def calcScore():
stop = stopwords.words('english') + ["scene change"] + ['.',',']
subtitle_list = get_subtitle_list_from_file("../subtitles/el.srt")
print "Subtitles Parsed..."
iter = 0
# print stop
score = list()
for el in subtitle_list:
token = word_tokenize(el['text'])
token = [x for x in token if x not in stop]
words = dict()
for to in token:
to = to.lower()
if words.has_key(to):
words[to] = words[to] + 1
else:
words[to] = 1
if len(words)==0:
continue
ret = get_results(words)
ret['time']=el['time']
score.append(ret)
print "Scoring Done..."
with open("data/emp.json","w+") as f:
json.dump(score,f)
print "Saved."
def calcScore():
stop = stopwords.words('english') + ["scene change"] + ['.', ',']
subtitle_list = get_subtitle_list_from_file("../subtitles/el.srt")
print "Subtitles Parsed..."
iter = 0
# print stop
score = list()
for el in subtitle_list:
token = word_tokenize(el['text'])
token = [x for x in token if x not in stop]
words = dict()
for to in token:
to = to.lower()
if words.has_key(to):
words[to] = words[to] + 1
else:
words[to] = 1
if len(words) == 0:
continue
ret = get_results(words)
ret['time'] = el['time']
score.append(ret)
print "Scoring Done..."
with open("data/emp.json", "w+") as f:
json.dump(score, f)
print "Saved."
def fill_dialogues_times():
# TODO[@9310gaurav] fix the sql syntax according to the update table syntax
subtitle_list = get_subtitle_list_from_file("/Users/arkanath/Dropbox/IIT-Kgp_Coursework/NLP/NLP_Project/flixify/subtitles/gladiator.srt")
db = mdb.connect(host="10.5.18.68", user="******", passwd="dual12", db="12CS30010", cursorclass=curs.DictCursor, charset='utf8')
cur = db.cursor()
cur.execute('select * from scriptData where typ="dialogue"')
data = cur.fetchall()
for entry in data:
# print entry['content']
time = find_nearest_time(subtitle_list, entry['content'])
if(time!=""):
print entry['inde'], time
cur.execute('update scriptData set time="'+ time +'" where inde = "' + entry['inde'] +'"')
