search(i).group(1).strip())
            except:
                IMDb_['Year'].append('None')
    return str(IMDb_['Year'])[2:-2]

def Tagline(url):
    IMDb_ = {'Tagline':[]}
    tagline = re.compile(r'<b class="ch">Tagline:</b>.*')
    in_tagline = re.compile(r"</b>(.*)")
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()

    for i in page:
        if tagline.match(i) != None:
            try:
                IMDb_['Tagline'].append(in_tagline.search(i).group(1).strip())
            except:
                IMDb_['Tagline'].append('None')
    return str(IMDb_['Tagline'])[2:-72]

def Plot(url):
    IMDb_ = {'Plot':[]}
    plot = re.compile(r'<b class="ch">Plot Outline:</b>.*')
    in_plot = re.compile(r"</b>(.*?)<a href")
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()

    for i in page:
        if plot.match(i) != None:
            try:
                IMDb_['Plot'].append(in_plot.search(i).group(1).strip())
            except:
                IMDb_['Plot'].append('None')
    return str(IMDb_['Plot'])[2:-2]


def Rating(url):
    IMDb_ = {'Rating':[]}
    rating = re.compile(r'<b>.*/.*</b>.*')
    in_rating = re.compile(r"<b>(.*?)/.*</b> .*")
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()

    for i in page:
        if rating.match(i) != None:
            try:
                IMDb_['Rating'].append(in_rating.search(i).group(1).strip())
            except:
                IMDb_['Rating'].append('None')
    return str(IMDb_['Rating'][0])


def Runtime(url):
    IMDb_ = {'Runtime':[]}
    runtime = re.compile(r'(.*?) min')
    in_runtime = re.compile(r"(.*?) min")
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()

    for i in page:
        if runtime.match(i) != None:
            try:
                IMDb_['Runtime'].append(in_runtime.search(i).group(1).strip())
            except:
                IMDb_['Runtime'].append('None')
    return str(IMDb_['Runtime'][0]) + " min"

def Cast(url):
    IMDb_ = {'CastActor':[]}
    IMDb_ = {'CastAlias':[]}
    IMDb_ = {'Cast':[]}
    cast = re.compile(r'.*<b class="blackcatheader">Cast overview, first billed only: </b>.*')
    in_cast = re.compile(r'.*?/">(.*?)</.*?')
    in_cast1 = re.compile(r'.*? .... </td><td valign="top">(.*?)</td>.*?')
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()

    for i in page:
        if cast.match(i) != None:
            try:
                IMDb_['CastActor'] = in_cast.findall(i)
            except:
                IMDb_['CastActor'].append('None')
            try:
                IMDb_['CastAlias'] = in_cast1.findall(i)
            except:
                IMDb_['CastAlias'].append('None')
    for a,b in zip(IMDb_['CastActor'],IMDb_['CastAlias']):
        Cast = '%s as %s' % (a,b)
        IMDb_['Cast'].append(Cast)
    return str(IMDb_['Cast'])

def Country(url):
    IMDb_ = {'Country':[]}
    country = re.compile(r'<b class="ch">Country:</b>')
    in_country = re.compile(r'.*?<a href="/Sections/Countries/(.*?)/">.*?')
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()
        
    for i in range(len(page)):
        if country.search(page[i]) != None:
            i+=1
            while in_country.search(page[i]) != None:
                IMDb_['Country'] = in_country.findall(page[i])
                i+=1
        else:
            i+=1
    return str(IMDb_['Country'])[2:-2]

def Language(url):
    IMDb_ = {'Language':[]}
    language = re.compile(r'<b class="ch">Language:</b>')
    in_language = re.compile(r'.*?<a href="/Sections/Languages/(.*?)/">.*?')
    sock = urllib.urlopen(url)
    page = sock.readlines()
    sock.close()
        
    for i in range(len(page)):
        if language.search(page[i]) != None:
            i+=1
            while in_language.search(page[i]) != None:
                IMDb_['Language'] = in_language.findall(page[i])
                i+=1
        else:
            i+=1
    return str(IMDb_['Language'])[1:-1]

title = Title("http://www.imdb.com/title/tt0317219/")
print title
language = Language("http://www.imdb.com/title/tt0317219/")
print language
country = Country("http://www.imdb.com/title/tt0317219/")
print country
cast = Cast("http://www.imdb.com/title/tt0317219/")
print cast
detail = Details("http://www.imdb.com/title/tt0317219/plotsummary")
print detail
genre = Genre("http://www.imdb.com/title/tt0317219/")
print genre
director = Director("http://www.imdb.com/title/tt0317219/")
print director
#writer = Writer("http://www.imdb.com/title/tt0441694/")
writer = Writer("http://www.imdb.com/title/tt0317219/")
print writer
year = Year("http://www.imdb.com/title/tt0317219/")
print year
tagline = Tagline("http://www.imdb.com/title/tt0317219/")
print tagline
plot = Plot("http://www.imdb.com/title/tt0317219/")
print plot
rating = Rating("http://www.imdb.com/title/tt0317219/")
print rating
runtime = Runtime("http://www.imdb.com/title/tt0317219/")
print runtime